gpu is available
Dataset({
    features: ['sentence', 'label', 'user_id', 'datetime'],
    num_rows: 30000
})
Dataset({
    features: ['sentence', 'label', 'user_id', 'datetime'],
    num_rows: 2500
})

Map:   0%|          | 0/2500 [00:00<?, ? examples/s]Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.

Map:  30%|███       | 759/2500 [00:00<00:00, 7556.08 examples/s]
Map:  71%|███████▏  | 1784/2500 [00:00<00:00, 7055.33 examples/s]
Map: 100%|██████████| 2500/2500 [00:00<00:00, 7031.90 examples/s]
Map: 100%|██████████| 2500/2500 [00:00<00:00, 7066.54 examples/s]
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
[I 2023-10-26 21:59:47,933] A new study created in memory with name: no-name-27bdc1c3-17f6-4a5f-a2a4-42d3ed4c43c4
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:16,  3.58it/s]
  0%|          | 2/705 [00:00<03:10,  3.68it/s]
  0%|          | 3/705 [00:00<03:07,  3.74it/s]
  1%|          | 4/705 [00:01<03:06,  3.76it/s]
  1%|          | 5/705 [00:01<03:04,  3.79it/s]
  1%|          | 6/705 [00:01<02:59,  3.89it/s]
  1%|          | 7/705 [00:01<02:59,  3.88it/s]
  1%|          | 8/705 [00:02<02:57,  3.92it/s]
  1%|▏         | 9/705 [00:02<02:59,  3.88it/s]
  1%|▏         | 10/705 [00:02<03:00,  3.85it/s]
  2%|▏         | 11/705 [00:02<03:00,  3.85it/s]
  2%|▏         | 12/705 [00:03<02:58,  3.87it/s]
  2%|▏         | 13/705 [00:03<02:55,  3.94it/s]
  2%|▏         | 14/705 [00:03<02:55,  3.94it/s]
  2%|▏         | 15/705 [00:03<02:56,  3.90it/s]
  2%|▏         | 16/705 [00:04<02:56,  3.91it/s]
  2%|▏         | 17/705 [00:04<02:57,  3.87it/s]
  3%|▎         | 18/705 [00:04<02:58,  3.84it/s]
  3%|▎         | 19/705 [00:04<02:56,  3.89it/s]
  3%|▎         | 20/705 [00:05<02:56,  3.88it/s]
  3%|▎         | 21/705 [00:05<02:56,  3.87it/s]
  3%|▎         | 22/705 [00:05<02:54,  3.92it/s]
  3%|▎         | 23/705 [00:05<02:55,  3.88it/s]
  3%|▎         | 24/705 [00:06<02:56,  3.86it/s]
  4%|▎         | 25/705 [00:06<02:55,  3.87it/s]
  4%|▎         | 26/705 [00:06<02:56,  3.86it/s]
  4%|▍         | 27/705 [00:06<02:56,  3.83it/s]
  4%|▍         | 28/705 [00:07<02:57,  3.82it/s]
  4%|▍         | 29/705 [00:07<02:51,  3.94it/s]
  4%|▍         | 30/705 [00:07<02:53,  3.90it/s]
  4%|▍         | 31/705 [00:08<02:53,  3.88it/s]
  5%|▍         | 32/705 [00:08<02:53,  3.87it/s]
  5%|▍         | 33/705 [00:08<02:51,  3.91it/s]
  5%|▍         | 34/705 [00:08<02:53,  3.87it/s]
  5%|▍         | 35/705 [00:09<02:51,  3.91it/s]
  5%|▌         | 36/705 [00:09<02:51,  3.91it/s]
  5%|▌         | 37/705 [00:09<02:47,  3.98it/s]
  5%|▌         | 38/705 [00:09<02:49,  3.94it/s]
  6%|▌         | 39/705 [00:10<02:50,  3.91it/s]
  6%|▌         | 40/705 [00:10<02:51,  3.88it/s]
  6%|▌         | 41/705 [00:10<02:51,  3.86it/s]
  6%|▌         | 42/705 [00:10<02:51,  3.86it/s]
  6%|▌         | 43/705 [00:11<02:52,  3.83it/s]
  6%|▌         | 44/705 [00:11<02:50,  3.88it/s]
  6%|▋         | 45/705 [00:11<02:51,  3.84it/s]
  7%|▋         | 46/705 [00:11<02:52,  3.81it/s]
  7%|▋         | 47/705 [00:12<02:52,  3.82it/s]
  7%|▋         | 48/705 [00:12<02:51,  3.82it/s]
  7%|▋         | 49/705 [00:12<02:51,  3.83it/s]
  7%|▋         | 50/705 [00:12<02:51,  3.81it/s]
  7%|▋         | 51/705 [00:13<02:50,  3.84it/s]
  7%|▋         | 52/705 [00:13<02:51,  3.82it/s]
  8%|▊         | 53/705 [00:13<02:46,  3.92it/s]
  8%|▊         | 54/705 [00:13<02:46,  3.92it/s]
  8%|▊         | 55/705 [00:14<02:46,  3.90it/s]
  8%|▊         | 56/705 [00:14<02:47,  3.88it/s]
  8%|▊         | 57/705 [00:14<02:47,  3.88it/s]
  8%|▊         | 58/705 [00:14<02:48,  3.84it/s]
  8%|▊         | 59/705 [00:15<02:49,  3.82it/s]
  9%|▊         | 60/705 [00:15<02:48,  3.83it/s]
  9%|▊         | 61/705 [00:15<02:47,  3.85it/s]
  9%|▉         | 62/705 [00:16<02:41,  3.97it/s]
  9%|▉         | 63/705 [00:16<02:43,  3.91it/s]
  9%|▉         | 64/705 [00:16<02:43,  3.92it/s]
  9%|▉         | 65/705 [00:16<02:45,  3.87it/s]
  9%|▉         | 66/705 [00:17<02:46,  3.84it/s]
 10%|▉         | 67/705 [00:17<02:47,  3.82it/s]
 10%|▉         | 68/705 [00:17<02:44,  3.87it/s]
 10%|▉         | 69/705 [00:17<02:42,  3.92it/s]
 10%|▉         | 70/705 [00:18<02:41,  3.92it/s]
 10%|█         | 71/705 [00:18<02:42,  3.90it/s]
 10%|█         | 72/705 [00:18<02:38,  3.99it/s]
 10%|█         | 73/705 [00:18<02:39,  3.95it/s]
 10%|█         | 74/705 [00:19<02:41,  3.92it/s]
 11%|█         | 75/705 [00:19<02:42,  3.89it/s]
 11%|█         | 76/705 [00:19<02:43,  3.86it/s]
 11%|█         | 77/705 [00:19<02:43,  3.85it/s]
 11%|█         | 78/705 [00:20<02:40,  3.90it/s]
 11%|█         | 79/705 [00:20<02:42,  3.85it/s]
 11%|█▏        | 80/705 [00:20<02:42,  3.85it/s]
 11%|█▏        | 81/705 [00:20<02:43,  3.82it/s]
 12%|█▏        | 82/705 [00:21<02:43,  3.80it/s]
 12%|█▏        | 83/705 [00:21<02:42,  3.83it/s]
 12%|█▏        | 84/705 [00:21<02:39,  3.90it/s]
 12%|█▏        | 85/705 [00:21<02:39,  3.88it/s]
 12%|█▏        | 86/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 87/705 [00:22<02:41,  3.83it/s]
 12%|█▏        | 88/705 [00:22<02:41,  3.83it/s]
 13%|█▎        | 89/705 [00:23<02:40,  3.83it/s]
 13%|█▎        | 90/705 [00:23<02:41,  3.81it/s]
 13%|█▎        | 91/705 [00:23<02:39,  3.86it/s]
 13%|█▎        | 92/705 [00:23<02:39,  3.84it/s]
 13%|█▎        | 93/705 [00:24<02:40,  3.82it/s]
 13%|█▎        | 94/705 [00:24<02:40,  3.82it/s]
 13%|█▎        | 95/705 [00:24<02:40,  3.81it/s]
 14%|█▎        | 96/705 [00:24<02:39,  3.82it/s]
 14%|█▍        | 97/705 [00:25<02:40,  3.80it/s]
 14%|█▍        | 98/705 [00:25<02:39,  3.81it/s]
 14%|█▍        | 99/705 [00:25<02:39,  3.79it/s]
 14%|█▍        | 100/705 [00:25<02:39,  3.79it/s]
 14%|█▍        | 101/705 [00:26<02:39,  3.78it/s]
 14%|█▍        | 102/705 [00:26<02:39,  3.77it/s]
 15%|█▍        | 103/705 [00:26<02:38,  3.79it/s]
 15%|█▍        | 104/705 [00:26<02:38,  3.80it/s]
 15%|█▍        | 105/705 [00:27<02:35,  3.85it/s]
 15%|█▌        | 106/705 [00:27<02:33,  3.89it/s]
 15%|█▌        | 107/705 [00:27<02:35,  3.85it/s]
 15%|█▌        | 108/705 [00:27<02:35,  3.84it/s]
 15%|█▌        | 109/705 [00:28<02:35,  3.84it/s]
 16%|█▌        | 110/705 [00:28<02:35,  3.83it/s]
 16%|█▌        | 111/705 [00:28<02:34,  3.85it/s]
 16%|█▌        | 112/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 113/705 [00:29<02:32,  3.89it/s]
 16%|█▌        | 114/705 [00:29<02:32,  3.87it/s]
 16%|█▋        | 115/705 [00:29<02:33,  3.84it/s]
 16%|█▋        | 116/705 [00:30<02:33,  3.83it/s]
 17%|█▋        | 117/705 [00:30<02:32,  3.85it/s]
 17%|█▋        | 118/705 [00:30<02:32,  3.86it/s]
 17%|█▋        | 119/705 [00:30<02:33,  3.82it/s]
 17%|█▋        | 120/705 [00:31<02:32,  3.85it/s]
 17%|█▋        | 121/705 [00:31<02:29,  3.90it/s]
 17%|█▋        | 122/705 [00:31<02:30,  3.87it/s]
 17%|█▋        | 123/705 [00:31<02:30,  3.88it/s]
 18%|█▊        | 124/705 [00:32<02:26,  3.96it/s]
 18%|█▊        | 125/705 [00:32<02:27,  3.93it/s]
 18%|█▊        | 126/705 [00:32<02:27,  3.92it/s]
 18%|█▊        | 127/705 [00:32<02:27,  3.91it/s]
 18%|█▊        | 128/705 [00:33<02:27,  3.91it/s]
 18%|█▊        | 129/705 [00:33<02:27,  3.91it/s]
 18%|█▊        | 130/705 [00:33<02:28,  3.88it/s]
 19%|█▊        | 131/705 [00:33<02:28,  3.87it/s]
 19%|█▊        | 132/705 [00:34<02:27,  3.88it/s]
 19%|█▉        | 133/705 [00:34<02:28,  3.85it/s]
 19%|█▉        | 134/705 [00:34<02:28,  3.85it/s]
 19%|█▉        | 135/705 [00:34<02:28,  3.84it/s]
 19%|█▉        | 136/705 [00:35<02:28,  3.84it/s]
 19%|█▉        | 137/705 [00:35<02:27,  3.85it/s]
 20%|█▉        | 138/705 [00:35<02:26,  3.87it/s]
 20%|█▉        | 139/705 [00:35<02:27,  3.83it/s]
 20%|█▉        | 140/705 [00:36<02:28,  3.81it/s]
 20%|██        | 141/705 [00:36<02:28,  3.79it/s]
 20%|██        | 142/705 [00:36<02:22,  3.94it/s]
 20%|██        | 143/705 [00:37<02:24,  3.88it/s]
 20%|██        | 144/705 [00:37<02:23,  3.90it/s]
 21%|██        | 145/705 [00:37<02:25,  3.85it/s]
 21%|██        | 146/705 [00:37<02:26,  3.82it/s]
 21%|██        | 147/705 [00:38<02:22,  3.92it/s]
 21%|██        | 148/705 [00:38<02:20,  3.95it/s]
 21%|██        | 149/705 [00:38<02:22,  3.91it/s]
 21%|██▏       | 150/705 [00:38<02:23,  3.86it/s]
 21%|██▏       | 151/705 [00:39<02:23,  3.87it/s]
 22%|██▏       | 152/705 [00:39<02:21,  3.92it/s]
 22%|██▏       | 153/705 [00:39<02:22,  3.86it/s]
 22%|██▏       | 154/705 [00:39<02:23,  3.84it/s]
 22%|██▏       | 155/705 [00:40<02:23,  3.83it/s]
 22%|██▏       | 156/705 [00:40<02:21,  3.87it/s]
 22%|██▏       | 157/705 [00:40<02:17,  3.98it/s]
 22%|██▏       | 158/705 [00:40<02:19,  3.92it/s]
 23%|██▎       | 159/705 [00:41<02:21,  3.86it/s]
 23%|██▎       | 160/705 [00:41<02:22,  3.83it/s]
 23%|██▎       | 161/705 [00:41<02:21,  3.83it/s]
 23%|██▎       | 162/705 [00:41<02:22,  3.81it/s]
 23%|██▎       | 163/705 [00:42<02:22,  3.80it/s]
 23%|██▎       | 164/705 [00:42<02:20,  3.86it/s]
 23%|██▎       | 165/705 [00:42<02:19,  3.87it/s]
 24%|██▎       | 166/705 [00:42<02:19,  3.85it/s]
 24%|██▎       | 167/705 [00:43<02:17,  3.90it/s]
 24%|██▍       | 168/705 [00:43<02:18,  3.88it/s]
 24%|██▍       | 169/705 [00:43<02:16,  3.92it/s]
 24%|██▍       | 170/705 [00:43<02:17,  3.89it/s]
 24%|██▍       | 171/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 172/705 [00:44<02:19,  3.82it/s]
 25%|██▍       | 173/705 [00:44<02:20,  3.79it/s]
 25%|██▍       | 174/705 [00:45<02:19,  3.80it/s]
 25%|██▍       | 175/705 [00:45<02:15,  3.92it/s]
 25%|██▍       | 176/705 [00:45<02:16,  3.89it/s]
 25%|██▌       | 177/705 [00:45<02:17,  3.83it/s]
 25%|██▌       | 178/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 179/705 [00:46<02:15,  3.88it/s]
 26%|██▌       | 180/705 [00:46<02:17,  3.83it/s]
 26%|██▌       | 181/705 [00:46<02:17,  3.82it/s]
 26%|██▌       | 182/705 [00:47<02:17,  3.79it/s]
 26%|██▌       | 183/705 [00:47<02:17,  3.78it/s]
 26%|██▌       | 184/705 [00:47<02:17,  3.79it/s]
 26%|██▌       | 185/705 [00:47<02:16,  3.82it/s]
 26%|██▋       | 186/705 [00:48<02:14,  3.87it/s]
 27%|██▋       | 187/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 188/705 [00:48<02:16,  3.80it/s]
 27%|██▋       | 189/705 [00:48<02:14,  3.84it/s]
 27%|██▋       | 190/705 [00:49<02:12,  3.88it/s]
 27%|██▋       | 191/705 [00:49<02:13,  3.86it/s]
 27%|██▋       | 192/705 [00:49<02:13,  3.84it/s]
 27%|██▋       | 193/705 [00:50<02:13,  3.82it/s]
 28%|██▊       | 194/705 [00:50<02:13,  3.83it/s]
 28%|██▊       | 195/705 [00:50<02:10,  3.92it/s]
 28%|██▊       | 196/705 [00:50<02:10,  3.91it/s]
 28%|██▊       | 197/705 [00:51<02:10,  3.89it/s]
 28%|██▊       | 198/705 [00:51<02:10,  3.89it/s]
 28%|██▊       | 199/705 [00:51<02:09,  3.91it/s]
 28%|██▊       | 200/705 [00:51<02:07,  3.96it/s]
 29%|██▊       | 201/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 202/705 [00:52<02:09,  3.89it/s]
 29%|██▉       | 203/705 [00:52<02:02,  4.08it/s]
 29%|██▉       | 204/705 [00:52<02:05,  3.99it/s]
 29%|██▉       | 205/705 [00:53<02:07,  3.93it/s]
 29%|██▉       | 206/705 [00:53<02:08,  3.89it/s]
 29%|██▉       | 207/705 [00:53<02:08,  3.88it/s]
 30%|██▉       | 208/705 [00:53<02:09,  3.84it/s]
 30%|██▉       | 209/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 210/705 [00:54<02:09,  3.81it/s]
 30%|██▉       | 211/705 [00:54<02:10,  3.79it/s]
 30%|███       | 212/705 [00:54<02:06,  3.91it/s]
 30%|███       | 213/705 [00:55<02:06,  3.88it/s]
 30%|███       | 214/705 [00:55<02:07,  3.86it/s]
 30%|███       | 215/705 [00:55<02:08,  3.83it/s]
 31%|███       | 216/705 [00:55<02:05,  3.88it/s]
 31%|███       | 217/705 [00:56<02:07,  3.84it/s]
 31%|███       | 218/705 [00:56<02:08,  3.80it/s]
 31%|███       | 219/705 [00:56<02:07,  3.80it/s]
 31%|███       | 220/705 [00:56<02:06,  3.84it/s]
 31%|███▏      | 221/705 [00:57<02:05,  3.87it/s]
 31%|███▏      | 222/705 [00:57<02:05,  3.85it/s]
 32%|███▏      | 223/705 [00:57<02:06,  3.81it/s]
 32%|███▏      | 224/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 225/705 [00:58<02:04,  3.85it/s]
 32%|███▏      | 226/705 [00:58<02:06,  3.79it/s]
 32%|███▏      | 227/705 [00:58<02:05,  3.81it/s]
 32%|███▏      | 228/705 [00:59<02:04,  3.83it/s]
 32%|███▏      | 229/705 [00:59<02:05,  3.80it/s]
 33%|███▎      | 230/705 [00:59<02:03,  3.84it/s]
 33%|███▎      | 231/705 [00:59<02:04,  3.81it/s]
 33%|███▎      | 232/705 [01:00<02:00,  3.93it/s]
 33%|███▎      | 233/705 [01:00<02:00,  3.90it/s]
 33%|███▎      | 234/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 235/705 [01:00<01:41,  4.65it/s]
                                                 

 33%|███▎      | 235/705 [01:00<01:41,  4.65it/s]{'loss': 0.7609, 'learning_rate': 9.359952753352034e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 211.48it/s]

 14%|█▍        | 44/313 [00:00<00:01, 198.58it/s]

 21%|██        | 66/313 [00:00<00:01, 207.17it/s]

 28%|██▊       | 87/313 [00:00<00:01, 196.63it/s]

 34%|███▍      | 107/313 [00:00<00:01, 189.03it/s]

 40%|████      | 126/313 [00:00<00:01, 186.81it/s]

 46%|████▋     | 145/313 [00:00<00:00, 184.71it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 185.65it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 180.57it/s]

 65%|██████▍   | 202/313 [00:01<00:00, 174.90it/s]

 70%|███████   | 220/313 [00:01<00:00, 168.59it/s]

 76%|███████▌  | 237/313 [00:01<00:00, 167.11it/s]

 83%|████████▎ | 261/313 [00:01<00:00, 187.32it/s]

 89%|████████▉ | 280/313 [00:01<00:00, 185.26it/s]

 96%|█████████▌| 299/313 [00:01<00:00, 180.27it/s]
                                                 

                                                  

 33%|███▎      | 235/705 [01:02<01:41,  4.65it/s]

100%|██████████| 313/313 [00:01<00:00, 180.27it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:03<07:48,  1.00it/s]
 34%|███▎      | 237/705 [01:03<06:03,  1.29it/s]
 34%|███▍      | 238/705 [01:04<04:51,  1.60it/s]
 34%|███▍      | 239/705 [01:04<03:59,  1.94it/s]
 34%|███▍      | 240/705 [01:04<03:24,  2.27it/s]
 34%|███▍      | 241/705 [01:04<02:58,  2.59it/s]
 34%|███▍      | 242/705 [01:05<02:42,  2.85it/s]
 34%|███▍      | 243/705 [01:05<02:29,  3.09it/s]
 35%|███▍      | 244/705 [01:05<02:19,  3.31it/s]
 35%|███▍      | 245/705 [01:05<02:13,  3.44it/s]
 35%|███▍      | 246/705 [01:06<02:10,  3.52it/s]
 35%|███▌      | 247/705 [01:06<02:08,  3.58it/s]
 35%|███▌      | 248/705 [01:06<02:02,  3.73it/s]
 35%|███▌      | 249/705 [01:06<02:01,  3.75it/s]
 35%|███▌      | 250/705 [01:07<02:01,  3.75it/s]
 36%|███▌      | 251/705 [01:07<01:54,  3.97it/s]
 36%|███▌      | 252/705 [01:07<01:54,  3.94it/s]
 36%|███▌      | 253/705 [01:07<01:50,  4.10it/s]
 36%|███▌      | 254/705 [01:08<01:53,  3.98it/s]
 36%|███▌      | 255/705 [01:08<01:53,  3.97it/s]
 36%|███▋      | 256/705 [01:08<01:55,  3.89it/s]
 36%|███▋      | 257/705 [01:08<01:56,  3.83it/s]
 37%|███▋      | 258/705 [01:09<01:55,  3.88it/s]
 37%|███▋      | 259/705 [01:09<01:55,  3.86it/s]
 37%|███▋      | 260/705 [01:09<01:56,  3.83it/s]
 37%|███▋      | 261/705 [01:09<01:54,  3.88it/s]
 37%|███▋      | 262/705 [01:10<01:55,  3.83it/s]
 37%|███▋      | 263/705 [01:10<01:51,  3.95it/s]
 37%|███▋      | 264/705 [01:10<01:52,  3.91it/s]
 38%|███▊      | 265/705 [01:11<01:51,  3.93it/s]
 38%|███▊      | 266/705 [01:11<01:52,  3.89it/s]
 38%|███▊      | 267/705 [01:11<01:53,  3.85it/s]
 38%|███▊      | 268/705 [01:11<02:05,  3.50it/s]
 38%|███▊      | 269/705 [01:12<02:02,  3.56it/s]
 38%|███▊      | 270/705 [01:12<01:59,  3.63it/s]
 38%|███▊      | 271/705 [01:12<01:56,  3.72it/s]
 39%|███▊      | 272/705 [01:12<01:54,  3.80it/s]
 39%|███▊      | 273/705 [01:13<01:53,  3.81it/s]
 39%|███▉      | 274/705 [01:13<01:53,  3.79it/s]
 39%|███▉      | 275/705 [01:13<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:13<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:14<01:47,  4.00it/s]
 39%|███▉      | 278/705 [01:14<01:48,  3.92it/s]
 40%|███▉      | 279/705 [01:14<01:50,  3.86it/s]
 40%|███▉      | 280/705 [01:14<01:50,  3.84it/s]
 40%|███▉      | 281/705 [01:15<01:50,  3.83it/s]
 40%|████      | 282/705 [01:15<01:49,  3.88it/s]
 40%|████      | 283/705 [01:15<01:49,  3.85it/s]
 40%|████      | 284/705 [01:15<01:48,  3.89it/s]
 40%|████      | 285/705 [01:16<01:48,  3.85it/s]
 41%|████      | 286/705 [01:16<01:49,  3.82it/s]
 41%|████      | 287/705 [01:16<01:48,  3.84it/s]
 41%|████      | 288/705 [01:17<01:49,  3.80it/s]
 41%|████      | 289/705 [01:17<01:47,  3.86it/s]
 41%|████      | 290/705 [01:17<01:47,  3.86it/s]
 41%|████▏     | 291/705 [01:17<01:47,  3.85it/s]
 41%|████▏     | 292/705 [01:18<01:45,  3.91it/s]
 42%|████▏     | 293/705 [01:18<01:46,  3.87it/s]
 42%|████▏     | 294/705 [01:18<01:46,  3.84it/s]
 42%|████▏     | 295/705 [01:18<01:47,  3.81it/s]
 42%|████▏     | 296/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 297/705 [01:19<01:43,  3.95it/s]
 42%|████▏     | 298/705 [01:19<01:44,  3.90it/s]
 42%|████▏     | 299/705 [01:19<01:44,  3.87it/s]
 43%|████▎     | 300/705 [01:20<01:44,  3.87it/s]
 43%|████▎     | 301/705 [01:20<01:44,  3.86it/s]
 43%|████▎     | 302/705 [01:20<01:44,  3.84it/s]
 43%|████▎     | 303/705 [01:20<01:45,  3.82it/s]
 43%|████▎     | 304/705 [01:21<01:42,  3.93it/s]
 43%|████▎     | 305/705 [01:21<01:40,  3.97it/s]
 43%|████▎     | 306/705 [01:21<01:41,  3.92it/s]
 44%|████▎     | 307/705 [01:21<01:43,  3.86it/s]
 44%|████▎     | 308/705 [01:22<01:44,  3.81it/s]
 44%|████▍     | 309/705 [01:22<01:43,  3.83it/s]
 44%|████▍     | 310/705 [01:22<01:44,  3.80it/s]
 44%|████▍     | 311/705 [01:23<01:43,  3.79it/s]
 44%|████▍     | 312/705 [01:23<01:43,  3.79it/s]
 44%|████▍     | 313/705 [01:23<01:43,  3.78it/s]
 45%|████▍     | 314/705 [01:23<01:37,  4.03it/s]
 45%|████▍     | 315/705 [01:24<01:38,  3.94it/s]
 45%|████▍     | 316/705 [01:24<01:39,  3.90it/s]
 45%|████▍     | 317/705 [01:24<01:39,  3.91it/s]
 45%|████▌     | 318/705 [01:24<01:40,  3.86it/s]
 45%|████▌     | 319/705 [01:25<01:41,  3.82it/s]
 45%|████▌     | 320/705 [01:25<01:41,  3.78it/s]
 46%|████▌     | 321/705 [01:25<01:40,  3.81it/s]
 46%|████▌     | 322/705 [01:25<01:40,  3.81it/s]
 46%|████▌     | 323/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 324/705 [01:26<01:41,  3.76it/s]
 46%|████▌     | 325/705 [01:26<01:40,  3.80it/s]
 46%|████▌     | 326/705 [01:26<01:39,  3.82it/s]
 46%|████▋     | 327/705 [01:27<01:39,  3.79it/s]
 47%|████▋     | 328/705 [01:27<01:40,  3.76it/s]
 47%|████▋     | 329/705 [01:27<01:38,  3.83it/s]
 47%|████▋     | 330/705 [01:27<01:38,  3.80it/s]
 47%|████▋     | 331/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 332/705 [01:28<01:38,  3.78it/s]
 47%|████▋     | 333/705 [01:28<01:38,  3.78it/s]
 47%|████▋     | 334/705 [01:29<01:38,  3.77it/s]
 48%|████▊     | 335/705 [01:29<01:37,  3.80it/s]
 48%|████▊     | 336/705 [01:29<01:37,  3.80it/s]
 48%|████▊     | 337/705 [01:29<01:37,  3.78it/s]
 48%|████▊     | 338/705 [01:30<01:36,  3.80it/s]
 48%|████▊     | 339/705 [01:30<01:36,  3.78it/s]
 48%|████▊     | 340/705 [01:30<01:36,  3.76it/s]
 48%|████▊     | 341/705 [01:30<01:37,  3.75it/s]
 49%|████▊     | 342/705 [01:31<01:32,  3.91it/s]
 49%|████▊     | 343/705 [01:31<01:33,  3.87it/s]
 49%|████▉     | 344/705 [01:31<01:34,  3.82it/s]
 49%|████▉     | 345/705 [01:31<01:33,  3.87it/s]
 49%|████▉     | 346/705 [01:32<01:44,  3.42it/s]
 49%|████▉     | 347/705 [01:32<01:41,  3.53it/s]
 49%|████▉     | 348/705 [01:32<01:39,  3.60it/s]
 50%|████▉     | 349/705 [01:33<01:36,  3.70it/s]
 50%|████▉     | 350/705 [01:33<01:35,  3.70it/s]
 50%|████▉     | 351/705 [01:33<01:35,  3.71it/s]
 50%|████▉     | 352/705 [01:33<01:33,  3.77it/s]
 50%|█████     | 353/705 [01:34<01:33,  3.77it/s]
 50%|█████     | 354/705 [01:34<01:33,  3.75it/s]
 50%|█████     | 355/705 [01:34<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:34<01:32,  3.75it/s]
 51%|█████     | 357/705 [01:35<01:33,  3.74it/s]
 51%|█████     | 358/705 [01:35<01:33,  3.73it/s]
 51%|█████     | 359/705 [01:35<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:35<01:31,  3.76it/s]
 51%|█████     | 361/705 [01:36<01:31,  3.75it/s]
 51%|█████▏    | 362/705 [01:36<01:31,  3.76it/s]
 51%|█████▏    | 363/705 [01:36<01:31,  3.75it/s]
 52%|█████▏    | 364/705 [01:37<01:31,  3.73it/s]
 52%|█████▏    | 365/705 [01:37<01:39,  3.40it/s]
 52%|█████▏    | 366/705 [01:37<01:36,  3.51it/s]
 52%|█████▏    | 367/705 [01:37<01:33,  3.62it/s]
 52%|█████▏    | 368/705 [01:38<01:31,  3.67it/s]
 52%|█████▏    | 369/705 [01:38<01:30,  3.71it/s]
 52%|█████▏    | 370/705 [01:38<01:29,  3.75it/s]
 53%|█████▎    | 371/705 [01:38<01:27,  3.82it/s]
 53%|█████▎    | 372/705 [01:39<01:27,  3.78it/s]
 53%|█████▎    | 373/705 [01:39<01:27,  3.78it/s]
 53%|█████▎    | 374/705 [01:39<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:40<01:27,  3.77it/s]
 53%|█████▎    | 376/705 [01:40<01:27,  3.75it/s]
 53%|█████▎    | 377/705 [01:40<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:40<01:25,  3.83it/s]
 54%|█████▍    | 379/705 [01:41<01:24,  3.84it/s]
 54%|█████▍    | 380/705 [01:41<01:24,  3.84it/s]
 54%|█████▍    | 381/705 [01:41<01:24,  3.82it/s]
 54%|█████▍    | 382/705 [01:41<01:24,  3.81it/s]
 54%|█████▍    | 383/705 [01:42<01:23,  3.85it/s]
 54%|█████▍    | 384/705 [01:42<01:24,  3.81it/s]
 55%|█████▍    | 385/705 [01:42<01:24,  3.77it/s]
 55%|█████▍    | 386/705 [01:42<01:23,  3.82it/s]
 55%|█████▍    | 387/705 [01:43<01:23,  3.80it/s]
 55%|█████▌    | 388/705 [01:43<01:24,  3.77it/s]
 55%|█████▌    | 389/705 [01:43<01:22,  3.81it/s]
 55%|█████▌    | 390/705 [01:43<01:22,  3.81it/s]
 55%|█████▌    | 391/705 [01:44<01:23,  3.78it/s]
 56%|█████▌    | 392/705 [01:44<01:21,  3.82it/s]
 56%|█████▌    | 393/705 [01:44<01:21,  3.81it/s]
 56%|█████▌    | 394/705 [01:45<01:21,  3.84it/s]
 56%|█████▌    | 395/705 [01:45<01:21,  3.81it/s]
 56%|█████▌    | 396/705 [01:45<01:21,  3.78it/s]
 56%|█████▋    | 397/705 [01:45<01:21,  3.76it/s]
 56%|█████▋    | 398/705 [01:46<01:21,  3.76it/s]
 57%|█████▋    | 399/705 [01:46<01:21,  3.77it/s]
 57%|█████▋    | 400/705 [01:46<01:20,  3.77it/s]
 57%|█████▋    | 401/705 [01:46<01:18,  3.87it/s]
 57%|█████▋    | 402/705 [01:47<01:19,  3.82it/s]
 57%|█████▋    | 403/705 [01:47<01:19,  3.78it/s]
 57%|█████▋    | 404/705 [01:47<01:16,  3.93it/s]
 57%|█████▋    | 405/705 [01:47<01:17,  3.88it/s]
 58%|█████▊    | 406/705 [01:48<01:18,  3.83it/s]
 58%|█████▊    | 407/705 [01:48<01:16,  3.92it/s]
 58%|█████▊    | 408/705 [01:48<01:16,  3.90it/s]
 58%|█████▊    | 409/705 [01:48<01:16,  3.87it/s]
 58%|█████▊    | 410/705 [01:49<01:17,  3.83it/s]
 58%|█████▊    | 411/705 [01:49<01:17,  3.81it/s]
 58%|█████▊    | 412/705 [01:49<01:16,  3.82it/s]
 59%|█████▊    | 413/705 [01:49<01:15,  3.85it/s]
 59%|█████▊    | 414/705 [01:50<01:15,  3.83it/s]
 59%|█████▉    | 415/705 [01:50<01:16,  3.81it/s]
 59%|█████▉    | 416/705 [01:50<01:15,  3.82it/s]
 59%|█████▉    | 417/705 [01:51<01:15,  3.84it/s]
 59%|█████▉    | 418/705 [01:51<01:13,  3.90it/s]
 59%|█████▉    | 419/705 [01:51<01:13,  3.89it/s]
 60%|█████▉    | 420/705 [01:51<01:13,  3.88it/s]
 60%|█████▉    | 421/705 [01:52<01:13,  3.84it/s]
 60%|█████▉    | 422/705 [01:52<01:13,  3.82it/s]
 60%|██████    | 423/705 [01:52<01:14,  3.79it/s]
 60%|██████    | 424/705 [01:52<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:53<01:13,  3.80it/s]
 60%|██████    | 426/705 [01:53<01:13,  3.81it/s]
 61%|██████    | 427/705 [01:53<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:53<01:13,  3.77it/s]
 61%|██████    | 429/705 [01:54<01:12,  3.82it/s]
 61%|██████    | 430/705 [01:54<01:12,  3.81it/s]
 61%|██████    | 431/705 [01:54<01:12,  3.78it/s]
 61%|██████▏   | 432/705 [01:54<01:11,  3.80it/s]
 61%|██████▏   | 433/705 [01:55<01:11,  3.79it/s]
 62%|██████▏   | 434/705 [01:55<01:11,  3.79it/s]
 62%|██████▏   | 435/705 [01:55<01:09,  3.87it/s]
 62%|██████▏   | 436/705 [01:55<01:09,  3.86it/s]
 62%|██████▏   | 437/705 [01:56<01:10,  3.83it/s]
 62%|██████▏   | 438/705 [01:56<01:10,  3.81it/s]
 62%|██████▏   | 439/705 [01:56<01:09,  3.80it/s]
 62%|██████▏   | 440/705 [01:57<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:57<01:10,  3.75it/s]
 63%|██████▎   | 442/705 [01:57<01:09,  3.76it/s]
 63%|██████▎   | 443/705 [01:57<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:58<01:09,  3.78it/s]
 63%|██████▎   | 445/705 [01:58<01:08,  3.79it/s]
 63%|██████▎   | 446/705 [01:58<01:06,  3.90it/s]
 63%|██████▎   | 447/705 [01:58<01:06,  3.88it/s]
 64%|██████▎   | 448/705 [01:59<01:06,  3.85it/s]
 64%|██████▎   | 449/705 [01:59<01:06,  3.88it/s]
 64%|██████▍   | 450/705 [01:59<01:06,  3.82it/s]
 64%|██████▍   | 451/705 [01:59<01:06,  3.81it/s]
 64%|██████▍   | 452/705 [02:00<01:05,  3.84it/s]
 64%|██████▍   | 453/705 [02:00<01:04,  3.88it/s]
 64%|██████▍   | 454/705 [02:00<01:04,  3.89it/s]
 65%|██████▍   | 455/705 [02:00<01:04,  3.86it/s]
 65%|██████▍   | 456/705 [02:01<01:04,  3.85it/s]
 65%|██████▍   | 457/705 [02:01<01:04,  3.83it/s]
 65%|██████▍   | 458/705 [02:01<01:04,  3.82it/s]
 65%|██████▌   | 459/705 [02:02<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:02<01:04,  3.80it/s]
 65%|██████▌   | 461/705 [02:02<01:04,  3.79it/s]
 66%|██████▌   | 462/705 [02:02<01:04,  3.78it/s]
 66%|██████▌   | 463/705 [02:03<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:03<01:04,  3.74it/s]
 66%|██████▌   | 465/705 [02:03<01:03,  3.77it/s]
 66%|██████▌   | 466/705 [02:03<01:03,  3.75it/s]
 66%|██████▌   | 467/705 [02:04<01:02,  3.78it/s]
 66%|██████▋   | 468/705 [02:04<01:03,  3.76it/s]
 67%|██████▋   | 469/705 [02:04<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:04<00:51,  4.54it/s]
                                                 

 67%|██████▋   | 470/705 [02:04<00:51,  4.54it/s]{'eval_loss': 0.6741517186164856, 'eval_accuracy': 0.6952, 'eval_f1': 0.6945519480519379, 'eval_runtime': 1.7174, 'eval_samples_per_second': 1455.663, 'eval_steps_per_second': 182.249, 'epoch': 1.0}
{'loss': 0.5253, 'learning_rate': 9.359952753352034e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.22it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.78it/s]

 21%|██        | 66/313 [00:00<00:01, 206.48it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.69it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.76it/s]

 40%|████      | 126/313 [00:00<00:01, 185.39it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.40it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.42it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.55it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.50it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.12it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.14it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.96it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.93it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.79it/s]
                                                 

                                                  

 67%|██████▋   | 470/705 [02:06<00:51,  4.54it/s]

100%|██████████| 313/313 [00:01<00:00, 178.79it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:07<03:58,  1.02s/it]
 67%|██████▋   | 472/705 [02:07<03:04,  1.26it/s]
 67%|██████▋   | 473/705 [02:08<02:26,  1.58it/s]
 67%|██████▋   | 474/705 [02:08<02:00,  1.92it/s]
 67%|██████▋   | 475/705 [02:08<01:42,  2.25it/s]
 68%|██████▊   | 476/705 [02:08<01:29,  2.55it/s]
 68%|██████▊   | 477/705 [02:09<01:20,  2.82it/s]
 68%|██████▊   | 478/705 [02:09<01:14,  3.04it/s]
 68%|██████▊   | 479/705 [02:09<01:10,  3.23it/s]
 68%|██████▊   | 480/705 [02:10<01:06,  3.37it/s]
 68%|██████▊   | 481/705 [02:10<01:03,  3.52it/s]
 68%|██████▊   | 482/705 [02:10<01:02,  3.57it/s]
 69%|██████▊   | 483/705 [02:10<01:01,  3.62it/s]
 69%|██████▊   | 484/705 [02:11<01:00,  3.65it/s]
 69%|██████▉   | 485/705 [02:11<00:58,  3.78it/s]
 69%|██████▉   | 486/705 [02:11<00:58,  3.77it/s]
 69%|██████▉   | 487/705 [02:11<00:57,  3.77it/s]
 69%|██████▉   | 488/705 [02:12<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:12<00:56,  3.79it/s]
 70%|██████▉   | 490/705 [02:12<00:56,  3.79it/s]
 70%|██████▉   | 491/705 [02:12<00:55,  3.83it/s]
 70%|██████▉   | 492/705 [02:13<00:56,  3.79it/s]
 70%|██████▉   | 493/705 [02:13<00:55,  3.79it/s]
 70%|███████   | 494/705 [02:13<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:13<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:14<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:14<00:54,  3.81it/s]
 71%|███████   | 498/705 [02:14<00:53,  3.88it/s]
 71%|███████   | 499/705 [02:15<00:53,  3.85it/s]
 71%|███████   | 500/705 [02:15<00:53,  3.87it/s]
 71%|███████   | 501/705 [02:15<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:15<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:16<00:52,  3.81it/s]
 71%|███████▏  | 504/705 [02:16<00:53,  3.78it/s]
 72%|███████▏  | 505/705 [02:16<00:52,  3.78it/s]
 72%|███████▏  | 506/705 [02:16<00:52,  3.78it/s]
 72%|███████▏  | 507/705 [02:17<00:52,  3.81it/s]
 72%|███████▏  | 508/705 [02:17<00:52,  3.77it/s]
 72%|███████▏  | 509/705 [02:17<00:51,  3.82it/s]
 72%|███████▏  | 510/705 [02:17<00:51,  3.78it/s]
 72%|███████▏  | 511/705 [02:18<00:51,  3.80it/s]
 73%|███████▎  | 512/705 [02:18<00:50,  3.80it/s]
 73%|███████▎  | 513/705 [02:18<00:50,  3.79it/s]
 73%|███████▎  | 514/705 [02:18<00:50,  3.77it/s]
 73%|███████▎  | 515/705 [02:19<00:50,  3.77it/s]
 73%|███████▎  | 516/705 [02:19<00:50,  3.77it/s]
 73%|███████▎  | 517/705 [02:19<00:49,  3.77it/s]
 73%|███████▎  | 518/705 [02:20<00:49,  3.77it/s]
 74%|███████▎  | 519/705 [02:20<00:49,  3.79it/s]
 74%|███████▍  | 520/705 [02:20<00:48,  3.85it/s]
 74%|███████▍  | 521/705 [02:20<00:47,  3.85it/s]
 74%|███████▍  | 522/705 [02:21<00:47,  3.85it/s]
 74%|███████▍  | 523/705 [02:21<00:47,  3.83it/s]
 74%|███████▍  | 524/705 [02:21<00:46,  3.86it/s]
 74%|███████▍  | 525/705 [02:21<00:46,  3.84it/s]
 75%|███████▍  | 526/705 [02:22<00:47,  3.80it/s]
 75%|███████▍  | 527/705 [02:22<00:47,  3.77it/s]
 75%|███████▍  | 528/705 [02:22<00:47,  3.76it/s]
 75%|███████▌  | 529/705 [02:22<00:46,  3.77it/s]
 75%|███████▌  | 530/705 [02:23<00:45,  3.83it/s]
 75%|███████▌  | 531/705 [02:23<00:45,  3.83it/s]
 75%|███████▌  | 532/705 [02:23<00:45,  3.79it/s]
 76%|███████▌  | 533/705 [02:23<00:45,  3.80it/s]
 76%|███████▌  | 534/705 [02:24<00:45,  3.78it/s]
 76%|███████▌  | 535/705 [02:24<00:44,  3.84it/s]
 76%|███████▌  | 536/705 [02:24<00:44,  3.80it/s]
 76%|███████▌  | 537/705 [02:25<00:44,  3.79it/s]
 76%|███████▋  | 538/705 [02:25<00:49,  3.37it/s]
 76%|███████▋  | 539/705 [02:25<00:47,  3.46it/s]
 77%|███████▋  | 540/705 [02:25<00:46,  3.59it/s]
 77%|███████▋  | 541/705 [02:26<00:45,  3.64it/s]
 77%|███████▋  | 542/705 [02:26<00:43,  3.74it/s]
 77%|███████▋  | 543/705 [02:26<00:43,  3.74it/s]
 77%|███████▋  | 544/705 [02:26<00:42,  3.75it/s]
 77%|███████▋  | 545/705 [02:27<00:42,  3.74it/s]
 77%|███████▋  | 546/705 [02:27<00:41,  3.79it/s]
 78%|███████▊  | 547/705 [02:27<00:41,  3.81it/s]
 78%|███████▊  | 548/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 549/705 [02:28<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:28<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:28<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:29<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:29<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:29<00:40,  3.75it/s]
 79%|███████▊  | 555/705 [02:29<00:40,  3.74it/s]
 79%|███████▉  | 556/705 [02:30<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:30<00:38,  3.84it/s]
 79%|███████▉  | 558/705 [02:30<00:38,  3.84it/s]
 79%|███████▉  | 559/705 [02:30<00:38,  3.82it/s]
 79%|███████▉  | 560/705 [02:31<00:37,  3.84it/s]
 80%|███████▉  | 561/705 [02:31<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:31<00:35,  4.04it/s]
 80%|███████▉  | 563/705 [02:31<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:32<00:33,  4.17it/s]
 80%|████████  | 565/705 [02:32<00:33,  4.19it/s]
 80%|████████  | 566/705 [02:32<00:34,  4.03it/s]
 80%|████████  | 567/705 [02:32<00:34,  3.94it/s]
 81%|████████  | 568/705 [02:33<00:35,  3.91it/s]
 81%|████████  | 569/705 [02:33<00:34,  3.97it/s]
 81%|████████  | 570/705 [02:33<00:34,  3.96it/s]
 81%|████████  | 571/705 [02:33<00:33,  3.95it/s]
 81%|████████  | 572/705 [02:34<00:34,  3.87it/s]
 81%|████████▏ | 573/705 [02:34<00:34,  3.82it/s]
 81%|████████▏ | 574/705 [02:34<00:34,  3.80it/s]
 82%|████████▏ | 575/705 [02:34<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:35<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:35<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:35<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:36<00:33,  3.77it/s]
 82%|████████▏ | 580/705 [02:36<00:33,  3.75it/s]
 82%|████████▏ | 581/705 [02:36<00:32,  3.80it/s]
 83%|████████▎ | 582/705 [02:36<00:32,  3.77it/s]
 83%|████████▎ | 583/705 [02:37<00:32,  3.75it/s]
 83%|████████▎ | 584/705 [02:37<00:31,  3.82it/s]
 83%|████████▎ | 585/705 [02:37<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:37<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:38<00:31,  3.79it/s]
 83%|████████▎ | 588/705 [02:38<00:30,  3.78it/s]
 84%|████████▎ | 589/705 [02:38<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:38<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:39<00:30,  3.73it/s]
 84%|████████▍ | 592/705 [02:39<00:29,  3.79it/s]
 84%|████████▍ | 593/705 [02:39<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:39<00:29,  3.75it/s]
 84%|████████▍ | 595/705 [02:40<00:28,  3.81it/s]
 85%|████████▍ | 596/705 [02:40<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:40<00:28,  3.80it/s]
 85%|████████▍ | 598/705 [02:41<00:28,  3.78it/s]
 85%|████████▍ | 599/705 [02:41<00:27,  3.86it/s]
 85%|████████▌ | 600/705 [02:41<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:41<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:42<00:26,  3.94it/s]
 86%|████████▌ | 603/705 [02:42<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:42<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:42<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:43<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:43<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:43<00:24,  3.94it/s]
 86%|████████▋ | 609/705 [02:43<00:24,  3.86it/s]
 87%|████████▋ | 610/705 [02:44<00:24,  3.92it/s]
 87%|████████▋ | 611/705 [02:44<00:23,  3.99it/s]
 87%|████████▋ | 612/705 [02:44<00:23,  3.94it/s]
 87%|████████▋ | 613/705 [02:44<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:45<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:45<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:45<00:23,  3.84it/s]
 88%|████████▊ | 617/705 [02:45<00:22,  3.91it/s]
 88%|████████▊ | 618/705 [02:46<00:22,  3.87it/s]
 88%|████████▊ | 619/705 [02:46<00:21,  3.96it/s]
 88%|████████▊ | 620/705 [02:46<00:21,  3.90it/s]
 88%|████████▊ | 621/705 [02:46<00:21,  3.92it/s]
 88%|████████▊ | 622/705 [02:47<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:47<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:47<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:47<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:48<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:48<00:20,  3.79it/s]
 89%|████████▉ | 628/705 [02:48<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:49<00:19,  3.82it/s]
 89%|████████▉ | 630/705 [02:49<00:19,  3.80it/s]
 90%|████████▉ | 631/705 [02:49<00:19,  3.77it/s]
 90%|████████▉ | 632/705 [02:49<00:19,  3.76it/s]
 90%|████████▉ | 633/705 [02:50<00:18,  3.80it/s]
 90%|████████▉ | 634/705 [02:50<00:18,  3.85it/s]
 90%|█████████ | 635/705 [02:50<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:50<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:51<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:51<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:51<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:51<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:52<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:52<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:52<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:52<00:15,  3.83it/s]
 91%|█████████▏| 645/705 [02:53<00:15,  3.81it/s]
 92%|█████████▏| 646/705 [02:53<00:15,  3.80it/s]
 92%|█████████▏| 647/705 [02:53<00:15,  3.77it/s]
 92%|█████████▏| 648/705 [02:53<00:15,  3.80it/s]
 92%|█████████▏| 649/705 [02:54<00:14,  3.79it/s]
 92%|█████████▏| 650/705 [02:54<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:54<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:55<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:55<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:55<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:55<00:13,  3.80it/s]
 93%|█████████▎| 656/705 [02:56<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:56<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:56<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:56<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:57<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:57<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:57<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:57<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:58<00:10,  3.77it/s]
 94%|█████████▍| 665/705 [02:58<00:10,  3.90it/s]
 94%|█████████▍| 666/705 [02:58<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [02:58<00:09,  3.83it/s]
 95%|█████████▍| 668/705 [02:59<00:09,  3.83it/s]
 95%|█████████▍| 669/705 [02:59<00:09,  3.80it/s]
 95%|█████████▌| 670/705 [02:59<00:09,  3.80it/s]
 95%|█████████▌| 671/705 [03:00<00:08,  3.79it/s]
 95%|█████████▌| 672/705 [03:00<00:08,  3.78it/s]
 95%|█████████▌| 673/705 [03:00<00:08,  3.84it/s]
 96%|█████████▌| 674/705 [03:00<00:07,  3.90it/s]
 96%|█████████▌| 675/705 [03:01<00:07,  3.84it/s]
 96%|█████████▌| 676/705 [03:01<00:07,  3.86it/s]
 96%|█████████▌| 677/705 [03:01<00:07,  3.82it/s]
 96%|█████████▌| 678/705 [03:01<00:07,  3.78it/s]
 96%|█████████▋| 679/705 [03:02<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:02<00:06,  3.77it/s]
 97%|█████████▋| 681/705 [03:02<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:02<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:03<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:03<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:03<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:03<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:04<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:04<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:04<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:05<00:03,  3.78it/s]
 98%|█████████▊| 691/705 [03:05<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:05<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:05<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:06<00:02,  3.83it/s]
 99%|█████████▊| 695/705 [03:06<00:02,  3.79it/s]
 99%|█████████▊| 696/705 [03:06<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:06<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:07<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:07<00:01,  3.85it/s]
 99%|█████████▉| 700/705 [03:07<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:07<00:01,  3.80it/s]
100%|█████████▉| 702/705 [03:08<00:00,  3.78it/s]
100%|█████████▉| 703/705 [03:08<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:08<00:00,  3.80it/s]
100%|██████████| 705/705 [03:08<00:00,  4.55it/s]
                                                 

100%|██████████| 705/705 [03:08<00:00,  4.55it/s]{'eval_loss': 0.7190243601799011, 'eval_accuracy': 0.702, 'eval_f1': 0.6933534436833712, 'eval_runtime': 1.7307, 'eval_samples_per_second': 1444.481, 'eval_steps_per_second': 180.849, 'epoch': 2.0}
{'loss': 0.3247, 'learning_rate': 9.359952753352034e-05, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.61it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.86it/s]

 21%|██        | 66/313 [00:00<00:01, 204.87it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.75it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.41it/s]

 40%|████      | 126/313 [00:00<00:01, 185.33it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.45it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.35it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.24it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.34it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.79it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.63it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.47it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 185.25it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.97it/s]
                                                 

                                                  

100%|██████████| 705/705 [03:10<00:00,  4.55it/s]

100%|██████████| 313/313 [00:01<00:00, 178.97it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:11<00:00,  4.55it/s]
100%|██████████| 705/705 [03:11<00:00,  3.68it/s]
[I 2023-10-26 22:03:00,307] Trial 0 finished with value: 0.6938848740526541 and parameters: {'lr_scheduler_type': 'constant', 'learning_rate': 9.359952753352034e-05, 'per_device_train_batch_size': 128, 'weight_decay': 0.0007368598115037885}. Best is trial 0 with value: 0.6938848740526541.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.826500415802002, 'eval_accuracy': 0.6924, 'eval_f1': 0.6938848740526541, 'eval_runtime': 1.7296, 'eval_samples_per_second': 1445.446, 'eval_steps_per_second': 180.97, 'epoch': 3.0}
{'train_runtime': 191.5343, 'train_samples_per_second': 469.89, 'train_steps_per_second': 3.681, 'train_loss': 0.5369771538051308, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:12,  3.66it/s]
  0%|          | 2/705 [00:00<03:10,  3.69it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:54,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.77it/s]
  7%|▋         | 50/705 [00:13<02:54,  3.75it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.78it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:49,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.86it/s]
 10%|█         | 71/705 [00:18<02:45,  3.84it/s]
 10%|█         | 72/705 [00:18<02:41,  3.93it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:44,  3.82it/s]
 11%|█         | 76/705 [00:19<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:44,  3.82it/s]
 11%|█         | 78/705 [00:20<02:42,  3.87it/s]
 11%|█         | 79/705 [00:20<02:44,  3.82it/s]
 11%|█▏        | 80/705 [00:21<02:44,  3.80it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.78it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:43,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.79it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.73it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.80it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.79it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:35,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.80it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:31,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.89it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:36<03:12,  2.96it/s]
 19%|█▉        | 137/705 [00:36<02:58,  3.18it/s]
 20%|█▉        | 138/705 [00:36<02:49,  3.35it/s]
 20%|█▉        | 139/705 [00:36<02:44,  3.45it/s]
 20%|█▉        | 140/705 [00:37<02:40,  3.53it/s]
 20%|██        | 141/705 [00:37<02:37,  3.58it/s]
 20%|██        | 142/705 [00:37<02:29,  3.77it/s]
 20%|██        | 143/705 [00:37<02:30,  3.74it/s]
 20%|██        | 144/705 [00:38<02:28,  3.79it/s]
 21%|██        | 145/705 [00:38<02:28,  3.76it/s]
 21%|██        | 146/705 [00:38<02:29,  3.74it/s]
 21%|██        | 147/705 [00:38<02:24,  3.85it/s]
 21%|██        | 148/705 [00:39<02:23,  3.89it/s]
 21%|██        | 149/705 [00:39<02:24,  3.85it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:25,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:41<02:57,  3.10it/s]
 22%|██▏       | 156/705 [00:41<02:45,  3.31it/s]
 22%|██▏       | 157/705 [00:41<02:34,  3.54it/s]
 22%|██▏       | 158/705 [00:41<02:31,  3.60it/s]
 23%|██▎       | 159/705 [00:42<02:30,  3.63it/s]
 23%|██▎       | 160/705 [00:42<02:28,  3.66it/s]
 23%|██▎       | 161/705 [00:42<02:27,  3.69it/s]
 23%|██▎       | 162/705 [00:43<02:26,  3.70it/s]
 23%|██▎       | 163/705 [00:43<02:25,  3.72it/s]
 23%|██▎       | 164/705 [00:43<02:22,  3.79it/s]
 23%|██▎       | 165/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 166/705 [00:44<02:21,  3.80it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.83it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:45<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:46<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:48<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:49<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.85it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 197/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.97it/s]
 29%|██▉       | 205/705 [00:54<02:07,  3.91it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.87it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.86it/s]
 30%|██▉       | 208/705 [00:55<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.76it/s]
 30%|███       | 212/705 [00:56<02:07,  3.88it/s]
 30%|███       | 213/705 [00:56<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.80it/s]
 31%|███       | 216/705 [00:57<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:05,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [01:00<02:05,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.79it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:01<02:05,  3.79it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8396, 'learning_rate': 1.579732234533526e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.36it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.54it/s]

 21%|██        | 66/313 [00:00<00:01, 205.91it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.14it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.53it/s]

 40%|████      | 126/313 [00:00<00:01, 185.20it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.23it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.23it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.31it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.39it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.48it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.10it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.89it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.82it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.70it/s]
                                                 

                                                  

 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

100%|██████████| 313/313 [00:01<00:00, 178.70it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<07:54,  1.01s/it]
 34%|███▎      | 237/705 [01:05<06:07,  1.27it/s]
 34%|███▍      | 238/705 [01:05<04:54,  1.59it/s]
 34%|███▍      | 239/705 [01:05<04:02,  1.93it/s]
 34%|███▍      | 240/705 [01:05<03:26,  2.25it/s]
 34%|███▍      | 241/705 [01:06<03:00,  2.57it/s]
 34%|███▍      | 242/705 [01:06<02:43,  2.83it/s]
 34%|███▍      | 243/705 [01:06<02:30,  3.06it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.29it/s]
 35%|███▍      | 245/705 [01:07<02:14,  3.41it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.49it/s]
 35%|███▌      | 247/705 [01:07<02:08,  3.55it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.73it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:09<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:10<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:11<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:12<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.87it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.83it/s]
 38%|███▊      | 268/705 [01:13<01:55,  3.79it/s]
 38%|███▊      | 269/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.86it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:17<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:18<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:19<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:46,  3.83it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.88it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:23<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:54,  3.47it/s]
 44%|████▍     | 310/705 [01:24<01:51,  3.53it/s]
 44%|████▍     | 311/705 [01:24<01:49,  3.60it/s]
 44%|████▍     | 312/705 [01:24<01:47,  3.65it/s]
 44%|████▍     | 313/705 [01:24<01:46,  3.68it/s]
 45%|████▍     | 314/705 [01:25<01:39,  3.94it/s]
 45%|████▍     | 315/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 316/705 [01:25<01:41,  3.84it/s]
 45%|████▍     | 317/705 [01:25<01:40,  3.86it/s]
 45%|████▌     | 318/705 [01:26<01:41,  3.82it/s]
 45%|████▌     | 319/705 [01:26<01:42,  3.78it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.75it/s]
 46%|████▌     | 321/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:28<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.80it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.77it/s]
 47%|████▋     | 328/705 [01:28<01:43,  3.63it/s]
 47%|████▋     | 329/705 [01:29<01:41,  3.72it/s]
 47%|████▋     | 330/705 [01:29<01:40,  3.72it/s]
 47%|████▋     | 331/705 [01:29<01:40,  3.74it/s]
 47%|████▋     | 332/705 [01:29<01:40,  3.73it/s]
 47%|████▋     | 333/705 [01:30<01:39,  3.73it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.73it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:31<01:37,  3.77it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:32<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.89it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.86it/s]
 49%|████▉     | 344/705 [01:33<01:34,  3.81it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:36<01:33,  3.75it/s]
 50%|█████     | 356/705 [01:36<01:32,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.74it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:37<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.75it/s]
 51%|█████▏    | 363/705 [01:38<01:31,  3.74it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:39<01:44,  3.25it/s]
 52%|█████▏    | 367/705 [01:39<01:38,  3.42it/s]
 52%|█████▏    | 368/705 [01:39<01:35,  3.53it/s]
 52%|█████▏    | 369/705 [01:39<01:33,  3.60it/s]
 52%|█████▏    | 370/705 [01:40<01:31,  3.67it/s]
 53%|█████▎    | 371/705 [01:40<01:28,  3.75it/s]
 53%|█████▎    | 372/705 [01:40<01:29,  3.73it/s]
 53%|█████▎    | 373/705 [01:40<01:28,  3.75it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.73it/s]
 53%|█████▎    | 375/705 [01:41<01:28,  3.74it/s]
 53%|█████▎    | 376/705 [01:41<01:28,  3.73it/s]
 53%|█████▎    | 377/705 [01:42<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:43<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.83it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:44<01:34,  3.40it/s]
 55%|█████▍    | 386/705 [01:44<01:30,  3.54it/s]
 55%|█████▍    | 387/705 [01:44<01:28,  3.60it/s]
 55%|█████▌    | 388/705 [01:45<01:27,  3.63it/s]
 55%|█████▌    | 389/705 [01:45<01:25,  3.71it/s]
 55%|█████▌    | 390/705 [01:45<01:24,  3.73it/s]
 55%|█████▌    | 391/705 [01:45<01:24,  3.72it/s]
 56%|█████▌    | 392/705 [01:46<01:22,  3.78it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.77it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.81it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.79it/s]
 56%|█████▌    | 396/705 [01:47<01:22,  3.76it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:51<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:52<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:53<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.84it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:56<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.80it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:57<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:58<01:10,  3.81it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 442/705 [01:59<01:10,  3.76it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 452/705 [02:01<01:05,  3.84it/s]
 64%|██████▍   | 453/705 [02:02<01:05,  3.88it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 457/705 [02:03<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:06<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.7195790410041809, 'eval_accuracy': 0.6872, 'eval_f1': 0.6855307403953875, 'eval_runtime': 1.7316, 'eval_samples_per_second': 1443.737, 'eval_steps_per_second': 180.756, 'epoch': 1.0}
{'loss': 0.6268, 'learning_rate': 7.915431153925946e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.65it/s]

 14%|█▎        | 43/313 [00:00<00:01, 198.11it/s]

 21%|██        | 65/313 [00:00<00:01, 205.10it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.51it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.75it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.41it/s]

 46%|████▌     | 144/313 [00:00<00:00, 184.16it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 185.04it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.60it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.31it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.22it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.30it/s]

 83%|████████▎ | 259/313 [00:01<00:00, 184.27it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.07it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.36it/s]
                                                 

                                                  

 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

100%|██████████| 313/313 [00:01<00:00, 179.36it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<03:59,  1.03s/it]
 67%|██████▋   | 472/705 [02:09<03:05,  1.26it/s]
 67%|██████▋   | 473/705 [02:09<02:27,  1.57it/s]
 67%|██████▋   | 474/705 [02:10<02:01,  1.91it/s]
 67%|██████▋   | 475/705 [02:10<01:42,  2.24it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.54it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.81it/s]
 68%|██████▊   | 478/705 [02:11<01:15,  3.03it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.22it/s]
 68%|██████▊   | 480/705 [02:11<01:06,  3.36it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.51it/s]
 68%|██████▊   | 482/705 [02:12<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.62it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.77it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:14<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.83it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.79it/s]
 70%|██████▉   | 493/705 [02:15<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:16<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.88it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:17<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.78it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:19<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.76it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:46,  3.86it/s]
 74%|███████▍  | 525/705 [02:23<00:46,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:24<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.80it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 535/705 [02:26<00:44,  3.84it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.76it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.74it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.81it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.77it/s]
 77%|███████▋  | 546/705 [02:29<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.83it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.83it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.86it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.86it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.74it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.84it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.84it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.80it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.77it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 588/705 [02:39<00:30,  3.77it/s]
 84%|████████▎ | 589/705 [02:40<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:41<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:41<00:31,  3.49it/s]
 85%|████████▍ | 596/705 [02:42<00:30,  3.57it/s]
 85%|████████▍ | 597/705 [02:42<00:29,  3.64it/s]
 85%|████████▍ | 598/705 [02:42<00:29,  3.66it/s]
 85%|████████▍ | 599/705 [02:42<00:28,  3.77it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.77it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.01it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.90it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.86it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.83it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 606/705 [02:44<00:26,  3.81it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.92it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:24,  3.68it/s]
 87%|████████▋ | 616/705 [02:47<00:23,  3.74it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.83it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.82it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.92it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.88it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.84it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.82it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.82it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:19,  3.65it/s]
 90%|█████████ | 635/705 [02:52<00:19,  3.66it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.70it/s]
 90%|█████████ | 637/705 [02:52<00:18,  3.72it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.73it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.76it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.91it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.87it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.92it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:15,  3.45it/s]
 93%|█████████▎| 654/705 [02:57<00:14,  3.54it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.59it/s]
 93%|█████████▎| 656/705 [02:57<00:13,  3.64it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.70it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.76it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.77it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.81it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.79it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.77it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.77it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.75it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.85it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.90it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.80it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.78it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.55it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.55it/s]{'eval_loss': 0.6828795075416565, 'eval_accuracy': 0.7104, 'eval_f1': 0.7063611173392533, 'eval_runtime': 1.7276, 'eval_samples_per_second': 1447.103, 'eval_steps_per_second': 181.177, 'epoch': 2.0}
{'loss': 0.5355, 'learning_rate': 3.353996251663537e-08, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.36it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.78it/s]

 21%|██        | 66/313 [00:00<00:01, 206.33it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.50it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.86it/s]

 40%|████      | 126/313 [00:00<00:01, 185.65it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.52it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.60it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.69it/s]

 65%|██████▍   | 202/313 [00:01<00:00, 174.08it/s]

 70%|███████   | 220/313 [00:01<00:00, 167.86it/s]

 76%|███████▌  | 237/313 [00:01<00:00, 166.26it/s]

 83%|████████▎ | 261/313 [00:01<00:00, 186.56it/s]

 89%|████████▉ | 280/313 [00:01<00:00, 184.24it/s]

 96%|█████████▌| 299/313 [00:01<00:00, 179.25it/s]
                                                 

                                                  

100%|██████████| 705/705 [03:12<00:00,  4.55it/s]

100%|██████████| 313/313 [00:01<00:00, 179.25it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.55it/s]
100%|██████████| 705/705 [03:13<00:00,  3.64it/s]
[I 2023-10-26 22:06:14,481] Trial 1 finished with value: 0.7159626561431993 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 2.1264336235546823e-05, 'per_device_train_batch_size': 128, 'weight_decay': 0.0026241816378998264}. Best is trial 1 with value: 0.7159626561431993.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6736130118370056, 'eval_accuracy': 0.7172, 'eval_f1': 0.7159626561431993, 'eval_runtime': 1.7259, 'eval_samples_per_second': 1448.481, 'eval_steps_per_second': 181.35, 'epoch': 3.0}
{'train_runtime': 193.4236, 'train_samples_per_second': 465.3, 'train_steps_per_second': 3.645, 'train_loss': 0.6673052415780142, 'epoch': 3.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:03,  1.92it/s]
  1%|          | 2/354 [00:01<03:00,  1.95it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:53,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:54,  2.00it/s]
  2%|▏         | 6/354 [00:03<02:52,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.05it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.03it/s]
  3%|▎         | 9/354 [00:04<02:51,  2.01it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:49,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:50,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:50,  2.00it/s]
  4%|▍         | 14/354 [00:06<02:51,  1.99it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.99it/s]
  5%|▍         | 16/354 [00:07<02:49,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:49,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:45,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:45,  2.01it/s]
  6%|▌         | 22/354 [00:10<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:46,  1.98it/s]
  7%|▋         | 24/354 [00:11<02:45,  1.99it/s]
  7%|▋         | 25/354 [00:12<02:45,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:45,  1.98it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.02it/s]
  8%|▊         | 28/354 [00:13<02:41,  2.02it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:42,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:15<02:39,  2.01it/s]
  9%|▉         | 33/354 [00:16<02:40,  2.00it/s]
 10%|▉         | 34/354 [00:16<02:40,  1.99it/s]
 10%|▉         | 35/354 [00:17<02:37,  2.03it/s]
 10%|█         | 36/354 [00:17<02:35,  2.05it/s]
 10%|█         | 37/354 [00:18<02:34,  2.05it/s]
 11%|█         | 38/354 [00:18<02:35,  2.03it/s]
 11%|█         | 39/354 [00:19<02:35,  2.02it/s]
 11%|█▏        | 40/354 [00:19<02:36,  2.00it/s]
 12%|█▏        | 41/354 [00:20<02:37,  1.99it/s]
 12%|█▏        | 42/354 [00:20<02:33,  2.03it/s]
 12%|█▏        | 43/354 [00:21<02:34,  2.01it/s]
 12%|█▏        | 44/354 [00:21<02:34,  2.01it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:22<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:23<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:25<02:32,  1.99it/s]
 15%|█▍        | 53/354 [00:26<02:27,  2.04it/s]
 15%|█▌        | 54/354 [00:26<02:28,  2.01it/s]
 16%|█▌        | 55/354 [00:27<02:28,  2.01it/s]
 16%|█▌        | 56/354 [00:27<02:28,  2.00it/s]
 16%|█▌        | 57/354 [00:28<02:26,  2.03it/s]
 16%|█▋        | 58/354 [00:28<02:27,  2.01it/s]
 17%|█▋        | 59/354 [00:29<02:24,  2.04it/s]
 17%|█▋        | 60/354 [00:29<02:25,  2.01it/s]
 17%|█▋        | 61/354 [00:30<02:25,  2.01it/s]
 18%|█▊        | 62/354 [00:30<02:23,  2.04it/s]
 18%|█▊        | 63/354 [00:31<02:21,  2.06it/s]
 18%|█▊        | 64/354 [00:31<02:19,  2.07it/s]
 18%|█▊        | 65/354 [00:32<02:20,  2.06it/s]
 19%|█▊        | 66/354 [00:32<02:20,  2.05it/s]
 19%|█▉        | 67/354 [00:33<02:20,  2.04it/s]
 19%|█▉        | 68/354 [00:33<02:20,  2.03it/s]
 19%|█▉        | 69/354 [00:34<02:18,  2.05it/s]
 20%|█▉        | 70/354 [00:34<02:20,  2.03it/s]
 20%|██        | 71/354 [00:35<02:21,  2.01it/s]
 20%|██        | 72/354 [00:35<02:21,  1.99it/s]
 21%|██        | 73/354 [00:36<02:21,  1.98it/s]
 21%|██        | 74/354 [00:36<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.02it/s]
 21%|██▏       | 76/354 [00:37<02:15,  2.05it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:38<02:17,  2.01it/s]
 22%|██▏       | 79/354 [00:39<02:16,  2.01it/s]
 23%|██▎       | 80/354 [00:39<02:17,  1.99it/s]
 23%|██▎       | 81/354 [00:40<02:17,  1.99it/s]
 23%|██▎       | 82/354 [00:40<02:16,  1.99it/s]
 23%|██▎       | 83/354 [00:41<02:14,  2.01it/s]
 24%|██▎       | 84/354 [00:41<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:13,  2.02it/s]
 24%|██▍       | 86/354 [00:42<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  2.00it/s]
 25%|██▍       | 88/354 [00:43<02:12,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:44<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 92/354 [00:45<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.02it/s]
 27%|██▋       | 94/354 [00:46<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.05it/s]
 27%|██▋       | 96/354 [00:47<02:06,  2.05it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:48<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.10it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:03,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  2.00it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  2.00it/s]
 31%|███       | 109/354 [00:54<02:03,  1.99it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:58,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.9651, 'learning_rate': 5.797453357893295e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.29it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.38it/s]

 21%|██        | 66/313 [00:00<00:01, 205.91it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.11it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.51it/s]

 40%|████      | 126/313 [00:00<00:01, 185.22it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.16it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.16it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.34it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.44it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.38it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.02it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.69it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.63it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.46it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.46it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 34%|███▎      | 119/354 [01:01<04:42,  1.20s/it]
 34%|███▍      | 120/354 [01:01<03:52,  1.01it/s]
 34%|███▍      | 121/354 [01:02<03:17,  1.18it/s]
 34%|███▍      | 122/354 [01:02<02:53,  1.34it/s]
 35%|███▍      | 123/354 [01:03<02:35,  1.49it/s]
 35%|███▌      | 124/354 [01:03<02:23,  1.60it/s]
 35%|███▌      | 125/354 [01:04<02:12,  1.72it/s]
 36%|███▌      | 126/354 [01:04<02:07,  1.79it/s]
 36%|███▌      | 127/354 [01:05<02:00,  1.88it/s]
 36%|███▌      | 128/354 [01:05<01:58,  1.90it/s]
 36%|███▋      | 129/354 [01:06<01:57,  1.92it/s]
 37%|███▋      | 130/354 [01:06<01:55,  1.95it/s]
 37%|███▋      | 131/354 [01:07<01:53,  1.96it/s]
 37%|███▋      | 132/354 [01:07<01:53,  1.96it/s]
 38%|███▊      | 133/354 [01:08<01:51,  1.98it/s]
 38%|███▊      | 134/354 [01:08<01:51,  1.98it/s]
 38%|███▊      | 135/354 [01:09<01:50,  1.97it/s]
 38%|███▊      | 136/354 [01:09<01:48,  2.01it/s]
 39%|███▊      | 137/354 [01:10<01:46,  2.04it/s]
 39%|███▉      | 138/354 [01:10<01:46,  2.02it/s]
 39%|███▉      | 139/354 [01:11<01:44,  2.06it/s]
 40%|███▉      | 140/354 [01:11<01:45,  2.03it/s]
 40%|███▉      | 141/354 [01:12<01:45,  2.03it/s]
 40%|████      | 142/354 [01:12<01:45,  2.02it/s]
 40%|████      | 143/354 [01:13<01:44,  2.01it/s]
 41%|████      | 144/354 [01:13<01:44,  2.00it/s]
 41%|████      | 145/354 [01:14<01:44,  1.99it/s]
 41%|████      | 146/354 [01:14<01:44,  2.00it/s]
 42%|████▏     | 147/354 [01:15<01:42,  2.01it/s]
 42%|████▏     | 148/354 [01:15<01:42,  2.00it/s]
 42%|████▏     | 149/354 [01:16<01:40,  2.04it/s]
 42%|████▏     | 150/354 [01:16<01:40,  2.03it/s]
 43%|████▎     | 151/354 [01:17<01:38,  2.05it/s]
 43%|████▎     | 152/354 [01:17<01:39,  2.04it/s]
 43%|████▎     | 153/354 [01:18<01:35,  2.10it/s]
 44%|████▎     | 154/354 [01:18<01:37,  2.06it/s]
 44%|████▍     | 155/354 [01:19<01:38,  2.03it/s]
 44%|████▍     | 156/354 [01:19<01:38,  2.01it/s]
 44%|████▍     | 157/354 [01:20<01:38,  2.01it/s]
 45%|████▍     | 158/354 [01:20<01:38,  2.00it/s]
 45%|████▍     | 159/354 [01:21<01:37,  2.00it/s]
 45%|████▌     | 160/354 [01:21<01:37,  1.99it/s]
 45%|████▌     | 161/354 [01:22<01:37,  1.98it/s]
 46%|████▌     | 162/354 [01:22<01:37,  1.98it/s]
 46%|████▌     | 163/354 [01:23<01:36,  1.98it/s]
 46%|████▋     | 164/354 [01:23<01:36,  1.97it/s]
 47%|████▋     | 165/354 [01:24<01:35,  1.97it/s]
 47%|████▋     | 166/354 [01:24<01:35,  1.97it/s]
 47%|████▋     | 167/354 [01:25<01:34,  1.97it/s]
 47%|████▋     | 168/354 [01:25<01:34,  1.98it/s]
 48%|████▊     | 169/354 [01:26<01:33,  1.98it/s]
 48%|████▊     | 170/354 [01:26<01:33,  1.97it/s]
 48%|████▊     | 171/354 [01:27<01:32,  1.97it/s]
 49%|████▊     | 172/354 [01:27<01:30,  2.01it/s]
 49%|████▉     | 173/354 [01:28<01:30,  1.99it/s]
 49%|████▉     | 174/354 [01:28<01:28,  2.03it/s]
 49%|████▉     | 175/354 [01:29<01:28,  2.02it/s]
 50%|████▉     | 176/354 [01:29<01:28,  2.00it/s]
 50%|█████     | 177/354 [01:30<01:27,  2.03it/s]
 50%|█████     | 178/354 [01:30<01:27,  2.01it/s]
 51%|█████     | 179/354 [01:31<01:27,  1.99it/s]
 51%|█████     | 180/354 [01:31<01:27,  1.98it/s]
 51%|█████     | 181/354 [01:32<01:27,  1.98it/s]
 51%|█████▏    | 182/354 [01:32<01:26,  1.98it/s]
 52%|█████▏    | 183/354 [01:33<01:26,  1.98it/s]
 52%|█████▏    | 184/354 [01:33<01:24,  2.01it/s]
 52%|█████▏    | 185/354 [01:34<01:23,  2.04it/s]
 53%|█████▎    | 186/354 [01:34<01:21,  2.06it/s]
 53%|█████▎    | 187/354 [01:35<01:22,  2.03it/s]
 53%|█████▎    | 188/354 [01:35<01:22,  2.01it/s]
 53%|█████▎    | 189/354 [01:36<01:22,  1.99it/s]
 54%|█████▎    | 190/354 [01:36<01:21,  2.01it/s]
 54%|█████▍    | 191/354 [01:37<01:20,  2.02it/s]
 54%|█████▍    | 192/354 [01:37<01:19,  2.03it/s]
 55%|█████▍    | 193/354 [01:38<01:20,  2.01it/s]
 55%|█████▍    | 194/354 [01:38<01:19,  2.00it/s]
 55%|█████▌    | 195/354 [01:39<01:19,  1.99it/s]
 55%|█████▌    | 196/354 [01:39<01:19,  1.98it/s]
 56%|█████▌    | 197/354 [01:40<01:19,  1.99it/s]
 56%|█████▌    | 198/354 [01:40<01:18,  1.99it/s]
 56%|█████▌    | 199/354 [01:41<01:18,  1.98it/s]
 56%|█████▋    | 200/354 [01:41<01:17,  1.99it/s]
 57%|█████▋    | 201/354 [01:42<01:16,  1.99it/s]
 57%|█████▋    | 202/354 [01:42<01:16,  1.98it/s]
 57%|█████▋    | 203/354 [01:43<01:15,  2.00it/s]
 58%|█████▊    | 204/354 [01:43<01:15,  1.99it/s]
 58%|█████▊    | 205/354 [01:44<01:14,  2.01it/s]
 58%|█████▊    | 206/354 [01:44<01:14,  2.00it/s]
 58%|█████▊    | 207/354 [01:45<01:12,  2.03it/s]
 59%|█████▉    | 208/354 [01:45<01:12,  2.02it/s]
 59%|█████▉    | 209/354 [01:46<01:10,  2.05it/s]
 59%|█████▉    | 210/354 [01:46<01:09,  2.07it/s]
 60%|█████▉    | 211/354 [01:47<01:09,  2.05it/s]
 60%|█████▉    | 212/354 [01:47<01:10,  2.02it/s]
 60%|██████    | 213/354 [01:48<01:09,  2.02it/s]
 60%|██████    | 214/354 [01:48<01:09,  2.01it/s]
 61%|██████    | 215/354 [01:49<01:09,  2.00it/s]
 61%|██████    | 216/354 [01:49<01:09,  1.99it/s]
 61%|██████▏   | 217/354 [01:50<01:08,  1.99it/s]
 62%|██████▏   | 218/354 [01:50<01:08,  2.00it/s]
 62%|██████▏   | 219/354 [01:51<01:07,  2.00it/s]
 62%|██████▏   | 220/354 [01:51<01:06,  2.00it/s]
 62%|██████▏   | 221/354 [01:52<01:06,  1.99it/s]
 63%|██████▎   | 222/354 [01:52<01:05,  2.02it/s]
 63%|██████▎   | 223/354 [01:53<01:05,  2.00it/s]
 63%|██████▎   | 224/354 [01:53<01:03,  2.03it/s]
 64%|██████▎   | 225/354 [01:54<01:03,  2.04it/s]
 64%|██████▍   | 226/354 [01:54<01:03,  2.01it/s]
 64%|██████▍   | 227/354 [01:55<01:01,  2.05it/s]
 64%|██████▍   | 228/354 [01:55<01:01,  2.04it/s]
 65%|██████▍   | 229/354 [01:56<01:01,  2.04it/s]
 65%|██████▍   | 230/354 [01:56<01:00,  2.03it/s]
 65%|██████▌   | 231/354 [01:57<01:00,  2.02it/s]
 66%|██████▌   | 232/354 [01:57<01:03,  1.91it/s]
 66%|██████▌   | 233/354 [01:58<01:02,  1.93it/s]
 66%|██████▌   | 234/354 [01:58<01:01,  1.94it/s]
 66%|██████▋   | 235/354 [01:59<01:00,  1.95it/s]
 67%|██████▋   | 236/354 [01:59<00:46,  2.54it/s]
                                                 

 67%|██████▋   | 236/354 [01:59<00:46,  2.54it/s]{'eval_loss': 0.7920665144920349, 'eval_accuracy': 0.6356, 'eval_f1': 0.6216742390199435, 'eval_runtime': 1.7323, 'eval_samples_per_second': 1443.195, 'eval_steps_per_second': 180.688, 'epoch': 1.0}
{'loss': 0.759, 'learning_rate': 2.8987266789466477e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.93it/s]

 14%|█▎        | 43/313 [00:00<00:01, 198.08it/s]

 21%|██        | 65/313 [00:00<00:01, 205.10it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.48it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.52it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.04it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.60it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.46it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.14it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.19it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.38it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.50it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.58it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.84it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.00it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.00it/s]
 67%|██████▋   | 236/354 [02:01<00:46,  2.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 237/354 [02:02<02:22,  1.22s/it]
 67%|██████▋   | 238/354 [02:03<01:55,  1.00it/s]
 68%|██████▊   | 239/354 [02:03<01:37,  1.18it/s]
 68%|██████▊   | 240/354 [02:04<01:25,  1.34it/s]
 68%|██████▊   | 241/354 [02:04<01:16,  1.48it/s]
 68%|██████▊   | 242/354 [02:05<01:09,  1.60it/s]
 69%|██████▊   | 243/354 [02:05<01:05,  1.70it/s]
 69%|██████▉   | 244/354 [02:06<01:01,  1.78it/s]
 69%|██████▉   | 245/354 [02:06<00:59,  1.84it/s]
 69%|██████▉   | 246/354 [02:07<00:57,  1.87it/s]
 70%|██████▉   | 247/354 [02:07<00:56,  1.90it/s]
 70%|███████   | 248/354 [02:08<00:55,  1.92it/s]
 70%|███████   | 249/354 [02:08<00:53,  1.97it/s]
 71%|███████   | 250/354 [02:09<00:52,  1.97it/s]
 71%|███████   | 251/354 [02:09<00:51,  1.99it/s]
 71%|███████   | 252/354 [02:10<00:50,  2.01it/s]
 71%|███████▏  | 253/354 [02:10<00:50,  2.00it/s]
 72%|███████▏  | 254/354 [02:11<00:50,  2.00it/s]
 72%|███████▏  | 255/354 [02:11<00:49,  1.99it/s]
 72%|███████▏  | 256/354 [02:12<00:49,  1.98it/s]
 73%|███████▎  | 257/354 [02:12<00:48,  2.01it/s]
 73%|███████▎  | 258/354 [02:13<00:48,  2.00it/s]
 73%|███████▎  | 259/354 [02:13<00:47,  2.00it/s]
 73%|███████▎  | 260/354 [02:14<00:47,  2.00it/s]
 74%|███████▎  | 261/354 [02:14<00:45,  2.03it/s]
 74%|███████▍  | 262/354 [02:14<00:44,  2.06it/s]
 74%|███████▍  | 263/354 [02:15<00:44,  2.06it/s]
 75%|███████▍  | 264/354 [02:15<00:44,  2.03it/s]
 75%|███████▍  | 265/354 [02:16<00:44,  2.01it/s]
 75%|███████▌  | 266/354 [02:16<00:43,  2.02it/s]
 75%|███████▌  | 267/354 [02:17<00:43,  2.00it/s]
 76%|███████▌  | 268/354 [02:18<00:43,  2.00it/s]
 76%|███████▌  | 269/354 [02:18<00:42,  1.99it/s]
 76%|███████▋  | 270/354 [02:19<00:42,  1.98it/s]
 77%|███████▋  | 271/354 [02:19<00:42,  1.97it/s]
 77%|███████▋  | 272/354 [02:20<00:41,  1.99it/s]
 77%|███████▋  | 273/354 [02:20<00:40,  1.99it/s]
 77%|███████▋  | 274/354 [02:21<00:40,  1.98it/s]
 78%|███████▊  | 275/354 [02:21<00:39,  2.02it/s]
 78%|███████▊  | 276/354 [02:21<00:38,  2.05it/s]
 78%|███████▊  | 277/354 [02:22<00:37,  2.03it/s]
 79%|███████▊  | 278/354 [02:23<00:37,  2.01it/s]
 79%|███████▉  | 279/354 [02:23<00:37,  2.00it/s]
 79%|███████▉  | 280/354 [02:23<00:36,  2.02it/s]
 79%|███████▉  | 281/354 [02:24<00:36,  2.02it/s]
 80%|███████▉  | 282/354 [02:24<00:35,  2.05it/s]
 80%|███████▉  | 283/354 [02:25<00:34,  2.07it/s]
 80%|████████  | 284/354 [02:25<00:34,  2.04it/s]
 81%|████████  | 285/354 [02:26<00:34,  2.02it/s]
 81%|████████  | 286/354 [02:26<00:32,  2.06it/s]
 81%|████████  | 287/354 [02:27<00:32,  2.03it/s]
 81%|████████▏ | 288/354 [02:27<00:32,  2.01it/s]
 82%|████████▏ | 289/354 [02:28<00:32,  2.02it/s]
 82%|████████▏ | 290/354 [02:28<00:31,  2.01it/s]
 82%|████████▏ | 291/354 [02:29<00:31,  2.00it/s]
 82%|████████▏ | 292/354 [02:29<00:31,  1.99it/s]
 83%|████████▎ | 293/354 [02:30<00:30,  1.98it/s]
 83%|████████▎ | 294/354 [02:30<00:29,  2.00it/s]
 83%|████████▎ | 295/354 [02:31<00:29,  2.00it/s]
 84%|████████▎ | 296/354 [02:31<00:29,  1.99it/s]
 84%|████████▍ | 297/354 [02:32<00:28,  1.98it/s]
 84%|████████▍ | 298/354 [02:32<00:28,  1.98it/s]
 84%|████████▍ | 299/354 [02:33<00:27,  1.99it/s]
 85%|████████▍ | 300/354 [02:33<00:27,  1.99it/s]
 85%|████████▌ | 301/354 [02:34<00:26,  2.00it/s]
 85%|████████▌ | 302/354 [02:34<00:26,  1.99it/s]
 86%|████████▌ | 303/354 [02:35<00:25,  2.00it/s]
 86%|████████▌ | 304/354 [02:35<00:25,  2.00it/s]
 86%|████████▌ | 305/354 [02:36<00:24,  2.03it/s]
 86%|████████▋ | 306/354 [02:36<00:23,  2.01it/s]
 87%|████████▋ | 307/354 [02:37<00:23,  2.04it/s]
 87%|████████▋ | 308/354 [02:37<00:22,  2.01it/s]
 87%|████████▋ | 309/354 [02:38<00:22,  2.04it/s]
 88%|████████▊ | 310/354 [02:38<00:21,  2.03it/s]
 88%|████████▊ | 311/354 [02:39<00:20,  2.05it/s]
 88%|████████▊ | 312/354 [02:39<00:20,  2.03it/s]
 88%|████████▊ | 313/354 [02:40<00:20,  2.05it/s]
 89%|████████▊ | 314/354 [02:40<00:19,  2.05it/s]
 89%|████████▉ | 315/354 [02:41<00:19,  2.03it/s]
 89%|████████▉ | 316/354 [02:41<00:18,  2.02it/s]
 90%|████████▉ | 317/354 [02:42<00:18,  2.00it/s]
 90%|████████▉ | 318/354 [02:42<00:17,  2.04it/s]
 90%|█████████ | 319/354 [02:43<00:17,  2.02it/s]
 90%|█████████ | 320/354 [02:43<00:16,  2.01it/s]
 91%|█████████ | 321/354 [02:44<00:16,  2.04it/s]
 91%|█████████ | 322/354 [02:44<00:15,  2.04it/s]
 91%|█████████ | 323/354 [02:45<00:15,  2.02it/s]
 92%|█████████▏| 324/354 [02:45<00:14,  2.01it/s]
 92%|█████████▏| 325/354 [02:46<00:14,  2.00it/s]
 92%|█████████▏| 326/354 [02:46<00:13,  2.01it/s]
 92%|█████████▏| 327/354 [02:47<00:13,  2.00it/s]
 93%|█████████▎| 328/354 [02:47<00:12,  2.01it/s]
 93%|█████████▎| 329/354 [02:48<00:12,  2.00it/s]
 93%|█████████▎| 330/354 [02:48<00:11,  2.03it/s]
 94%|█████████▎| 331/354 [02:49<00:11,  2.03it/s]
 94%|█████████▍| 332/354 [02:49<00:10,  2.01it/s]
 94%|█████████▍| 333/354 [02:50<00:10,  2.00it/s]
 94%|█████████▍| 334/354 [02:50<00:09,  2.01it/s]
 95%|█████████▍| 335/354 [02:51<00:09,  2.01it/s]
 95%|█████████▍| 336/354 [02:51<00:09,  2.00it/s]
 95%|█████████▌| 337/354 [02:52<00:08,  2.00it/s]
 95%|█████████▌| 338/354 [02:52<00:07,  2.05it/s]
 96%|█████████▌| 339/354 [02:53<00:07,  2.02it/s]
 96%|█████████▌| 340/354 [02:53<00:06,  2.00it/s]
 96%|█████████▋| 341/354 [02:54<00:06,  2.00it/s]
 97%|█████████▋| 342/354 [02:54<00:06,  2.00it/s]
 97%|█████████▋| 343/354 [02:55<00:05,  1.99it/s]
 97%|█████████▋| 344/354 [02:55<00:05,  1.98it/s]
 97%|█████████▋| 345/354 [02:56<00:04,  2.02it/s]
 98%|█████████▊| 346/354 [02:56<00:04,  2.00it/s]
 98%|█████████▊| 347/354 [02:57<00:03,  2.03it/s]
 98%|█████████▊| 348/354 [02:57<00:02,  2.01it/s]
 99%|█████████▊| 349/354 [02:58<00:02,  2.00it/s]
 99%|█████████▉| 350/354 [02:58<00:01,  2.04it/s]
 99%|█████████▉| 351/354 [02:59<00:01,  2.03it/s]
 99%|█████████▉| 352/354 [02:59<00:00,  2.01it/s]
100%|█████████▉| 353/354 [03:00<00:00,  2.01it/s]
100%|██████████| 354/354 [03:00<00:00,  2.61it/s]
                                                 

100%|██████████| 354/354 [03:00<00:00,  2.61it/s]{'eval_loss': 0.7321943640708923, 'eval_accuracy': 0.6776, 'eval_f1': 0.671782835869641, 'eval_runtime': 1.73, 'eval_samples_per_second': 1445.119, 'eval_steps_per_second': 180.929, 'epoch': 2.0}
{'loss': 0.7035, 'learning_rate': 0.0, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.99it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.28it/s]

 20%|██        | 63/313 [00:00<00:01, 202.69it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.98it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.30it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.73it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.26it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.25it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.00it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.12it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 167.79it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.85it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.28it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.64it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 179.15it/s]

100%|██████████| 313/313 [00:01<00:00, 176.03it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 176.03it/s]
100%|██████████| 354/354 [03:02<00:00,  2.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 354/354 [03:03<00:00,  2.61it/s]
100%|██████████| 354/354 [03:03<00:00,  1.93it/s]
[I 2023-10-26 22:09:18,503] Trial 2 finished with value: 0.680785165258707 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 7.811822744957915e-06, 'per_device_train_batch_size': 256, 'weight_decay': 1.4340577376294298e-06}. Best is trial 1 with value: 0.7159626561431993.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7185611128807068, 'eval_accuracy': 0.6832, 'eval_f1': 0.680785165258707, 'eval_runtime': 1.7344, 'eval_samples_per_second': 1441.411, 'eval_steps_per_second': 180.465, 'epoch': 3.0}
{'train_runtime': 183.1788, 'train_samples_per_second': 491.323, 'train_steps_per_second': 1.933, 'train_loss': 0.8091936704129149, 'epoch': 3.0}

  0%|          | 0/5625 [00:00<?, ?it/s]
  0%|          | 2/5625 [00:00<05:10, 18.14it/s]
  0%|          | 4/5625 [00:00<05:05, 18.37it/s]
  0%|          | 6/5625 [00:00<04:57, 18.90it/s]
  0%|          | 8/5625 [00:00<04:58, 18.82it/s]
  0%|          | 10/5625 [00:00<04:59, 18.73it/s]
  0%|          | 12/5625 [00:00<04:53, 19.10it/s]
  0%|          | 14/5625 [00:00<05:03, 18.49it/s]
  0%|          | 17/5625 [00:00<04:48, 19.43it/s]
  0%|          | 20/5625 [00:01<04:47, 19.53it/s]
  0%|          | 22/5625 [00:01<04:52, 19.14it/s]
  0%|          | 24/5625 [00:01<04:56, 18.88it/s]
  0%|          | 26/5625 [00:01<05:04, 18.39it/s]
  0%|          | 28/5625 [00:01<05:05, 18.34it/s]
  1%|          | 30/5625 [00:01<04:58, 18.71it/s]
  1%|          | 33/5625 [00:01<04:50, 19.24it/s]
  1%|          | 36/5625 [00:01<04:46, 19.52it/s]
  1%|          | 39/5625 [00:02<04:35, 20.31it/s]
  1%|          | 42/5625 [00:02<04:43, 19.70it/s]
  1%|          | 45/5625 [00:02<04:35, 20.28it/s]
  1%|          | 48/5625 [00:02<04:32, 20.50it/s]
  1%|          | 51/5625 [00:02<04:35, 20.26it/s]
  1%|          | 54/5625 [00:02<04:38, 19.98it/s]
  1%|          | 57/5625 [00:02<04:45, 19.49it/s]
  1%|          | 60/5625 [00:03<04:46, 19.42it/s]
  1%|          | 63/5625 [00:03<04:32, 20.38it/s]
  1%|          | 66/5625 [00:03<04:36, 20.08it/s]
  1%|          | 69/5625 [00:03<04:36, 20.07it/s]
  1%|▏         | 72/5625 [00:03<04:38, 19.95it/s]
  1%|▏         | 75/5625 [00:03<04:43, 19.58it/s]
  1%|▏         | 77/5625 [00:03<04:51, 19.01it/s]
  1%|▏         | 79/5625 [00:04<04:59, 18.54it/s]
  1%|▏         | 82/5625 [00:04<04:49, 19.17it/s]
  1%|▏         | 84/5625 [00:04<04:47, 19.29it/s]
  2%|▏         | 86/5625 [00:04<04:45, 19.42it/s]
  2%|▏         | 88/5625 [00:04<04:45, 19.38it/s]
  2%|▏         | 90/5625 [00:04<04:48, 19.21it/s]
  2%|▏         | 92/5625 [00:04<04:51, 19.00it/s]
  2%|▏         | 94/5625 [00:04<04:51, 19.00it/s]
  2%|▏         | 96/5625 [00:04<04:58, 18.54it/s]
  2%|▏         | 99/5625 [00:05<04:50, 19.02it/s]
  2%|▏         | 101/5625 [00:05<04:47, 19.21it/s]
  2%|▏         | 103/5625 [00:05<04:44, 19.40it/s]
  2%|▏         | 105/5625 [00:05<04:47, 19.20it/s]
  2%|▏         | 107/5625 [00:05<04:48, 19.14it/s]
  2%|▏         | 109/5625 [00:05<04:50, 18.96it/s]
  2%|▏         | 112/5625 [00:05<04:40, 19.68it/s]
  2%|▏         | 114/5625 [00:05<04:48, 19.12it/s]
  2%|▏         | 117/5625 [00:06<04:44, 19.36it/s]
  2%|▏         | 119/5625 [00:06<04:43, 19.45it/s]
  2%|▏         | 122/5625 [00:06<04:35, 20.00it/s]
  2%|▏         | 125/5625 [00:06<04:27, 20.57it/s]
  2%|▏         | 128/5625 [00:06<04:39, 19.65it/s]
  2%|▏         | 130/5625 [00:06<04:40, 19.59it/s]
  2%|▏         | 132/5625 [00:06<04:40, 19.59it/s]
  2%|▏         | 134/5625 [00:06<04:46, 19.14it/s]
  2%|▏         | 136/5625 [00:07<04:52, 18.75it/s]
  2%|▏         | 139/5625 [00:07<04:48, 19.01it/s]
  3%|▎         | 141/5625 [00:07<04:55, 18.58it/s]
  3%|▎         | 143/5625 [00:07<04:54, 18.60it/s]
  3%|▎         | 145/5625 [00:07<04:59, 18.30it/s]
  3%|▎         | 147/5625 [00:07<04:53, 18.66it/s]
  3%|▎         | 149/5625 [00:07<04:53, 18.65it/s]
  3%|▎         | 151/5625 [00:07<04:49, 18.90it/s]
  3%|▎         | 154/5625 [00:07<04:45, 19.19it/s]
  3%|▎         | 156/5625 [00:08<04:46, 19.11it/s]
  3%|▎         | 158/5625 [00:08<04:52, 18.67it/s]
  3%|▎         | 161/5625 [00:08<04:36, 19.76it/s]
  3%|▎         | 163/5625 [00:08<04:37, 19.68it/s]
  3%|▎         | 165/5625 [00:08<04:46, 19.03it/s]
  3%|▎         | 167/5625 [00:08<04:47, 19.01it/s]
  3%|▎         | 169/5625 [00:08<04:46, 19.04it/s]
  3%|▎         | 171/5625 [00:08<04:43, 19.25it/s]
  3%|▎         | 173/5625 [00:08<04:44, 19.16it/s]
  3%|▎         | 176/5625 [00:09<04:34, 19.83it/s]
  3%|▎         | 179/5625 [00:09<04:28, 20.27it/s]
  3%|▎         | 182/5625 [00:09<04:29, 20.16it/s]
  3%|▎         | 185/5625 [00:09<04:35, 19.71it/s]
  3%|▎         | 187/5625 [00:09<04:39, 19.45it/s]
  3%|▎         | 190/5625 [00:09<04:39, 19.43it/s]
  3%|▎         | 193/5625 [00:09<04:36, 19.61it/s]
  3%|▎         | 195/5625 [00:10<04:41, 19.31it/s]
  4%|▎         | 197/5625 [00:10<04:42, 19.23it/s]
  4%|▎         | 199/5625 [00:10<04:40, 19.36it/s]
  4%|▎         | 201/5625 [00:10<04:49, 18.76it/s]
  4%|▎         | 204/5625 [00:10<04:32, 19.91it/s]
  4%|▎         | 207/5625 [00:10<04:24, 20.45it/s]
  4%|▎         | 210/5625 [00:10<04:34, 19.73it/s]
  4%|▍         | 212/5625 [00:10<04:34, 19.70it/s]
  4%|▍         | 215/5625 [00:11<04:38, 19.45it/s]
  4%|▍         | 217/5625 [00:11<04:42, 19.16it/s]
  4%|▍         | 220/5625 [00:11<04:36, 19.55it/s]
  4%|▍         | 222/5625 [00:11<04:37, 19.49it/s]
  4%|▍         | 224/5625 [00:11<04:41, 19.18it/s]
  4%|▍         | 227/5625 [00:11<04:40, 19.22it/s]
  4%|▍         | 229/5625 [00:11<04:38, 19.38it/s]
  4%|▍         | 231/5625 [00:11<04:38, 19.40it/s]
  4%|▍         | 234/5625 [00:12<04:35, 19.57it/s]
  4%|▍         | 236/5625 [00:12<04:38, 19.33it/s]
  4%|▍         | 238/5625 [00:12<04:37, 19.45it/s]
  4%|▍         | 240/5625 [00:12<04:37, 19.37it/s]
  4%|▍         | 242/5625 [00:12<04:45, 18.84it/s]
  4%|▍         | 244/5625 [00:12<04:49, 18.62it/s]
  4%|▍         | 247/5625 [00:12<04:36, 19.42it/s]
  4%|▍         | 249/5625 [00:12<04:34, 19.56it/s]
  4%|▍         | 251/5625 [00:12<04:42, 19.01it/s]
  4%|▍         | 253/5625 [00:13<04:46, 18.76it/s]
  5%|▍         | 255/5625 [00:13<04:42, 19.04it/s]
  5%|▍         | 257/5625 [00:13<04:47, 18.66it/s]
  5%|▍         | 260/5625 [00:13<04:43, 18.95it/s]
  5%|▍         | 263/5625 [00:13<04:32, 19.69it/s]
  5%|▍         | 266/5625 [00:13<04:27, 20.03it/s]
  5%|▍         | 268/5625 [00:13<04:34, 19.55it/s]
  5%|▍         | 271/5625 [00:13<04:33, 19.57it/s]
  5%|▍         | 273/5625 [00:14<04:37, 19.28it/s]
  5%|▍         | 275/5625 [00:14<04:40, 19.08it/s]
  5%|▍         | 277/5625 [00:14<04:42, 18.95it/s]
  5%|▍         | 280/5625 [00:14<04:31, 19.66it/s]
  5%|▌         | 283/5625 [00:14<04:24, 20.20it/s]
  5%|▌         | 286/5625 [00:14<04:32, 19.61it/s]
  5%|▌         | 288/5625 [00:14<04:35, 19.40it/s]
  5%|▌         | 291/5625 [00:15<04:36, 19.30it/s]
  5%|▌         | 294/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 296/5625 [00:15<04:36, 19.25it/s]
  5%|▌         | 299/5625 [00:15<04:30, 19.72it/s]
  5%|▌         | 301/5625 [00:15<04:34, 19.42it/s]
  5%|▌         | 303/5625 [00:15<04:40, 19.00it/s]
  5%|▌         | 305/5625 [00:15<04:42, 18.81it/s]
  5%|▌         | 308/5625 [00:15<04:34, 19.36it/s]
  6%|▌         | 311/5625 [00:16<04:29, 19.69it/s]
  6%|▌         | 313/5625 [00:16<04:30, 19.65it/s]
  6%|▌         | 315/5625 [00:16<04:30, 19.60it/s]
  6%|▌         | 317/5625 [00:16<04:33, 19.39it/s]
  6%|▌         | 319/5625 [00:16<04:38, 19.03it/s]
  6%|▌         | 321/5625 [00:16<04:36, 19.21it/s]
  6%|▌         | 323/5625 [00:16<04:39, 18.99it/s]
  6%|▌         | 326/5625 [00:16<04:22, 20.18it/s]
  6%|▌         | 329/5625 [00:16<04:21, 20.22it/s]
  6%|▌         | 332/5625 [00:17<04:27, 19.77it/s]
  6%|▌         | 334/5625 [00:17<04:27, 19.79it/s]
  6%|▌         | 337/5625 [00:17<04:23, 20.08it/s]
  6%|▌         | 340/5625 [00:17<04:28, 19.65it/s]
  6%|▌         | 342/5625 [00:17<04:36, 19.14it/s]
  6%|▌         | 344/5625 [00:17<04:40, 18.85it/s]
  6%|▌         | 346/5625 [00:17<04:43, 18.62it/s]
  6%|▌         | 349/5625 [00:18<04:31, 19.44it/s]
  6%|▋         | 352/5625 [00:18<04:29, 19.59it/s]
  6%|▋         | 354/5625 [00:18<04:31, 19.40it/s]
  6%|▋         | 357/5625 [00:18<04:18, 20.40it/s]
  6%|▋         | 360/5625 [00:18<04:31, 19.39it/s]
  6%|▋         | 362/5625 [00:18<04:30, 19.47it/s]
  6%|▋         | 364/5625 [00:18<04:38, 18.88it/s]
  7%|▋         | 366/5625 [00:18<04:39, 18.80it/s]
  7%|▋         | 368/5625 [00:19<04:46, 18.38it/s]
  7%|▋         | 370/5625 [00:19<04:44, 18.45it/s]
  7%|▋         | 372/5625 [00:19<04:39, 18.78it/s]
  7%|▋         | 374/5625 [00:19<04:35, 19.06it/s]
  7%|▋         | 376/5625 [00:19<04:41, 18.64it/s]
  7%|▋         | 378/5625 [00:19<04:37, 18.89it/s]
  7%|▋         | 380/5625 [00:19<04:36, 19.00it/s]
  7%|▋         | 382/5625 [00:19<04:38, 18.83it/s]
  7%|▋         | 385/5625 [00:19<04:25, 19.76it/s]
  7%|▋         | 387/5625 [00:20<04:32, 19.22it/s]
  7%|▋         | 389/5625 [00:20<04:35, 19.03it/s]
  7%|▋         | 391/5625 [00:20<04:31, 19.26it/s]
  7%|▋         | 393/5625 [00:20<04:38, 18.81it/s]
  7%|▋         | 395/5625 [00:20<04:34, 19.08it/s]
  7%|▋         | 397/5625 [00:20<04:31, 19.23it/s]
  7%|▋         | 399/5625 [00:20<04:32, 19.17it/s]
  7%|▋         | 401/5625 [00:20<04:29, 19.40it/s]
  7%|▋         | 403/5625 [00:20<04:30, 19.30it/s]
  7%|▋         | 405/5625 [00:20<04:37, 18.82it/s]
  7%|▋         | 407/5625 [00:21<04:37, 18.81it/s]
  7%|▋         | 409/5625 [00:21<04:33, 19.07it/s]
  7%|▋         | 411/5625 [00:21<04:39, 18.66it/s]
  7%|▋         | 413/5625 [00:21<04:34, 18.97it/s]
  7%|▋         | 416/5625 [00:21<04:23, 19.79it/s]
  7%|▋         | 419/5625 [00:21<04:24, 19.69it/s]
  7%|▋         | 421/5625 [00:21<04:28, 19.39it/s]
  8%|▊         | 423/5625 [00:21<04:26, 19.55it/s]
  8%|▊         | 425/5625 [00:21<04:31, 19.13it/s]
  8%|▊         | 428/5625 [00:22<04:22, 19.78it/s]
  8%|▊         | 430/5625 [00:22<04:23, 19.69it/s]
  8%|▊         | 432/5625 [00:22<04:23, 19.69it/s]
  8%|▊         | 435/5625 [00:22<04:18, 20.10it/s]
  8%|▊         | 438/5625 [00:22<04:19, 19.99it/s]
  8%|▊         | 441/5625 [00:22<04:20, 19.91it/s]
  8%|▊         | 443/5625 [00:22<04:20, 19.91it/s]
  8%|▊         | 445/5625 [00:22<04:21, 19.81it/s]
  8%|▊         | 447/5625 [00:23<04:21, 19.77it/s]
  8%|▊         | 449/5625 [00:23<04:25, 19.48it/s]
  8%|▊         | 451/5625 [00:23<04:31, 19.09it/s]
  8%|▊         | 453/5625 [00:23<04:27, 19.33it/s]
  8%|▊         | 456/5625 [00:23<04:15, 20.26it/s]
  8%|▊         | 459/5625 [00:23<04:29, 19.20it/s]
  8%|▊         | 461/5625 [00:23<04:32, 18.93it/s]
  8%|▊         | 463/5625 [00:23<04:29, 19.14it/s]
  8%|▊         | 465/5625 [00:24<04:34, 18.77it/s]
  8%|▊         | 468/5625 [00:24<04:22, 19.64it/s]
  8%|▊         | 470/5625 [00:24<04:27, 19.25it/s]
  8%|▊         | 473/5625 [00:24<04:23, 19.58it/s]
  8%|▊         | 475/5625 [00:24<04:22, 19.59it/s]
  8%|▊         | 477/5625 [00:24<04:26, 19.29it/s]
  9%|▊         | 480/5625 [00:24<04:20, 19.72it/s]
  9%|▊         | 482/5625 [00:24<04:20, 19.74it/s]
  9%|▊         | 484/5625 [00:24<04:24, 19.43it/s]
  9%|▊         | 486/5625 [00:25<04:30, 18.97it/s]
  9%|▊         | 489/5625 [00:25<04:18, 19.86it/s]
  9%|▊         | 491/5625 [00:25<04:22, 19.53it/s]
  9%|▉         | 494/5625 [00:25<04:09, 20.56it/s]
  9%|▉         | 497/5625 [00:25<04:14, 20.16it/s]
  9%|▉         | 500/5625 [00:25<04:20, 19.68it/s]
  9%|▉         | 502/5625 [00:25<04:27, 19.15it/s]
  9%|▉         | 504/5625 [00:26<04:27, 19.11it/s]
  9%|▉         | 507/5625 [00:26<04:17, 19.85it/s]
  9%|▉         | 510/5625 [00:26<04:14, 20.10it/s]
  9%|▉         | 513/5625 [00:26<04:22, 19.48it/s]
  9%|▉         | 515/5625 [00:26<04:28, 19.06it/s]
  9%|▉         | 517/5625 [00:26<04:32, 18.74it/s]
  9%|▉         | 520/5625 [00:26<04:29, 18.93it/s]
  9%|▉         | 522/5625 [00:26<04:28, 18.97it/s]
  9%|▉         | 524/5625 [00:27<04:31, 18.80it/s]
  9%|▉         | 526/5625 [00:27<04:35, 18.52it/s]
  9%|▉         | 529/5625 [00:27<04:28, 19.00it/s]
  9%|▉         | 531/5625 [00:27<04:32, 18.67it/s]
  9%|▉         | 533/5625 [00:27<04:39, 18.23it/s]
 10%|▉         | 536/5625 [00:27<04:24, 19.25it/s]
 10%|▉         | 539/5625 [00:27<04:20, 19.54it/s]
 10%|▉         | 541/5625 [00:27<04:19, 19.60it/s]
 10%|▉         | 544/5625 [00:28<04:20, 19.47it/s]
 10%|▉         | 546/5625 [00:28<04:21, 19.42it/s]
 10%|▉         | 548/5625 [00:28<04:25, 19.10it/s]
 10%|▉         | 550/5625 [00:28<04:27, 18.99it/s]
 10%|▉         | 553/5625 [00:28<04:21, 19.39it/s]
 10%|▉         | 555/5625 [00:28<04:20, 19.44it/s]
 10%|▉         | 557/5625 [00:28<04:24, 19.18it/s]
 10%|▉         | 559/5625 [00:28<04:24, 19.17it/s]
 10%|▉         | 562/5625 [00:29<04:19, 19.54it/s]
 10%|█         | 564/5625 [00:29<04:25, 19.06it/s]
 10%|█         | 566/5625 [00:29<04:30, 18.71it/s]
 10%|█         | 568/5625 [00:29<04:33, 18.49it/s]
 10%|█         | 570/5625 [00:29<04:33, 18.48it/s]
 10%|█         | 573/5625 [00:29<04:25, 19.06it/s]
 10%|█         | 576/5625 [00:29<04:18, 19.51it/s]
 10%|█         | 578/5625 [00:29<04:21, 19.27it/s]
 10%|█         | 580/5625 [00:29<04:27, 18.84it/s]
 10%|█         | 583/5625 [00:30<04:25, 18.99it/s]
 10%|█         | 585/5625 [00:30<04:30, 18.64it/s]
 10%|█         | 587/5625 [00:30<04:31, 18.58it/s]
 10%|█         | 589/5625 [00:30<04:29, 18.72it/s]
 11%|█         | 592/5625 [00:30<04:20, 19.31it/s]
 11%|█         | 594/5625 [00:30<04:26, 18.90it/s]
 11%|█         | 596/5625 [00:30<04:25, 18.92it/s]
 11%|█         | 598/5625 [00:30<04:23, 19.09it/s]
 11%|█         | 601/5625 [00:31<04:15, 19.66it/s]
 11%|█         | 603/5625 [00:31<04:17, 19.52it/s]
 11%|█         | 605/5625 [00:31<04:24, 18.95it/s]
 11%|█         | 608/5625 [00:31<04:16, 19.58it/s]
 11%|█         | 610/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 612/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 614/5625 [00:31<04:22, 19.06it/s]
 11%|█         | 616/5625 [00:31<04:19, 19.28it/s]
 11%|█         | 618/5625 [00:31<04:24, 18.91it/s]
 11%|█         | 621/5625 [00:32<04:07, 20.18it/s]
 11%|█         | 624/5625 [00:32<04:15, 19.57it/s]
 11%|█         | 626/5625 [00:32<04:21, 19.15it/s]
 11%|█         | 628/5625 [00:32<04:18, 19.35it/s]
 11%|█         | 631/5625 [00:32<04:10, 19.92it/s]
 11%|█▏        | 633/5625 [00:32<04:20, 19.13it/s]
 11%|█▏        | 635/5625 [00:32<04:23, 18.95it/s]
 11%|█▏        | 637/5625 [00:32<04:22, 19.00it/s]
 11%|█▏        | 640/5625 [00:33<04:16, 19.42it/s]
 11%|█▏        | 642/5625 [00:33<04:16, 19.41it/s]
 11%|█▏        | 645/5625 [00:33<04:11, 19.80it/s]
 12%|█▏        | 647/5625 [00:33<04:20, 19.13it/s]
 12%|█▏        | 649/5625 [00:33<04:19, 19.16it/s]
 12%|█▏        | 651/5625 [00:33<04:25, 18.73it/s]
 12%|█▏        | 653/5625 [00:33<04:22, 18.93it/s]
 12%|█▏        | 656/5625 [00:33<04:10, 19.80it/s]
 12%|█▏        | 658/5625 [00:34<04:12, 19.66it/s]
 12%|█▏        | 661/5625 [00:34<04:13, 19.60it/s]
 12%|█▏        | 663/5625 [00:34<04:16, 19.31it/s]
 12%|█▏        | 665/5625 [00:34<04:21, 18.94it/s]
 12%|█▏        | 667/5625 [00:34<04:25, 18.69it/s]
 12%|█▏        | 669/5625 [00:34<04:26, 18.57it/s]
 12%|█▏        | 671/5625 [00:34<04:21, 18.93it/s]
 12%|█▏        | 673/5625 [00:34<05:24, 15.25it/s]
 12%|█▏        | 675/5625 [00:35<05:07, 16.10it/s]
 12%|█▏        | 677/5625 [00:35<05:00, 16.44it/s]
 12%|█▏        | 679/5625 [00:35<04:50, 17.00it/s]
 12%|█▏        | 681/5625 [00:35<04:43, 17.45it/s]
 12%|█▏        | 683/5625 [00:35<04:43, 17.42it/s]
 12%|█▏        | 685/5625 [00:35<04:36, 17.88it/s]
 12%|█▏        | 687/5625 [00:35<04:30, 18.23it/s]
 12%|█▏        | 689/5625 [00:35<04:25, 18.57it/s]
 12%|█▏        | 691/5625 [00:35<04:20, 18.91it/s]
 12%|█▏        | 693/5625 [00:36<04:23, 18.70it/s]
 12%|█▏        | 696/5625 [00:36<04:16, 19.24it/s]
 12%|█▏        | 699/5625 [00:36<04:14, 19.33it/s]
 12%|█▏        | 701/5625 [00:36<04:20, 18.92it/s]
 12%|█▏        | 703/5625 [00:36<04:23, 18.66it/s]
 13%|█▎        | 705/5625 [00:36<04:19, 18.93it/s]
 13%|█▎        | 707/5625 [00:36<04:20, 18.86it/s]
 13%|█▎        | 709/5625 [00:36<04:21, 18.78it/s]
 13%|█▎        | 711/5625 [00:36<04:24, 18.56it/s]
 13%|█▎        | 714/5625 [00:37<04:18, 19.01it/s]
 13%|█▎        | 716/5625 [00:37<04:16, 19.17it/s]
 13%|█▎        | 718/5625 [00:37<04:15, 19.20it/s]
 13%|█▎        | 720/5625 [00:37<04:15, 19.17it/s]
 13%|█▎        | 722/5625 [00:37<04:17, 19.06it/s]
 13%|█▎        | 725/5625 [00:37<04:13, 19.31it/s]
 13%|█▎        | 728/5625 [00:37<04:04, 20.03it/s]
 13%|█▎        | 730/5625 [00:37<04:12, 19.39it/s]
 13%|█▎        | 733/5625 [00:38<04:11, 19.44it/s]
 13%|█▎        | 735/5625 [00:38<04:13, 19.31it/s]
 13%|█▎        | 737/5625 [00:38<04:10, 19.49it/s]
 13%|█▎        | 739/5625 [00:38<04:18, 18.91it/s]
 13%|█▎        | 742/5625 [00:38<04:09, 19.56it/s]
 13%|█▎        | 745/5625 [00:38<04:08, 19.62it/s]
 13%|█▎        | 747/5625 [00:38<04:15, 19.07it/s]
 13%|█▎        | 750/5625 [00:38<04:08, 19.62it/s]
 13%|█▎        | 752/5625 [00:39<04:09, 19.52it/s]
 13%|█▎        | 754/5625 [00:39<04:12, 19.27it/s]
 13%|█▎        | 756/5625 [00:39<04:18, 18.87it/s]
 13%|█▎        | 758/5625 [00:39<04:16, 19.00it/s]
 14%|█▎        | 761/5625 [00:39<04:11, 19.32it/s]
 14%|█▎        | 763/5625 [00:39<04:12, 19.26it/s]
 14%|█▎        | 765/5625 [00:39<04:13, 19.13it/s]
 14%|█▎        | 767/5625 [00:39<04:16, 18.96it/s]
 14%|█▎        | 769/5625 [00:39<04:13, 19.18it/s]
 14%|█▎        | 771/5625 [00:40<05:07, 15.77it/s]
 14%|█▍        | 774/5625 [00:40<04:43, 17.11it/s]
 14%|█▍        | 776/5625 [00:40<04:39, 17.36it/s]
 14%|█▍        | 779/5625 [00:40<04:29, 17.96it/s]
 14%|█▍        | 782/5625 [00:40<04:17, 18.83it/s]
 14%|█▍        | 785/5625 [00:40<04:10, 19.36it/s]
 14%|█▍        | 787/5625 [00:40<04:16, 18.88it/s]
 14%|█▍        | 789/5625 [00:41<04:17, 18.78it/s]
 14%|█▍        | 791/5625 [00:41<04:21, 18.51it/s]
 14%|█▍        | 794/5625 [00:41<04:07, 19.51it/s]
 14%|█▍        | 796/5625 [00:41<04:12, 19.09it/s]
 14%|█▍        | 798/5625 [00:41<04:17, 18.77it/s]
 14%|█▍        | 800/5625 [00:41<04:20, 18.51it/s]
 14%|█▍        | 803/5625 [00:41<04:09, 19.34it/s]
 14%|█▍        | 805/5625 [00:41<04:15, 18.83it/s]
 14%|█▍        | 808/5625 [00:42<04:07, 19.47it/s]
 14%|█▍        | 810/5625 [00:42<04:10, 19.20it/s]
 14%|█▍        | 812/5625 [00:42<04:16, 18.78it/s]
 14%|█▍        | 815/5625 [00:42<04:06, 19.54it/s]
 15%|█▍        | 817/5625 [00:42<04:10, 19.23it/s]
 15%|█▍        | 819/5625 [00:42<04:16, 18.72it/s]
 15%|█▍        | 821/5625 [00:42<04:12, 19.00it/s]
 15%|█▍        | 823/5625 [00:42<04:14, 18.89it/s]
 15%|█▍        | 826/5625 [00:42<04:06, 19.46it/s]
 15%|█▍        | 829/5625 [00:43<04:04, 19.61it/s]
 15%|█▍        | 832/5625 [00:43<03:55, 20.35it/s]
 15%|█▍        | 835/5625 [00:43<03:57, 20.16it/s]
 15%|█▍        | 838/5625 [00:43<04:02, 19.76it/s]
 15%|█▍        | 840/5625 [00:43<04:06, 19.45it/s]
 15%|█▍        | 842/5625 [00:43<04:11, 19.05it/s]
 15%|█▌        | 844/5625 [00:43<04:08, 19.21it/s]
 15%|█▌        | 846/5625 [00:44<04:09, 19.12it/s]
 15%|█▌        | 848/5625 [00:44<04:15, 18.66it/s]
 15%|█▌        | 851/5625 [00:44<04:10, 19.08it/s]
 15%|█▌        | 854/5625 [00:44<04:08, 19.18it/s]
 15%|█▌        | 856/5625 [00:44<04:07, 19.25it/s]
 15%|█▌        | 859/5625 [00:44<04:01, 19.73it/s]
 15%|█▌        | 862/5625 [00:44<04:01, 19.70it/s]
 15%|█▌        | 864/5625 [00:44<04:08, 19.18it/s]
 15%|█▌        | 867/5625 [00:45<03:56, 20.13it/s]
 15%|█▌        | 870/5625 [00:45<03:58, 19.96it/s]
 16%|█▌        | 872/5625 [00:45<03:59, 19.87it/s]
 16%|█▌        | 874/5625 [00:45<04:02, 19.63it/s]
 16%|█▌        | 876/5625 [00:45<04:03, 19.47it/s]
 16%|█▌        | 879/5625 [00:45<04:01, 19.62it/s]
 16%|█▌        | 882/5625 [00:45<03:59, 19.83it/s]
 16%|█▌        | 885/5625 [00:46<03:58, 19.87it/s]
 16%|█▌        | 888/5625 [00:46<03:57, 19.96it/s]
 16%|█▌        | 890/5625 [00:46<04:01, 19.63it/s]
 16%|█▌        | 893/5625 [00:46<04:01, 19.56it/s]
 16%|█▌        | 895/5625 [00:46<04:10, 18.91it/s]
 16%|█▌        | 898/5625 [00:46<03:57, 19.89it/s]
 16%|█▌        | 901/5625 [00:46<03:55, 20.10it/s]
 16%|█▌        | 904/5625 [00:46<03:51, 20.43it/s]
 16%|█▌        | 907/5625 [00:47<03:56, 19.96it/s]
 16%|█▌        | 909/5625 [00:47<03:59, 19.65it/s]
 16%|█▌        | 912/5625 [00:47<03:52, 20.23it/s]
 16%|█▋        | 915/5625 [00:47<03:53, 20.20it/s]
 16%|█▋        | 918/5625 [00:47<03:59, 19.67it/s]
 16%|█▋        | 920/5625 [00:47<04:03, 19.32it/s]
 16%|█▋        | 922/5625 [00:47<04:02, 19.37it/s]
 16%|█▋        | 924/5625 [00:47<04:05, 19.14it/s]
 16%|█▋        | 926/5625 [00:48<04:02, 19.36it/s]
 16%|█▋        | 928/5625 [00:48<04:02, 19.37it/s]
 17%|█▋        | 930/5625 [00:48<04:02, 19.33it/s]
 17%|█▋        | 933/5625 [00:48<03:52, 20.22it/s]
 17%|█▋        | 936/5625 [00:48<03:53, 20.08it/s]
 17%|█▋        | 939/5625 [00:48<03:52, 20.19it/s]
 17%|█▋        | 942/5625 [00:48<03:51, 20.25it/s]
 17%|█▋        | 945/5625 [00:49<03:55, 19.89it/s]
 17%|█▋        | 947/5625 [00:49<03:56, 19.77it/s]
 17%|█▋        | 950/5625 [00:49<03:52, 20.14it/s]
 17%|█▋        | 953/5625 [00:49<04:00, 19.42it/s]
 17%|█▋        | 955/5625 [00:49<03:59, 19.53it/s]
 17%|█▋        | 958/5625 [00:49<03:54, 19.91it/s]
 17%|█▋        | 960/5625 [00:49<03:57, 19.61it/s]
 17%|█▋        | 962/5625 [00:49<04:03, 19.18it/s]
 17%|█▋        | 964/5625 [00:50<04:00, 19.35it/s]
 17%|█▋        | 966/5625 [00:50<03:58, 19.53it/s]
 17%|█▋        | 968/5625 [00:50<03:57, 19.60it/s]
 17%|█▋        | 970/5625 [00:50<03:58, 19.54it/s]
 17%|█▋        | 972/5625 [00:50<04:01, 19.24it/s]
 17%|█▋        | 974/5625 [00:50<03:59, 19.45it/s]
 17%|█▋        | 976/5625 [00:50<04:01, 19.29it/s]
 17%|█▋        | 979/5625 [00:50<03:57, 19.54it/s]
 17%|█▋        | 982/5625 [00:50<03:57, 19.58it/s]
 17%|█▋        | 984/5625 [00:51<04:02, 19.13it/s]
 18%|█▊        | 986/5625 [00:51<04:03, 19.04it/s]
 18%|█▊        | 988/5625 [00:51<04:05, 18.91it/s]
 18%|█▊        | 991/5625 [00:51<03:56, 19.60it/s]
 18%|█▊        | 994/5625 [00:51<03:55, 19.67it/s]
 18%|█▊        | 996/5625 [00:51<03:57, 19.52it/s]
 18%|█▊        | 998/5625 [00:51<03:55, 19.63it/s]
 18%|█▊        | 1000/5625 [00:51<03:55, 19.61it/s]
 18%|█▊        | 1002/5625 [00:51<03:57, 19.50it/s]
 18%|█▊        | 1005/5625 [00:52<03:55, 19.64it/s]
 18%|█▊        | 1008/5625 [00:52<03:48, 20.23it/s]
 18%|█▊        | 1011/5625 [00:52<03:49, 20.07it/s]
 18%|█▊        | 1014/5625 [00:52<03:50, 19.99it/s]
 18%|█▊        | 1016/5625 [00:52<03:56, 19.48it/s]
 18%|█▊        | 1018/5625 [00:52<03:55, 19.56it/s]
 18%|█▊        | 1021/5625 [00:52<03:50, 19.96it/s]
 18%|█▊        | 1023/5625 [00:53<03:55, 19.53it/s]
 18%|█▊        | 1025/5625 [00:53<03:55, 19.57it/s]
 18%|█▊        | 1027/5625 [00:53<03:56, 19.42it/s]
 18%|█▊        | 1030/5625 [00:53<03:57, 19.38it/s]
 18%|█▊        | 1032/5625 [00:53<03:59, 19.15it/s]
 18%|█▊        | 1034/5625 [00:53<04:05, 18.68it/s]
 18%|█▊        | 1037/5625 [00:53<03:57, 19.33it/s]
 18%|█▊        | 1040/5625 [00:53<03:57, 19.30it/s]
 19%|█▊        | 1042/5625 [00:54<03:57, 19.28it/s]
 19%|█▊        | 1044/5625 [00:54<04:03, 18.85it/s]
 19%|█▊        | 1047/5625 [00:54<03:53, 19.64it/s]
 19%|█▊        | 1050/5625 [00:54<03:45, 20.27it/s]
 19%|█▊        | 1053/5625 [00:54<03:48, 20.03it/s]
 19%|█▉        | 1056/5625 [00:54<03:47, 20.07it/s]
 19%|█▉        | 1059/5625 [00:54<03:51, 19.69it/s]
 19%|█▉        | 1061/5625 [00:54<03:51, 19.70it/s]
 19%|█▉        | 1063/5625 [00:55<03:56, 19.33it/s]
 19%|█▉        | 1066/5625 [00:55<03:49, 19.91it/s]
 19%|█▉        | 1068/5625 [00:55<05:18, 14.32it/s]
 19%|█▉        | 1070/5625 [00:55<05:00, 15.13it/s]
 19%|█▉        | 1072/5625 [00:55<04:45, 15.95it/s]
 19%|█▉        | 1074/5625 [00:55<04:32, 16.72it/s]
 19%|█▉        | 1076/5625 [00:55<04:24, 17.18it/s]
 19%|█▉        | 1078/5625 [00:56<04:22, 17.35it/s]
 19%|█▉        | 1081/5625 [00:56<04:11, 18.08it/s]
 19%|█▉        | 1084/5625 [00:56<04:02, 18.70it/s]
 19%|█▉        | 1086/5625 [00:56<03:59, 18.97it/s]
 19%|█▉        | 1089/5625 [00:56<03:48, 19.84it/s]
 19%|█▉        | 1091/5625 [00:56<03:49, 19.76it/s]
 19%|█▉        | 1093/5625 [00:56<03:53, 19.42it/s]
 19%|█▉        | 1095/5625 [00:56<03:59, 18.90it/s]
 20%|█▉        | 1098/5625 [00:57<03:45, 20.07it/s]
 20%|█▉        | 1100/5625 [00:57<03:46, 19.98it/s]
 20%|█▉        | 1103/5625 [00:57<03:49, 19.70it/s]
 20%|█▉        | 1105/5625 [00:57<03:52, 19.41it/s]
 20%|█▉        | 1107/5625 [00:57<03:53, 19.35it/s]
 20%|█▉        | 1110/5625 [00:57<03:47, 19.83it/s]
 20%|█▉        | 1113/5625 [00:57<03:42, 20.29it/s]
 20%|█▉        | 1116/5625 [00:57<03:49, 19.66it/s]
 20%|█▉        | 1119/5625 [00:58<03:44, 20.11it/s]
 20%|█▉        | 1122/5625 [00:58<03:54, 19.20it/s]
 20%|█▉        | 1124/5625 [00:58<03:54, 19.22it/s]
 20%|██        | 1126/5625 [00:58<03:52, 19.31it/s]
 20%|██        | 1128/5625 [00:58<03:57, 18.92it/s]
 20%|██        | 1130/5625 [00:58<03:58, 18.88it/s]
 20%|██        | 1133/5625 [00:58<03:47, 19.78it/s]
 20%|██        | 1135/5625 [00:58<03:50, 19.48it/s]
 20%|██        | 1137/5625 [00:59<03:56, 19.01it/s]
 20%|██        | 1139/5625 [00:59<04:00, 18.66it/s]
 20%|██        | 1141/5625 [00:59<03:57, 18.85it/s]
 20%|██        | 1143/5625 [00:59<04:01, 18.52it/s]
 20%|██        | 1146/5625 [00:59<03:48, 19.62it/s]
 20%|██        | 1148/5625 [00:59<03:51, 19.35it/s]
 20%|██        | 1150/5625 [00:59<03:51, 19.34it/s]
 20%|██        | 1153/5625 [00:59<03:42, 20.08it/s]
 21%|██        | 1155/5625 [00:59<03:44, 19.90it/s]
 21%|██        | 1157/5625 [01:00<03:53, 19.12it/s]
 21%|██        | 1159/5625 [01:00<03:59, 18.66it/s]
 21%|██        | 1162/5625 [01:00<03:47, 19.63it/s]
 21%|██        | 1164/5625 [01:00<03:53, 19.09it/s]
 21%|██        | 1166/5625 [01:00<05:18, 13.99it/s]
 21%|██        | 1169/5625 [01:00<04:38, 15.99it/s]
 21%|██        | 1171/5625 [01:00<04:28, 16.62it/s]
 21%|██        | 1173/5625 [01:01<04:20, 17.07it/s]
 21%|██        | 1176/5625 [01:01<04:00, 18.50it/s]
 21%|██        | 1178/5625 [01:01<03:55, 18.85it/s]
 21%|██        | 1180/5625 [01:01<03:54, 18.96it/s]
 21%|██        | 1182/5625 [01:01<03:54, 18.95it/s]
 21%|██        | 1185/5625 [01:01<03:48, 19.44it/s]
 21%|██        | 1188/5625 [01:01<03:47, 19.54it/s]
 21%|██        | 1190/5625 [01:01<03:47, 19.54it/s]
 21%|██        | 1192/5625 [01:02<03:47, 19.48it/s]
 21%|██        | 1194/5625 [01:02<03:50, 19.22it/s]
 21%|██▏       | 1196/5625 [01:02<03:53, 18.96it/s]
 21%|██▏       | 1199/5625 [01:02<03:39, 20.20it/s]
 21%|██▏       | 1202/5625 [01:02<03:32, 20.84it/s]
 21%|██▏       | 1205/5625 [01:02<03:35, 20.55it/s]
 21%|██▏       | 1208/5625 [01:02<03:40, 20.08it/s]
 22%|██▏       | 1211/5625 [01:02<03:39, 20.09it/s]
 22%|██▏       | 1214/5625 [01:03<03:38, 20.15it/s]
 22%|██▏       | 1217/5625 [01:03<03:39, 20.05it/s]
 22%|██▏       | 1220/5625 [01:03<03:34, 20.49it/s]
 22%|██▏       | 1223/5625 [01:03<03:42, 19.80it/s]
 22%|██▏       | 1225/5625 [01:03<03:44, 19.59it/s]
 22%|██▏       | 1227/5625 [01:03<03:51, 18.97it/s]
 22%|██▏       | 1229/5625 [01:03<03:57, 18.52it/s]
 22%|██▏       | 1231/5625 [01:03<03:56, 18.55it/s]
 22%|██▏       | 1233/5625 [01:04<03:57, 18.46it/s]
 22%|██▏       | 1236/5625 [01:04<03:46, 19.41it/s]
 22%|██▏       | 1238/5625 [01:04<03:51, 18.96it/s]
 22%|██▏       | 1241/5625 [01:04<03:43, 19.58it/s]
 22%|██▏       | 1243/5625 [01:04<03:43, 19.64it/s]
 22%|██▏       | 1245/5625 [01:04<03:45, 19.43it/s]
 22%|██▏       | 1248/5625 [01:04<03:43, 19.62it/s]
 22%|██▏       | 1250/5625 [01:04<03:46, 19.31it/s]
 22%|██▏       | 1253/5625 [01:05<03:38, 19.99it/s]
 22%|██▏       | 1256/5625 [01:05<03:34, 20.37it/s]
 22%|██▏       | 1259/5625 [01:05<03:34, 20.33it/s]
 22%|██▏       | 1262/5625 [01:05<03:32, 20.57it/s]
 22%|██▏       | 1265/5625 [01:05<03:36, 20.10it/s]
 23%|██▎       | 1268/5625 [01:05<03:40, 19.75it/s]
 23%|██▎       | 1270/5625 [01:05<03:42, 19.54it/s]
 23%|██▎       | 1272/5625 [01:06<03:42, 19.60it/s]
 23%|██▎       | 1274/5625 [01:06<03:43, 19.43it/s]
 23%|██▎       | 1276/5625 [01:06<03:51, 18.79it/s]
 23%|██▎       | 1278/5625 [01:06<03:56, 18.40it/s]
 23%|██▎       | 1280/5625 [01:06<03:54, 18.50it/s]
 23%|██▎       | 1283/5625 [01:06<03:46, 19.19it/s]
 23%|██▎       | 1286/5625 [01:06<03:38, 19.87it/s]
 23%|██▎       | 1289/5625 [01:06<03:37, 19.97it/s]
 23%|██▎       | 1291/5625 [01:07<03:45, 19.23it/s]
 23%|██▎       | 1293/5625 [01:07<03:48, 18.95it/s]
 23%|██▎       | 1295/5625 [01:07<03:47, 19.05it/s]
 23%|██▎       | 1297/5625 [01:07<03:45, 19.23it/s]
 23%|██▎       | 1299/5625 [01:07<03:43, 19.32it/s]
 23%|██▎       | 1301/5625 [01:07<03:50, 18.75it/s]
 23%|██▎       | 1303/5625 [01:07<03:56, 18.30it/s]
 23%|██▎       | 1305/5625 [01:07<03:56, 18.30it/s]
 23%|██▎       | 1307/5625 [01:07<03:54, 18.41it/s]
 23%|██▎       | 1309/5625 [01:08<03:52, 18.59it/s]
 23%|██▎       | 1312/5625 [01:08<03:41, 19.46it/s]
 23%|██▎       | 1314/5625 [01:08<03:41, 19.49it/s]
 23%|██▎       | 1317/5625 [01:08<03:37, 19.85it/s]
 23%|██▎       | 1319/5625 [01:08<03:40, 19.54it/s]
 23%|██▎       | 1321/5625 [01:08<03:40, 19.56it/s]
 24%|██▎       | 1323/5625 [01:08<03:40, 19.53it/s]
 24%|██▎       | 1325/5625 [01:08<03:42, 19.28it/s]
 24%|██▎       | 1328/5625 [01:08<03:38, 19.65it/s]
 24%|██▎       | 1331/5625 [01:09<03:35, 19.93it/s]
 24%|██▎       | 1333/5625 [01:09<03:40, 19.49it/s]
 24%|██▎       | 1335/5625 [01:09<03:41, 19.33it/s]
 24%|██▍       | 1337/5625 [01:09<03:40, 19.48it/s]
 24%|██▍       | 1340/5625 [01:09<03:41, 19.32it/s]
 24%|██▍       | 1343/5625 [01:09<03:41, 19.32it/s]
 24%|██▍       | 1346/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1348/5625 [01:10<03:38, 19.60it/s]
 24%|██▍       | 1351/5625 [01:10<03:38, 19.61it/s]
 24%|██▍       | 1354/5625 [01:10<03:31, 20.20it/s]
 24%|██▍       | 1357/5625 [01:10<03:29, 20.37it/s]
 24%|██▍       | 1360/5625 [01:10<03:35, 19.83it/s]
 24%|██▍       | 1362/5625 [01:10<03:34, 19.87it/s]
 24%|██▍       | 1365/5625 [01:10<03:36, 19.65it/s]
 24%|██▍       | 1367/5625 [01:10<03:36, 19.62it/s]
 24%|██▍       | 1369/5625 [01:11<03:40, 19.33it/s]
 24%|██▍       | 1371/5625 [01:11<03:43, 19.04it/s]
 24%|██▍       | 1373/5625 [01:11<03:45, 18.88it/s]
 24%|██▍       | 1375/5625 [01:11<03:42, 19.12it/s]
 24%|██▍       | 1377/5625 [01:11<03:40, 19.25it/s]
 25%|██▍       | 1379/5625 [01:11<03:43, 18.97it/s]
 25%|██▍       | 1381/5625 [01:11<03:43, 19.02it/s]
 25%|██▍       | 1384/5625 [01:11<03:41, 19.12it/s]
 25%|██▍       | 1386/5625 [01:11<03:39, 19.32it/s]
 25%|██▍       | 1389/5625 [01:12<03:32, 19.95it/s]
 25%|██▍       | 1391/5625 [01:12<03:35, 19.61it/s]
 25%|██▍       | 1393/5625 [01:12<03:35, 19.62it/s]
 25%|██▍       | 1396/5625 [01:12<03:33, 19.78it/s]
 25%|██▍       | 1399/5625 [01:12<03:34, 19.66it/s]
 25%|██▍       | 1402/5625 [01:12<03:28, 20.27it/s]
 25%|██▍       | 1405/5625 [01:12<03:29, 20.13it/s]
 25%|██▌       | 1408/5625 [01:13<03:37, 19.39it/s]
 25%|██▌       | 1410/5625 [01:13<03:36, 19.45it/s]
 25%|██▌       | 1413/5625 [01:13<03:25, 20.50it/s]
 25%|██▌       | 1416/5625 [01:13<03:27, 20.32it/s]
 25%|██▌       | 1419/5625 [01:13<03:35, 19.50it/s]
 25%|██▌       | 1422/5625 [01:13<03:34, 19.59it/s]
 25%|██▌       | 1424/5625 [01:13<03:37, 19.31it/s]
 25%|██▌       | 1427/5625 [01:14<03:34, 19.59it/s]
 25%|██▌       | 1429/5625 [01:14<03:33, 19.64it/s]
 25%|██▌       | 1432/5625 [01:14<03:32, 19.73it/s]
 25%|██▌       | 1434/5625 [01:14<03:35, 19.46it/s]
 26%|██▌       | 1436/5625 [01:14<03:36, 19.36it/s]
 26%|██▌       | 1438/5625 [01:14<03:41, 18.88it/s]
 26%|██▌       | 1440/5625 [01:14<03:45, 18.53it/s]
 26%|██▌       | 1442/5625 [01:14<03:45, 18.59it/s]
 26%|██▌       | 1444/5625 [01:14<03:44, 18.65it/s]
 26%|██▌       | 1446/5625 [01:15<03:41, 18.84it/s]
 26%|██▌       | 1449/5625 [01:15<03:24, 20.40it/s]
 26%|██▌       | 1452/5625 [01:15<03:24, 20.37it/s]
 26%|██▌       | 1455/5625 [01:15<03:33, 19.54it/s]
 26%|██▌       | 1457/5625 [01:15<03:33, 19.56it/s]
 26%|██▌       | 1459/5625 [01:15<03:32, 19.63it/s]
 26%|██▌       | 1461/5625 [01:15<03:34, 19.45it/s]
 26%|██▌       | 1464/5625 [01:15<03:29, 19.83it/s]
 26%|██▌       | 1466/5625 [01:16<03:31, 19.69it/s]
 26%|██▌       | 1468/5625 [01:16<03:32, 19.53it/s]
 26%|██▌       | 1470/5625 [01:16<03:34, 19.41it/s]
 26%|██▌       | 1472/5625 [01:16<03:32, 19.51it/s]
 26%|██▌       | 1474/5625 [01:16<03:33, 19.48it/s]
 26%|██▌       | 1476/5625 [01:16<03:37, 19.08it/s]
 26%|██▋       | 1479/5625 [01:16<03:26, 20.09it/s]
 26%|██▋       | 1481/5625 [01:16<03:31, 19.63it/s]
 26%|██▋       | 1484/5625 [01:16<03:27, 19.95it/s]
 26%|██▋       | 1487/5625 [01:17<03:20, 20.68it/s]
 26%|██▋       | 1490/5625 [01:17<03:28, 19.87it/s]
 27%|██▋       | 1492/5625 [01:17<03:34, 19.25it/s]
 27%|██▋       | 1494/5625 [01:17<03:33, 19.37it/s]
 27%|██▋       | 1496/5625 [01:17<03:35, 19.18it/s]
 27%|██▋       | 1498/5625 [01:17<03:39, 18.78it/s]
 27%|██▋       | 1500/5625 [01:17<03:35, 19.10it/s]
 27%|██▋       | 1502/5625 [01:17<03:33, 19.30it/s]
 27%|██▋       | 1504/5625 [01:17<03:37, 18.96it/s]
 27%|██▋       | 1506/5625 [01:18<03:37, 18.90it/s]
 27%|██▋       | 1508/5625 [01:18<03:40, 18.65it/s]
 27%|██▋       | 1511/5625 [01:18<03:35, 19.05it/s]
 27%|██▋       | 1513/5625 [01:18<03:39, 18.71it/s]
 27%|██▋       | 1515/5625 [01:18<03:39, 18.68it/s]
 27%|██▋       | 1517/5625 [01:18<03:42, 18.50it/s]
 27%|██▋       | 1520/5625 [01:18<03:31, 19.37it/s]
 27%|██▋       | 1523/5625 [01:18<03:29, 19.54it/s]
 27%|██▋       | 1526/5625 [01:19<03:28, 19.68it/s]
 27%|██▋       | 1529/5625 [01:19<03:23, 20.14it/s]
 27%|██▋       | 1532/5625 [01:19<03:27, 19.68it/s]
 27%|██▋       | 1535/5625 [01:19<03:28, 19.60it/s]
 27%|██▋       | 1538/5625 [01:19<03:26, 19.77it/s]
 27%|██▋       | 1540/5625 [01:19<03:27, 19.71it/s]
 27%|██▋       | 1542/5625 [01:19<03:30, 19.38it/s]
 27%|██▋       | 1544/5625 [01:20<03:32, 19.16it/s]
 27%|██▋       | 1546/5625 [01:20<03:31, 19.31it/s]
 28%|██▊       | 1549/5625 [01:20<03:30, 19.37it/s]
 28%|██▊       | 1551/5625 [01:20<03:30, 19.39it/s]
 28%|██▊       | 1554/5625 [01:20<03:25, 19.79it/s]
 28%|██▊       | 1556/5625 [01:20<03:32, 19.13it/s]
 28%|██▊       | 1558/5625 [01:20<03:34, 18.99it/s]
 28%|██▊       | 1560/5625 [01:20<03:33, 19.06it/s]
 28%|██▊       | 1562/5625 [01:20<03:33, 19.03it/s]
 28%|██▊       | 1564/5625 [01:21<03:30, 19.28it/s]
 28%|██▊       | 1566/5625 [01:21<03:34, 18.89it/s]
 28%|██▊       | 1569/5625 [01:21<03:27, 19.53it/s]
 28%|██▊       | 1571/5625 [01:21<03:30, 19.30it/s]
 28%|██▊       | 1573/5625 [01:21<03:27, 19.48it/s]
 28%|██▊       | 1575/5625 [01:21<03:30, 19.28it/s]
 28%|██▊       | 1578/5625 [01:21<03:27, 19.51it/s]
 28%|██▊       | 1581/5625 [01:21<03:19, 20.28it/s]
 28%|██▊       | 1584/5625 [01:22<03:24, 19.77it/s]
 28%|██▊       | 1587/5625 [01:22<03:23, 19.87it/s]
 28%|██▊       | 1589/5625 [01:22<03:25, 19.62it/s]
 28%|██▊       | 1592/5625 [01:22<03:22, 19.94it/s]
 28%|██▊       | 1594/5625 [01:22<03:27, 19.45it/s]
 28%|██▊       | 1596/5625 [01:22<03:29, 19.21it/s]
 28%|██▊       | 1598/5625 [01:22<03:30, 19.15it/s]
 28%|██▊       | 1600/5625 [01:22<03:30, 19.14it/s]
 28%|██▊       | 1602/5625 [01:23<03:34, 18.76it/s]
 29%|██▊       | 1604/5625 [01:23<03:30, 19.08it/s]
 29%|██▊       | 1606/5625 [01:23<03:28, 19.23it/s]
 29%|██▊       | 1608/5625 [01:23<03:27, 19.40it/s]
 29%|██▊       | 1610/5625 [01:23<03:30, 19.10it/s]
 29%|██▊       | 1613/5625 [01:23<03:28, 19.20it/s]
 29%|██▊       | 1616/5625 [01:23<03:22, 19.82it/s]
 29%|██▉       | 1619/5625 [01:23<03:18, 20.19it/s]
 29%|██▉       | 1622/5625 [01:24<03:18, 20.15it/s]
 29%|██▉       | 1625/5625 [01:24<03:23, 19.66it/s]
 29%|██▉       | 1628/5625 [01:24<03:20, 19.90it/s]
 29%|██▉       | 1630/5625 [01:24<03:22, 19.76it/s]
 29%|██▉       | 1633/5625 [01:24<03:16, 20.30it/s]
 29%|██▉       | 1636/5625 [01:24<03:18, 20.11it/s]
 29%|██▉       | 1639/5625 [01:24<03:19, 19.94it/s]
 29%|██▉       | 1641/5625 [01:25<03:21, 19.80it/s]
 29%|██▉       | 1643/5625 [01:25<03:26, 19.27it/s]
 29%|██▉       | 1645/5625 [01:25<03:32, 18.74it/s]
 29%|██▉       | 1648/5625 [01:25<03:24, 19.44it/s]
 29%|██▉       | 1650/5625 [01:25<03:28, 19.04it/s]
 29%|██▉       | 1652/5625 [01:25<03:31, 18.79it/s]
 29%|██▉       | 1654/5625 [01:25<03:33, 18.61it/s]
 29%|██▉       | 1656/5625 [01:25<03:35, 18.41it/s]
 29%|██▉       | 1658/5625 [01:25<03:31, 18.72it/s]
 30%|██▉       | 1660/5625 [01:26<03:32, 18.62it/s]
 30%|██▉       | 1662/5625 [01:26<03:34, 18.49it/s]
 30%|██▉       | 1665/5625 [01:26<03:30, 18.77it/s]
 30%|██▉       | 1667/5625 [01:26<03:31, 18.70it/s]
 30%|██▉       | 1669/5625 [01:26<03:30, 18.75it/s]
 30%|██▉       | 1672/5625 [01:26<03:22, 19.57it/s]
 30%|██▉       | 1674/5625 [01:26<03:25, 19.21it/s]
 30%|██▉       | 1677/5625 [01:26<03:16, 20.06it/s]
 30%|██▉       | 1679/5625 [01:27<03:24, 19.31it/s]
 30%|██▉       | 1681/5625 [01:27<03:23, 19.39it/s]
 30%|██▉       | 1683/5625 [01:27<03:30, 18.74it/s]
 30%|██▉       | 1685/5625 [01:27<03:34, 18.40it/s]
 30%|██▉       | 1687/5625 [01:27<03:32, 18.57it/s]
 30%|███       | 1689/5625 [01:27<03:30, 18.70it/s]
 30%|███       | 1691/5625 [01:27<03:27, 18.97it/s]
 30%|███       | 1694/5625 [01:27<03:18, 19.83it/s]
 30%|███       | 1697/5625 [01:27<03:20, 19.61it/s]
 30%|███       | 1699/5625 [01:28<03:21, 19.47it/s]
 30%|███       | 1701/5625 [01:28<03:27, 18.93it/s]
 30%|███       | 1703/5625 [01:28<03:27, 18.94it/s]
 30%|███       | 1706/5625 [01:28<03:25, 19.03it/s]
 30%|███       | 1708/5625 [01:28<03:27, 18.92it/s]
 30%|███       | 1711/5625 [01:28<03:24, 19.15it/s]
 30%|███       | 1713/5625 [01:28<03:28, 18.74it/s]
 30%|███       | 1715/5625 [01:28<03:31, 18.46it/s]
 31%|███       | 1718/5625 [01:29<03:19, 19.58it/s]
 31%|███       | 1720/5625 [01:29<03:25, 19.00it/s]
 31%|███       | 1722/5625 [01:29<03:25, 18.99it/s]
 31%|███       | 1724/5625 [01:29<03:25, 19.02it/s]
 31%|███       | 1727/5625 [01:29<03:20, 19.39it/s]
 31%|███       | 1729/5625 [01:29<03:20, 19.45it/s]
 31%|███       | 1732/5625 [01:29<03:13, 20.12it/s]
 31%|███       | 1735/5625 [01:29<03:11, 20.27it/s]
 31%|███       | 1738/5625 [01:30<03:16, 19.81it/s]
 31%|███       | 1740/5625 [01:30<03:23, 19.11it/s]
 31%|███       | 1742/5625 [01:30<03:23, 19.08it/s]
 31%|███       | 1745/5625 [01:30<03:21, 19.30it/s]
 31%|███       | 1748/5625 [01:30<03:11, 20.25it/s]
 31%|███       | 1751/5625 [01:30<03:15, 19.78it/s]
 31%|███       | 1753/5625 [01:30<03:18, 19.54it/s]
 31%|███       | 1755/5625 [01:30<03:18, 19.54it/s]
 31%|███       | 1757/5625 [01:31<03:19, 19.34it/s]
 31%|███▏      | 1759/5625 [01:31<03:22, 19.09it/s]
 31%|███▏      | 1761/5625 [01:31<03:23, 19.02it/s]
 31%|███▏      | 1763/5625 [01:31<03:23, 18.94it/s]
 31%|███▏      | 1765/5625 [01:31<03:27, 18.60it/s]
 31%|███▏      | 1767/5625 [01:31<03:26, 18.72it/s]
 31%|███▏      | 1769/5625 [01:31<03:28, 18.46it/s]
 31%|███▏      | 1771/5625 [01:31<03:27, 18.61it/s]
 32%|███▏      | 1774/5625 [01:31<03:18, 19.36it/s]
 32%|███▏      | 1776/5625 [01:32<03:24, 18.78it/s]
 32%|███▏      | 1778/5625 [01:32<03:22, 19.00it/s]
 32%|███▏      | 1780/5625 [01:32<03:19, 19.23it/s]
 32%|███▏      | 1782/5625 [01:32<03:18, 19.38it/s]
 32%|███▏      | 1784/5625 [01:32<03:24, 18.76it/s]
 32%|███▏      | 1786/5625 [01:32<03:24, 18.76it/s]
 32%|███▏      | 1788/5625 [01:32<03:24, 18.80it/s]
 32%|███▏      | 1791/5625 [01:32<03:16, 19.51it/s]
 32%|███▏      | 1794/5625 [01:33<03:14, 19.66it/s]
 32%|███▏      | 1797/5625 [01:33<03:07, 20.43it/s]
 32%|███▏      | 1800/5625 [01:33<03:08, 20.29it/s]
 32%|███▏      | 1803/5625 [01:33<03:06, 20.44it/s]
 32%|███▏      | 1806/5625 [01:33<03:08, 20.26it/s]
 32%|███▏      | 1809/5625 [01:33<03:05, 20.53it/s]
 32%|███▏      | 1812/5625 [01:33<03:06, 20.46it/s]
 32%|███▏      | 1815/5625 [01:34<03:10, 20.00it/s]
 32%|███▏      | 1818/5625 [01:34<03:15, 19.49it/s]
 32%|███▏      | 1820/5625 [01:34<03:14, 19.58it/s]
 32%|███▏      | 1822/5625 [01:34<03:16, 19.36it/s]
 32%|███▏      | 1824/5625 [01:34<03:19, 19.01it/s]
 32%|███▏      | 1827/5625 [01:34<03:15, 19.46it/s]
 33%|███▎      | 1829/5625 [01:34<03:20, 18.91it/s]
 33%|███▎      | 1831/5625 [01:34<03:25, 18.44it/s]
 33%|███▎      | 1834/5625 [01:35<03:21, 18.80it/s]
 33%|███▎      | 1836/5625 [01:35<03:25, 18.41it/s]
 33%|███▎      | 1838/5625 [01:35<03:23, 18.59it/s]
 33%|███▎      | 1841/5625 [01:35<03:20, 18.85it/s]
 33%|███▎      | 1844/5625 [01:35<03:12, 19.68it/s]
 33%|███▎      | 1846/5625 [01:35<03:18, 19.00it/s]
 33%|███▎      | 1848/5625 [01:35<03:20, 18.84it/s]
 33%|███▎      | 1851/5625 [01:35<03:11, 19.71it/s]
 33%|███▎      | 1854/5625 [01:36<03:07, 20.16it/s]
 33%|███▎      | 1857/5625 [01:36<03:07, 20.08it/s]
 33%|███▎      | 1859/5625 [01:36<03:12, 19.56it/s]
 33%|███▎      | 1861/5625 [01:36<03:17, 19.10it/s]
 33%|███▎      | 1863/5625 [01:36<03:15, 19.20it/s]
 33%|███▎      | 1865/5625 [01:36<03:19, 18.85it/s]
 33%|███▎      | 1867/5625 [01:36<03:17, 19.01it/s]
 33%|███▎      | 1869/5625 [01:36<03:21, 18.68it/s]
 33%|███▎      | 1871/5625 [01:36<03:17, 19.02it/s]
 33%|███▎      | 1873/5625 [01:37<03:16, 19.13it/s]
                                                   

 33%|███▎      | 1875/5625 [01:37<03:16, 19.13it/s]{'loss': 0.9289, 'learning_rate': 1.283500761534296e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.72it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.53it/s]

 21%|██        | 66/313 [00:00<00:01, 206.07it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.37it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.73it/s]

 40%|████      | 126/313 [00:00<00:01, 185.42it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.15it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.13it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.26it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.41it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.49it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.04it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.86it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.78it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.85it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.85it/s]
 33%|███▎      | 1875/5625 [01:38<03:16, 19.13it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 1876/5625 [01:39<24:20,  2.57it/s]
 33%|███▎      | 1878/5625 [01:39<18:40,  3.34it/s]
 33%|███▎      | 1880/5625 [01:40<14:28,  4.31it/s]
 33%|███▎      | 1882/5625 [01:40<11:20,  5.50it/s]
 34%|███▎      | 1885/5625 [01:40<08:16,  7.53it/s]
 34%|███▎      | 1887/5625 [01:40<06:58,  8.93it/s]
 34%|███▎      | 1889/5625 [01:40<06:00, 10.35it/s]
 34%|███▎      | 1891/5625 [01:40<05:15, 11.84it/s]
 34%|███▎      | 1894/5625 [01:40<04:28, 13.87it/s]
 34%|███▎      | 1896/5625 [01:40<04:11, 14.80it/s]
 34%|███▍      | 1899/5625 [01:41<03:44, 16.57it/s]
 34%|███▍      | 1902/5625 [01:41<03:29, 17.76it/s]
 34%|███▍      | 1904/5625 [01:41<03:29, 17.80it/s]
 34%|███▍      | 1906/5625 [01:41<03:24, 18.21it/s]
 34%|███▍      | 1908/5625 [01:41<03:26, 18.04it/s]
 34%|███▍      | 1910/5625 [01:41<03:27, 17.90it/s]
 34%|███▍      | 1912/5625 [01:41<03:21, 18.40it/s]
 34%|███▍      | 1915/5625 [01:41<03:16, 18.88it/s]
 34%|███▍      | 1918/5625 [01:42<03:06, 19.92it/s]
 34%|███▍      | 1921/5625 [01:42<03:08, 19.66it/s]
 34%|███▍      | 1923/5625 [01:42<03:09, 19.52it/s]
 34%|███▍      | 1925/5625 [01:42<03:08, 19.58it/s]
 34%|███▍      | 1927/5625 [01:42<03:12, 19.26it/s]
 34%|███▍      | 1930/5625 [01:42<03:07, 19.67it/s]
 34%|███▍      | 1932/5625 [01:42<03:07, 19.68it/s]
 34%|███▍      | 1934/5625 [01:42<03:09, 19.48it/s]
 34%|███▍      | 1937/5625 [01:43<03:04, 19.98it/s]
 34%|███▍      | 1939/5625 [01:43<03:10, 19.39it/s]
 35%|███▍      | 1942/5625 [01:43<03:06, 19.75it/s]
 35%|███▍      | 1944/5625 [01:43<03:10, 19.32it/s]
 35%|███▍      | 1946/5625 [01:43<03:13, 18.98it/s]
 35%|███▍      | 1949/5625 [01:43<03:11, 19.15it/s]
 35%|███▍      | 1951/5625 [01:43<03:12, 19.08it/s]
 35%|███▍      | 1953/5625 [01:43<03:17, 18.62it/s]
 35%|███▍      | 1955/5625 [01:43<03:16, 18.70it/s]
 35%|███▍      | 1958/5625 [01:44<03:10, 19.20it/s]
 35%|███▍      | 1960/5625 [01:44<03:16, 18.66it/s]
 35%|███▍      | 1963/5625 [01:44<03:12, 19.05it/s]
 35%|███▍      | 1965/5625 [01:44<03:13, 18.91it/s]
 35%|███▍      | 1968/5625 [01:44<03:08, 19.36it/s]
 35%|███▌      | 1970/5625 [01:44<03:10, 19.19it/s]
 35%|███▌      | 1972/5625 [01:44<03:10, 19.13it/s]
 35%|███▌      | 1975/5625 [01:45<03:02, 20.02it/s]
 35%|███▌      | 1977/5625 [01:45<03:02, 19.94it/s]
 35%|███▌      | 1980/5625 [01:45<02:57, 20.49it/s]
 35%|███▌      | 1983/5625 [01:45<03:05, 19.61it/s]
 35%|███▌      | 1986/5625 [01:45<03:04, 19.73it/s]
 35%|███▌      | 1988/5625 [01:45<03:06, 19.55it/s]
 35%|███▌      | 1990/5625 [01:45<03:11, 18.98it/s]
 35%|███▌      | 1992/5625 [01:45<03:11, 18.96it/s]
 35%|███▌      | 1994/5625 [01:46<03:13, 18.73it/s]
 35%|███▌      | 1996/5625 [01:46<03:12, 18.89it/s]
 36%|███▌      | 1999/5625 [01:46<03:04, 19.64it/s]
 36%|███▌      | 2001/5625 [01:46<03:05, 19.56it/s]
 36%|███▌      | 2004/5625 [01:46<03:00, 20.08it/s]
 36%|███▌      | 2006/5625 [01:46<03:00, 20.04it/s]
 36%|███▌      | 2008/5625 [01:46<03:06, 19.44it/s]
 36%|███▌      | 2010/5625 [01:46<03:08, 19.14it/s]
 36%|███▌      | 2012/5625 [01:46<03:08, 19.21it/s]
 36%|███▌      | 2015/5625 [01:47<03:00, 19.99it/s]
 36%|███▌      | 2017/5625 [01:47<03:01, 19.90it/s]
 36%|███▌      | 2019/5625 [01:47<03:03, 19.61it/s]
 36%|███▌      | 2021/5625 [01:47<03:07, 19.21it/s]
 36%|███▌      | 2023/5625 [01:47<03:06, 19.36it/s]
 36%|███▌      | 2025/5625 [01:47<03:04, 19.50it/s]
 36%|███▌      | 2027/5625 [01:47<03:08, 19.06it/s]
 36%|███▌      | 2029/5625 [01:47<03:09, 18.93it/s]
 36%|███▌      | 2031/5625 [01:47<03:12, 18.67it/s]
 36%|███▌      | 2033/5625 [01:48<03:11, 18.76it/s]
 36%|███▌      | 2036/5625 [01:48<03:01, 19.81it/s]
 36%|███▌      | 2038/5625 [01:48<03:04, 19.49it/s]
 36%|███▋      | 2041/5625 [01:48<03:04, 19.37it/s]
 36%|███▋      | 2043/5625 [01:48<03:08, 19.01it/s]
 36%|███▋      | 2045/5625 [01:48<03:09, 18.88it/s]
 36%|███▋      | 2047/5625 [01:48<03:14, 18.36it/s]
 36%|███▋      | 2049/5625 [01:48<03:12, 18.54it/s]
 36%|███▋      | 2051/5625 [01:48<03:09, 18.87it/s]
 37%|███▋      | 2054/5625 [01:49<03:06, 19.15it/s]
 37%|███▋      | 2057/5625 [01:49<03:01, 19.62it/s]
 37%|███▋      | 2059/5625 [01:49<03:02, 19.55it/s]
 37%|███▋      | 2061/5625 [01:49<03:04, 19.30it/s]
 37%|███▋      | 2064/5625 [01:49<03:04, 19.35it/s]
 37%|███▋      | 2067/5625 [01:49<02:56, 20.19it/s]
 37%|███▋      | 2070/5625 [01:49<03:03, 19.42it/s]
 37%|███▋      | 2072/5625 [01:50<03:03, 19.39it/s]
 37%|███▋      | 2074/5625 [01:50<03:07, 18.94it/s]
 37%|███▋      | 2077/5625 [01:50<03:00, 19.69it/s]
 37%|███▋      | 2080/5625 [01:50<02:58, 19.81it/s]
 37%|███▋      | 2082/5625 [01:50<03:02, 19.37it/s]
 37%|███▋      | 2084/5625 [01:50<03:04, 19.23it/s]
 37%|███▋      | 2086/5625 [01:50<03:06, 18.93it/s]
 37%|███▋      | 2088/5625 [01:50<03:10, 18.58it/s]
 37%|███▋      | 2090/5625 [01:50<03:13, 18.28it/s]
 37%|███▋      | 2092/5625 [01:51<03:10, 18.52it/s]
 37%|███▋      | 2095/5625 [01:51<03:04, 19.10it/s]
 37%|███▋      | 2097/5625 [01:51<03:02, 19.29it/s]
 37%|███▋      | 2100/5625 [01:51<02:57, 19.86it/s]
 37%|███▋      | 2102/5625 [01:51<03:00, 19.55it/s]
 37%|███▋      | 2104/5625 [01:51<03:02, 19.25it/s]
 37%|███▋      | 2107/5625 [01:51<02:56, 19.91it/s]
 38%|███▊      | 2110/5625 [01:51<02:57, 19.77it/s]
 38%|███▊      | 2112/5625 [01:52<03:01, 19.31it/s]
 38%|███▊      | 2115/5625 [01:52<02:55, 19.96it/s]
 38%|███▊      | 2118/5625 [01:52<02:58, 19.69it/s]
 38%|███▊      | 2120/5625 [01:52<03:03, 19.14it/s]
 38%|███▊      | 2122/5625 [01:52<03:05, 18.90it/s]
 38%|███▊      | 2124/5625 [01:52<03:07, 18.68it/s]
 38%|███▊      | 2126/5625 [01:52<03:10, 18.41it/s]
 38%|███▊      | 2128/5625 [01:52<03:09, 18.48it/s]
 38%|███▊      | 2130/5625 [01:53<03:08, 18.54it/s]
 38%|███▊      | 2132/5625 [01:53<03:06, 18.68it/s]
 38%|███▊      | 2134/5625 [01:53<03:06, 18.70it/s]
 38%|███▊      | 2137/5625 [01:53<03:04, 18.92it/s]
 38%|███▊      | 2139/5625 [01:53<03:05, 18.79it/s]
 38%|███▊      | 2141/5625 [01:53<03:05, 18.78it/s]
 38%|███▊      | 2143/5625 [01:53<03:03, 19.01it/s]
 38%|███▊      | 2146/5625 [01:53<03:02, 19.11it/s]
 38%|███▊      | 2148/5625 [01:54<03:06, 18.66it/s]
 38%|███▊      | 2150/5625 [01:54<03:08, 18.46it/s]
 38%|███▊      | 2153/5625 [01:54<02:58, 19.42it/s]
 38%|███▊      | 2155/5625 [01:54<03:02, 19.05it/s]
 38%|███▊      | 2158/5625 [01:54<02:55, 19.76it/s]
 38%|███▊      | 2160/5625 [01:54<02:55, 19.73it/s]
 38%|███▊      | 2162/5625 [01:54<02:59, 19.26it/s]
 38%|███▊      | 2165/5625 [01:54<02:49, 20.40it/s]
 39%|███▊      | 2168/5625 [01:55<02:52, 20.08it/s]
 39%|███▊      | 2171/5625 [01:55<02:48, 20.47it/s]
 39%|███▊      | 2174/5625 [01:55<02:54, 19.73it/s]
 39%|███▊      | 2176/5625 [01:55<02:56, 19.57it/s]
 39%|███▊      | 2178/5625 [01:55<02:59, 19.25it/s]
 39%|███▉      | 2180/5625 [01:55<02:57, 19.42it/s]
 39%|███▉      | 2182/5625 [01:55<03:03, 18.81it/s]
 39%|███▉      | 2185/5625 [01:55<02:54, 19.67it/s]
 39%|███▉      | 2187/5625 [01:55<02:54, 19.66it/s]
 39%|███▉      | 2190/5625 [01:56<02:52, 19.90it/s]
 39%|███▉      | 2192/5625 [01:56<02:52, 19.85it/s]
 39%|███▉      | 2195/5625 [01:56<02:46, 20.55it/s]
 39%|███▉      | 2198/5625 [01:56<02:50, 20.13it/s]
 39%|███▉      | 2201/5625 [01:56<02:54, 19.66it/s]
 39%|███▉      | 2203/5625 [01:56<02:57, 19.24it/s]
 39%|███▉      | 2205/5625 [01:56<02:56, 19.36it/s]
 39%|███▉      | 2207/5625 [01:57<02:55, 19.47it/s]
 39%|███▉      | 2209/5625 [01:57<02:54, 19.61it/s]
 39%|███▉      | 2211/5625 [01:57<02:56, 19.37it/s]
 39%|███▉      | 2213/5625 [01:57<02:58, 19.13it/s]
 39%|███▉      | 2215/5625 [01:57<03:39, 15.54it/s]
 39%|███▉      | 2217/5625 [01:57<03:32, 16.07it/s]
 39%|███▉      | 2219/5625 [01:57<03:20, 16.97it/s]
 39%|███▉      | 2221/5625 [01:57<03:14, 17.51it/s]
 40%|███▉      | 2223/5625 [01:57<03:14, 17.51it/s]
 40%|███▉      | 2225/5625 [01:58<03:08, 18.02it/s]
 40%|███▉      | 2227/5625 [01:58<03:08, 18.01it/s]
 40%|███▉      | 2229/5625 [01:58<03:04, 18.41it/s]
 40%|███▉      | 2231/5625 [01:58<03:03, 18.46it/s]
 40%|███▉      | 2233/5625 [01:58<03:01, 18.65it/s]
 40%|███▉      | 2235/5625 [01:58<03:03, 18.46it/s]
 40%|███▉      | 2237/5625 [01:58<02:59, 18.84it/s]
 40%|███▉      | 2239/5625 [01:58<03:04, 18.38it/s]
 40%|███▉      | 2241/5625 [01:58<03:05, 18.21it/s]
 40%|███▉      | 2243/5625 [01:59<03:01, 18.59it/s]
 40%|███▉      | 2245/5625 [01:59<03:01, 18.57it/s]
 40%|███▉      | 2247/5625 [01:59<03:01, 18.62it/s]
 40%|███▉      | 2249/5625 [01:59<02:58, 18.88it/s]
 40%|████      | 2252/5625 [01:59<02:53, 19.41it/s]
 40%|████      | 2254/5625 [01:59<02:57, 18.95it/s]
 40%|████      | 2256/5625 [01:59<03:00, 18.68it/s]
 40%|████      | 2258/5625 [01:59<03:00, 18.65it/s]
 40%|████      | 2260/5625 [01:59<02:58, 18.83it/s]
 40%|████      | 2263/5625 [02:00<02:50, 19.74it/s]
 40%|████      | 2265/5625 [02:00<02:50, 19.67it/s]
 40%|████      | 2267/5625 [02:00<02:50, 19.66it/s]
 40%|████      | 2269/5625 [02:00<02:53, 19.37it/s]
 40%|████      | 2271/5625 [02:00<02:54, 19.24it/s]
 40%|████      | 2274/5625 [02:00<02:50, 19.65it/s]
 40%|████      | 2277/5625 [02:00<02:49, 19.72it/s]
 41%|████      | 2279/5625 [02:00<02:53, 19.28it/s]
 41%|████      | 2281/5625 [02:00<02:53, 19.32it/s]
 41%|████      | 2283/5625 [02:01<02:52, 19.38it/s]
 41%|████      | 2285/5625 [02:01<02:52, 19.34it/s]
 41%|████      | 2287/5625 [02:01<02:54, 19.18it/s]
 41%|████      | 2289/5625 [02:01<02:57, 18.74it/s]
 41%|████      | 2292/5625 [02:01<02:52, 19.35it/s]
 41%|████      | 2294/5625 [02:01<02:56, 18.88it/s]
 41%|████      | 2296/5625 [02:01<02:56, 18.81it/s]
 41%|████      | 2298/5625 [02:01<02:58, 18.60it/s]
 41%|████      | 2300/5625 [02:01<02:55, 18.93it/s]
 41%|████      | 2302/5625 [02:02<02:58, 18.67it/s]
 41%|████      | 2305/5625 [02:02<02:48, 19.70it/s]
 41%|████      | 2308/5625 [02:02<02:46, 19.90it/s]
 41%|████      | 2310/5625 [02:02<02:47, 19.85it/s]
 41%|████      | 2312/5625 [02:02<03:25, 16.13it/s]
 41%|████      | 2314/5625 [02:02<03:18, 16.67it/s]
 41%|████      | 2317/5625 [02:02<03:00, 18.30it/s]
 41%|████      | 2320/5625 [02:03<02:49, 19.50it/s]
 41%|████▏     | 2322/5625 [02:03<02:49, 19.45it/s]
 41%|████▏     | 2324/5625 [02:03<02:54, 18.92it/s]
 41%|████▏     | 2326/5625 [02:03<02:55, 18.79it/s]
 41%|████▏     | 2328/5625 [02:03<02:52, 19.07it/s]
 41%|████▏     | 2330/5625 [02:03<02:52, 19.16it/s]
 41%|████▏     | 2332/5625 [02:03<02:55, 18.75it/s]
 41%|████▏     | 2334/5625 [02:03<02:53, 19.02it/s]
 42%|████▏     | 2336/5625 [02:03<02:57, 18.53it/s]
 42%|████▏     | 2339/5625 [02:04<02:55, 18.76it/s]
 42%|████▏     | 2341/5625 [02:04<02:59, 18.34it/s]
 42%|████▏     | 2343/5625 [02:04<02:58, 18.43it/s]
 42%|████▏     | 2345/5625 [02:04<02:58, 18.38it/s]
 42%|████▏     | 2347/5625 [02:04<02:55, 18.72it/s]
 42%|████▏     | 2349/5625 [02:04<02:53, 18.85it/s]
 42%|████▏     | 2351/5625 [02:04<02:52, 18.96it/s]
 42%|████▏     | 2353/5625 [02:04<02:53, 18.82it/s]
 42%|████▏     | 2355/5625 [02:04<02:50, 19.13it/s]
 42%|████▏     | 2358/5625 [02:05<02:50, 19.17it/s]
 42%|████▏     | 2361/5625 [02:05<02:47, 19.44it/s]
 42%|████▏     | 2363/5625 [02:05<02:48, 19.38it/s]
 42%|████▏     | 2365/5625 [02:05<02:47, 19.47it/s]
 42%|████▏     | 2367/5625 [02:05<02:48, 19.30it/s]
 42%|████▏     | 2369/5625 [02:05<02:48, 19.36it/s]
 42%|████▏     | 2371/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2374/5625 [02:05<02:44, 19.73it/s]
 42%|████▏     | 2376/5625 [02:05<02:44, 19.70it/s]
 42%|████▏     | 2378/5625 [02:06<02:48, 19.27it/s]
 42%|████▏     | 2380/5625 [02:06<02:53, 18.70it/s]
 42%|████▏     | 2382/5625 [02:06<02:54, 18.55it/s]
 42%|████▏     | 2385/5625 [02:06<02:43, 19.86it/s]
 42%|████▏     | 2387/5625 [02:06<02:42, 19.88it/s]
 42%|████▏     | 2389/5625 [02:06<02:43, 19.82it/s]
 43%|████▎     | 2391/5625 [02:06<02:43, 19.84it/s]
 43%|████▎     | 2393/5625 [02:06<02:46, 19.45it/s]
 43%|████▎     | 2395/5625 [02:06<02:47, 19.34it/s]
 43%|████▎     | 2398/5625 [02:07<02:38, 20.41it/s]
 43%|████▎     | 2401/5625 [02:07<02:42, 19.79it/s]
 43%|████▎     | 2403/5625 [02:07<02:44, 19.54it/s]
 43%|████▎     | 2405/5625 [02:07<02:44, 19.62it/s]
 43%|████▎     | 2407/5625 [02:07<02:45, 19.42it/s]
 43%|████▎     | 2410/5625 [02:07<02:44, 19.60it/s]
 43%|████▎     | 2413/5625 [02:07<02:42, 19.81it/s]
 43%|████▎     | 2415/5625 [02:08<02:47, 19.17it/s]
 43%|████▎     | 2418/5625 [02:08<02:41, 19.91it/s]
 43%|████▎     | 2420/5625 [02:08<02:44, 19.44it/s]
 43%|████▎     | 2422/5625 [02:08<02:45, 19.40it/s]
 43%|████▎     | 2425/5625 [02:08<02:43, 19.57it/s]
 43%|████▎     | 2427/5625 [02:08<02:44, 19.48it/s]
 43%|████▎     | 2429/5625 [02:08<02:43, 19.52it/s]
 43%|████▎     | 2432/5625 [02:08<02:35, 20.48it/s]
 43%|████▎     | 2435/5625 [02:08<02:31, 21.02it/s]
 43%|████▎     | 2438/5625 [02:09<02:33, 20.80it/s]
 43%|████▎     | 2441/5625 [02:09<02:36, 20.39it/s]
 43%|████▎     | 2444/5625 [02:09<02:37, 20.18it/s]
 44%|████▎     | 2447/5625 [02:09<02:42, 19.51it/s]
 44%|████▎     | 2450/5625 [02:09<02:38, 19.98it/s]
 44%|████▎     | 2453/5625 [02:09<02:38, 20.04it/s]
 44%|████▎     | 2456/5625 [02:10<02:36, 20.24it/s]
 44%|████▎     | 2459/5625 [02:10<02:39, 19.91it/s]
 44%|████▍     | 2461/5625 [02:10<02:41, 19.61it/s]
 44%|████▍     | 2464/5625 [02:10<02:40, 19.69it/s]
 44%|████▍     | 2467/5625 [02:10<02:41, 19.52it/s]
 44%|████▍     | 2469/5625 [02:10<02:41, 19.60it/s]
 44%|████▍     | 2471/5625 [02:10<02:41, 19.49it/s]
 44%|████▍     | 2474/5625 [02:10<02:39, 19.77it/s]
 44%|████▍     | 2476/5625 [02:11<02:39, 19.74it/s]
 44%|████▍     | 2478/5625 [02:11<02:44, 19.08it/s]
 44%|████▍     | 2480/5625 [02:11<02:43, 19.26it/s]
 44%|████▍     | 2483/5625 [02:11<02:35, 20.16it/s]
 44%|████▍     | 2486/5625 [02:11<02:37, 19.98it/s]
 44%|████▍     | 2488/5625 [02:11<02:42, 19.32it/s]
 44%|████▍     | 2490/5625 [02:11<02:43, 19.14it/s]
 44%|████▍     | 2492/5625 [02:11<02:47, 18.71it/s]
 44%|████▍     | 2495/5625 [02:12<02:43, 19.10it/s]
 44%|████▍     | 2497/5625 [02:12<02:46, 18.75it/s]
 44%|████▍     | 2499/5625 [02:12<02:46, 18.75it/s]
 44%|████▍     | 2502/5625 [02:12<02:38, 19.68it/s]
 45%|████▍     | 2504/5625 [02:12<02:38, 19.69it/s]
 45%|████▍     | 2507/5625 [02:12<02:31, 20.64it/s]
 45%|████▍     | 2510/5625 [02:12<02:36, 19.87it/s]
 45%|████▍     | 2513/5625 [02:12<02:31, 20.53it/s]
 45%|████▍     | 2516/5625 [02:13<02:30, 20.67it/s]
 45%|████▍     | 2519/5625 [02:13<02:30, 20.68it/s]
 45%|████▍     | 2522/5625 [02:13<02:36, 19.85it/s]
 45%|████▍     | 2525/5625 [02:13<02:32, 20.28it/s]
 45%|████▍     | 2528/5625 [02:13<02:38, 19.59it/s]
 45%|████▍     | 2530/5625 [02:13<02:38, 19.47it/s]
 45%|████▌     | 2532/5625 [02:13<02:42, 19.07it/s]
 45%|████▌     | 2534/5625 [02:14<02:45, 18.70it/s]
 45%|████▌     | 2536/5625 [02:14<02:45, 18.66it/s]
 45%|████▌     | 2538/5625 [02:14<02:47, 18.41it/s]
 45%|████▌     | 2540/5625 [02:14<02:50, 18.14it/s]
 45%|████▌     | 2542/5625 [02:14<02:47, 18.44it/s]
 45%|████▌     | 2545/5625 [02:14<02:39, 19.26it/s]
 45%|████▌     | 2547/5625 [02:14<02:43, 18.88it/s]
 45%|████▌     | 2549/5625 [02:14<02:42, 18.88it/s]
 45%|████▌     | 2551/5625 [02:14<02:41, 19.02it/s]
 45%|████▌     | 2553/5625 [02:15<02:39, 19.27it/s]
 45%|████▌     | 2555/5625 [02:15<02:41, 19.06it/s]
 45%|████▌     | 2557/5625 [02:15<02:39, 19.26it/s]
 45%|████▌     | 2559/5625 [02:15<02:40, 19.07it/s]
 46%|████▌     | 2561/5625 [02:15<02:39, 19.15it/s]
 46%|████▌     | 2563/5625 [02:15<02:39, 19.22it/s]
 46%|████▌     | 2565/5625 [02:15<02:43, 18.70it/s]
 46%|████▌     | 2568/5625 [02:15<02:39, 19.14it/s]
 46%|████▌     | 2571/5625 [02:15<02:33, 19.88it/s]
 46%|████▌     | 2574/5625 [02:16<02:33, 19.84it/s]
 46%|████▌     | 2576/5625 [02:16<02:39, 19.13it/s]
 46%|████▌     | 2579/5625 [02:16<02:37, 19.32it/s]
 46%|████▌     | 2581/5625 [02:16<02:40, 18.99it/s]
 46%|████▌     | 2583/5625 [02:16<02:44, 18.53it/s]
 46%|████▌     | 2586/5625 [02:16<02:39, 19.09it/s]
 46%|████▌     | 2589/5625 [02:16<02:33, 19.77it/s]
 46%|████▌     | 2591/5625 [02:17<02:37, 19.23it/s]
 46%|████▌     | 2594/5625 [02:17<02:36, 19.33it/s]
 46%|████▌     | 2596/5625 [02:17<02:39, 18.98it/s]
 46%|████▌     | 2598/5625 [02:17<02:43, 18.56it/s]
 46%|████▌     | 2601/5625 [02:17<02:38, 19.03it/s]
 46%|████▋     | 2603/5625 [02:17<02:41, 18.69it/s]
 46%|████▋     | 2605/5625 [02:17<02:45, 18.30it/s]
 46%|████▋     | 2607/5625 [02:17<02:43, 18.50it/s]
 46%|████▋     | 2609/5625 [02:17<02:42, 18.56it/s]
 46%|████▋     | 2611/5625 [02:18<02:45, 18.23it/s]
 46%|████▋     | 2613/5625 [02:18<02:44, 18.27it/s]
 47%|████▋     | 2616/5625 [02:18<02:39, 18.86it/s]
 47%|████▋     | 2618/5625 [02:18<02:39, 18.87it/s]
 47%|████▋     | 2620/5625 [02:18<02:40, 18.71it/s]
 47%|████▋     | 2623/5625 [02:18<02:36, 19.15it/s]
 47%|████▋     | 2625/5625 [02:18<02:37, 19.04it/s]
 47%|████▋     | 2627/5625 [02:18<02:39, 18.80it/s]
 47%|████▋     | 2629/5625 [02:19<02:40, 18.71it/s]
 47%|████▋     | 2632/5625 [02:19<02:34, 19.34it/s]
 47%|████▋     | 2634/5625 [02:19<02:36, 19.09it/s]
 47%|████▋     | 2636/5625 [02:19<02:37, 19.03it/s]
 47%|████▋     | 2638/5625 [02:19<02:34, 19.28it/s]
 47%|████▋     | 2640/5625 [02:19<02:35, 19.20it/s]
 47%|████▋     | 2643/5625 [02:19<02:29, 19.90it/s]
 47%|████▋     | 2645/5625 [02:19<02:30, 19.76it/s]
 47%|████▋     | 2647/5625 [02:19<02:33, 19.40it/s]
 47%|████▋     | 2649/5625 [02:20<02:34, 19.31it/s]
 47%|████▋     | 2651/5625 [02:20<02:36, 18.96it/s]
 47%|████▋     | 2653/5625 [02:20<02:39, 18.62it/s]
 47%|████▋     | 2655/5625 [02:20<02:40, 18.54it/s]
 47%|████▋     | 2658/5625 [02:20<02:32, 19.48it/s]
 47%|████▋     | 2661/5625 [02:20<02:26, 20.20it/s]
 47%|████▋     | 2664/5625 [02:20<02:27, 20.03it/s]
 47%|████▋     | 2666/5625 [02:20<02:30, 19.63it/s]
 47%|████▋     | 2669/5625 [02:21<02:27, 20.01it/s]
 47%|████▋     | 2671/5625 [02:21<02:29, 19.75it/s]
 48%|████▊     | 2673/5625 [02:21<02:29, 19.70it/s]
 48%|████▊     | 2676/5625 [02:21<02:30, 19.65it/s]
 48%|████▊     | 2678/5625 [02:21<02:32, 19.28it/s]
 48%|████▊     | 2680/5625 [02:21<02:32, 19.30it/s]
 48%|████▊     | 2682/5625 [02:21<02:31, 19.41it/s]
 48%|████▊     | 2684/5625 [02:21<02:32, 19.33it/s]
 48%|████▊     | 2686/5625 [02:21<02:30, 19.49it/s]
 48%|████▊     | 2688/5625 [02:22<02:31, 19.41it/s]
 48%|████▊     | 2691/5625 [02:22<02:30, 19.46it/s]
 48%|████▊     | 2693/5625 [02:22<02:34, 18.99it/s]
 48%|████▊     | 2696/5625 [02:22<02:27, 19.82it/s]
 48%|████▊     | 2699/5625 [02:22<02:24, 20.24it/s]
 48%|████▊     | 2702/5625 [02:22<02:27, 19.83it/s]
 48%|████▊     | 2704/5625 [02:22<02:29, 19.50it/s]
 48%|████▊     | 2706/5625 [02:22<02:33, 19.00it/s]
 48%|████▊     | 2709/5625 [02:23<02:30, 19.38it/s]
 48%|████▊     | 2711/5625 [02:23<02:33, 18.92it/s]
 48%|████▊     | 2713/5625 [02:23<02:34, 18.90it/s]
 48%|████▊     | 2715/5625 [02:23<02:37, 18.48it/s]
 48%|████▊     | 2717/5625 [02:23<02:34, 18.78it/s]
 48%|████▊     | 2719/5625 [02:23<02:38, 18.37it/s]
 48%|████▊     | 2721/5625 [02:23<02:35, 18.70it/s]
 48%|████▊     | 2723/5625 [02:23<02:35, 18.68it/s]
 48%|████▊     | 2725/5625 [02:24<02:33, 18.86it/s]
 48%|████▊     | 2727/5625 [02:24<02:31, 19.15it/s]
 49%|████▊     | 2730/5625 [02:24<02:28, 19.56it/s]
 49%|████▊     | 2732/5625 [02:24<02:29, 19.37it/s]
 49%|████▊     | 2734/5625 [02:24<02:32, 18.97it/s]
 49%|████▊     | 2737/5625 [02:24<02:26, 19.77it/s]
 49%|████▊     | 2739/5625 [02:24<02:26, 19.67it/s]
 49%|████▊     | 2741/5625 [02:24<02:29, 19.31it/s]
 49%|████▉     | 2743/5625 [02:24<02:31, 19.04it/s]
 49%|████▉     | 2746/5625 [02:25<02:29, 19.30it/s]
 49%|████▉     | 2748/5625 [02:25<02:28, 19.38it/s]
 49%|████▉     | 2750/5625 [02:25<02:27, 19.46it/s]
 49%|████▉     | 2752/5625 [02:25<02:27, 19.44it/s]
 49%|████▉     | 2754/5625 [02:25<02:28, 19.29it/s]
 49%|████▉     | 2757/5625 [02:25<02:29, 19.20it/s]
 49%|████▉     | 2760/5625 [02:25<02:25, 19.69it/s]
 49%|████▉     | 2762/5625 [02:25<02:27, 19.44it/s]
 49%|████▉     | 2764/5625 [02:26<02:30, 18.97it/s]
 49%|████▉     | 2767/5625 [02:26<02:25, 19.60it/s]
 49%|████▉     | 2770/5625 [02:26<02:24, 19.75it/s]
 49%|████▉     | 2772/5625 [02:26<02:28, 19.27it/s]
 49%|████▉     | 2774/5625 [02:26<02:27, 19.33it/s]
 49%|████▉     | 2776/5625 [02:26<02:26, 19.43it/s]
 49%|████▉     | 2778/5625 [02:26<02:28, 19.20it/s]
 49%|████▉     | 2780/5625 [02:26<02:29, 18.99it/s]
 49%|████▉     | 2783/5625 [02:27<02:27, 19.21it/s]
 50%|████▉     | 2785/5625 [02:27<02:29, 19.01it/s]
 50%|████▉     | 2788/5625 [02:27<02:23, 19.75it/s]
 50%|████▉     | 2790/5625 [02:27<02:26, 19.31it/s]
 50%|████▉     | 2792/5625 [02:27<02:28, 19.14it/s]
 50%|████▉     | 2794/5625 [02:27<02:26, 19.32it/s]
 50%|████▉     | 2796/5625 [02:27<02:31, 18.72it/s]
 50%|████▉     | 2798/5625 [02:27<02:29, 18.88it/s]
 50%|████▉     | 2800/5625 [02:27<02:27, 19.15it/s]
 50%|████▉     | 2802/5625 [02:28<02:32, 18.56it/s]
 50%|████▉     | 2804/5625 [02:28<02:29, 18.87it/s]
 50%|████▉     | 2806/5625 [02:28<02:29, 18.91it/s]
 50%|████▉     | 2809/5625 [02:28<02:27, 19.12it/s]
 50%|████▉     | 2811/5625 [02:28<02:26, 19.25it/s]
 50%|█████     | 2814/5625 [02:28<02:24, 19.51it/s]
 50%|█████     | 2816/5625 [02:28<02:25, 19.28it/s]
 50%|█████     | 2818/5625 [02:28<02:25, 19.31it/s]
 50%|█████     | 2820/5625 [02:28<02:29, 18.73it/s]
 50%|█████     | 2822/5625 [02:29<02:28, 18.91it/s]
 50%|█████     | 2824/5625 [02:29<02:25, 19.19it/s]
 50%|█████     | 2827/5625 [02:29<02:19, 20.03it/s]
 50%|█████     | 2829/5625 [02:29<02:22, 19.69it/s]
 50%|█████     | 2831/5625 [02:29<02:23, 19.42it/s]
 50%|█████     | 2833/5625 [02:29<02:26, 19.08it/s]
 50%|█████     | 2835/5625 [02:29<02:24, 19.26it/s]
 50%|█████     | 2838/5625 [02:29<02:20, 19.81it/s]
 50%|█████     | 2840/5625 [02:29<02:21, 19.72it/s]
 51%|█████     | 2843/5625 [02:30<02:16, 20.41it/s]
 51%|█████     | 2846/5625 [02:30<02:22, 19.51it/s]
 51%|█████     | 2849/5625 [02:30<02:21, 19.58it/s]
 51%|█████     | 2851/5625 [02:30<02:23, 19.38it/s]
 51%|█████     | 2853/5625 [02:30<02:25, 19.10it/s]
 51%|█████     | 2856/5625 [02:30<02:21, 19.60it/s]
 51%|█████     | 2858/5625 [02:30<02:25, 19.02it/s]
 51%|█████     | 2861/5625 [02:31<02:18, 19.93it/s]
 51%|█████     | 2863/5625 [02:31<02:20, 19.67it/s]
 51%|█████     | 2865/5625 [02:31<02:22, 19.39it/s]
 51%|█████     | 2867/5625 [02:31<02:21, 19.48it/s]
 51%|█████     | 2870/5625 [02:31<02:15, 20.30it/s]
 51%|█████     | 2873/5625 [02:31<02:18, 19.83it/s]
 51%|█████     | 2875/5625 [02:31<02:20, 19.55it/s]
 51%|█████     | 2877/5625 [02:31<02:21, 19.46it/s]
 51%|█████     | 2879/5625 [02:31<02:23, 19.14it/s]
 51%|█████     | 2882/5625 [02:32<02:21, 19.38it/s]
 51%|█████▏    | 2884/5625 [02:32<02:23, 19.13it/s]
 51%|█████▏    | 2887/5625 [02:32<02:16, 20.09it/s]
 51%|█████▏    | 2889/5625 [02:32<02:21, 19.31it/s]
 51%|█████▏    | 2891/5625 [02:32<02:20, 19.42it/s]
 51%|█████▏    | 2894/5625 [02:32<02:16, 20.00it/s]
 51%|█████▏    | 2896/5625 [02:32<02:19, 19.52it/s]
 52%|█████▏    | 2898/5625 [02:32<02:20, 19.36it/s]
 52%|█████▏    | 2900/5625 [02:33<02:25, 18.67it/s]
 52%|█████▏    | 2903/5625 [02:33<02:19, 19.58it/s]
 52%|█████▏    | 2906/5625 [02:33<02:14, 20.17it/s]
 52%|█████▏    | 2909/5625 [02:33<02:18, 19.55it/s]
 52%|█████▏    | 2912/5625 [02:33<02:13, 20.36it/s]
 52%|█████▏    | 2915/5625 [02:33<02:16, 19.81it/s]
 52%|█████▏    | 2917/5625 [02:33<02:20, 19.32it/s]
 52%|█████▏    | 2919/5625 [02:34<02:22, 18.93it/s]
 52%|█████▏    | 2921/5625 [02:34<02:25, 18.56it/s]
 52%|█████▏    | 2923/5625 [02:34<02:23, 18.88it/s]
 52%|█████▏    | 2925/5625 [02:34<02:24, 18.66it/s]
 52%|█████▏    | 2927/5625 [02:34<02:24, 18.64it/s]
 52%|█████▏    | 2929/5625 [02:34<02:22, 18.95it/s]
 52%|█████▏    | 2931/5625 [02:34<02:20, 19.12it/s]
 52%|█████▏    | 2934/5625 [02:34<02:20, 19.21it/s]
 52%|█████▏    | 2937/5625 [02:34<02:19, 19.24it/s]
 52%|█████▏    | 2940/5625 [02:35<02:13, 20.09it/s]
 52%|█████▏    | 2943/5625 [02:35<02:11, 20.45it/s]
 52%|█████▏    | 2946/5625 [02:35<02:14, 19.88it/s]
 52%|█████▏    | 2948/5625 [02:35<02:15, 19.78it/s]
 52%|█████▏    | 2950/5625 [02:35<02:18, 19.34it/s]
 52%|█████▏    | 2952/5625 [02:35<02:18, 19.35it/s]
 53%|█████▎    | 2954/5625 [02:35<02:20, 18.97it/s]
 53%|█████▎    | 2957/5625 [02:35<02:17, 19.42it/s]
 53%|█████▎    | 2960/5625 [02:36<02:15, 19.60it/s]
 53%|█████▎    | 2963/5625 [02:36<02:15, 19.65it/s]
 53%|█████▎    | 2965/5625 [02:36<02:19, 19.04it/s]
 53%|█████▎    | 2967/5625 [02:36<02:18, 19.26it/s]
 53%|█████▎    | 2970/5625 [02:36<02:16, 19.40it/s]
 53%|█████▎    | 2973/5625 [02:36<02:14, 19.65it/s]
 53%|█████▎    | 2976/5625 [02:36<02:14, 19.69it/s]
 53%|█████▎    | 2978/5625 [02:37<02:15, 19.53it/s]
 53%|█████▎    | 2980/5625 [02:37<02:17, 19.21it/s]
 53%|█████▎    | 2983/5625 [02:37<02:17, 19.26it/s]
 53%|█████▎    | 2985/5625 [02:37<02:19, 18.93it/s]
 53%|█████▎    | 2988/5625 [02:37<02:16, 19.38it/s]
 53%|█████▎    | 2990/5625 [02:37<02:17, 19.10it/s]
 53%|█████▎    | 2992/5625 [02:37<02:16, 19.32it/s]
 53%|█████▎    | 2995/5625 [02:37<02:11, 19.95it/s]
 53%|█████▎    | 2997/5625 [02:38<02:13, 19.62it/s]
 53%|█████▎    | 2999/5625 [02:38<02:16, 19.30it/s]
 53%|█████▎    | 3002/5625 [02:38<02:12, 19.77it/s]
 53%|█████▎    | 3005/5625 [02:38<02:09, 20.27it/s]
 53%|█████▎    | 3008/5625 [02:38<02:11, 19.96it/s]
 54%|█████▎    | 3010/5625 [02:38<02:13, 19.54it/s]
 54%|█████▎    | 3012/5625 [02:38<02:14, 19.37it/s]
 54%|█████▎    | 3014/5625 [02:38<02:17, 18.97it/s]
 54%|█████▎    | 3017/5625 [02:39<02:13, 19.59it/s]
 54%|█████▎    | 3019/5625 [02:39<02:14, 19.35it/s]
 54%|█████▎    | 3022/5625 [02:39<02:13, 19.56it/s]
 54%|█████▍    | 3024/5625 [02:39<02:12, 19.65it/s]
 54%|█████▍    | 3027/5625 [02:39<02:09, 20.04it/s]
 54%|█████▍    | 3029/5625 [02:39<02:11, 19.76it/s]
 54%|█████▍    | 3032/5625 [02:39<02:09, 20.10it/s]
 54%|█████▍    | 3034/5625 [02:39<02:09, 20.01it/s]
 54%|█████▍    | 3037/5625 [02:40<02:07, 20.25it/s]
 54%|█████▍    | 3040/5625 [02:40<02:13, 19.37it/s]
 54%|█████▍    | 3042/5625 [02:40<02:15, 19.06it/s]
 54%|█████▍    | 3044/5625 [02:40<02:16, 18.95it/s]
 54%|█████▍    | 3047/5625 [02:40<02:14, 19.10it/s]
 54%|█████▍    | 3050/5625 [02:40<02:10, 19.78it/s]
 54%|█████▍    | 3053/5625 [02:40<02:09, 19.81it/s]
 54%|█████▍    | 3056/5625 [02:41<02:06, 20.32it/s]
 54%|█████▍    | 3059/5625 [02:41<02:08, 19.92it/s]
 54%|█████▍    | 3061/5625 [02:41<02:09, 19.81it/s]
 54%|█████▍    | 3063/5625 [02:41<02:09, 19.83it/s]
 54%|█████▍    | 3065/5625 [02:41<02:12, 19.30it/s]
 55%|█████▍    | 3068/5625 [02:41<02:10, 19.62it/s]
 55%|█████▍    | 3070/5625 [02:41<02:12, 19.31it/s]
 55%|█████▍    | 3072/5625 [02:41<02:12, 19.22it/s]
 55%|█████▍    | 3074/5625 [02:41<02:14, 19.01it/s]
 55%|█████▍    | 3077/5625 [02:42<02:08, 19.88it/s]
 55%|█████▍    | 3079/5625 [02:42<02:09, 19.61it/s]
 55%|█████▍    | 3081/5625 [02:42<02:11, 19.41it/s]
 55%|█████▍    | 3084/5625 [02:42<02:10, 19.45it/s]
 55%|█████▍    | 3086/5625 [02:42<02:09, 19.54it/s]
 55%|█████▍    | 3088/5625 [02:42<02:09, 19.63it/s]
 55%|█████▍    | 3090/5625 [02:42<02:10, 19.43it/s]
 55%|█████▍    | 3092/5625 [02:42<02:10, 19.43it/s]
 55%|█████▌    | 3095/5625 [02:43<02:10, 19.34it/s]
 55%|█████▌    | 3097/5625 [02:43<02:12, 19.10it/s]
 55%|█████▌    | 3100/5625 [02:43<02:10, 19.42it/s]
 55%|█████▌    | 3103/5625 [02:43<02:04, 20.20it/s]
 55%|█████▌    | 3106/5625 [02:43<02:07, 19.83it/s]
 55%|█████▌    | 3109/5625 [02:43<02:03, 20.45it/s]
 55%|█████▌    | 3112/5625 [02:43<02:07, 19.65it/s]
 55%|█████▌    | 3114/5625 [02:43<02:09, 19.43it/s]
 55%|█████▌    | 3116/5625 [02:44<02:12, 18.98it/s]
 55%|█████▌    | 3118/5625 [02:44<02:14, 18.63it/s]
 55%|█████▌    | 3120/5625 [02:44<02:12, 18.91it/s]
 56%|█████▌    | 3123/5625 [02:44<02:09, 19.28it/s]
 56%|█████▌    | 3125/5625 [02:44<02:09, 19.27it/s]
 56%|█████▌    | 3127/5625 [02:44<02:10, 19.08it/s]
 56%|█████▌    | 3129/5625 [02:44<02:13, 18.70it/s]
 56%|█████▌    | 3132/5625 [02:44<02:10, 19.04it/s]
 56%|█████▌    | 3134/5625 [02:45<02:11, 19.01it/s]
 56%|█████▌    | 3136/5625 [02:45<02:13, 18.70it/s]
 56%|█████▌    | 3138/5625 [02:45<02:13, 18.61it/s]
 56%|█████▌    | 3140/5625 [02:45<02:15, 18.32it/s]
 56%|█████▌    | 3143/5625 [02:45<02:07, 19.43it/s]
 56%|█████▌    | 3146/5625 [02:45<02:01, 20.35it/s]
 56%|█████▌    | 3149/5625 [02:45<02:06, 19.61it/s]
 56%|█████▌    | 3152/5625 [02:45<02:05, 19.63it/s]
 56%|█████▌    | 3155/5625 [02:46<02:02, 20.12it/s]
 56%|█████▌    | 3158/5625 [02:46<02:03, 19.95it/s]
 56%|█████▌    | 3160/5625 [02:46<02:05, 19.59it/s]
 56%|█████▌    | 3162/5625 [02:46<02:09, 18.98it/s]
 56%|█████▌    | 3164/5625 [02:46<02:10, 18.81it/s]
 56%|█████▋    | 3166/5625 [02:46<02:09, 19.02it/s]
 56%|█████▋    | 3168/5625 [02:46<02:09, 18.92it/s]
 56%|█████▋    | 3170/5625 [02:46<02:12, 18.54it/s]
 56%|█████▋    | 3172/5625 [02:47<02:13, 18.44it/s]
 56%|█████▋    | 3174/5625 [02:47<02:14, 18.20it/s]
 56%|█████▋    | 3176/5625 [02:47<02:14, 18.25it/s]
 56%|█████▋    | 3178/5625 [02:47<02:14, 18.13it/s]
 57%|█████▋    | 3180/5625 [02:47<02:12, 18.48it/s]
 57%|█████▋    | 3183/5625 [02:47<02:09, 18.87it/s]
 57%|█████▋    | 3185/5625 [02:47<02:11, 18.61it/s]
 57%|█████▋    | 3187/5625 [02:47<02:11, 18.54it/s]
 57%|█████▋    | 3189/5625 [02:47<02:08, 18.90it/s]
 57%|█████▋    | 3191/5625 [02:48<02:10, 18.70it/s]
 57%|█████▋    | 3194/5625 [02:48<02:09, 18.82it/s]
 57%|█████▋    | 3196/5625 [02:48<02:07, 19.09it/s]
 57%|█████▋    | 3198/5625 [02:48<02:07, 19.05it/s]
 57%|█████▋    | 3200/5625 [02:48<02:07, 18.99it/s]
 57%|█████▋    | 3203/5625 [02:48<02:04, 19.46it/s]
 57%|█████▋    | 3206/5625 [02:48<02:05, 19.32it/s]
 57%|█████▋    | 3209/5625 [02:48<02:03, 19.60it/s]
 57%|█████▋    | 3211/5625 [02:49<02:03, 19.62it/s]
 57%|█████▋    | 3213/5625 [02:49<02:02, 19.64it/s]
 57%|█████▋    | 3216/5625 [02:49<02:00, 19.92it/s]
 57%|█████▋    | 3218/5625 [02:49<02:02, 19.69it/s]
 57%|█████▋    | 3220/5625 [02:49<02:04, 19.25it/s]
 57%|█████▋    | 3223/5625 [02:49<02:00, 19.88it/s]
 57%|█████▋    | 3226/5625 [02:49<01:58, 20.20it/s]
 57%|█████▋    | 3229/5625 [02:49<02:01, 19.72it/s]
 57%|█████▋    | 3231/5625 [02:50<02:03, 19.43it/s]
 57%|█████▋    | 3234/5625 [02:50<02:02, 19.56it/s]
 58%|█████▊    | 3237/5625 [02:50<02:02, 19.43it/s]
 58%|█████▊    | 3239/5625 [02:50<02:02, 19.54it/s]
 58%|█████▊    | 3241/5625 [02:50<02:06, 18.87it/s]
 58%|█████▊    | 3244/5625 [02:50<02:02, 19.40it/s]
 58%|█████▊    | 3246/5625 [02:50<02:03, 19.30it/s]
 58%|█████▊    | 3249/5625 [02:51<02:00, 19.79it/s]
 58%|█████▊    | 3251/5625 [02:51<02:01, 19.55it/s]
 58%|█████▊    | 3254/5625 [02:51<02:00, 19.73it/s]
 58%|█████▊    | 3257/5625 [02:51<01:58, 19.95it/s]
 58%|█████▊    | 3259/5625 [02:51<02:00, 19.66it/s]
 58%|█████▊    | 3262/5625 [02:51<01:59, 19.80it/s]
 58%|█████▊    | 3264/5625 [02:51<02:00, 19.55it/s]
 58%|█████▊    | 3267/5625 [02:51<02:00, 19.61it/s]
 58%|█████▊    | 3269/5625 [02:52<02:01, 19.32it/s]
 58%|█████▊    | 3272/5625 [02:52<02:00, 19.53it/s]
 58%|█████▊    | 3275/5625 [02:52<01:57, 20.01it/s]
 58%|█████▊    | 3277/5625 [02:52<01:57, 19.94it/s]
 58%|█████▊    | 3279/5625 [02:52<01:58, 19.79it/s]
 58%|█████▊    | 3281/5625 [02:52<02:00, 19.43it/s]
 58%|█████▊    | 3283/5625 [02:52<02:03, 19.03it/s]
 58%|█████▊    | 3285/5625 [02:52<02:01, 19.28it/s]
 58%|█████▊    | 3287/5625 [02:52<02:01, 19.20it/s]
 58%|█████▊    | 3289/5625 [02:53<02:03, 18.96it/s]
 59%|█████▊    | 3292/5625 [02:53<01:58, 19.61it/s]
 59%|█████▊    | 3294/5625 [02:53<02:02, 19.10it/s]
 59%|█████▊    | 3296/5625 [02:53<02:01, 19.21it/s]
 59%|█████▊    | 3299/5625 [02:53<01:56, 20.00it/s]
 59%|█████▊    | 3301/5625 [02:53<02:00, 19.27it/s]
 59%|█████▊    | 3303/5625 [02:53<02:00, 19.28it/s]
 59%|█████▉    | 3306/5625 [02:53<01:58, 19.60it/s]
 59%|█████▉    | 3308/5625 [02:54<01:59, 19.40it/s]
 59%|█████▉    | 3310/5625 [02:54<02:03, 18.77it/s]
 59%|█████▉    | 3312/5625 [02:54<02:03, 18.78it/s]
 59%|█████▉    | 3314/5625 [02:54<02:01, 19.03it/s]
 59%|█████▉    | 3316/5625 [02:54<02:04, 18.61it/s]
 59%|█████▉    | 3319/5625 [02:54<02:00, 19.07it/s]
 59%|█████▉    | 3321/5625 [02:54<02:01, 18.98it/s]
 59%|█████▉    | 3323/5625 [02:54<02:03, 18.69it/s]
 59%|█████▉    | 3325/5625 [02:54<02:00, 19.05it/s]
 59%|█████▉    | 3328/5625 [02:55<01:57, 19.62it/s]
 59%|█████▉    | 3330/5625 [02:55<02:00, 19.10it/s]
 59%|█████▉    | 3333/5625 [02:55<01:56, 19.69it/s]
 59%|█████▉    | 3335/5625 [02:55<01:56, 19.59it/s]
 59%|█████▉    | 3338/5625 [02:55<01:52, 20.29it/s]
 59%|█████▉    | 3341/5625 [02:55<01:54, 20.01it/s]
 59%|█████▉    | 3344/5625 [02:55<01:53, 20.18it/s]
 60%|█████▉    | 3347/5625 [02:56<01:53, 20.11it/s]
 60%|█████▉    | 3350/5625 [02:56<01:52, 20.16it/s]
 60%|█████▉    | 3353/5625 [02:56<01:54, 19.77it/s]
 60%|█████▉    | 3355/5625 [02:56<01:56, 19.50it/s]
 60%|█████▉    | 3357/5625 [02:56<01:56, 19.55it/s]
 60%|█████▉    | 3359/5625 [02:56<01:58, 19.08it/s]
 60%|█████▉    | 3362/5625 [02:56<01:56, 19.43it/s]
 60%|█████▉    | 3364/5625 [02:56<01:55, 19.50it/s]
 60%|█████▉    | 3366/5625 [02:57<01:57, 19.27it/s]
 60%|█████▉    | 3368/5625 [02:57<01:58, 18.99it/s]
 60%|█████▉    | 3370/5625 [02:57<01:57, 19.22it/s]
 60%|█████▉    | 3372/5625 [02:57<02:00, 18.67it/s]
 60%|██████    | 3375/5625 [02:57<01:55, 19.45it/s]
 60%|██████    | 3377/5625 [02:57<01:59, 18.88it/s]
 60%|██████    | 3380/5625 [02:57<01:55, 19.38it/s]
 60%|██████    | 3382/5625 [02:57<01:56, 19.24it/s]
 60%|██████    | 3385/5625 [02:58<01:51, 20.07it/s]
 60%|██████    | 3387/5625 [02:58<01:52, 19.90it/s]
 60%|██████    | 3389/5625 [02:58<01:53, 19.75it/s]
 60%|██████    | 3391/5625 [02:58<01:56, 19.21it/s]
 60%|██████    | 3393/5625 [02:58<01:58, 18.91it/s]
 60%|██████    | 3395/5625 [02:58<01:57, 18.91it/s]
 60%|██████    | 3397/5625 [02:58<01:57, 18.95it/s]
 60%|██████    | 3399/5625 [02:58<01:57, 18.90it/s]
 60%|██████    | 3402/5625 [02:58<01:56, 19.08it/s]
 61%|██████    | 3404/5625 [02:59<01:57, 18.85it/s]
 61%|██████    | 3406/5625 [02:59<02:00, 18.44it/s]
 61%|██████    | 3409/5625 [02:59<01:58, 18.70it/s]
 61%|██████    | 3411/5625 [02:59<01:57, 18.79it/s]
 61%|██████    | 3414/5625 [02:59<01:50, 19.96it/s]
 61%|██████    | 3416/5625 [02:59<01:52, 19.59it/s]
 61%|██████    | 3418/5625 [02:59<01:53, 19.48it/s]
 61%|██████    | 3420/5625 [02:59<01:54, 19.24it/s]
 61%|██████    | 3423/5625 [02:59<01:53, 19.47it/s]
 61%|██████    | 3426/5625 [03:00<01:50, 19.85it/s]
 61%|██████    | 3428/5625 [03:00<01:53, 19.39it/s]
 61%|██████    | 3431/5625 [03:00<01:51, 19.65it/s]
 61%|██████    | 3433/5625 [03:00<01:53, 19.29it/s]
 61%|██████    | 3436/5625 [03:00<01:51, 19.66it/s]
 61%|██████    | 3438/5625 [03:00<01:53, 19.23it/s]
 61%|██████    | 3440/5625 [03:00<01:56, 18.82it/s]
 61%|██████    | 3442/5625 [03:00<01:58, 18.40it/s]
 61%|██████    | 3444/5625 [03:01<01:59, 18.32it/s]
 61%|██████▏   | 3446/5625 [03:01<01:56, 18.72it/s]
 61%|██████▏   | 3449/5625 [03:01<01:50, 19.72it/s]
 61%|██████▏   | 3451/5625 [03:01<01:52, 19.39it/s]
 61%|██████▏   | 3453/5625 [03:01<01:53, 19.07it/s]
 61%|██████▏   | 3456/5625 [03:01<01:51, 19.54it/s]
 61%|██████▏   | 3459/5625 [03:01<01:48, 20.02it/s]
 62%|██████▏   | 3462/5625 [03:02<01:47, 20.03it/s]
 62%|██████▏   | 3464/5625 [03:02<01:50, 19.59it/s]
 62%|██████▏   | 3466/5625 [03:02<01:51, 19.37it/s]
 62%|██████▏   | 3469/5625 [03:02<01:49, 19.63it/s]
 62%|██████▏   | 3471/5625 [03:02<01:49, 19.60it/s]
 62%|██████▏   | 3473/5625 [03:02<01:49, 19.68it/s]
 62%|██████▏   | 3475/5625 [03:02<01:49, 19.71it/s]
 62%|██████▏   | 3477/5625 [03:02<01:51, 19.34it/s]
 62%|██████▏   | 3479/5625 [03:02<01:50, 19.41it/s]
 62%|██████▏   | 3481/5625 [03:02<01:50, 19.49it/s]
 62%|██████▏   | 3484/5625 [03:03<01:44, 20.41it/s]
 62%|██████▏   | 3487/5625 [03:03<01:49, 19.56it/s]
 62%|██████▏   | 3489/5625 [03:03<01:52, 19.01it/s]
 62%|██████▏   | 3492/5625 [03:03<01:49, 19.51it/s]
 62%|██████▏   | 3494/5625 [03:03<01:51, 19.12it/s]
 62%|██████▏   | 3496/5625 [03:03<01:53, 18.77it/s]
 62%|██████▏   | 3498/5625 [03:03<01:51, 19.02it/s]
 62%|██████▏   | 3501/5625 [03:04<01:47, 19.78it/s]
 62%|██████▏   | 3503/5625 [03:04<01:47, 19.66it/s]
 62%|██████▏   | 3506/5625 [03:04<01:44, 20.22it/s]
 62%|██████▏   | 3509/5625 [03:04<01:46, 19.78it/s]
 62%|██████▏   | 3511/5625 [03:04<01:50, 19.10it/s]
 62%|██████▏   | 3514/5625 [03:04<01:49, 19.26it/s]
 63%|██████▎   | 3516/5625 [03:04<01:52, 18.67it/s]
 63%|██████▎   | 3518/5625 [03:04<01:53, 18.50it/s]
 63%|██████▎   | 3521/5625 [03:05<01:49, 19.28it/s]
 63%|██████▎   | 3524/5625 [03:05<01:47, 19.58it/s]
 63%|██████▎   | 3527/5625 [03:05<01:44, 20.16it/s]
 63%|██████▎   | 3530/5625 [03:05<01:46, 19.72it/s]
 63%|██████▎   | 3532/5625 [03:05<01:48, 19.30it/s]
 63%|██████▎   | 3535/5625 [03:05<01:48, 19.30it/s]
 63%|██████▎   | 3537/5625 [03:05<01:50, 18.94it/s]
 63%|██████▎   | 3540/5625 [03:06<01:45, 19.77it/s]
 63%|██████▎   | 3542/5625 [03:06<01:46, 19.62it/s]
 63%|██████▎   | 3545/5625 [03:06<01:43, 20.09it/s]
 63%|██████▎   | 3547/5625 [03:06<01:44, 19.93it/s]
 63%|██████▎   | 3549/5625 [03:06<01:45, 19.69it/s]
 63%|██████▎   | 3551/5625 [03:06<01:48, 19.17it/s]
 63%|██████▎   | 3554/5625 [03:06<01:44, 19.82it/s]
 63%|██████▎   | 3556/5625 [03:06<01:47, 19.31it/s]
 63%|██████▎   | 3559/5625 [03:06<01:42, 20.11it/s]
 63%|██████▎   | 3562/5625 [03:07<01:41, 20.41it/s]
 63%|██████▎   | 3565/5625 [03:07<01:42, 20.08it/s]
 63%|██████▎   | 3568/5625 [03:07<01:45, 19.54it/s]
 63%|██████▎   | 3570/5625 [03:07<01:46, 19.27it/s]
 64%|██████▎   | 3572/5625 [03:07<01:46, 19.19it/s]
 64%|██████▎   | 3574/5625 [03:07<01:47, 19.05it/s]
 64%|██████▎   | 3576/5625 [03:07<01:47, 19.12it/s]
 64%|██████▎   | 3578/5625 [03:07<01:49, 18.75it/s]
 64%|██████▎   | 3580/5625 [03:08<01:47, 18.99it/s]
 64%|██████▎   | 3582/5625 [03:08<01:47, 18.97it/s]
 64%|██████▎   | 3584/5625 [03:08<01:46, 19.16it/s]
 64%|██████▍   | 3586/5625 [03:08<01:46, 19.19it/s]
 64%|██████▍   | 3588/5625 [03:08<01:45, 19.37it/s]
 64%|██████▍   | 3590/5625 [03:08<01:48, 18.74it/s]
 64%|██████▍   | 3592/5625 [03:08<01:49, 18.48it/s]
 64%|██████▍   | 3594/5625 [03:08<01:52, 18.02it/s]
 64%|██████▍   | 3596/5625 [03:08<01:51, 18.17it/s]
 64%|██████▍   | 3598/5625 [03:09<01:49, 18.48it/s]
 64%|██████▍   | 3600/5625 [03:09<01:50, 18.29it/s]
 64%|██████▍   | 3602/5625 [03:09<01:49, 18.48it/s]
 64%|██████▍   | 3604/5625 [03:09<01:48, 18.70it/s]
 64%|██████▍   | 3606/5625 [03:09<01:47, 18.73it/s]
 64%|██████▍   | 3608/5625 [03:09<01:46, 19.02it/s]
 64%|██████▍   | 3610/5625 [03:09<01:44, 19.30it/s]
 64%|██████▍   | 3613/5625 [03:09<01:42, 19.64it/s]
 64%|██████▍   | 3616/5625 [03:09<01:39, 20.14it/s]
 64%|██████▍   | 3619/5625 [03:10<01:41, 19.76it/s]
 64%|██████▍   | 3621/5625 [03:10<01:41, 19.66it/s]
 64%|██████▍   | 3623/5625 [03:10<01:44, 19.24it/s]
 64%|██████▍   | 3625/5625 [03:10<01:46, 18.85it/s]
 64%|██████▍   | 3628/5625 [03:10<01:42, 19.54it/s]
 65%|██████▍   | 3630/5625 [03:10<01:43, 19.34it/s]
 65%|██████▍   | 3632/5625 [03:10<01:46, 18.77it/s]
 65%|██████▍   | 3635/5625 [03:10<01:44, 19.00it/s]
 65%|██████▍   | 3638/5625 [03:11<01:39, 20.01it/s]
 65%|██████▍   | 3641/5625 [03:11<01:38, 20.21it/s]
 65%|██████▍   | 3644/5625 [03:11<01:40, 19.75it/s]
 65%|██████▍   | 3647/5625 [03:11<01:39, 19.88it/s]
 65%|██████▍   | 3649/5625 [03:11<01:40, 19.60it/s]
 65%|██████▍   | 3651/5625 [03:11<01:40, 19.59it/s]
 65%|██████▍   | 3653/5625 [03:11<01:43, 19.01it/s]
 65%|██████▍   | 3656/5625 [03:12<01:41, 19.36it/s]
 65%|██████▌   | 3658/5625 [03:12<01:43, 19.07it/s]
 65%|██████▌   | 3661/5625 [03:12<01:41, 19.34it/s]
 65%|██████▌   | 3663/5625 [03:12<01:40, 19.50it/s]
 65%|██████▌   | 3665/5625 [03:12<01:42, 19.07it/s]
 65%|██████▌   | 3668/5625 [03:12<01:41, 19.35it/s]
 65%|██████▌   | 3670/5625 [03:12<01:43, 18.95it/s]
 65%|██████▌   | 3672/5625 [03:12<01:42, 19.10it/s]
 65%|██████▌   | 3674/5625 [03:12<01:44, 18.63it/s]
 65%|██████▌   | 3677/5625 [03:13<01:41, 19.17it/s]
 65%|██████▌   | 3680/5625 [03:13<01:40, 19.28it/s]
 65%|██████▌   | 3682/5625 [03:13<01:41, 19.19it/s]
 66%|██████▌   | 3685/5625 [03:13<01:41, 19.12it/s]
 66%|██████▌   | 3687/5625 [03:13<01:41, 19.06it/s]
 66%|██████▌   | 3690/5625 [03:13<01:40, 19.19it/s]
 66%|██████▌   | 3692/5625 [03:13<01:40, 19.20it/s]
 66%|██████▌   | 3694/5625 [03:14<01:41, 19.02it/s]
 66%|██████▌   | 3696/5625 [03:14<01:43, 18.58it/s]
 66%|██████▌   | 3698/5625 [03:14<01:43, 18.56it/s]
 66%|██████▌   | 3700/5625 [03:14<01:44, 18.48it/s]
 66%|██████▌   | 3702/5625 [03:14<01:44, 18.47it/s]
 66%|██████▌   | 3704/5625 [03:14<01:41, 18.84it/s]
 66%|██████▌   | 3706/5625 [03:14<01:40, 19.05it/s]
 66%|██████▌   | 3708/5625 [03:14<01:41, 18.86it/s]
 66%|██████▌   | 3710/5625 [03:14<01:40, 19.09it/s]
 66%|██████▌   | 3713/5625 [03:15<01:39, 19.22it/s]
 66%|██████▌   | 3715/5625 [03:15<01:41, 18.78it/s]
 66%|██████▌   | 3717/5625 [03:15<01:40, 19.06it/s]
 66%|██████▌   | 3719/5625 [03:15<01:42, 18.60it/s]
 66%|██████▌   | 3721/5625 [03:15<01:43, 18.41it/s]
 66%|██████▌   | 3724/5625 [03:15<01:35, 19.91it/s]
 66%|██████▌   | 3726/5625 [03:15<01:36, 19.76it/s]
 66%|██████▋   | 3728/5625 [03:15<01:37, 19.36it/s]
 66%|██████▋   | 3731/5625 [03:15<01:37, 19.53it/s]
 66%|██████▋   | 3734/5625 [03:16<01:36, 19.65it/s]
 66%|██████▋   | 3736/5625 [03:16<01:36, 19.64it/s]
 66%|██████▋   | 3738/5625 [03:16<01:37, 19.31it/s]
 66%|██████▋   | 3740/5625 [03:16<01:37, 19.28it/s]
 67%|██████▋   | 3743/5625 [03:16<01:36, 19.58it/s]
 67%|██████▋   | 3745/5625 [03:16<01:37, 19.35it/s]
 67%|██████▋   | 3747/5625 [03:16<01:36, 19.37it/s]
 67%|██████▋   | 3749/5625 [03:16<01:39, 18.93it/s]
                                                   

 67%|██████▋   | 3750/5625 [03:16<01:39, 18.93it/s]{'eval_loss': 0.7685990929603577, 'eval_accuracy': 0.6484, 'eval_f1': 0.642029354074808, 'eval_runtime': 1.7302, 'eval_samples_per_second': 1444.938, 'eval_steps_per_second': 180.906, 'epoch': 1.0}
{'loss': 0.7502, 'learning_rate': 6.4243454961658e-07, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.53it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.63it/s]

 21%|██        | 66/313 [00:00<00:01, 206.06it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.31it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.59it/s]

 40%|████      | 126/313 [00:00<00:01, 185.37it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.16it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.24it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.39it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.45it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.47it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.14it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.05it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.94it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.67it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.67it/s]
 67%|██████▋   | 3750/5625 [03:18<01:39, 18.93it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 3751/5625 [03:19<13:18,  2.35it/s]
 67%|██████▋   | 3753/5625 [03:19<09:55,  3.14it/s]
 67%|██████▋   | 3755/5625 [03:19<07:30,  4.15it/s]
 67%|██████▋   | 3757/5625 [03:19<05:47,  5.38it/s]
 67%|██████▋   | 3760/5625 [03:20<04:05,  7.59it/s]
 67%|██████▋   | 3762/5625 [03:20<03:26,  9.04it/s]
 67%|██████▋   | 3764/5625 [03:20<02:55, 10.58it/s]
 67%|██████▋   | 3766/5625 [03:20<02:34, 12.07it/s]
 67%|██████▋   | 3769/5625 [03:20<02:10, 14.27it/s]
 67%|██████▋   | 3771/5625 [03:20<02:01, 15.29it/s]
 67%|██████▋   | 3774/5625 [03:20<01:51, 16.64it/s]
 67%|██████▋   | 3776/5625 [03:20<01:47, 17.20it/s]
 67%|██████▋   | 3778/5625 [03:21<01:43, 17.79it/s]
 67%|██████▋   | 3781/5625 [03:21<01:39, 18.58it/s]
 67%|██████▋   | 3784/5625 [03:21<01:36, 19.06it/s]
 67%|██████▋   | 3786/5625 [03:21<01:37, 18.94it/s]
 67%|██████▋   | 3788/5625 [03:21<01:38, 18.61it/s]
 67%|██████▋   | 3790/5625 [03:21<01:38, 18.57it/s]
 67%|██████▋   | 3792/5625 [03:21<01:37, 18.72it/s]
 67%|██████▋   | 3795/5625 [03:21<01:32, 19.70it/s]
 68%|██████▊   | 3797/5625 [03:21<01:35, 19.07it/s]
 68%|██████▊   | 3800/5625 [03:22<01:35, 19.20it/s]
 68%|██████▊   | 3802/5625 [03:22<01:34, 19.26it/s]
 68%|██████▊   | 3804/5625 [03:22<01:35, 19.07it/s]
 68%|██████▊   | 3807/5625 [03:22<01:33, 19.44it/s]
 68%|██████▊   | 3809/5625 [03:22<01:34, 19.18it/s]
 68%|██████▊   | 3811/5625 [03:22<01:36, 18.73it/s]
 68%|██████▊   | 3813/5625 [03:22<01:35, 18.93it/s]
 68%|██████▊   | 3816/5625 [03:22<01:32, 19.46it/s]
 68%|██████▊   | 3818/5625 [03:23<01:33, 19.23it/s]
 68%|██████▊   | 3820/5625 [03:23<01:33, 19.39it/s]
 68%|██████▊   | 3822/5625 [03:23<01:33, 19.34it/s]
 68%|██████▊   | 3824/5625 [03:23<01:35, 18.89it/s]
 68%|██████▊   | 3827/5625 [03:23<01:34, 19.01it/s]
 68%|██████▊   | 3830/5625 [03:23<01:33, 19.25it/s]
 68%|██████▊   | 3832/5625 [03:23<01:33, 19.16it/s]
 68%|██████▊   | 3835/5625 [03:23<01:33, 19.22it/s]
 68%|██████▊   | 3837/5625 [03:24<01:32, 19.39it/s]
 68%|██████▊   | 3840/5625 [03:24<01:30, 19.63it/s]
 68%|██████▊   | 3842/5625 [03:24<01:32, 19.19it/s]
 68%|██████▊   | 3844/5625 [03:24<01:32, 19.18it/s]
 68%|██████▊   | 3846/5625 [03:24<01:33, 19.08it/s]
 68%|██████▊   | 3848/5625 [03:24<01:35, 18.63it/s]
 68%|██████▊   | 3850/5625 [03:24<01:52, 15.77it/s]
 68%|██████▊   | 3853/5625 [03:24<01:44, 17.03it/s]
 69%|██████▊   | 3856/5625 [03:25<01:37, 18.09it/s]
 69%|██████▊   | 3858/5625 [03:25<01:38, 17.96it/s]
 69%|██████▊   | 3860/5625 [03:25<01:38, 17.88it/s]
 69%|██████▊   | 3863/5625 [03:25<01:33, 18.94it/s]
 69%|██████▊   | 3866/5625 [03:25<01:29, 19.58it/s]
 69%|██████▉   | 3869/5625 [03:25<01:28, 19.79it/s]
 69%|██████▉   | 3871/5625 [03:25<01:29, 19.52it/s]
 69%|██████▉   | 3873/5625 [03:26<01:32, 18.98it/s]
 69%|██████▉   | 3876/5625 [03:26<01:31, 19.21it/s]
 69%|██████▉   | 3878/5625 [03:26<01:31, 19.14it/s]
 69%|██████▉   | 3880/5625 [03:26<01:30, 19.23it/s]
 69%|██████▉   | 3882/5625 [03:26<01:29, 19.42it/s]
 69%|██████▉   | 3885/5625 [03:26<01:28, 19.55it/s]
 69%|██████▉   | 3888/5625 [03:26<01:26, 20.03it/s]
 69%|██████▉   | 3890/5625 [03:26<01:26, 19.98it/s]
 69%|██████▉   | 3893/5625 [03:27<01:27, 19.91it/s]
 69%|██████▉   | 3895/5625 [03:27<01:28, 19.63it/s]
 69%|██████▉   | 3897/5625 [03:27<01:27, 19.65it/s]
 69%|██████▉   | 3899/5625 [03:27<01:29, 19.21it/s]
 69%|██████▉   | 3901/5625 [03:27<01:29, 19.26it/s]
 69%|██████▉   | 3903/5625 [03:27<01:30, 19.04it/s]
 69%|██████▉   | 3905/5625 [03:27<01:29, 19.22it/s]
 69%|██████▉   | 3907/5625 [03:27<01:31, 18.73it/s]
 70%|██████▉   | 3910/5625 [03:27<01:27, 19.64it/s]
 70%|██████▉   | 3912/5625 [03:28<01:29, 19.12it/s]
 70%|██████▉   | 3915/5625 [03:28<01:27, 19.47it/s]
 70%|██████▉   | 3918/5625 [03:28<01:25, 20.07it/s]
 70%|██████▉   | 3921/5625 [03:28<01:25, 19.92it/s]
 70%|██████▉   | 3923/5625 [03:28<01:28, 19.19it/s]
 70%|██████▉   | 3926/5625 [03:28<01:24, 20.03it/s]
 70%|██████▉   | 3928/5625 [03:28<01:26, 19.51it/s]
 70%|██████▉   | 3931/5625 [03:28<01:24, 20.15it/s]
 70%|██████▉   | 3933/5625 [03:29<01:24, 19.98it/s]
 70%|██████▉   | 3936/5625 [03:29<01:25, 19.80it/s]
 70%|███████   | 3938/5625 [03:29<01:28, 19.11it/s]
 70%|███████   | 3941/5625 [03:29<01:26, 19.39it/s]
 70%|███████   | 3943/5625 [03:29<01:26, 19.53it/s]
 70%|███████   | 3946/5625 [03:29<01:25, 19.65it/s]
 70%|███████   | 3948/5625 [03:29<01:26, 19.42it/s]
 70%|███████   | 3950/5625 [03:29<01:26, 19.33it/s]
 70%|███████   | 3952/5625 [03:30<01:28, 18.80it/s]
 70%|███████   | 3955/5625 [03:30<01:22, 20.14it/s]
 70%|███████   | 3958/5625 [03:30<01:22, 20.31it/s]
 70%|███████   | 3961/5625 [03:30<01:18, 21.10it/s]
 70%|███████   | 3964/5625 [03:30<01:22, 20.24it/s]
 71%|███████   | 3967/5625 [03:30<01:25, 19.28it/s]
 71%|███████   | 3969/5625 [03:30<01:26, 19.06it/s]
 71%|███████   | 3972/5625 [03:31<01:22, 19.92it/s]
 71%|███████   | 3974/5625 [03:31<01:22, 19.93it/s]
 71%|███████   | 3976/5625 [03:31<01:23, 19.67it/s]
 71%|███████   | 3978/5625 [03:31<01:25, 19.31it/s]
 71%|███████   | 3980/5625 [03:31<01:25, 19.31it/s]
 71%|███████   | 3982/5625 [03:31<01:24, 19.45it/s]
 71%|███████   | 3985/5625 [03:31<01:23, 19.76it/s]
 71%|███████   | 3987/5625 [03:31<01:22, 19.80it/s]
 71%|███████   | 3989/5625 [03:31<01:24, 19.44it/s]
 71%|███████   | 3991/5625 [03:32<01:26, 18.99it/s]
 71%|███████   | 3994/5625 [03:32<01:24, 19.27it/s]
 71%|███████   | 3997/5625 [03:32<01:23, 19.47it/s]
 71%|███████   | 3999/5625 [03:32<01:24, 19.30it/s]
 71%|███████   | 4001/5625 [03:32<01:23, 19.38it/s]
 71%|███████   | 4004/5625 [03:32<01:17, 20.88it/s]
 71%|███████   | 4007/5625 [03:32<01:19, 20.39it/s]
 71%|███████▏  | 4010/5625 [03:32<01:19, 20.44it/s]
 71%|███████▏  | 4013/5625 [03:33<01:20, 19.96it/s]
 71%|███████▏  | 4016/5625 [03:33<01:23, 19.24it/s]
 71%|███████▏  | 4018/5625 [03:33<01:24, 18.92it/s]
 71%|███████▏  | 4021/5625 [03:33<01:22, 19.47it/s]
 72%|███████▏  | 4023/5625 [03:33<01:23, 19.16it/s]
 72%|███████▏  | 4025/5625 [03:33<01:23, 19.22it/s]
 72%|███████▏  | 4027/5625 [03:33<01:23, 19.19it/s]
 72%|███████▏  | 4029/5625 [03:33<01:22, 19.40it/s]
 72%|███████▏  | 4031/5625 [03:34<01:23, 19.15it/s]
 72%|███████▏  | 4034/5625 [03:34<01:18, 20.29it/s]
 72%|███████▏  | 4037/5625 [03:34<01:21, 19.44it/s]
 72%|███████▏  | 4040/5625 [03:34<01:18, 20.19it/s]
 72%|███████▏  | 4043/5625 [03:34<01:21, 19.52it/s]
 72%|███████▏  | 4045/5625 [03:34<01:20, 19.55it/s]
 72%|███████▏  | 4047/5625 [03:34<01:20, 19.48it/s]
 72%|███████▏  | 4050/5625 [03:35<01:20, 19.67it/s]
 72%|███████▏  | 4052/5625 [03:35<01:22, 19.11it/s]
 72%|███████▏  | 4054/5625 [03:35<01:22, 19.07it/s]
 72%|███████▏  | 4056/5625 [03:35<01:22, 18.91it/s]
 72%|███████▏  | 4059/5625 [03:35<01:21, 19.19it/s]
 72%|███████▏  | 4061/5625 [03:35<01:21, 19.14it/s]
 72%|███████▏  | 4063/5625 [03:35<01:23, 18.76it/s]
 72%|███████▏  | 4066/5625 [03:35<01:18, 19.81it/s]
 72%|███████▏  | 4068/5625 [03:35<01:19, 19.57it/s]
 72%|███████▏  | 4070/5625 [03:36<01:19, 19.48it/s]
 72%|███████▏  | 4073/5625 [03:36<01:16, 20.40it/s]
 72%|███████▏  | 4076/5625 [03:36<01:14, 20.79it/s]
 73%|███████▎  | 4079/5625 [03:36<01:16, 20.12it/s]
 73%|███████▎  | 4082/5625 [03:36<01:19, 19.34it/s]
 73%|███████▎  | 4085/5625 [03:36<01:16, 20.09it/s]
 73%|███████▎  | 4088/5625 [03:36<01:18, 19.68it/s]
 73%|███████▎  | 4090/5625 [03:37<01:19, 19.27it/s]
 73%|███████▎  | 4092/5625 [03:37<01:21, 18.89it/s]
 73%|███████▎  | 4094/5625 [03:37<01:21, 18.86it/s]
 73%|███████▎  | 4097/5625 [03:37<01:16, 19.94it/s]
 73%|███████▎  | 4099/5625 [03:37<01:19, 19.31it/s]
 73%|███████▎  | 4101/5625 [03:37<01:19, 19.22it/s]
 73%|███████▎  | 4103/5625 [03:37<01:21, 18.75it/s]
 73%|███████▎  | 4106/5625 [03:37<01:15, 20.17it/s]
 73%|███████▎  | 4109/5625 [03:38<01:16, 19.77it/s]
 73%|███████▎  | 4112/5625 [03:38<01:14, 20.24it/s]
 73%|███████▎  | 4115/5625 [03:38<01:17, 19.50it/s]
 73%|███████▎  | 4118/5625 [03:38<01:16, 19.75it/s]
 73%|███████▎  | 4120/5625 [03:38<01:18, 19.27it/s]
 73%|███████▎  | 4122/5625 [03:38<01:18, 19.07it/s]
 73%|███████▎  | 4124/5625 [03:38<01:17, 19.26it/s]
 73%|███████▎  | 4126/5625 [03:38<01:18, 19.21it/s]
 73%|███████▎  | 4128/5625 [03:39<01:19, 18.86it/s]
 73%|███████▎  | 4130/5625 [03:39<01:18, 19.12it/s]
 73%|███████▎  | 4132/5625 [03:39<01:18, 18.90it/s]
 73%|███████▎  | 4134/5625 [03:39<01:19, 18.70it/s]
 74%|███████▎  | 4136/5625 [03:39<01:20, 18.42it/s]
 74%|███████▎  | 4138/5625 [03:39<01:20, 18.36it/s]
 74%|███████▎  | 4141/5625 [03:39<01:18, 18.89it/s]
 74%|███████▎  | 4143/5625 [03:39<01:19, 18.75it/s]
 74%|███████▎  | 4145/5625 [03:40<01:46, 13.95it/s]
 74%|███████▎  | 4147/5625 [03:40<01:36, 15.25it/s]
 74%|███████▍  | 4149/5625 [03:40<01:31, 16.12it/s]
 74%|███████▍  | 4151/5625 [03:40<01:27, 16.89it/s]
 74%|███████▍  | 4153/5625 [03:40<01:25, 17.13it/s]
 74%|███████▍  | 4155/5625 [03:40<01:22, 17.82it/s]
 74%|███████▍  | 4158/5625 [03:40<01:18, 18.74it/s]
 74%|███████▍  | 4161/5625 [03:40<01:17, 19.01it/s]
 74%|███████▍  | 4164/5625 [03:41<01:15, 19.29it/s]
 74%|███████▍  | 4167/5625 [03:41<01:11, 20.27it/s]
 74%|███████▍  | 4170/5625 [03:41<01:13, 19.80it/s]
 74%|███████▍  | 4172/5625 [03:41<01:15, 19.32it/s]
 74%|███████▍  | 4174/5625 [03:41<01:14, 19.42it/s]
 74%|███████▍  | 4176/5625 [03:41<01:15, 19.30it/s]
 74%|███████▍  | 4179/5625 [03:41<01:14, 19.37it/s]
 74%|███████▍  | 4181/5625 [03:41<01:14, 19.37it/s]
 74%|███████▍  | 4184/5625 [03:42<01:14, 19.39it/s]
 74%|███████▍  | 4186/5625 [03:42<01:15, 19.05it/s]
 74%|███████▍  | 4188/5625 [03:42<01:15, 18.95it/s]
 75%|███████▍  | 4191/5625 [03:42<01:13, 19.47it/s]
 75%|███████▍  | 4193/5625 [03:42<01:14, 19.27it/s]
 75%|███████▍  | 4196/5625 [03:42<01:14, 19.16it/s]
 75%|███████▍  | 4199/5625 [03:42<01:12, 19.76it/s]
 75%|███████▍  | 4201/5625 [03:42<01:13, 19.38it/s]
 75%|███████▍  | 4203/5625 [03:43<01:14, 19.03it/s]
 75%|███████▍  | 4205/5625 [03:43<01:14, 18.97it/s]
 75%|███████▍  | 4207/5625 [03:43<01:15, 18.87it/s]
 75%|███████▍  | 4209/5625 [03:43<01:16, 18.55it/s]
 75%|███████▍  | 4211/5625 [03:43<01:15, 18.81it/s]
 75%|███████▍  | 4213/5625 [03:43<01:17, 18.32it/s]
 75%|███████▍  | 4215/5625 [03:43<01:17, 18.21it/s]
 75%|███████▍  | 4217/5625 [03:43<01:18, 18.04it/s]
 75%|███████▌  | 4220/5625 [03:44<01:14, 18.92it/s]
 75%|███████▌  | 4223/5625 [03:44<01:10, 19.89it/s]
 75%|███████▌  | 4226/5625 [03:44<01:08, 20.32it/s]
 75%|███████▌  | 4229/5625 [03:44<01:09, 20.12it/s]
 75%|███████▌  | 4232/5625 [03:44<01:11, 19.55it/s]
 75%|███████▌  | 4235/5625 [03:44<01:09, 20.08it/s]
 75%|███████▌  | 4238/5625 [03:44<01:11, 19.39it/s]
 75%|███████▌  | 4240/5625 [03:45<01:33, 14.84it/s]
 75%|███████▌  | 4243/5625 [03:45<01:23, 16.62it/s]
 75%|███████▌  | 4245/5625 [03:45<01:22, 16.77it/s]
 76%|███████▌  | 4248/5625 [03:45<01:15, 18.31it/s]
 76%|███████▌  | 4250/5625 [03:45<01:15, 18.15it/s]
 76%|███████▌  | 4252/5625 [03:45<01:14, 18.34it/s]
 76%|███████▌  | 4254/5625 [03:45<01:15, 18.12it/s]
 76%|███████▌  | 4256/5625 [03:45<01:13, 18.52it/s]
 76%|███████▌  | 4258/5625 [03:46<01:15, 18.21it/s]
 76%|███████▌  | 4260/5625 [03:46<01:14, 18.45it/s]
 76%|███████▌  | 4262/5625 [03:46<01:13, 18.66it/s]
 76%|███████▌  | 4264/5625 [03:46<01:13, 18.49it/s]
 76%|███████▌  | 4266/5625 [03:46<01:13, 18.43it/s]
 76%|███████▌  | 4268/5625 [03:46<01:13, 18.53it/s]
 76%|███████▌  | 4271/5625 [03:46<01:11, 18.96it/s]
 76%|███████▌  | 4273/5625 [03:46<01:10, 19.20it/s]
 76%|███████▌  | 4275/5625 [03:46<01:10, 19.25it/s]
 76%|███████▌  | 4277/5625 [03:47<01:11, 18.73it/s]
 76%|███████▌  | 4279/5625 [03:47<01:11, 18.73it/s]
 76%|███████▌  | 4281/5625 [03:47<01:12, 18.45it/s]
 76%|███████▌  | 4283/5625 [03:47<01:12, 18.60it/s]
 76%|███████▌  | 4286/5625 [03:47<01:10, 19.10it/s]
 76%|███████▌  | 4289/5625 [03:47<01:07, 19.69it/s]
 76%|███████▋  | 4291/5625 [03:47<01:09, 19.21it/s]
 76%|███████▋  | 4293/5625 [03:47<01:11, 18.69it/s]
 76%|███████▋  | 4295/5625 [03:48<01:11, 18.65it/s]
 76%|███████▋  | 4297/5625 [03:48<01:11, 18.63it/s]
 76%|███████▋  | 4300/5625 [03:48<01:09, 19.06it/s]
 76%|███████▋  | 4302/5625 [03:48<01:11, 18.62it/s]
 77%|███████▋  | 4305/5625 [03:48<01:08, 19.40it/s]
 77%|███████▋  | 4307/5625 [03:48<01:09, 18.99it/s]
 77%|███████▋  | 4309/5625 [03:48<01:08, 19.21it/s]
 77%|███████▋  | 4311/5625 [03:48<01:09, 18.94it/s]
 77%|███████▋  | 4313/5625 [03:48<01:08, 19.07it/s]
 77%|███████▋  | 4315/5625 [03:49<01:09, 18.88it/s]
 77%|███████▋  | 4317/5625 [03:49<01:09, 18.77it/s]
 77%|███████▋  | 4319/5625 [03:49<01:10, 18.48it/s]
 77%|███████▋  | 4322/5625 [03:49<01:08, 18.90it/s]
 77%|███████▋  | 4325/5625 [03:49<01:05, 19.80it/s]
 77%|███████▋  | 4327/5625 [03:49<01:05, 19.76it/s]
 77%|███████▋  | 4329/5625 [03:49<01:07, 19.16it/s]
 77%|███████▋  | 4332/5625 [03:49<01:07, 19.29it/s]
 77%|███████▋  | 4335/5625 [03:50<01:05, 19.57it/s]
 77%|███████▋  | 4337/5625 [03:50<01:35, 13.53it/s]
 77%|███████▋  | 4339/5625 [03:50<01:28, 14.45it/s]
 77%|███████▋  | 4342/5625 [03:50<01:18, 16.32it/s]
 77%|███████▋  | 4344/5625 [03:50<01:15, 16.99it/s]
 77%|███████▋  | 4347/5625 [03:50<01:11, 17.95it/s]
 77%|███████▋  | 4349/5625 [03:51<01:10, 18.04it/s]
 77%|███████▋  | 4351/5625 [03:51<01:11, 17.90it/s]
 77%|███████▋  | 4353/5625 [03:51<01:11, 17.83it/s]
 77%|███████▋  | 4356/5625 [03:51<01:06, 19.03it/s]
 77%|███████▋  | 4358/5625 [03:51<01:05, 19.22it/s]
 78%|███████▊  | 4360/5625 [03:51<01:05, 19.29it/s]
 78%|███████▊  | 4363/5625 [03:51<01:03, 19.78it/s]
 78%|███████▊  | 4365/5625 [03:51<01:05, 19.30it/s]
 78%|███████▊  | 4368/5625 [03:52<01:04, 19.47it/s]
 78%|███████▊  | 4371/5625 [03:52<01:04, 19.34it/s]
 78%|███████▊  | 4373/5625 [03:52<01:05, 19.23it/s]
 78%|███████▊  | 4375/5625 [03:52<01:06, 18.78it/s]
 78%|███████▊  | 4377/5625 [03:52<01:05, 19.09it/s]
 78%|███████▊  | 4379/5625 [03:52<01:06, 18.80it/s]
 78%|███████▊  | 4381/5625 [03:52<01:05, 19.05it/s]
 78%|███████▊  | 4383/5625 [03:52<01:05, 18.97it/s]
 78%|███████▊  | 4386/5625 [03:52<01:02, 19.90it/s]
 78%|███████▊  | 4389/5625 [03:53<01:02, 19.75it/s]
 78%|███████▊  | 4391/5625 [03:53<01:02, 19.80it/s]
 78%|███████▊  | 4394/5625 [03:53<01:02, 19.63it/s]
 78%|███████▊  | 4397/5625 [03:53<01:02, 19.63it/s]
 78%|███████▊  | 4399/5625 [03:53<01:03, 19.42it/s]
 78%|███████▊  | 4401/5625 [03:53<01:03, 19.16it/s]
 78%|███████▊  | 4403/5625 [03:53<01:03, 19.34it/s]
 78%|███████▊  | 4406/5625 [03:53<01:01, 19.74it/s]
 78%|███████▊  | 4408/5625 [03:54<01:01, 19.68it/s]
 78%|███████▊  | 4410/5625 [03:54<01:03, 19.04it/s]
 78%|███████▊  | 4413/5625 [03:54<01:01, 19.64it/s]
 79%|███████▊  | 4416/5625 [03:54<01:01, 19.69it/s]
 79%|███████▊  | 4419/5625 [03:54<01:01, 19.57it/s]
 79%|███████▊  | 4421/5625 [03:54<01:03, 18.92it/s]
 79%|███████▊  | 4424/5625 [03:54<01:02, 19.11it/s]
 79%|███████▊  | 4426/5625 [03:55<01:04, 18.68it/s]
 79%|███████▊  | 4429/5625 [03:55<01:02, 19.22it/s]
 79%|███████▉  | 4431/5625 [03:55<01:03, 18.94it/s]
 79%|███████▉  | 4433/5625 [03:55<01:02, 18.98it/s]
 79%|███████▉  | 4436/5625 [03:55<01:00, 19.73it/s]
 79%|███████▉  | 4439/5625 [03:55<00:59, 19.81it/s]
 79%|███████▉  | 4441/5625 [03:55<00:59, 19.77it/s]
 79%|███████▉  | 4443/5625 [03:55<00:59, 19.79it/s]
 79%|███████▉  | 4445/5625 [03:55<01:01, 19.26it/s]
 79%|███████▉  | 4447/5625 [03:56<01:02, 18.99it/s]
 79%|███████▉  | 4449/5625 [03:56<01:02, 18.91it/s]
 79%|███████▉  | 4452/5625 [03:56<01:00, 19.26it/s]
 79%|███████▉  | 4454/5625 [03:56<01:01, 19.17it/s]
 79%|███████▉  | 4456/5625 [03:56<01:00, 19.34it/s]
 79%|███████▉  | 4459/5625 [03:56<00:59, 19.66it/s]
 79%|███████▉  | 4462/5625 [03:56<00:58, 19.76it/s]
 79%|███████▉  | 4464/5625 [03:56<00:58, 19.77it/s]
 79%|███████▉  | 4466/5625 [03:57<00:58, 19.80it/s]
 79%|███████▉  | 4468/5625 [03:57<00:58, 19.80it/s]
 79%|███████▉  | 4470/5625 [03:57<01:00, 19.25it/s]
 80%|███████▉  | 4472/5625 [03:57<00:59, 19.36it/s]
 80%|███████▉  | 4474/5625 [03:57<01:00, 18.88it/s]
 80%|███████▉  | 4476/5625 [03:57<01:00, 18.94it/s]
 80%|███████▉  | 4478/5625 [03:57<01:01, 18.67it/s]
 80%|███████▉  | 4481/5625 [03:57<00:59, 19.14it/s]
 80%|███████▉  | 4484/5625 [03:57<00:55, 20.46it/s]
 80%|███████▉  | 4487/5625 [03:58<00:56, 20.07it/s]
 80%|███████▉  | 4490/5625 [03:58<00:57, 19.67it/s]
 80%|███████▉  | 4492/5625 [03:58<00:57, 19.73it/s]
 80%|███████▉  | 4494/5625 [03:58<00:57, 19.51it/s]
 80%|███████▉  | 4497/5625 [03:58<00:55, 20.26it/s]
 80%|████████  | 4500/5625 [03:58<00:54, 20.48it/s]
 80%|████████  | 4503/5625 [03:58<00:52, 21.18it/s]
 80%|████████  | 4506/5625 [03:59<00:53, 20.84it/s]
 80%|████████  | 4509/5625 [03:59<00:54, 20.52it/s]
 80%|████████  | 4512/5625 [03:59<00:55, 20.06it/s]
 80%|████████  | 4515/5625 [03:59<00:57, 19.29it/s]
 80%|████████  | 4518/5625 [03:59<00:57, 19.34it/s]
 80%|████████  | 4521/5625 [03:59<00:54, 20.26it/s]
 80%|████████  | 4524/5625 [03:59<00:55, 19.88it/s]
 80%|████████  | 4527/5625 [04:00<00:53, 20.48it/s]
 81%|████████  | 4530/5625 [04:00<00:55, 19.73it/s]
 81%|████████  | 4533/5625 [04:00<00:55, 19.75it/s]
 81%|████████  | 4535/5625 [04:00<00:55, 19.68it/s]
 81%|████████  | 4537/5625 [04:00<00:55, 19.53it/s]
 81%|████████  | 4539/5625 [04:00<00:56, 19.31it/s]
 81%|████████  | 4542/5625 [04:00<00:55, 19.69it/s]
 81%|████████  | 4544/5625 [04:01<00:55, 19.65it/s]
 81%|████████  | 4546/5625 [04:01<00:55, 19.40it/s]
 81%|████████  | 4548/5625 [04:01<00:55, 19.49it/s]
 81%|████████  | 4551/5625 [04:01<00:52, 20.33it/s]
 81%|████████  | 4554/5625 [04:01<00:50, 21.07it/s]
 81%|████████  | 4557/5625 [04:01<00:50, 21.15it/s]
 81%|████████  | 4560/5625 [04:01<00:52, 20.24it/s]
 81%|████████  | 4563/5625 [04:01<00:53, 19.69it/s]
 81%|████████  | 4566/5625 [04:02<00:54, 19.61it/s]
 81%|████████  | 4568/5625 [04:02<00:55, 19.22it/s]
 81%|████████  | 4570/5625 [04:02<00:54, 19.26it/s]
 81%|████████▏ | 4572/5625 [04:02<00:55, 18.81it/s]
 81%|████████▏ | 4575/5625 [04:02<00:54, 19.10it/s]
 81%|████████▏ | 4577/5625 [04:02<00:54, 19.29it/s]
 81%|████████▏ | 4579/5625 [04:02<00:54, 19.17it/s]
 81%|████████▏ | 4581/5625 [04:02<00:54, 19.12it/s]
 81%|████████▏ | 4583/5625 [04:02<00:54, 19.07it/s]
 82%|████████▏ | 4585/5625 [04:03<00:53, 19.32it/s]
 82%|████████▏ | 4587/5625 [04:03<00:54, 19.07it/s]
 82%|████████▏ | 4589/5625 [04:03<00:55, 18.76it/s]
 82%|████████▏ | 4592/5625 [04:03<00:53, 19.31it/s]
 82%|████████▏ | 4594/5625 [04:03<00:54, 19.05it/s]
 82%|████████▏ | 4597/5625 [04:03<00:52, 19.53it/s]
 82%|████████▏ | 4599/5625 [04:03<00:52, 19.60it/s]
 82%|████████▏ | 4601/5625 [04:03<00:52, 19.63it/s]
 82%|████████▏ | 4603/5625 [04:04<00:52, 19.32it/s]
 82%|████████▏ | 4605/5625 [04:04<00:52, 19.29it/s]
 82%|████████▏ | 4607/5625 [04:04<00:53, 18.87it/s]
 82%|████████▏ | 4609/5625 [04:04<00:54, 18.62it/s]
 82%|████████▏ | 4611/5625 [04:04<00:55, 18.21it/s]
 82%|████████▏ | 4613/5625 [04:04<00:54, 18.62it/s]
 82%|████████▏ | 4615/5625 [04:04<00:53, 18.93it/s]
 82%|████████▏ | 4617/5625 [04:04<00:53, 18.90it/s]
 82%|████████▏ | 4619/5625 [04:04<00:52, 19.19it/s]
 82%|████████▏ | 4621/5625 [04:04<00:52, 19.22it/s]
 82%|████████▏ | 4623/5625 [04:05<00:53, 18.74it/s]
 82%|████████▏ | 4625/5625 [04:05<00:53, 18.63it/s]
 82%|████████▏ | 4627/5625 [04:05<00:53, 18.62it/s]
 82%|████████▏ | 4629/5625 [04:05<00:53, 18.69it/s]
 82%|████████▏ | 4631/5625 [04:05<00:54, 18.39it/s]
 82%|████████▏ | 4634/5625 [04:05<00:50, 19.72it/s]
 82%|████████▏ | 4637/5625 [04:05<00:50, 19.58it/s]
 82%|████████▏ | 4639/5625 [04:05<00:50, 19.52it/s]
 83%|████████▎ | 4641/5625 [04:06<00:50, 19.53it/s]
 83%|████████▎ | 4643/5625 [04:06<00:51, 18.97it/s]
 83%|████████▎ | 4645/5625 [04:06<00:51, 19.03it/s]
 83%|████████▎ | 4647/5625 [04:06<00:51, 19.00it/s]
 83%|████████▎ | 4649/5625 [04:06<00:52, 18.69it/s]
 83%|████████▎ | 4651/5625 [04:06<00:52, 18.62it/s]
 83%|████████▎ | 4653/5625 [04:06<00:51, 18.99it/s]
 83%|████████▎ | 4655/5625 [04:06<00:51, 18.90it/s]
 83%|████████▎ | 4657/5625 [04:06<00:50, 19.17it/s]
 83%|████████▎ | 4659/5625 [04:06<00:51, 18.89it/s]
 83%|████████▎ | 4661/5625 [04:07<00:50, 18.94it/s]
 83%|████████▎ | 4663/5625 [04:07<00:52, 18.45it/s]
 83%|████████▎ | 4665/5625 [04:07<00:52, 18.31it/s]
 83%|████████▎ | 4667/5625 [04:07<00:51, 18.74it/s]
 83%|████████▎ | 4670/5625 [04:07<00:49, 19.35it/s]
 83%|████████▎ | 4672/5625 [04:07<00:50, 18.84it/s]
 83%|████████▎ | 4675/5625 [04:07<00:49, 19.29it/s]
 83%|████████▎ | 4677/5625 [04:07<00:50, 18.86it/s]
 83%|████████▎ | 4680/5625 [04:08<00:48, 19.54it/s]
 83%|████████▎ | 4682/5625 [04:08<00:48, 19.60it/s]
 83%|████████▎ | 4684/5625 [04:08<00:48, 19.51it/s]
 83%|████████▎ | 4686/5625 [04:08<00:48, 19.46it/s]
 83%|████████▎ | 4688/5625 [04:08<00:48, 19.38it/s]
 83%|████████▎ | 4691/5625 [04:08<00:47, 19.73it/s]
 83%|████████▎ | 4693/5625 [04:08<00:47, 19.63it/s]
 83%|████████▎ | 4695/5625 [04:08<00:47, 19.59it/s]
 84%|████████▎ | 4697/5625 [04:08<00:48, 19.21it/s]
 84%|████████▎ | 4699/5625 [04:09<00:47, 19.37it/s]
 84%|████████▎ | 4701/5625 [04:09<00:48, 19.03it/s]
 84%|████████▎ | 4703/5625 [04:09<00:49, 18.48it/s]
 84%|████████▎ | 4706/5625 [04:09<00:47, 19.15it/s]
 84%|████████▎ | 4709/5625 [04:09<00:46, 19.49it/s]
 84%|████████▍ | 4711/5625 [04:09<00:47, 19.15it/s]
 84%|████████▍ | 4713/5625 [04:09<00:47, 19.08it/s]
 84%|████████▍ | 4715/5625 [04:09<00:49, 18.56it/s]
 84%|████████▍ | 4717/5625 [04:10<00:49, 18.45it/s]
 84%|████████▍ | 4719/5625 [04:10<00:49, 18.39it/s]
 84%|████████▍ | 4722/5625 [04:10<00:46, 19.41it/s]
 84%|████████▍ | 4724/5625 [04:10<00:47, 18.97it/s]
 84%|████████▍ | 4727/5625 [04:10<00:45, 19.70it/s]
 84%|████████▍ | 4730/5625 [04:10<00:44, 20.19it/s]
 84%|████████▍ | 4733/5625 [04:10<00:43, 20.29it/s]
 84%|████████▍ | 4736/5625 [04:10<00:45, 19.67it/s]
 84%|████████▍ | 4738/5625 [04:11<00:45, 19.68it/s]
 84%|████████▍ | 4740/5625 [04:11<00:45, 19.41it/s]
 84%|████████▍ | 4742/5625 [04:11<00:45, 19.28it/s]
 84%|████████▍ | 4744/5625 [04:11<00:46, 19.13it/s]
 84%|████████▍ | 4746/5625 [04:11<00:46, 18.78it/s]
 84%|████████▍ | 4748/5625 [04:11<00:45, 19.08it/s]
 84%|████████▍ | 4751/5625 [04:11<00:44, 19.85it/s]
 84%|████████▍ | 4753/5625 [04:11<00:45, 19.20it/s]
 85%|████████▍ | 4755/5625 [04:11<00:45, 19.11it/s]
 85%|████████▍ | 4757/5625 [04:12<00:44, 19.30it/s]
 85%|████████▍ | 4759/5625 [04:12<00:46, 18.82it/s]
 85%|████████▍ | 4761/5625 [04:12<00:46, 18.74it/s]
 85%|████████▍ | 4764/5625 [04:12<00:43, 19.69it/s]
 85%|████████▍ | 4766/5625 [04:12<00:43, 19.76it/s]
 85%|████████▍ | 4769/5625 [04:12<00:41, 20.41it/s]
 85%|████████▍ | 4772/5625 [04:12<00:44, 19.25it/s]
 85%|████████▍ | 4775/5625 [04:12<00:42, 19.88it/s]
 85%|████████▍ | 4777/5625 [04:13<00:43, 19.67it/s]
 85%|████████▍ | 4779/5625 [04:13<00:43, 19.56it/s]
 85%|████████▍ | 4781/5625 [04:13<00:43, 19.33it/s]
 85%|████████▌ | 4784/5625 [04:13<00:43, 19.30it/s]
 85%|████████▌ | 4786/5625 [04:13<00:44, 18.82it/s]
 85%|████████▌ | 4788/5625 [04:13<00:44, 18.76it/s]
 85%|████████▌ | 4791/5625 [04:13<00:41, 19.97it/s]
 85%|████████▌ | 4794/5625 [04:13<00:40, 20.35it/s]
 85%|████████▌ | 4797/5625 [04:14<00:40, 20.22it/s]
 85%|████████▌ | 4800/5625 [04:14<00:39, 20.73it/s]
 85%|████████▌ | 4803/5625 [04:14<00:40, 20.23it/s]
 85%|████████▌ | 4806/5625 [04:14<00:41, 19.54it/s]
 85%|████████▌ | 4808/5625 [04:14<00:41, 19.55it/s]
 86%|████████▌ | 4810/5625 [04:14<00:42, 18.99it/s]
 86%|████████▌ | 4813/5625 [04:14<00:40, 19.85it/s]
 86%|████████▌ | 4815/5625 [04:15<00:41, 19.56it/s]
 86%|████████▌ | 4818/5625 [04:15<00:40, 19.97it/s]
 86%|████████▌ | 4820/5625 [04:15<00:41, 19.39it/s]
 86%|████████▌ | 4822/5625 [04:15<00:42, 18.99it/s]
 86%|████████▌ | 4824/5625 [04:15<00:42, 18.95it/s]
 86%|████████▌ | 4826/5625 [04:15<00:41, 19.23it/s]
 86%|████████▌ | 4829/5625 [04:15<00:41, 19.41it/s]
 86%|████████▌ | 4831/5625 [04:15<00:40, 19.55it/s]
 86%|████████▌ | 4834/5625 [04:15<00:39, 20.01it/s]
 86%|████████▌ | 4836/5625 [04:16<00:39, 19.95it/s]
 86%|████████▌ | 4839/5625 [04:16<00:38, 20.20it/s]
 86%|████████▌ | 4842/5625 [04:16<00:38, 20.58it/s]
 86%|████████▌ | 4845/5625 [04:16<00:37, 20.53it/s]
 86%|████████▌ | 4848/5625 [04:16<00:38, 20.13it/s]
 86%|████████▌ | 4851/5625 [04:16<00:38, 20.17it/s]
 86%|████████▋ | 4854/5625 [04:16<00:39, 19.56it/s]
 86%|████████▋ | 4856/5625 [04:17<00:39, 19.57it/s]
 86%|████████▋ | 4858/5625 [04:17<00:39, 19.47it/s]
 86%|████████▋ | 4861/5625 [04:17<00:38, 19.83it/s]
 86%|████████▋ | 4863/5625 [04:17<00:38, 19.64it/s]
 86%|████████▋ | 4865/5625 [04:17<00:39, 19.42it/s]
 87%|████████▋ | 4868/5625 [04:17<00:37, 20.00it/s]
 87%|████████▋ | 4871/5625 [04:17<00:37, 20.14it/s]
 87%|████████▋ | 4874/5625 [04:17<00:36, 20.45it/s]
 87%|████████▋ | 4877/5625 [04:18<00:37, 19.82it/s]
 87%|████████▋ | 4879/5625 [04:18<00:38, 19.59it/s]
 87%|████████▋ | 4881/5625 [04:18<00:38, 19.18it/s]
 87%|████████▋ | 4883/5625 [04:18<00:38, 19.38it/s]
 87%|████████▋ | 4886/5625 [04:18<00:37, 19.83it/s]
 87%|████████▋ | 4888/5625 [04:18<00:37, 19.45it/s]
 87%|████████▋ | 4890/5625 [04:18<00:38, 19.25it/s]
 87%|████████▋ | 4893/5625 [04:18<00:37, 19.35it/s]
 87%|████████▋ | 4896/5625 [04:19<00:37, 19.65it/s]
 87%|████████▋ | 4899/5625 [04:19<00:36, 19.79it/s]
 87%|████████▋ | 4902/5625 [04:19<00:36, 19.99it/s]
 87%|████████▋ | 4904/5625 [04:19<00:36, 19.64it/s]
 87%|████████▋ | 4906/5625 [04:19<00:37, 19.31it/s]
 87%|████████▋ | 4909/5625 [04:19<00:36, 19.55it/s]
 87%|████████▋ | 4911/5625 [04:19<00:37, 19.08it/s]
 87%|████████▋ | 4914/5625 [04:20<00:35, 19.93it/s]
 87%|████████▋ | 4916/5625 [04:20<00:35, 19.71it/s]
 87%|████████▋ | 4918/5625 [04:20<00:36, 19.48it/s]
 87%|████████▋ | 4920/5625 [04:20<00:35, 19.59it/s]
 88%|████████▊ | 4922/5625 [04:20<00:35, 19.61it/s]
 88%|████████▊ | 4925/5625 [04:20<00:35, 19.67it/s]
 88%|████████▊ | 4928/5625 [04:20<00:34, 20.21it/s]
 88%|████████▊ | 4931/5625 [04:20<00:35, 19.62it/s]
 88%|████████▊ | 4933/5625 [04:21<00:36, 19.08it/s]
 88%|████████▊ | 4935/5625 [04:21<00:36, 18.95it/s]
 88%|████████▊ | 4938/5625 [04:21<00:35, 19.24it/s]
 88%|████████▊ | 4941/5625 [04:21<00:34, 19.67it/s]
 88%|████████▊ | 4944/5625 [04:21<00:33, 20.21it/s]
 88%|████████▊ | 4947/5625 [04:21<00:33, 20.10it/s]
 88%|████████▊ | 4950/5625 [04:21<00:34, 19.42it/s]
 88%|████████▊ | 4952/5625 [04:21<00:34, 19.32it/s]
 88%|████████▊ | 4955/5625 [04:22<00:32, 20.34it/s]
 88%|████████▊ | 4958/5625 [04:22<00:33, 19.85it/s]
 88%|████████▊ | 4960/5625 [04:22<00:33, 19.86it/s]
 88%|████████▊ | 4962/5625 [04:22<00:34, 19.21it/s]
 88%|████████▊ | 4964/5625 [04:22<00:34, 19.04it/s]
 88%|████████▊ | 4966/5625 [04:22<00:34, 19.24it/s]
 88%|████████▊ | 4968/5625 [04:22<00:34, 18.84it/s]
 88%|████████▊ | 4970/5625 [04:22<00:34, 19.11it/s]
 88%|████████▊ | 4972/5625 [04:23<00:34, 18.76it/s]
 88%|████████▊ | 4974/5625 [04:23<00:34, 18.63it/s]
 88%|████████▊ | 4976/5625 [04:23<00:35, 18.45it/s]
 89%|████████▊ | 4979/5625 [04:23<00:33, 19.22it/s]
 89%|████████▊ | 4981/5625 [04:23<00:33, 19.28it/s]
 89%|████████▊ | 4984/5625 [04:23<00:32, 19.74it/s]
 89%|████████▊ | 4987/5625 [04:23<00:31, 19.99it/s]
 89%|████████▊ | 4989/5625 [04:23<00:32, 19.38it/s]
 89%|████████▊ | 4992/5625 [04:24<00:30, 20.63it/s]
 89%|████████▉ | 4995/5625 [04:24<00:31, 19.87it/s]
 89%|████████▉ | 4997/5625 [04:24<00:31, 19.63it/s]
 89%|████████▉ | 5000/5625 [04:24<00:30, 20.34it/s]
 89%|████████▉ | 5003/5625 [04:24<00:31, 19.72it/s]
 89%|████████▉ | 5005/5625 [04:24<00:32, 19.20it/s]
 89%|████████▉ | 5007/5625 [04:24<00:32, 19.27it/s]
 89%|████████▉ | 5009/5625 [04:24<00:32, 19.14it/s]
 89%|████████▉ | 5011/5625 [04:25<00:32, 18.71it/s]
 89%|████████▉ | 5013/5625 [04:25<00:32, 18.90it/s]
 89%|████████▉ | 5015/5625 [04:25<00:32, 18.81it/s]
 89%|████████▉ | 5018/5625 [04:25<00:30, 19.70it/s]
 89%|████████▉ | 5021/5625 [04:25<00:30, 19.49it/s]
 89%|████████▉ | 5024/5625 [04:25<00:30, 19.84it/s]
 89%|████████▉ | 5027/5625 [04:25<00:29, 20.20it/s]
 89%|████████▉ | 5030/5625 [04:25<00:29, 19.96it/s]
 89%|████████▉ | 5032/5625 [04:26<00:30, 19.56it/s]
 90%|████████▉ | 5035/5625 [04:26<00:30, 19.60it/s]
 90%|████████▉ | 5037/5625 [04:26<00:30, 19.47it/s]
 90%|████████▉ | 5040/5625 [04:26<00:29, 19.82it/s]
 90%|████████▉ | 5042/5625 [04:26<00:29, 19.81it/s]
 90%|████████▉ | 5044/5625 [04:26<00:29, 19.85it/s]
 90%|████████▉ | 5046/5625 [04:26<00:29, 19.69it/s]
 90%|████████▉ | 5048/5625 [04:26<00:30, 19.18it/s]
 90%|████████▉ | 5050/5625 [04:27<00:29, 19.33it/s]
 90%|████████▉ | 5052/5625 [04:27<00:29, 19.48it/s]
 90%|████████▉ | 5054/5625 [04:27<00:29, 19.55it/s]
 90%|████████▉ | 5056/5625 [04:27<00:29, 19.24it/s]
 90%|████████▉ | 5058/5625 [04:27<00:29, 19.09it/s]
 90%|████████▉ | 5060/5625 [04:27<00:29, 19.02it/s]
 90%|█████████ | 5063/5625 [04:27<00:28, 20.02it/s]
 90%|█████████ | 5065/5625 [04:27<00:28, 19.79it/s]
 90%|█████████ | 5067/5625 [04:27<00:29, 19.17it/s]
 90%|█████████ | 5070/5625 [04:28<00:28, 19.35it/s]
 90%|█████████ | 5072/5625 [04:28<00:28, 19.19it/s]
 90%|█████████ | 5074/5625 [04:28<00:28, 19.34it/s]
 90%|█████████ | 5076/5625 [04:28<00:28, 19.08it/s]
 90%|█████████ | 5078/5625 [04:28<00:28, 19.06it/s]
 90%|█████████ | 5080/5625 [04:28<00:28, 19.03it/s]
 90%|█████████ | 5082/5625 [04:28<00:28, 19.30it/s]
 90%|█████████ | 5084/5625 [04:28<00:28, 19.07it/s]
 90%|█████████ | 5087/5625 [04:28<00:27, 19.37it/s]
 90%|█████████ | 5089/5625 [04:29<00:28, 19.07it/s]
 91%|█████████ | 5091/5625 [04:29<00:27, 19.27it/s]
 91%|█████████ | 5094/5625 [04:29<00:26, 19.68it/s]
 91%|█████████ | 5096/5625 [04:29<00:27, 19.17it/s]
 91%|█████████ | 5098/5625 [04:29<00:27, 18.97it/s]
 91%|█████████ | 5100/5625 [04:29<00:27, 18.90it/s]
 91%|█████████ | 5102/5625 [04:29<00:27, 19.17it/s]
 91%|█████████ | 5105/5625 [04:29<00:25, 20.48it/s]
 91%|█████████ | 5108/5625 [04:29<00:24, 20.93it/s]
 91%|█████████ | 5111/5625 [04:30<00:24, 20.79it/s]
 91%|█████████ | 5114/5625 [04:30<00:25, 19.81it/s]
 91%|█████████ | 5116/5625 [04:30<00:26, 19.29it/s]
 91%|█████████ | 5119/5625 [04:30<00:25, 19.97it/s]
 91%|█████████ | 5122/5625 [04:30<00:25, 19.83it/s]
 91%|█████████ | 5124/5625 [04:30<00:25, 19.64it/s]
 91%|█████████ | 5127/5625 [04:30<00:24, 20.33it/s]
 91%|█████████ | 5130/5625 [04:31<00:25, 19.74it/s]
 91%|█████████ | 5132/5625 [04:31<00:25, 19.52it/s]
 91%|█████████▏| 5134/5625 [04:31<00:25, 19.42it/s]
 91%|█████████▏| 5137/5625 [04:31<00:24, 19.83it/s]
 91%|█████████▏| 5139/5625 [04:31<00:25, 19.20it/s]
 91%|█████████▏| 5141/5625 [04:31<00:25, 18.98it/s]
 91%|█████████▏| 5143/5625 [04:31<00:25, 18.64it/s]
 91%|█████████▏| 5145/5625 [04:31<00:26, 18.24it/s]
 92%|█████████▏| 5147/5625 [04:32<00:26, 18.16it/s]
 92%|█████████▏| 5150/5625 [04:32<00:25, 18.71it/s]
 92%|█████████▏| 5152/5625 [04:32<00:25, 18.55it/s]
 92%|█████████▏| 5155/5625 [04:32<00:24, 19.06it/s]
 92%|█████████▏| 5158/5625 [04:32<00:24, 19.29it/s]
 92%|█████████▏| 5160/5625 [04:32<00:24, 19.04it/s]
 92%|█████████▏| 5162/5625 [04:32<00:24, 19.19it/s]
 92%|█████████▏| 5164/5625 [04:32<00:24, 19.17it/s]
 92%|█████████▏| 5166/5625 [04:33<00:24, 19.11it/s]
 92%|█████████▏| 5168/5625 [04:33<00:24, 18.64it/s]
 92%|█████████▏| 5170/5625 [04:33<00:24, 18.37it/s]
 92%|█████████▏| 5173/5625 [04:33<00:23, 18.94it/s]
 92%|█████████▏| 5176/5625 [04:33<00:23, 19.45it/s]
 92%|█████████▏| 5179/5625 [04:33<00:22, 19.94it/s]
 92%|█████████▏| 5181/5625 [04:33<00:22, 19.63it/s]
 92%|█████████▏| 5183/5625 [04:33<00:22, 19.58it/s]
 92%|█████████▏| 5186/5625 [04:34<00:22, 19.86it/s]
 92%|█████████▏| 5188/5625 [04:34<00:22, 19.32it/s]
 92%|█████████▏| 5190/5625 [04:34<00:23, 18.80it/s]
 92%|█████████▏| 5192/5625 [04:34<00:22, 19.02it/s]
 92%|█████████▏| 5194/5625 [04:34<00:22, 19.13it/s]
 92%|█████████▏| 5197/5625 [04:34<00:22, 19.36it/s]
 92%|█████████▏| 5199/5625 [04:34<00:21, 19.51it/s]
 92%|█████████▏| 5201/5625 [04:34<00:22, 19.25it/s]
 92%|█████████▏| 5203/5625 [04:34<00:22, 18.82it/s]
 93%|█████████▎| 5205/5625 [04:35<00:22, 18.63it/s]
 93%|█████████▎| 5207/5625 [04:35<00:22, 18.96it/s]
 93%|█████████▎| 5209/5625 [04:35<00:21, 19.24it/s]
 93%|█████████▎| 5211/5625 [04:35<00:21, 19.43it/s]
 93%|█████████▎| 5214/5625 [04:35<00:20, 19.73it/s]
 93%|█████████▎| 5216/5625 [04:35<00:21, 19.38it/s]
 93%|█████████▎| 5219/5625 [04:35<00:20, 20.17it/s]
 93%|█████████▎| 5222/5625 [04:35<00:20, 19.32it/s]
 93%|█████████▎| 5224/5625 [04:36<00:20, 19.11it/s]
 93%|█████████▎| 5226/5625 [04:36<00:21, 18.94it/s]
 93%|█████████▎| 5228/5625 [04:36<00:20, 19.01it/s]
 93%|█████████▎| 5231/5625 [04:36<00:20, 19.60it/s]
 93%|█████████▎| 5233/5625 [04:36<00:20, 19.09it/s]
 93%|█████████▎| 5235/5625 [04:36<00:20, 19.22it/s]
 93%|█████████▎| 5238/5625 [04:36<00:19, 19.84it/s]
 93%|█████████▎| 5240/5625 [04:36<00:19, 19.45it/s]
 93%|█████████▎| 5242/5625 [04:36<00:20, 19.10it/s]
 93%|█████████▎| 5245/5625 [04:37<00:19, 19.33it/s]
 93%|█████████▎| 5247/5625 [04:37<00:19, 19.22it/s]
 93%|█████████▎| 5249/5625 [04:37<00:20, 18.76it/s]
 93%|█████████▎| 5251/5625 [04:37<00:20, 18.63it/s]
 93%|█████████▎| 5254/5625 [04:37<00:19, 19.03it/s]
 93%|█████████▎| 5256/5625 [04:37<00:19, 19.05it/s]
 93%|█████████▎| 5258/5625 [04:37<00:19, 18.87it/s]
 94%|█████████▎| 5260/5625 [04:37<00:19, 18.70it/s]
 94%|█████████▎| 5263/5625 [04:38<00:18, 19.27it/s]
 94%|█████████▎| 5265/5625 [04:38<00:18, 19.24it/s]
 94%|█████████▎| 5267/5625 [04:38<00:18, 19.38it/s]
 94%|█████████▎| 5270/5625 [04:38<00:17, 19.81it/s]
 94%|█████████▎| 5272/5625 [04:38<00:18, 19.45it/s]
 94%|█████████▍| 5274/5625 [04:38<00:18, 18.87it/s]
 94%|█████████▍| 5276/5625 [04:38<00:18, 18.93it/s]
 94%|█████████▍| 5278/5625 [04:38<00:18, 18.83it/s]
 94%|█████████▍| 5280/5625 [04:38<00:18, 18.77it/s]
 94%|█████████▍| 5282/5625 [04:39<00:18, 19.02it/s]
 94%|█████████▍| 5284/5625 [04:39<00:18, 18.65it/s]
 94%|█████████▍| 5286/5625 [04:39<00:18, 18.60it/s]
 94%|█████████▍| 5288/5625 [04:39<00:18, 18.53it/s]
 94%|█████████▍| 5291/5625 [04:39<00:17, 18.90it/s]
 94%|█████████▍| 5293/5625 [04:39<00:17, 18.64it/s]
 94%|█████████▍| 5295/5625 [04:39<00:17, 18.38it/s]
 94%|█████████▍| 5297/5625 [04:39<00:17, 18.54it/s]
 94%|█████████▍| 5299/5625 [04:39<00:17, 18.33it/s]
 94%|█████████▍| 5301/5625 [04:40<00:17, 18.57it/s]
 94%|█████████▍| 5304/5625 [04:40<00:16, 19.04it/s]
 94%|█████████▍| 5306/5625 [04:40<00:16, 19.09it/s]
 94%|█████████▍| 5308/5625 [04:40<00:16, 19.32it/s]
 94%|█████████▍| 5310/5625 [04:40<00:16, 19.37it/s]
 94%|█████████▍| 5312/5625 [04:40<00:16, 18.95it/s]
 94%|█████████▍| 5315/5625 [04:40<00:16, 19.18it/s]
 95%|█████████▍| 5318/5625 [04:40<00:15, 19.53it/s]
 95%|█████████▍| 5320/5625 [04:41<00:15, 19.23it/s]
 95%|█████████▍| 5322/5625 [04:41<00:15, 19.28it/s]
 95%|█████████▍| 5324/5625 [04:41<00:15, 19.15it/s]
 95%|█████████▍| 5327/5625 [04:41<00:15, 19.36it/s]
 95%|█████████▍| 5329/5625 [04:41<00:15, 19.14it/s]
 95%|█████████▍| 5331/5625 [04:41<00:15, 19.21it/s]
 95%|█████████▍| 5334/5625 [04:41<00:15, 19.38it/s]
 95%|█████████▍| 5337/5625 [04:41<00:14, 19.46it/s]
 95%|█████████▍| 5339/5625 [04:42<00:15, 19.00it/s]
 95%|█████████▍| 5341/5625 [04:42<00:15, 18.88it/s]
 95%|█████████▍| 5343/5625 [04:42<00:15, 18.49it/s]
 95%|█████████▌| 5345/5625 [04:42<00:14, 18.75it/s]
 95%|█████████▌| 5348/5625 [04:42<00:14, 19.68it/s]
 95%|█████████▌| 5351/5625 [04:42<00:13, 19.64it/s]
 95%|█████████▌| 5353/5625 [04:42<00:13, 19.47it/s]
 95%|█████████▌| 5356/5625 [04:42<00:13, 19.81it/s]
 95%|█████████▌| 5358/5625 [04:43<00:13, 19.27it/s]
 95%|█████████▌| 5360/5625 [04:43<00:13, 19.22it/s]
 95%|█████████▌| 5362/5625 [04:43<00:14, 18.71it/s]
 95%|█████████▌| 5364/5625 [04:43<00:13, 18.66it/s]
 95%|█████████▌| 5366/5625 [04:43<00:13, 18.78it/s]
 95%|█████████▌| 5369/5625 [04:43<00:12, 20.02it/s]
 95%|█████████▌| 5371/5625 [04:43<00:13, 19.43it/s]
 96%|█████████▌| 5373/5625 [04:43<00:13, 19.32it/s]
 96%|█████████▌| 5375/5625 [04:43<00:13, 19.00it/s]
 96%|█████████▌| 5378/5625 [04:44<00:12, 19.92it/s]
 96%|█████████▌| 5381/5625 [04:44<00:12, 20.30it/s]
 96%|█████████▌| 5384/5625 [04:44<00:11, 20.73it/s]
 96%|█████████▌| 5387/5625 [04:44<00:12, 19.81it/s]
 96%|█████████▌| 5389/5625 [04:44<00:12, 19.17it/s]
 96%|█████████▌| 5391/5625 [04:44<00:12, 18.76it/s]
 96%|█████████▌| 5393/5625 [04:44<00:12, 18.78it/s]
 96%|█████████▌| 5395/5625 [04:44<00:12, 18.76it/s]
 96%|█████████▌| 5398/5625 [04:45<00:11, 19.65it/s]
 96%|█████████▌| 5400/5625 [04:45<00:11, 18.95it/s]
 96%|█████████▌| 5402/5625 [04:45<00:11, 18.72it/s]
 96%|█████████▌| 5404/5625 [04:45<00:11, 19.06it/s]
 96%|█████████▌| 5407/5625 [04:45<00:10, 19.98it/s]
 96%|█████████▌| 5409/5625 [04:45<00:10, 19.89it/s]
 96%|█████████▌| 5411/5625 [04:45<00:11, 19.31it/s]
 96%|█████████▌| 5413/5625 [04:45<00:11, 18.79it/s]
 96%|█████████▋| 5415/5625 [04:46<00:11, 18.38it/s]
 96%|█████████▋| 5418/5625 [04:46<00:10, 19.31it/s]
 96%|█████████▋| 5420/5625 [04:46<00:10, 19.25it/s]
 96%|█████████▋| 5422/5625 [04:46<00:10, 19.33it/s]
 96%|█████████▋| 5424/5625 [04:46<00:10, 18.92it/s]
 96%|█████████▋| 5426/5625 [04:46<00:10, 18.75it/s]
 96%|█████████▋| 5428/5625 [04:46<00:10, 18.99it/s]
 97%|█████████▋| 5430/5625 [04:46<00:10, 19.10it/s]
 97%|█████████▋| 5433/5625 [04:46<00:09, 19.52it/s]
 97%|█████████▋| 5435/5625 [04:47<00:09, 19.57it/s]
 97%|█████████▋| 5437/5625 [04:47<00:09, 19.46it/s]
 97%|█████████▋| 5439/5625 [04:47<00:09, 18.87it/s]
 97%|█████████▋| 5441/5625 [04:47<00:09, 18.79it/s]
 97%|█████████▋| 5443/5625 [04:47<00:09, 18.41it/s]
 97%|█████████▋| 5445/5625 [04:47<00:09, 18.68it/s]
 97%|█████████▋| 5447/5625 [04:47<00:09, 18.73it/s]
 97%|█████████▋| 5449/5625 [04:47<00:09, 18.98it/s]
 97%|█████████▋| 5451/5625 [04:47<00:09, 19.24it/s]
 97%|█████████▋| 5453/5625 [04:47<00:08, 19.17it/s]
 97%|█████████▋| 5455/5625 [04:48<00:08, 19.27it/s]
 97%|█████████▋| 5458/5625 [04:48<00:08, 19.33it/s]
 97%|█████████▋| 5460/5625 [04:48<00:08, 18.98it/s]
 97%|█████████▋| 5462/5625 [04:48<00:08, 18.44it/s]
 97%|█████████▋| 5464/5625 [04:48<00:08, 18.43it/s]
 97%|█████████▋| 5466/5625 [04:48<00:08, 18.49it/s]
 97%|█████████▋| 5468/5625 [04:48<00:08, 18.41it/s]
 97%|█████████▋| 5470/5625 [04:48<00:08, 18.48it/s]
 97%|█████████▋| 5473/5625 [04:49<00:08, 18.75it/s]
 97%|█████████▋| 5475/5625 [04:49<00:08, 18.54it/s]
 97%|█████████▋| 5478/5625 [04:49<00:07, 19.31it/s]
 97%|█████████▋| 5481/5625 [04:49<00:07, 20.34it/s]
 97%|█████████▋| 5484/5625 [04:49<00:07, 19.37it/s]
 98%|█████████▊| 5486/5625 [04:49<00:07, 19.04it/s]
 98%|█████████▊| 5489/5625 [04:49<00:07, 19.38it/s]
 98%|█████████▊| 5491/5625 [04:49<00:07, 19.05it/s]
 98%|█████████▊| 5494/5625 [04:50<00:06, 19.42it/s]
 98%|█████████▊| 5496/5625 [04:50<00:06, 19.10it/s]
 98%|█████████▊| 5498/5625 [04:50<00:06, 18.84it/s]
 98%|█████████▊| 5500/5625 [04:50<00:06, 19.13it/s]
 98%|█████████▊| 5502/5625 [04:50<00:06, 18.59it/s]
 98%|█████████▊| 5505/5625 [04:50<00:06, 18.74it/s]
 98%|█████████▊| 5507/5625 [04:50<00:06, 18.41it/s]
 98%|█████████▊| 5509/5625 [04:50<00:06, 18.22it/s]
 98%|█████████▊| 5511/5625 [04:51<00:06, 18.06it/s]
 98%|█████████▊| 5514/5625 [04:51<00:05, 18.98it/s]
 98%|█████████▊| 5516/5625 [04:51<00:05, 18.79it/s]
 98%|█████████▊| 5518/5625 [04:51<00:05, 19.03it/s]
 98%|█████████▊| 5521/5625 [04:51<00:05, 19.35it/s]
 98%|█████████▊| 5523/5625 [04:51<00:05, 19.24it/s]
 98%|█████████▊| 5526/5625 [04:51<00:05, 19.48it/s]
 98%|█████████▊| 5528/5625 [04:51<00:05, 19.30it/s]
 98%|█████████▊| 5530/5625 [04:52<00:04, 19.25it/s]
 98%|█████████▊| 5533/5625 [04:52<00:04, 19.73it/s]
 98%|█████████▊| 5535/5625 [04:52<00:04, 19.72it/s]
 98%|█████████▊| 5538/5625 [04:52<00:04, 20.27it/s]
 99%|█████████▊| 5541/5625 [04:52<00:04, 20.55it/s]
 99%|█████████▊| 5544/5625 [04:52<00:03, 20.36it/s]
 99%|█████████▊| 5547/5625 [04:52<00:03, 19.74it/s]
 99%|█████████▊| 5549/5625 [04:52<00:03, 19.60it/s]
 99%|█████████▊| 5551/5625 [04:53<00:03, 19.27it/s]
 99%|█████████▊| 5553/5625 [04:53<00:03, 19.12it/s]
 99%|█████████▉| 5556/5625 [04:53<00:03, 19.50it/s]
 99%|█████████▉| 5558/5625 [04:53<00:03, 18.93it/s]
 99%|█████████▉| 5560/5625 [04:53<00:03, 19.12it/s]
 99%|█████████▉| 5562/5625 [04:53<00:03, 18.98it/s]
 99%|█████████▉| 5565/5625 [04:53<00:03, 19.45it/s]
 99%|█████████▉| 5568/5625 [04:53<00:02, 19.68it/s]
 99%|█████████▉| 5570/5625 [04:54<00:02, 19.37it/s]
 99%|█████████▉| 5573/5625 [04:54<00:02, 19.63it/s]
 99%|█████████▉| 5576/5625 [04:54<00:02, 19.72it/s]
 99%|█████████▉| 5578/5625 [04:54<00:02, 19.39it/s]
 99%|█████████▉| 5580/5625 [04:54<00:02, 19.10it/s]
 99%|█████████▉| 5583/5625 [04:54<00:02, 19.88it/s]
 99%|█████████▉| 5586/5625 [04:54<00:01, 20.27it/s]
 99%|█████████▉| 5589/5625 [04:55<00:01, 19.65it/s]
 99%|█████████▉| 5591/5625 [04:55<00:01, 19.10it/s]
 99%|█████████▉| 5593/5625 [04:55<00:01, 19.22it/s]
 99%|█████████▉| 5595/5625 [04:55<00:01, 19.19it/s]
100%|█████████▉| 5597/5625 [04:55<00:01, 19.07it/s]
100%|█████████▉| 5599/5625 [04:55<00:01, 19.17it/s]
100%|█████████▉| 5602/5625 [04:55<00:01, 19.26it/s]
100%|█████████▉| 5604/5625 [04:55<00:01, 18.99it/s]
100%|█████████▉| 5606/5625 [04:55<00:01, 18.98it/s]
100%|█████████▉| 5608/5625 [04:56<00:00, 18.46it/s]
100%|█████████▉| 5610/5625 [04:56<00:00, 18.78it/s]
100%|█████████▉| 5613/5625 [04:56<00:00, 19.42it/s]
100%|█████████▉| 5616/5625 [04:56<00:00, 19.54it/s]
100%|█████████▉| 5618/5625 [04:56<00:00, 19.34it/s]
100%|█████████▉| 5620/5625 [04:56<00:00, 19.27it/s]
100%|█████████▉| 5622/5625 [04:56<00:00, 19.06it/s]
100%|█████████▉| 5624/5625 [04:56<00:00, 18.58it/s]
                                                   

100%|██████████| 5625/5625 [04:56<00:00, 18.58it/s]{'eval_loss': 0.7240970730781555, 'eval_accuracy': 0.682, 'eval_f1': 0.6759090004639122, 'eval_runtime': 1.7306, 'eval_samples_per_second': 1444.596, 'eval_steps_per_second': 180.863, 'epoch': 2.0}
{'loss': 0.7089, 'learning_rate': 1.368337698863855e-09, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.07it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.14it/s]

 21%|██        | 66/313 [00:00<00:01, 205.70it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.91it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.31it/s]

 40%|████      | 126/313 [00:00<00:01, 185.03it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.98it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.10it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.21it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.28it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.35it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.04it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.87it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.74it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.53it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.53it/s]
100%|██████████| 5625/5625 [04:58<00:00, 18.58it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 5625/5625 [04:59<00:00, 18.58it/s]
100%|██████████| 5625/5625 [04:59<00:00, 18.77it/s]
[I 2023-10-26 22:14:18,959] Trial 3 finished with value: 0.6801538506803347 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 1.7316313579122085e-06, 'per_device_train_batch_size': 16, 'weight_decay': 0.036181691951769485}. Best is trial 1 with value: 0.7159626561431993.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7167283296585083, 'eval_accuracy': 0.6824, 'eval_f1': 0.6801538506803347, 'eval_runtime': 1.7325, 'eval_samples_per_second': 1442.97, 'eval_steps_per_second': 180.66, 'epoch': 3.0}
{'train_runtime': 299.7032, 'train_samples_per_second': 300.297, 'train_steps_per_second': 18.769, 'train_loss': 0.7959844401041667, 'epoch': 3.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:04,  1.91it/s]
  1%|          | 2/354 [00:01<03:01,  1.94it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:53,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:55,  1.99it/s]
  2%|▏         | 6/354 [00:03<02:52,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.05it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.03it/s]
  3%|▎         | 9/354 [00:04<02:52,  2.01it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:50,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:50,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:50,  1.99it/s]
  4%|▍         | 14/354 [00:07<02:51,  1.98it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.98it/s]
  5%|▍         | 16/354 [00:08<02:50,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:50,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:46,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:46,  2.00it/s]
  6%|▌         | 22/354 [00:11<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:46,  1.98it/s]
  7%|▋         | 24/354 [00:12<02:46,  1.99it/s]
  7%|▋         | 25/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:46,  1.97it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.02it/s]
  8%|▊         | 28/354 [00:13<02:41,  2.02it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:42,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:15<02:39,  2.01it/s]
  9%|▉         | 33/354 [00:16<02:40,  2.00it/s]
 10%|▉         | 34/354 [00:17<02:40,  1.99it/s]
 10%|▉         | 35/354 [00:17<02:37,  2.03it/s]
 10%|█         | 36/354 [00:17<02:35,  2.05it/s]
 10%|█         | 37/354 [00:18<02:34,  2.05it/s]
 11%|█         | 38/354 [00:18<02:35,  2.03it/s]
 11%|█         | 39/354 [00:19<02:36,  2.02it/s]
 11%|█▏        | 40/354 [00:19<02:36,  2.00it/s]
 12%|█▏        | 41/354 [00:20<02:37,  1.99it/s]
 12%|█▏        | 42/354 [00:20<02:33,  2.03it/s]
 12%|█▏        | 43/354 [00:21<02:34,  2.01it/s]
 12%|█▏        | 44/354 [00:21<02:34,  2.01it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:22<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:23<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:25<02:32,  1.99it/s]
 15%|█▍        | 53/354 [00:26<02:27,  2.03it/s]
 15%|█▌        | 54/354 [00:26<02:29,  2.01it/s]
 16%|█▌        | 55/354 [00:27<02:28,  2.01it/s]
 16%|█▌        | 56/354 [00:27<02:28,  2.00it/s]
 16%|█▌        | 57/354 [00:28<02:42,  1.82it/s]
 16%|█▋        | 58/354 [00:29<02:38,  1.86it/s]
 17%|█▋        | 59/354 [00:29<02:32,  1.93it/s]
 17%|█▋        | 60/354 [00:30<02:31,  1.94it/s]
 17%|█▋        | 61/354 [00:30<02:29,  1.96it/s]
 18%|█▊        | 62/354 [00:31<02:25,  2.00it/s]
 18%|█▊        | 63/354 [00:31<02:23,  2.03it/s]
 18%|█▊        | 64/354 [00:32<02:21,  2.05it/s]
 18%|█▊        | 65/354 [00:32<02:21,  2.04it/s]
 19%|█▊        | 66/354 [00:33<02:21,  2.04it/s]
 19%|█▉        | 67/354 [00:33<02:21,  2.03it/s]
 19%|█▉        | 68/354 [00:34<02:21,  2.02it/s]
 19%|█▉        | 69/354 [00:34<02:19,  2.05it/s]
 20%|█▉        | 70/354 [00:35<02:20,  2.02it/s]
 20%|██        | 71/354 [00:35<02:21,  2.00it/s]
 20%|██        | 72/354 [00:36<02:21,  1.99it/s]
 21%|██        | 73/354 [00:36<02:21,  1.98it/s]
 21%|██        | 74/354 [00:37<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.01it/s]
 21%|██▏       | 76/354 [00:37<02:16,  2.04it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:38<02:16,  2.03it/s]
 22%|██▏       | 79/354 [00:39<02:16,  2.02it/s]
 23%|██▎       | 80/354 [00:39<02:16,  2.00it/s]
 23%|██▎       | 81/354 [00:40<02:16,  2.00it/s]
 23%|██▎       | 82/354 [00:40<02:16,  2.00it/s]
 23%|██▎       | 83/354 [00:41<02:14,  2.01it/s]
 24%|██▎       | 84/354 [00:41<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:13,  2.02it/s]
 24%|██▍       | 86/354 [00:42<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  2.00it/s]
 25%|██▍       | 88/354 [00:43<02:12,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 92/354 [00:46<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.02it/s]
 27%|██▋       | 94/354 [00:46<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 96/354 [00:47<02:06,  2.05it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:48<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.10it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:03,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  1.99it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  2.00it/s]
 31%|███       | 109/354 [00:54<02:03,  1.99it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:58,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.9043, 'learning_rate': 1.1460025910257355e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.03it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.37it/s]

 21%|██        | 66/313 [00:00<00:01, 205.98it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.22it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.58it/s]

 40%|████      | 126/313 [00:00<00:01, 185.26it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.02it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.95it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.20it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.55it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.88it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.66it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.36it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 185.10it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 179.04it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.04it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 34%|███▎      | 119/354 [01:01<04:40,  1.19s/it]
 34%|███▍      | 120/354 [01:02<03:51,  1.01it/s]
 34%|███▍      | 121/354 [01:02<03:16,  1.18it/s]
 34%|███▍      | 122/354 [01:03<02:52,  1.34it/s]
 35%|███▍      | 123/354 [01:03<02:35,  1.49it/s]
 35%|███▌      | 124/354 [01:04<02:23,  1.61it/s]
 35%|███▌      | 125/354 [01:04<02:12,  1.73it/s]
 36%|███▌      | 126/354 [01:05<02:07,  1.79it/s]
 36%|███▌      | 127/354 [01:05<02:00,  1.88it/s]
 36%|███▌      | 128/354 [01:06<01:58,  1.90it/s]
 36%|███▋      | 129/354 [01:06<01:57,  1.92it/s]
 37%|███▋      | 130/354 [01:07<01:55,  1.95it/s]
 37%|███▋      | 131/354 [01:07<01:53,  1.96it/s]
 37%|███▋      | 132/354 [01:08<01:53,  1.96it/s]
 38%|███▊      | 133/354 [01:08<01:51,  1.97it/s]
 38%|███▊      | 134/354 [01:09<01:51,  1.98it/s]
 38%|███▊      | 135/354 [01:09<01:51,  1.97it/s]
 38%|███▊      | 136/354 [01:10<01:48,  2.01it/s]
 39%|███▊      | 137/354 [01:10<01:46,  2.04it/s]
 39%|███▉      | 138/354 [01:11<01:46,  2.02it/s]
 39%|███▉      | 139/354 [01:11<01:44,  2.06it/s]
 40%|███▉      | 140/354 [01:12<01:45,  2.03it/s]
 40%|███▉      | 141/354 [01:12<01:45,  2.02it/s]
 40%|████      | 142/354 [01:13<01:45,  2.01it/s]
 40%|████      | 143/354 [01:13<01:45,  2.01it/s]
 41%|████      | 144/354 [01:14<01:44,  2.00it/s]
 41%|████      | 145/354 [01:14<01:45,  1.99it/s]
 41%|████      | 146/354 [01:15<01:44,  2.00it/s]
 42%|████▏     | 147/354 [01:15<01:42,  2.01it/s]
 42%|████▏     | 148/354 [01:16<01:42,  2.00it/s]
 42%|████▏     | 149/354 [01:16<01:40,  2.04it/s]
 42%|████▏     | 150/354 [01:16<01:40,  2.03it/s]
 43%|████▎     | 151/354 [01:17<01:38,  2.05it/s]
 43%|████▎     | 152/354 [01:17<01:39,  2.03it/s]
 43%|████▎     | 153/354 [01:18<01:35,  2.10it/s]
 44%|████▎     | 154/354 [01:18<01:37,  2.05it/s]
 44%|████▍     | 155/354 [01:19<01:38,  2.02it/s]
 44%|████▍     | 156/354 [01:19<01:38,  2.00it/s]
 44%|████▍     | 157/354 [01:20<01:38,  2.00it/s]
 45%|████▍     | 158/354 [01:20<01:38,  2.00it/s]
 45%|████▍     | 159/354 [01:21<01:37,  2.00it/s]
 45%|████▌     | 160/354 [01:21<01:37,  1.99it/s]
 45%|████▌     | 161/354 [01:22<01:37,  1.98it/s]
 46%|████▌     | 162/354 [01:22<01:37,  1.97it/s]
 46%|████▌     | 163/354 [01:23<01:36,  1.98it/s]
 46%|████▋     | 164/354 [01:23<01:36,  1.97it/s]
 47%|████▋     | 165/354 [01:24<01:36,  1.97it/s]
 47%|████▋     | 166/354 [01:25<01:35,  1.97it/s]
 47%|████▋     | 167/354 [01:25<01:34,  1.97it/s]
 47%|████▋     | 168/354 [01:26<01:34,  1.97it/s]
 48%|████▊     | 169/354 [01:26<01:33,  1.98it/s]
 48%|████▊     | 170/354 [01:27<01:33,  1.97it/s]
 48%|████▊     | 171/354 [01:27<01:32,  1.97it/s]
 49%|████▊     | 172/354 [01:28<01:30,  2.00it/s]
 49%|████▉     | 173/354 [01:28<01:30,  1.99it/s]
 49%|████▉     | 174/354 [01:29<01:28,  2.02it/s]
 49%|████▉     | 175/354 [01:29<01:28,  2.02it/s]
 50%|████▉     | 176/354 [01:30<01:29,  2.00it/s]
 50%|█████     | 177/354 [01:30<01:27,  2.03it/s]
 50%|█████     | 178/354 [01:31<01:27,  2.01it/s]
 51%|█████     | 179/354 [01:31<01:27,  1.99it/s]
 51%|█████     | 180/354 [01:32<01:27,  1.98it/s]
 51%|█████     | 181/354 [01:32<01:34,  1.82it/s]
 51%|█████▏    | 182/354 [01:33<01:32,  1.87it/s]
 52%|█████▏    | 183/354 [01:33<01:30,  1.90it/s]
 52%|█████▏    | 184/354 [01:34<01:27,  1.95it/s]
 52%|█████▏    | 185/354 [01:34<01:24,  1.99it/s]
 53%|█████▎    | 186/354 [01:35<01:22,  2.03it/s]
 53%|█████▎    | 187/354 [01:35<01:23,  2.01it/s]
 53%|█████▎    | 188/354 [01:36<01:23,  1.99it/s]
 53%|█████▎    | 189/354 [01:36<01:23,  1.98it/s]
 54%|█████▎    | 190/354 [01:37<01:21,  2.00it/s]
 54%|█████▍    | 191/354 [01:37<01:20,  2.02it/s]
 54%|█████▍    | 192/354 [01:38<01:20,  2.02it/s]
 55%|█████▍    | 193/354 [01:38<01:20,  2.01it/s]
 55%|█████▍    | 194/354 [01:39<01:19,  2.00it/s]
 55%|█████▌    | 195/354 [01:39<01:19,  1.99it/s]
 55%|█████▌    | 196/354 [01:40<01:19,  1.98it/s]
 56%|█████▌    | 197/354 [01:40<01:19,  1.99it/s]
 56%|█████▌    | 198/354 [01:41<01:18,  1.99it/s]
 56%|█████▌    | 199/354 [01:41<01:18,  1.98it/s]
 56%|█████▋    | 200/354 [01:42<01:17,  1.98it/s]
 57%|█████▋    | 201/354 [01:42<01:16,  1.99it/s]
 57%|█████▋    | 202/354 [01:43<01:16,  1.98it/s]
 57%|█████▋    | 203/354 [01:43<01:15,  2.00it/s]
 58%|█████▊    | 204/354 [01:44<01:15,  1.99it/s]
 58%|█████▊    | 205/354 [01:44<01:14,  2.00it/s]
 58%|█████▊    | 206/354 [01:45<01:14,  2.00it/s]
 58%|█████▊    | 207/354 [01:45<01:12,  2.03it/s]
 59%|█████▉    | 208/354 [01:46<01:12,  2.02it/s]
 59%|█████▉    | 209/354 [01:46<01:10,  2.05it/s]
 59%|█████▉    | 210/354 [01:47<01:09,  2.07it/s]
 60%|█████▉    | 211/354 [01:47<01:09,  2.05it/s]
 60%|█████▉    | 212/354 [01:48<01:10,  2.02it/s]
 60%|██████    | 213/354 [01:48<01:09,  2.02it/s]
 60%|██████    | 214/354 [01:49<01:09,  2.01it/s]
 61%|██████    | 215/354 [01:49<01:09,  2.00it/s]
 61%|██████    | 216/354 [01:50<01:09,  1.99it/s]
 61%|██████▏   | 217/354 [01:50<01:08,  1.99it/s]
 62%|██████▏   | 218/354 [01:51<01:08,  2.00it/s]
 62%|██████▏   | 219/354 [01:51<01:07,  2.00it/s]
 62%|██████▏   | 220/354 [01:52<01:06,  2.00it/s]
 62%|██████▏   | 221/354 [01:52<01:06,  1.99it/s]
 63%|██████▎   | 222/354 [01:53<01:05,  2.02it/s]
 63%|██████▎   | 223/354 [01:53<01:05,  2.00it/s]
 63%|██████▎   | 224/354 [01:54<01:03,  2.03it/s]
 64%|██████▎   | 225/354 [01:54<01:03,  2.04it/s]
 64%|██████▍   | 226/354 [01:55<01:03,  2.01it/s]
 64%|██████▍   | 227/354 [01:55<01:01,  2.05it/s]
 64%|██████▍   | 228/354 [01:56<01:01,  2.04it/s]
 65%|██████▍   | 229/354 [01:56<01:01,  2.04it/s]
 65%|██████▍   | 230/354 [01:57<01:00,  2.03it/s]
 65%|██████▌   | 231/354 [01:57<01:00,  2.02it/s]
 66%|██████▌   | 232/354 [01:58<01:00,  2.00it/s]
 66%|██████▌   | 233/354 [01:58<01:00,  1.99it/s]
 66%|██████▌   | 234/354 [01:59<01:00,  1.98it/s]
 66%|██████▋   | 235/354 [01:59<00:59,  1.99it/s]
 67%|██████▋   | 236/354 [01:59<00:45,  2.58it/s]
                                                 

 67%|██████▋   | 236/354 [01:59<00:45,  2.58it/s]{'eval_loss': 0.7390283942222595, 'eval_accuracy': 0.6768, 'eval_f1': 0.6707867008742644, 'eval_runtime': 1.7292, 'eval_samples_per_second': 1445.759, 'eval_steps_per_second': 181.009, 'epoch': 1.0}
{'loss': 0.702, 'learning_rate': 5.754190224981542e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.58it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.53it/s]

 21%|██        | 65/313 [00:00<00:01, 204.69it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.05it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.33it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.05it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.62it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.54it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.09it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.91it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.81it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.87it/s]

 83%|████████▎ | 259/313 [00:01<00:00, 184.07it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.91it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.12it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.12it/s]
 67%|██████▋   | 236/354 [02:01<00:45,  2.58it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 237/354 [02:02<02:21,  1.21s/it]
 67%|██████▋   | 238/354 [02:03<01:54,  1.01it/s]
 68%|██████▊   | 239/354 [02:03<01:37,  1.18it/s]
 68%|██████▊   | 240/354 [02:04<01:24,  1.34it/s]
 68%|██████▊   | 241/354 [02:04<01:15,  1.49it/s]
 68%|██████▊   | 242/354 [02:05<01:09,  1.60it/s]
 69%|██████▊   | 243/354 [02:05<01:05,  1.70it/s]
 69%|██████▉   | 244/354 [02:06<01:01,  1.78it/s]
 69%|██████▉   | 245/354 [02:06<00:59,  1.84it/s]
 69%|██████▉   | 246/354 [02:07<00:57,  1.87it/s]
 70%|██████▉   | 247/354 [02:07<00:56,  1.90it/s]
 70%|███████   | 248/354 [02:08<00:55,  1.91it/s]
 70%|███████   | 249/354 [02:08<00:53,  1.97it/s]
 71%|███████   | 250/354 [02:09<00:52,  1.96it/s]
 71%|███████   | 251/354 [02:09<00:51,  1.99it/s]
 71%|███████   | 252/354 [02:10<00:50,  2.01it/s]
 71%|███████▏  | 253/354 [02:10<00:50,  1.99it/s]
 72%|███████▏  | 254/354 [02:11<00:50,  1.99it/s]
 72%|███████▏  | 255/354 [02:11<00:49,  1.98it/s]
 72%|███████▏  | 256/354 [02:12<00:49,  1.98it/s]
 73%|███████▎  | 257/354 [02:12<00:48,  2.01it/s]
 73%|███████▎  | 258/354 [02:13<00:48,  2.00it/s]
 73%|███████▎  | 259/354 [02:13<00:47,  2.00it/s]
 73%|███████▎  | 260/354 [02:14<00:47,  1.99it/s]
 74%|███████▎  | 261/354 [02:14<00:45,  2.03it/s]
 74%|███████▍  | 262/354 [02:15<00:44,  2.06it/s]
 74%|███████▍  | 263/354 [02:15<00:44,  2.05it/s]
 75%|███████▍  | 264/354 [02:16<00:44,  2.03it/s]
 75%|███████▍  | 265/354 [02:16<00:44,  2.01it/s]
 75%|███████▌  | 266/354 [02:17<00:43,  2.02it/s]
 75%|███████▌  | 267/354 [02:17<00:43,  2.00it/s]
 76%|███████▌  | 268/354 [02:18<00:43,  2.00it/s]
 76%|███████▌  | 269/354 [02:18<00:42,  1.98it/s]
 76%|███████▋  | 270/354 [02:19<00:42,  1.98it/s]
 77%|███████▋  | 271/354 [02:19<00:42,  1.97it/s]
 77%|███████▋  | 272/354 [02:20<00:41,  1.99it/s]
 77%|███████▋  | 273/354 [02:20<00:40,  1.99it/s]
 77%|███████▋  | 274/354 [02:21<00:40,  1.98it/s]
 78%|███████▊  | 275/354 [02:21<00:39,  2.02it/s]
 78%|███████▊  | 276/354 [02:22<00:38,  2.05it/s]
 78%|███████▊  | 277/354 [02:22<00:37,  2.03it/s]
 79%|███████▊  | 278/354 [02:23<00:37,  2.01it/s]
 79%|███████▉  | 279/354 [02:23<00:37,  2.00it/s]
 79%|███████▉  | 280/354 [02:24<00:36,  2.03it/s]
 79%|███████▉  | 281/354 [02:24<00:36,  2.02it/s]
 80%|███████▉  | 282/354 [02:25<00:35,  2.05it/s]
 80%|███████▉  | 283/354 [02:25<00:34,  2.07it/s]
 80%|████████  | 284/354 [02:26<00:34,  2.04it/s]
 81%|████████  | 285/354 [02:26<00:34,  2.03it/s]
 81%|████████  | 286/354 [02:27<00:32,  2.06it/s]
 81%|████████  | 287/354 [02:27<00:32,  2.03it/s]
 81%|████████▏ | 288/354 [02:28<00:32,  2.01it/s]
 82%|████████▏ | 289/354 [02:28<00:32,  2.02it/s]
 82%|████████▏ | 290/354 [02:29<00:31,  2.01it/s]
 82%|████████▏ | 291/354 [02:29<00:31,  2.00it/s]
 82%|████████▏ | 292/354 [02:30<00:31,  1.99it/s]
 83%|████████▎ | 293/354 [02:30<00:30,  1.98it/s]
 83%|████████▎ | 294/354 [02:31<00:30,  2.00it/s]
 83%|████████▎ | 295/354 [02:31<00:29,  2.00it/s]
 84%|████████▎ | 296/354 [02:32<00:29,  1.99it/s]
 84%|████████▍ | 297/354 [02:32<00:28,  1.98it/s]
 84%|████████▍ | 298/354 [02:33<00:28,  1.97it/s]
 84%|████████▍ | 299/354 [02:33<00:27,  1.99it/s]
 85%|████████▍ | 300/354 [02:34<00:27,  1.99it/s]
 85%|████████▌ | 301/354 [02:34<00:26,  1.99it/s]
 85%|████████▌ | 302/354 [02:35<00:26,  1.98it/s]
 86%|████████▌ | 303/354 [02:35<00:25,  2.00it/s]
 86%|████████▌ | 304/354 [02:36<00:26,  1.87it/s]
 86%|████████▌ | 305/354 [02:36<00:25,  1.93it/s]
 86%|████████▋ | 306/354 [02:37<00:24,  1.94it/s]
 87%|████████▋ | 307/354 [02:37<00:23,  1.99it/s]
 87%|████████▋ | 308/354 [02:38<00:23,  1.98it/s]
 87%|████████▋ | 309/354 [02:38<00:22,  2.02it/s]
 88%|████████▊ | 310/354 [02:39<00:21,  2.02it/s]
 88%|████████▊ | 311/354 [02:39<00:21,  2.04it/s]
 88%|████████▊ | 312/354 [02:40<00:20,  2.02it/s]
 88%|████████▊ | 313/354 [02:40<00:20,  2.04it/s]
 89%|████████▊ | 314/354 [02:41<00:19,  2.04it/s]
 89%|████████▉ | 315/354 [02:41<00:19,  2.02it/s]
 89%|████████▉ | 316/354 [02:42<00:18,  2.02it/s]
 90%|████████▉ | 317/354 [02:42<00:18,  2.00it/s]
 90%|████████▉ | 318/354 [02:43<00:17,  2.04it/s]
 90%|█████████ | 319/354 [02:43<00:17,  2.02it/s]
 90%|█████████ | 320/354 [02:44<00:16,  2.01it/s]
 91%|█████████ | 321/354 [02:44<00:16,  2.04it/s]
 91%|█████████ | 322/354 [02:45<00:15,  2.04it/s]
 91%|█████████ | 323/354 [02:45<00:15,  2.02it/s]
 92%|█████████▏| 324/354 [02:46<00:14,  2.01it/s]
 92%|█████████▏| 325/354 [02:46<00:14,  2.00it/s]
 92%|█████████▏| 326/354 [02:47<00:13,  2.01it/s]
 92%|█████████▏| 327/354 [02:47<00:13,  2.00it/s]
 93%|█████████▎| 328/354 [02:48<00:12,  2.01it/s]
 93%|█████████▎| 329/354 [02:48<00:12,  2.00it/s]
 93%|█████████▎| 330/354 [02:49<00:11,  2.03it/s]
 94%|█████████▎| 331/354 [02:49<00:11,  2.03it/s]
 94%|█████████▍| 332/354 [02:50<00:10,  2.01it/s]
 94%|█████████▍| 333/354 [02:50<00:10,  2.00it/s]
 94%|█████████▍| 334/354 [02:51<00:09,  2.01it/s]
 95%|█████████▍| 335/354 [02:51<00:09,  2.01it/s]
 95%|█████████▍| 336/354 [02:52<00:08,  2.00it/s]
 95%|█████████▌| 337/354 [02:52<00:08,  2.00it/s]
 95%|█████████▌| 338/354 [02:53<00:07,  2.05it/s]
 96%|█████████▌| 339/354 [02:53<00:07,  2.02it/s]
 96%|█████████▌| 340/354 [02:54<00:06,  2.01it/s]
 96%|█████████▋| 341/354 [02:54<00:06,  2.00it/s]
 97%|█████████▋| 342/354 [02:55<00:06,  2.00it/s]
 97%|█████████▋| 343/354 [02:55<00:05,  1.99it/s]
 97%|█████████▋| 344/354 [02:56<00:05,  1.98it/s]
 97%|█████████▋| 345/354 [02:56<00:04,  2.02it/s]
 98%|█████████▊| 346/354 [02:57<00:03,  2.00it/s]
 98%|█████████▊| 347/354 [02:57<00:03,  2.03it/s]
 98%|█████████▊| 348/354 [02:58<00:02,  2.01it/s]
 99%|█████████▊| 349/354 [02:58<00:02,  2.00it/s]
 99%|█████████▉| 350/354 [02:59<00:01,  2.04it/s]
 99%|█████████▉| 351/354 [02:59<00:01,  2.03it/s]
 99%|█████████▉| 352/354 [03:00<00:00,  2.01it/s]
100%|█████████▉| 353/354 [03:00<00:00,  2.01it/s]
100%|██████████| 354/354 [03:00<00:00,  2.61it/s]
                                                 

100%|██████████| 354/354 [03:00<00:00,  2.61it/s]{'eval_loss': 0.7027534246444702, 'eval_accuracy': 0.6956, 'eval_f1': 0.6913317788087892, 'eval_runtime': 1.7309, 'eval_samples_per_second': 1444.332, 'eval_steps_per_second': 180.83, 'epoch': 2.0}
{'loss': 0.6325, 'learning_rate': 4.8354539705727245e-08, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.57it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.64it/s]

 21%|██        | 65/313 [00:00<00:01, 204.82it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.22it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.54it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.21it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.81it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.65it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.31it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.21it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.03it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.09it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.28it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.65it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.86it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.86it/s]
100%|██████████| 354/354 [03:02<00:00,  2.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 354/354 [03:03<00:00,  2.61it/s]
100%|██████████| 354/354 [03:03<00:00,  1.93it/s]
[I 2023-10-26 22:17:23,218] Trial 4 finished with value: 0.6978358078512498 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 1.5376743626421264e-05, 'per_device_train_batch_size': 256, 'weight_decay': 8.153211376539212e-05}. Best is trial 1 with value: 0.7159626561431993.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6886047124862671, 'eval_accuracy': 0.6996, 'eval_f1': 0.6978358078512498, 'eval_runtime': 1.7309, 'eval_samples_per_second': 1444.346, 'eval_steps_per_second': 180.832, 'epoch': 3.0}
{'train_runtime': 183.4816, 'train_samples_per_second': 490.512, 'train_steps_per_second': 1.929, 'train_loss': 0.74628689868302, 'epoch': 3.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:05,  1.91it/s]
  1%|          | 2/354 [00:01<03:01,  1.94it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:54,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:55,  1.99it/s]
  2%|▏         | 6/354 [00:03<02:53,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.05it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.02it/s]
  3%|▎         | 9/354 [00:04<02:52,  2.00it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:50,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:51,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:50,  1.99it/s]
  4%|▍         | 14/354 [00:07<02:51,  1.99it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.98it/s]
  5%|▍         | 16/354 [00:08<02:50,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:50,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:46,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:46,  2.00it/s]
  6%|▌         | 22/354 [00:11<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:46,  1.98it/s]
  7%|▋         | 24/354 [00:12<02:46,  1.99it/s]
  7%|▋         | 25/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:46,  1.97it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.02it/s]
  8%|▊         | 28/354 [00:13<02:41,  2.02it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:42,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:16<02:54,  1.84it/s]
  9%|▉         | 33/354 [00:16<02:50,  1.88it/s]
 10%|▉         | 34/354 [00:17<02:48,  1.90it/s]
 10%|▉         | 35/354 [00:17<02:42,  1.96it/s]
 10%|█         | 36/354 [00:18<02:38,  2.00it/s]
 10%|█         | 37/354 [00:18<02:37,  2.02it/s]
 11%|█         | 38/354 [00:19<02:37,  2.01it/s]
 11%|█         | 39/354 [00:19<02:37,  2.00it/s]
 11%|█▏        | 40/354 [00:20<02:37,  1.99it/s]
 12%|█▏        | 41/354 [00:20<02:37,  1.98it/s]
 12%|█▏        | 42/354 [00:21<02:34,  2.02it/s]
 12%|█▏        | 43/354 [00:21<02:35,  2.00it/s]
 12%|█▏        | 44/354 [00:22<02:34,  2.00it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:23<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:24<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:25<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:26<02:32,  1.99it/s]
 15%|█▍        | 53/354 [00:26<02:27,  2.04it/s]
 15%|█▌        | 54/354 [00:27<02:29,  2.01it/s]
 16%|█▌        | 55/354 [00:27<02:28,  2.01it/s]
 16%|█▌        | 56/354 [00:28<02:28,  2.00it/s]
 16%|█▌        | 57/354 [00:28<02:26,  2.03it/s]
 16%|█▋        | 58/354 [00:29<02:27,  2.01it/s]
 17%|█▋        | 59/354 [00:29<02:24,  2.04it/s]
 17%|█▋        | 60/354 [00:30<02:25,  2.01it/s]
 17%|█▋        | 61/354 [00:30<02:25,  2.01it/s]
 18%|█▊        | 62/354 [00:31<02:23,  2.04it/s]
 18%|█▊        | 63/354 [00:31<02:31,  1.92it/s]
 18%|█▊        | 64/354 [00:32<02:27,  1.97it/s]
 18%|█▊        | 65/354 [00:32<02:25,  1.98it/s]
 19%|█▊        | 66/354 [00:33<02:23,  2.00it/s]
 19%|█▉        | 67/354 [00:33<02:23,  2.00it/s]
 19%|█▉        | 68/354 [00:34<02:22,  2.00it/s]
 19%|█▉        | 69/354 [00:34<02:20,  2.03it/s]
 20%|█▉        | 70/354 [00:35<02:21,  2.01it/s]
 20%|██        | 71/354 [00:35<02:21,  2.00it/s]
 20%|██        | 72/354 [00:36<02:22,  1.98it/s]
 21%|██        | 73/354 [00:36<02:22,  1.98it/s]
 21%|██        | 74/354 [00:37<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.01it/s]
 21%|██▏       | 76/354 [00:38<02:16,  2.04it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:39<02:17,  2.01it/s]
 22%|██▏       | 79/354 [00:39<02:17,  2.01it/s]
 23%|██▎       | 80/354 [00:40<02:16,  2.01it/s]
 23%|██▎       | 81/354 [00:40<02:16,  2.00it/s]
 23%|██▎       | 82/354 [00:41<02:16,  2.00it/s]
 23%|██▎       | 83/354 [00:41<02:14,  2.01it/s]
 24%|██▎       | 84/354 [00:42<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:12,  2.02it/s]
 24%|██▍       | 86/354 [00:43<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  2.00it/s]
 25%|██▍       | 88/354 [00:44<02:12,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 92/354 [00:46<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.02it/s]
 27%|██▋       | 94/354 [00:47<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 96/354 [00:48<02:06,  2.05it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:49<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.10it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:03,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  2.00it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  2.00it/s]
 31%|███       | 109/354 [00:54<02:03,  1.99it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:58,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.9108, 'learning_rate': 7.828394882590733e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.69it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.56it/s]

 21%|██        | 65/313 [00:00<00:01, 204.48it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.86it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.12it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.80it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.43it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.23it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.67it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.63it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.63it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.72it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.96it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.67it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.81it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.81it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 34%|███▎      | 119/354 [01:01<04:45,  1.22s/it]
 34%|███▍      | 120/354 [01:02<03:54,  1.00s/it]
 34%|███▍      | 121/354 [01:02<03:19,  1.17it/s]
 34%|███▍      | 122/354 [01:03<02:54,  1.33it/s]
 35%|███▍      | 123/354 [01:03<02:36,  1.48it/s]
 35%|███▌      | 124/354 [01:04<02:24,  1.59it/s]
 35%|███▌      | 125/354 [01:04<02:13,  1.72it/s]
 36%|███▌      | 126/354 [01:05<02:07,  1.78it/s]
 36%|███▌      | 127/354 [01:05<02:01,  1.87it/s]
 36%|███▌      | 128/354 [01:06<01:59,  1.90it/s]
 36%|███▋      | 129/354 [01:06<01:57,  1.91it/s]
 37%|███▋      | 130/354 [01:07<01:55,  1.94it/s]
 37%|███▋      | 131/354 [01:07<01:54,  1.95it/s]
 37%|███▋      | 132/354 [01:08<01:53,  1.96it/s]
 38%|███▊      | 133/354 [01:08<01:52,  1.97it/s]
 38%|███▊      | 134/354 [01:09<01:51,  1.97it/s]
 38%|███▊      | 135/354 [01:09<01:51,  1.97it/s]
 38%|███▊      | 136/354 [01:10<01:48,  2.00it/s]
 39%|███▊      | 137/354 [01:10<01:46,  2.03it/s]
 39%|███▉      | 138/354 [01:11<01:47,  2.02it/s]
 39%|███▉      | 139/354 [01:11<01:44,  2.06it/s]
 40%|███▉      | 140/354 [01:12<01:45,  2.03it/s]
 40%|███▉      | 141/354 [01:12<01:45,  2.02it/s]
 40%|████      | 142/354 [01:13<01:45,  2.01it/s]
 40%|████      | 143/354 [01:13<01:45,  2.01it/s]
 41%|████      | 144/354 [01:14<01:45,  2.00it/s]
 41%|████      | 145/354 [01:14<01:45,  1.99it/s]
 41%|████      | 146/354 [01:15<01:44,  1.99it/s]
 42%|████▏     | 147/354 [01:15<01:43,  2.01it/s]
 42%|████▏     | 148/354 [01:16<01:42,  2.00it/s]
 42%|████▏     | 149/354 [01:16<01:40,  2.04it/s]
 42%|████▏     | 150/354 [01:17<01:40,  2.03it/s]
 43%|████▎     | 151/354 [01:17<01:38,  2.05it/s]
 43%|████▎     | 152/354 [01:18<01:39,  2.04it/s]
 43%|████▎     | 153/354 [01:18<01:35,  2.10it/s]
 44%|████▎     | 154/354 [01:19<01:37,  2.06it/s]
 44%|████▍     | 155/354 [01:19<01:38,  2.03it/s]
 44%|████▍     | 156/354 [01:20<01:38,  2.01it/s]
 44%|████▍     | 157/354 [01:20<01:38,  2.00it/s]
 45%|████▍     | 158/354 [01:21<01:38,  2.00it/s]
 45%|████▍     | 159/354 [01:21<01:37,  2.00it/s]
 45%|████▌     | 160/354 [01:22<01:37,  1.99it/s]
 45%|████▌     | 161/354 [01:22<01:37,  1.98it/s]
 46%|████▌     | 162/354 [01:23<01:37,  1.97it/s]
 46%|████▌     | 163/354 [01:23<01:36,  1.98it/s]
 46%|████▋     | 164/354 [01:24<01:36,  1.97it/s]
 47%|████▋     | 165/354 [01:24<01:42,  1.84it/s]
 47%|████▋     | 166/354 [01:25<01:39,  1.88it/s]
 47%|████▋     | 167/354 [01:25<01:38,  1.91it/s]
 47%|████▋     | 168/354 [01:26<01:36,  1.93it/s]
 48%|████▊     | 169/354 [01:26<01:35,  1.94it/s]
 48%|████▊     | 170/354 [01:27<01:34,  1.95it/s]
 48%|████▊     | 171/354 [01:27<01:33,  1.95it/s]
 49%|████▊     | 172/354 [01:28<01:31,  1.99it/s]
 49%|████▉     | 173/354 [01:28<01:31,  1.98it/s]
 49%|████▉     | 174/354 [01:29<01:29,  2.02it/s]
 49%|████▉     | 175/354 [01:30<01:40,  1.78it/s]
 50%|████▉     | 176/354 [01:30<01:37,  1.83it/s]
 50%|█████     | 177/354 [01:30<01:33,  1.90it/s]
 50%|█████     | 178/354 [01:31<01:31,  1.92it/s]
 51%|█████     | 179/354 [01:32<01:30,  1.93it/s]
 51%|█████     | 180/354 [01:32<01:29,  1.94it/s]
 51%|█████     | 181/354 [01:33<01:28,  1.95it/s]
 51%|█████▏    | 182/354 [01:33<01:27,  1.96it/s]
 52%|█████▏    | 183/354 [01:34<01:27,  1.96it/s]
 52%|█████▏    | 184/354 [01:34<01:24,  2.00it/s]
 52%|█████▏    | 185/354 [01:35<01:31,  1.85it/s]
 53%|█████▎    | 186/354 [01:35<01:27,  1.93it/s]
 53%|█████▎    | 187/354 [01:36<01:26,  1.94it/s]
 53%|█████▎    | 188/354 [01:36<01:25,  1.94it/s]
 53%|█████▎    | 189/354 [01:37<01:24,  1.95it/s]
 54%|█████▎    | 190/354 [01:37<01:22,  1.98it/s]
 54%|█████▍    | 191/354 [01:38<01:21,  2.00it/s]
 54%|█████▍    | 192/354 [01:38<01:20,  2.01it/s]
 55%|█████▍    | 193/354 [01:39<01:20,  2.00it/s]
 55%|█████▍    | 194/354 [01:39<01:20,  2.00it/s]
 55%|█████▌    | 195/354 [01:40<01:20,  1.99it/s]
 55%|█████▌    | 196/354 [01:40<01:19,  1.98it/s]
 56%|█████▌    | 197/354 [01:41<01:19,  1.98it/s]
 56%|█████▌    | 198/354 [01:41<01:18,  1.99it/s]
 56%|█████▌    | 199/354 [01:42<01:18,  1.98it/s]
 56%|█████▋    | 200/354 [01:42<01:17,  1.99it/s]
 57%|█████▋    | 201/354 [01:43<01:16,  1.99it/s]
 57%|█████▋    | 202/354 [01:43<01:16,  1.98it/s]
 57%|█████▋    | 203/354 [01:44<01:15,  2.00it/s]
 58%|█████▊    | 204/354 [01:44<01:15,  1.99it/s]
 58%|█████▊    | 205/354 [01:45<01:14,  2.01it/s]
 58%|█████▊    | 206/354 [01:45<01:14,  2.00it/s]
 58%|█████▊    | 207/354 [01:46<01:12,  2.03it/s]
 59%|█████▉    | 208/354 [01:46<01:12,  2.02it/s]
 59%|█████▉    | 209/354 [01:47<01:10,  2.05it/s]
 59%|█████▉    | 210/354 [01:47<01:09,  2.07it/s]
 60%|█████▉    | 211/354 [01:48<01:09,  2.05it/s]
 60%|█████▉    | 212/354 [01:48<01:10,  2.02it/s]
 60%|██████    | 213/354 [01:49<01:09,  2.02it/s]
 60%|██████    | 214/354 [01:49<01:09,  2.01it/s]
 61%|██████    | 215/354 [01:50<01:09,  2.00it/s]
 61%|██████    | 216/354 [01:50<01:09,  1.99it/s]
 61%|██████▏   | 217/354 [01:51<01:08,  1.99it/s]
 62%|██████▏   | 218/354 [01:51<01:08,  2.00it/s]
 62%|██████▏   | 219/354 [01:52<01:07,  2.00it/s]
 62%|██████▏   | 220/354 [01:52<01:06,  2.00it/s]
 62%|██████▏   | 221/354 [01:53<01:06,  1.99it/s]
 63%|██████▎   | 222/354 [01:53<01:05,  2.02it/s]
 63%|██████▎   | 223/354 [01:54<01:05,  2.00it/s]
 63%|██████▎   | 224/354 [01:54<01:03,  2.03it/s]
 64%|██████▎   | 225/354 [01:55<01:03,  2.04it/s]
 64%|██████▍   | 226/354 [01:55<01:03,  2.01it/s]
 64%|██████▍   | 227/354 [01:56<01:01,  2.05it/s]
 64%|██████▍   | 228/354 [01:56<01:01,  2.04it/s]
 65%|██████▍   | 229/354 [01:57<01:01,  2.04it/s]
 65%|██████▍   | 230/354 [01:57<01:00,  2.03it/s]
 65%|██████▌   | 231/354 [01:58<01:00,  2.02it/s]
 66%|██████▌   | 232/354 [01:58<01:00,  2.00it/s]
 66%|██████▌   | 233/354 [01:59<01:00,  1.99it/s]
 66%|██████▌   | 234/354 [01:59<01:00,  1.98it/s]
 66%|██████▋   | 235/354 [02:00<00:59,  1.99it/s]
 67%|██████▋   | 236/354 [02:00<00:45,  2.58it/s]
                                                 

 67%|██████▋   | 236/354 [02:00<00:45,  2.58it/s]{'eval_loss': 0.7605379819869995, 'eval_accuracy': 0.66, 'eval_f1': 0.6484508295682211, 'eval_runtime': 1.7343, 'eval_samples_per_second': 1441.509, 'eval_steps_per_second': 180.477, 'epoch': 1.0}
{'loss': 0.729, 'learning_rate': 7.828394882590733e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.22it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.44it/s]

 21%|██        | 66/313 [00:00<00:01, 205.98it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.21it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.46it/s]

 40%|████      | 126/313 [00:00<00:01, 185.17it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.98it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.03it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.18it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.42it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.68it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.32it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.78it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.41it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.49it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.49it/s]
 67%|██████▋   | 236/354 [02:01<00:45,  2.58it/s]

                                                  
 67%|██████▋   | 236/354 [02:01<01:00,  1.94it/s]
[I 2023-10-26 22:19:25,881] Trial 5 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7190857529640198, 'eval_accuracy': 0.6828, 'eval_f1': 0.6786458120809188, 'eval_runtime': 1.7314, 'eval_samples_per_second': 1443.957, 'eval_steps_per_second': 180.783, 'epoch': 2.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<04:02, 11.60it/s]
  0%|          | 4/2814 [00:00<04:01, 11.64it/s]
  0%|          | 6/2814 [00:00<04:00, 11.67it/s]
  0%|          | 8/2814 [00:00<03:57, 11.81it/s]
  0%|          | 10/2814 [00:00<04:00, 11.66it/s]
  0%|          | 12/2814 [00:01<04:02, 11.54it/s]
  0%|          | 14/2814 [00:01<04:02, 11.57it/s]
  1%|          | 16/2814 [00:01<03:54, 11.92it/s]
  1%|          | 18/2814 [00:01<03:55, 11.87it/s]
  1%|          | 20/2814 [00:01<03:49, 12.19it/s]
  1%|          | 22/2814 [00:01<03:51, 12.04it/s]
  1%|          | 24/2814 [00:01<03:36, 12.87it/s]
  1%|          | 26/2814 [00:02<03:39, 12.68it/s]
  1%|          | 28/2814 [00:02<03:46, 12.29it/s]
  1%|          | 30/2814 [00:02<03:48, 12.16it/s]
  1%|          | 32/2814 [00:02<03:38, 12.71it/s]
  1%|          | 34/2814 [00:02<03:36, 12.83it/s]
  1%|▏         | 36/2814 [00:02<03:38, 12.74it/s]
  1%|▏         | 38/2814 [00:03<03:46, 12.28it/s]
  1%|▏         | 40/2814 [00:03<03:52, 11.91it/s]
  1%|▏         | 42/2814 [00:03<03:46, 12.22it/s]
  2%|▏         | 44/2814 [00:03<03:50, 11.99it/s]
  2%|▏         | 46/2814 [00:03<03:53, 11.86it/s]
  2%|▏         | 48/2814 [00:03<03:52, 11.88it/s]
  2%|▏         | 50/2814 [00:04<03:50, 12.01it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.92it/s]
  2%|▏         | 54/2814 [00:04<03:51, 11.94it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.07it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.04it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.80it/s]
  2%|▏         | 62/2814 [00:05<03:29, 13.14it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.62it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.09it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.91it/s]
  2%|▏         | 70/2814 [00:05<03:55, 11.64it/s]
  3%|▎         | 72/2814 [00:05<03:55, 11.62it/s]
  3%|▎         | 74/2814 [00:06<03:49, 11.92it/s]
  3%|▎         | 76/2814 [00:06<03:51, 11.82it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.76it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.30it/s]
  3%|▎         | 82/2814 [00:06<03:47, 11.99it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.10it/s]
  3%|▎         | 86/2814 [00:07<03:44, 12.16it/s]
  3%|▎         | 88/2814 [00:07<03:43, 12.20it/s]
  3%|▎         | 90/2814 [00:07<03:44, 12.13it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.66it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.16it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.32it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.21it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.02it/s]
  4%|▎         | 102/2814 [00:08<03:41, 12.25it/s]
  4%|▎         | 104/2814 [00:08<03:30, 12.85it/s]
  4%|▍         | 106/2814 [00:08<03:38, 12.39it/s]
  4%|▍         | 108/2814 [00:08<03:40, 12.27it/s]
  4%|▍         | 110/2814 [00:09<03:32, 12.72it/s]
  4%|▍         | 112/2814 [00:09<03:39, 12.28it/s]
  4%|▍         | 114/2814 [00:09<03:42, 12.13it/s]
  4%|▍         | 116/2814 [00:09<03:36, 12.44it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.04it/s]
  4%|▍         | 120/2814 [00:09<03:37, 12.39it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.03it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.19it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.93it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.07it/s]
  5%|▍         | 130/2814 [00:10<03:44, 11.93it/s]
  5%|▍         | 132/2814 [00:10<03:34, 12.50it/s]
  5%|▍         | 134/2814 [00:11<03:32, 12.61it/s]
  5%|▍         | 136/2814 [00:11<03:34, 12.50it/s]
  5%|▍         | 138/2814 [00:11<03:35, 12.42it/s]
  5%|▍         | 140/2814 [00:11<03:39, 12.16it/s]
  5%|▌         | 142/2814 [00:11<03:34, 12.45it/s]
  5%|▌         | 144/2814 [00:11<03:39, 12.18it/s]
  5%|▌         | 146/2814 [00:12<03:39, 12.15it/s]
  5%|▌         | 148/2814 [00:12<03:41, 12.05it/s]
  5%|▌         | 150/2814 [00:12<03:35, 12.38it/s]
  5%|▌         | 152/2814 [00:12<03:40, 12.10it/s]
  5%|▌         | 154/2814 [00:12<03:43, 11.91it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.41it/s]
  6%|▌         | 158/2814 [00:12<03:34, 12.36it/s]
  6%|▌         | 160/2814 [00:13<03:41, 12.00it/s]
  6%|▌         | 162/2814 [00:13<03:38, 12.12it/s]
  6%|▌         | 164/2814 [00:13<03:39, 12.09it/s]
  6%|▌         | 166/2814 [00:13<03:37, 12.19it/s]
  6%|▌         | 168/2814 [00:13<03:33, 12.40it/s]
  6%|▌         | 170/2814 [00:13<03:37, 12.18it/s]
  6%|▌         | 172/2814 [00:14<03:40, 11.97it/s]
  6%|▌         | 174/2814 [00:14<03:34, 12.31it/s]
  6%|▋         | 176/2814 [00:14<03:30, 12.56it/s]
  6%|▋         | 178/2814 [00:14<03:22, 13.00it/s]
  6%|▋         | 180/2814 [00:14<03:31, 12.45it/s]
  6%|▋         | 182/2814 [00:14<03:33, 12.32it/s]
  7%|▋         | 184/2814 [00:15<03:38, 12.03it/s]
  7%|▋         | 186/2814 [00:15<03:41, 11.85it/s]
  7%|▋         | 188/2814 [00:15<03:37, 12.06it/s]
  7%|▋         | 190/2814 [00:15<03:39, 11.97it/s]
  7%|▋         | 192/2814 [00:15<03:37, 12.08it/s]
  7%|▋         | 194/2814 [00:15<03:39, 11.93it/s]
  7%|▋         | 196/2814 [00:16<03:41, 11.80it/s]
  7%|▋         | 198/2814 [00:16<03:39, 11.90it/s]
  7%|▋         | 200/2814 [00:16<03:38, 11.97it/s]
  7%|▋         | 202/2814 [00:16<03:40, 11.84it/s]
  7%|▋         | 204/2814 [00:16<03:41, 11.76it/s]
  7%|▋         | 206/2814 [00:16<03:46, 11.53it/s]
  7%|▋         | 208/2814 [00:17<03:29, 12.45it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.53it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 214/2814 [00:17<03:27, 12.50it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.52it/s]
  8%|▊         | 218/2814 [00:17<03:21, 12.86it/s]
  8%|▊         | 220/2814 [00:18<03:24, 12.71it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.90it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.43it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.09it/s]
  8%|▊         | 228/2814 [00:18<03:24, 12.67it/s]
  8%|▊         | 230/2814 [00:18<03:31, 12.23it/s]
  8%|▊         | 232/2814 [00:19<03:36, 11.93it/s]
  8%|▊         | 234/2814 [00:19<03:32, 12.14it/s]
  8%|▊         | 236/2814 [00:19<03:32, 12.11it/s]
  8%|▊         | 238/2814 [00:19<03:32, 12.10it/s]
  9%|▊         | 240/2814 [00:19<03:29, 12.31it/s]
  9%|▊         | 242/2814 [00:19<03:32, 12.08it/s]
  9%|▊         | 244/2814 [00:20<03:31, 12.12it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.31it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.80it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.56it/s]
  9%|▉         | 252/2814 [00:20<03:30, 12.17it/s]
  9%|▉         | 254/2814 [00:20<03:19, 12.82it/s]
  9%|▉         | 256/2814 [00:20<03:26, 12.40it/s]
  9%|▉         | 258/2814 [00:21<03:30, 12.13it/s]
  9%|▉         | 260/2814 [00:21<03:34, 11.88it/s]
  9%|▉         | 262/2814 [00:21<03:38, 11.66it/s]
  9%|▉         | 264/2814 [00:21<03:32, 11.99it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.77it/s]
 10%|▉         | 268/2814 [00:22<03:39, 11.62it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.98it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.25it/s]
 10%|▉         | 274/2814 [00:22<03:30, 12.05it/s]
 10%|▉         | 276/2814 [00:22<03:31, 11.99it/s]
 10%|▉         | 278/2814 [00:22<03:29, 12.08it/s]
 10%|▉         | 280/2814 [00:22<03:27, 12.24it/s]
 10%|█         | 282/2814 [00:23<03:30, 12.04it/s]
 10%|█         | 284/2814 [00:23<03:31, 11.95it/s]
 10%|█         | 286/2814 [00:23<03:25, 12.28it/s]
 10%|█         | 288/2814 [00:23<03:27, 12.16it/s]
 10%|█         | 290/2814 [00:23<03:28, 12.08it/s]
 10%|█         | 292/2814 [00:23<03:32, 11.87it/s]
 10%|█         | 294/2814 [00:24<03:34, 11.72it/s]
 11%|█         | 296/2814 [00:24<03:30, 11.98it/s]
 11%|█         | 298/2814 [00:24<03:33, 11.78it/s]
 11%|█         | 300/2814 [00:24<03:23, 12.38it/s]
 11%|█         | 302/2814 [00:24<03:29, 11.98it/s]
 11%|█         | 304/2814 [00:24<03:27, 12.11it/s]
 11%|█         | 306/2814 [00:25<03:29, 11.98it/s]
 11%|█         | 308/2814 [00:25<03:32, 11.82it/s]
 11%|█         | 310/2814 [00:25<03:26, 12.10it/s]
 11%|█         | 312/2814 [00:25<03:28, 11.99it/s]
 11%|█         | 314/2814 [00:25<03:26, 12.10it/s]
 11%|█         | 316/2814 [00:25<03:23, 12.27it/s]
 11%|█▏        | 318/2814 [00:26<03:27, 12.03it/s]
 11%|█▏        | 320/2814 [00:26<03:24, 12.17it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.57it/s]
 12%|█▏        | 324/2814 [00:26<03:24, 12.16it/s]
 12%|█▏        | 326/2814 [00:26<03:28, 11.95it/s]
 12%|█▏        | 328/2814 [00:26<03:20, 12.39it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.39it/s]
 12%|█▏        | 332/2814 [00:27<03:23, 12.18it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.02it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.35it/s]
 12%|█▏        | 338/2814 [00:27<03:25, 12.03it/s]
 12%|█▏        | 340/2814 [00:27<03:29, 11.80it/s]
 12%|█▏        | 342/2814 [00:28<03:32, 11.61it/s]
 12%|█▏        | 344/2814 [00:28<03:27, 11.92it/s]
 12%|█▏        | 346/2814 [00:28<03:24, 12.07it/s]
 12%|█▏        | 348/2814 [00:28<03:26, 11.95it/s]
 12%|█▏        | 350/2814 [00:28<03:23, 12.10it/s]
 13%|█▎        | 352/2814 [00:28<03:26, 11.94it/s]
 13%|█▎        | 354/2814 [00:29<03:28, 11.80it/s]
 13%|█▎        | 356/2814 [00:29<03:25, 11.99it/s]
 13%|█▎        | 358/2814 [00:29<03:27, 11.83it/s]
 13%|█▎        | 360/2814 [00:29<03:31, 11.61it/s]
 13%|█▎        | 362/2814 [00:29<03:25, 11.94it/s]
 13%|█▎        | 364/2814 [00:29<03:27, 11.83it/s]
 13%|█▎        | 366/2814 [00:30<03:29, 11.71it/s]
 13%|█▎        | 368/2814 [00:30<03:27, 11.78it/s]
 13%|█▎        | 370/2814 [00:30<03:30, 11.64it/s]
 13%|█▎        | 372/2814 [00:30<03:20, 12.19it/s]
 13%|█▎        | 374/2814 [00:30<03:24, 11.92it/s]
 13%|█▎        | 376/2814 [00:31<03:27, 11.76it/s]
 13%|█▎        | 378/2814 [00:31<03:27, 11.71it/s]
 14%|█▎        | 380/2814 [00:31<03:24, 11.91it/s]
 14%|█▎        | 382/2814 [00:31<03:26, 11.77it/s]
 14%|█▎        | 384/2814 [00:31<03:23, 11.95it/s]
 14%|█▎        | 386/2814 [00:31<03:26, 11.79it/s]
 14%|█▍        | 388/2814 [00:32<03:24, 11.88it/s]
 14%|█▍        | 390/2814 [00:32<03:26, 11.73it/s]
 14%|█▍        | 392/2814 [00:32<03:10, 12.68it/s]
 14%|█▍        | 394/2814 [00:32<03:18, 12.19it/s]
 14%|█▍        | 396/2814 [00:32<03:21, 11.99it/s]
 14%|█▍        | 398/2814 [00:32<03:19, 12.13it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.88it/s]
 14%|█▍        | 402/2814 [00:33<03:18, 12.17it/s]
 14%|█▍        | 404/2814 [00:33<03:20, 12.04it/s]
 14%|█▍        | 406/2814 [00:33<03:24, 11.79it/s]
 14%|█▍        | 408/2814 [00:33<03:16, 12.24it/s]
 15%|█▍        | 410/2814 [00:33<03:21, 11.95it/s]
 15%|█▍        | 412/2814 [00:34<03:19, 12.02it/s]
 15%|█▍        | 414/2814 [00:34<03:23, 11.81it/s]
 15%|█▍        | 416/2814 [00:34<03:11, 12.50it/s]
 15%|█▍        | 418/2814 [00:34<03:12, 12.46it/s]
 15%|█▍        | 420/2814 [00:34<03:14, 12.29it/s]
 15%|█▍        | 422/2814 [00:34<03:11, 12.46it/s]
 15%|█▌        | 424/2814 [00:34<03:16, 12.19it/s]
 15%|█▌        | 426/2814 [00:35<03:12, 12.38it/s]
 15%|█▌        | 428/2814 [00:35<03:14, 12.29it/s]
 15%|█▌        | 430/2814 [00:35<03:09, 12.61it/s]
 15%|█▌        | 432/2814 [00:35<03:14, 12.22it/s]
 15%|█▌        | 434/2814 [00:35<03:10, 12.51it/s]
 15%|█▌        | 436/2814 [00:35<03:10, 12.45it/s]
 16%|█▌        | 438/2814 [00:36<03:13, 12.25it/s]
 16%|█▌        | 440/2814 [00:36<03:16, 12.06it/s]
 16%|█▌        | 442/2814 [00:36<03:19, 11.89it/s]
 16%|█▌        | 444/2814 [00:36<03:13, 12.24it/s]
 16%|█▌        | 446/2814 [00:36<03:15, 12.09it/s]
 16%|█▌        | 448/2814 [00:36<03:21, 11.76it/s]
 16%|█▌        | 450/2814 [00:37<03:08, 12.54it/s]
 16%|█▌        | 452/2814 [00:37<03:06, 12.65it/s]
 16%|█▌        | 454/2814 [00:37<03:12, 12.26it/s]
 16%|█▌        | 456/2814 [00:37<03:08, 12.50it/s]
 16%|█▋        | 458/2814 [00:37<03:03, 12.86it/s]
 16%|█▋        | 460/2814 [00:37<03:11, 12.28it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.97it/s]
 16%|█▋        | 464/2814 [00:38<03:18, 11.87it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.26it/s]
 17%|█▋        | 468/2814 [00:38<03:11, 12.28it/s]
 17%|█▋        | 470/2814 [00:38<03:14, 12.07it/s]
 17%|█▋        | 472/2814 [00:38<03:09, 12.33it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.53it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 12.00it/s]
 17%|█▋        | 480/2814 [00:39<03:15, 11.95it/s]
 17%|█▋        | 482/2814 [00:39<03:14, 11.96it/s]
 17%|█▋        | 484/2814 [00:39<03:16, 11.86it/s]
 17%|█▋        | 486/2814 [00:40<03:19, 11.68it/s]
 17%|█▋        | 488/2814 [00:40<03:19, 11.64it/s]
 17%|█▋        | 490/2814 [00:40<03:13, 11.98it/s]
 17%|█▋        | 492/2814 [00:40<03:15, 11.86it/s]
 18%|█▊        | 494/2814 [00:40<03:16, 11.83it/s]
 18%|█▊        | 496/2814 [00:40<03:07, 12.37it/s]
 18%|█▊        | 498/2814 [00:41<03:11, 12.11it/s]
 18%|█▊        | 500/2814 [00:41<03:09, 12.24it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.42it/s]
 18%|█▊        | 504/2814 [00:41<03:02, 12.66it/s]
 18%|█▊        | 506/2814 [00:41<03:07, 12.32it/s]
 18%|█▊        | 508/2814 [00:41<03:04, 12.47it/s]
 18%|█▊        | 510/2814 [00:41<02:57, 12.98it/s]
 18%|█▊        | 512/2814 [00:42<03:03, 12.57it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.67it/s]
 18%|█▊        | 516/2814 [00:42<03:06, 12.30it/s]
 18%|█▊        | 518/2814 [00:42<03:03, 12.52it/s]
 18%|█▊        | 520/2814 [00:42<03:08, 12.19it/s]
 19%|█▊        | 522/2814 [00:42<03:12, 11.91it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.32it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.67it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.32it/s]
 19%|█▉        | 530/2814 [00:43<03:08, 12.11it/s]
 19%|█▉        | 532/2814 [00:43<03:07, 12.17it/s]
 19%|█▉        | 534/2814 [00:43<03:01, 12.54it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.15it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.01it/s]
 19%|█▉        | 540/2814 [00:44<03:13, 11.75it/s]
 19%|█▉        | 542/2814 [00:44<03:12, 11.79it/s]
 19%|█▉        | 544/2814 [00:44<03:02, 12.43it/s]
 19%|█▉        | 546/2814 [00:44<03:01, 12.48it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.16it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.52it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.33it/s]
 20%|█▉        | 554/2814 [00:45<03:04, 12.26it/s]
 20%|█▉        | 556/2814 [00:45<02:57, 12.72it/s]
 20%|█▉        | 558/2814 [00:45<03:00, 12.50it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.49it/s]
 20%|█▉        | 562/2814 [00:46<03:06, 12.05it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.95it/s]
 20%|██        | 566/2814 [00:46<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:46<03:02, 12.32it/s]
 20%|██        | 570/2814 [00:46<03:06, 12.00it/s]
 20%|██        | 572/2814 [00:47<03:10, 11.80it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.02it/s]
 20%|██        | 576/2814 [00:47<02:57, 12.63it/s]
 21%|██        | 578/2814 [00:47<02:57, 12.58it/s]
 21%|██        | 580/2814 [00:47<03:04, 12.12it/s]
 21%|██        | 582/2814 [00:47<02:55, 12.72it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.49it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.27it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.63it/s]
 21%|██        | 590/2814 [00:48<02:59, 12.39it/s]
 21%|██        | 592/2814 [00:48<02:57, 12.50it/s]
 21%|██        | 594/2814 [00:48<03:02, 12.19it/s]
 21%|██        | 596/2814 [00:49<03:05, 11.97it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.75it/s]
 21%|██▏       | 600/2814 [00:49<02:51, 12.91it/s]
 21%|██▏       | 602/2814 [00:49<02:47, 13.18it/s]
 21%|██▏       | 604/2814 [00:49<02:50, 13.00it/s]
 22%|██▏       | 606/2814 [00:49<02:54, 12.69it/s]
 22%|██▏       | 608/2814 [00:49<02:53, 12.69it/s]
 22%|██▏       | 610/2814 [00:50<02:48, 13.06it/s]
 22%|██▏       | 612/2814 [00:50<02:56, 12.50it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.04it/s]
 22%|██▏       | 616/2814 [00:50<03:05, 11.83it/s]
 22%|██▏       | 618/2814 [00:50<03:01, 12.13it/s]
 22%|██▏       | 620/2814 [00:50<03:00, 12.18it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.10it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.20it/s]
 22%|██▏       | 626/2814 [00:51<02:59, 12.16it/s]
 22%|██▏       | 628/2814 [00:51<02:51, 12.73it/s]
 22%|██▏       | 630/2814 [00:51<02:53, 12.62it/s]
 22%|██▏       | 632/2814 [00:51<02:52, 12.67it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.21it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.94it/s]
 23%|██▎       | 638/2814 [00:52<03:05, 11.76it/s]
 23%|██▎       | 640/2814 [00:52<03:06, 11.67it/s]
 23%|██▎       | 642/2814 [00:52<03:02, 11.91it/s]
 23%|██▎       | 644/2814 [00:52<02:52, 12.61it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.12it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.98it/s]
 23%|██▎       | 650/2814 [00:53<02:56, 12.24it/s]
 23%|██▎       | 652/2814 [00:53<03:01, 11.90it/s]
 23%|██▎       | 654/2814 [00:53<03:02, 11.83it/s]
 23%|██▎       | 656/2814 [00:53<02:54, 12.35it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.30it/s]
 23%|██▎       | 660/2814 [00:54<02:53, 12.39it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.36it/s]
 24%|██▎       | 664/2814 [00:54<02:57, 12.12it/s]
 24%|██▎       | 666/2814 [00:54<02:55, 12.24it/s]
 24%|██▎       | 668/2814 [00:54<02:58, 12.05it/s]
 24%|██▍       | 670/2814 [00:55<03:02, 11.78it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.04it/s]
 24%|██▍       | 674/2814 [00:55<02:55, 12.17it/s]
 24%|██▍       | 676/2814 [00:55<02:53, 12.29it/s]
 24%|██▍       | 678/2814 [00:55<02:53, 12.31it/s]
 24%|██▍       | 680/2814 [00:55<02:55, 12.15it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.10it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.76it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.91it/s]
 24%|██▍       | 688/2814 [00:56<02:56, 12.03it/s]
 25%|██▍       | 690/2814 [00:56<02:57, 11.98it/s]
 25%|██▍       | 692/2814 [00:56<03:01, 11.71it/s]
 25%|██▍       | 694/2814 [00:57<02:53, 12.25it/s]
 25%|██▍       | 696/2814 [00:57<02:53, 12.23it/s]
 25%|██▍       | 698/2814 [00:57<02:49, 12.46it/s]
 25%|██▍       | 700/2814 [00:57<02:49, 12.48it/s]
 25%|██▍       | 702/2814 [00:57<02:49, 12.48it/s]
 25%|██▌       | 704/2814 [00:57<02:53, 12.16it/s]
 25%|██▌       | 706/2814 [00:57<02:47, 12.57it/s]
 25%|██▌       | 708/2814 [00:58<02:43, 12.85it/s]
 25%|██▌       | 710/2814 [00:58<02:50, 12.37it/s]
 25%|██▌       | 712/2814 [00:58<02:52, 12.16it/s]
 25%|██▌       | 714/2814 [00:58<02:51, 12.23it/s]
 25%|██▌       | 716/2814 [00:58<02:50, 12.29it/s]
 26%|██▌       | 718/2814 [00:58<02:52, 12.18it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 724/2814 [00:59<02:51, 12.21it/s]
 26%|██▌       | 726/2814 [00:59<02:42, 12.81it/s]
 26%|██▌       | 728/2814 [00:59<02:50, 12.24it/s]
 26%|██▌       | 730/2814 [00:59<02:47, 12.47it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.44it/s]
 26%|██▌       | 734/2814 [01:00<02:51, 12.16it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.25it/s]
 26%|██▌       | 738/2814 [01:00<02:52, 12.07it/s]
 26%|██▋       | 740/2814 [01:00<02:47, 12.38it/s]
 26%|██▋       | 742/2814 [01:00<02:47, 12.40it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.63it/s]
 27%|██▋       | 746/2814 [01:01<02:48, 12.31it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.29it/s]
 27%|██▋       | 750/2814 [01:01<02:52, 11.94it/s]
 27%|██▋       | 752/2814 [01:01<02:52, 11.96it/s]
 27%|██▋       | 754/2814 [01:01<02:53, 11.85it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.06it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.93it/s]
 27%|██▋       | 760/2814 [01:02<02:49, 12.15it/s]
 27%|██▋       | 762/2814 [01:02<02:48, 12.17it/s]
 27%|██▋       | 764/2814 [01:02<02:44, 12.45it/s]
 27%|██▋       | 766/2814 [01:02<02:45, 12.36it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.11it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.92it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.80it/s]
 28%|██▊       | 774/2814 [01:03<02:46, 12.26it/s]
 28%|██▊       | 776/2814 [01:03<02:43, 12.45it/s]
 28%|██▊       | 778/2814 [01:03<02:45, 12.31it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.30it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.12it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 11.99it/s]
 28%|██▊       | 786/2814 [01:04<02:46, 12.14it/s]
 28%|██▊       | 788/2814 [01:04<02:46, 12.14it/s]
 28%|██▊       | 790/2814 [01:04<02:45, 12.22it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.29it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.12it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.51it/s]
 28%|██▊       | 798/2814 [01:05<02:44, 12.25it/s]
 28%|██▊       | 800/2814 [01:05<02:46, 12.09it/s]
 29%|██▊       | 802/2814 [01:05<02:48, 11.94it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.01it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.16it/s]
 29%|██▊       | 808/2814 [01:06<02:46, 12.02it/s]
 29%|██▉       | 810/2814 [01:06<02:43, 12.23it/s]
 29%|██▉       | 812/2814 [01:06<02:38, 12.61it/s]
 29%|██▉       | 814/2814 [01:06<02:41, 12.37it/s]
 29%|██▉       | 816/2814 [01:06<02:40, 12.48it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.65it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.51it/s]
 29%|██▉       | 822/2814 [01:07<02:44, 12.13it/s]
 29%|██▉       | 824/2814 [01:07<02:40, 12.42it/s]
 29%|██▉       | 826/2814 [01:07<02:43, 12.20it/s]
 29%|██▉       | 828/2814 [01:07<02:45, 12.00it/s]
 29%|██▉       | 830/2814 [01:08<02:44, 12.10it/s]
 30%|██▉       | 832/2814 [01:08<02:46, 11.94it/s]
 30%|██▉       | 834/2814 [01:08<02:49, 11.71it/s]
 30%|██▉       | 836/2814 [01:08<02:42, 12.17it/s]
 30%|██▉       | 838/2814 [01:08<02:41, 12.23it/s]
 30%|██▉       | 840/2814 [01:08<02:45, 11.94it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.84it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.75it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.13it/s]
 30%|███       | 848/2814 [01:09<02:37, 12.51it/s]
 30%|███       | 850/2814 [01:09<02:41, 12.19it/s]
 30%|███       | 852/2814 [01:09<02:41, 12.17it/s]
 30%|███       | 854/2814 [01:10<02:42, 12.08it/s]
 30%|███       | 856/2814 [01:10<02:44, 11.87it/s]
 30%|███       | 858/2814 [01:10<02:46, 11.76it/s]
 31%|███       | 860/2814 [01:10<02:43, 11.92it/s]
 31%|███       | 862/2814 [01:10<02:43, 11.90it/s]
 31%|███       | 864/2814 [01:10<02:39, 12.20it/s]
 31%|███       | 866/2814 [01:11<02:35, 12.56it/s]
 31%|███       | 868/2814 [01:11<02:34, 12.61it/s]
 31%|███       | 870/2814 [01:11<02:39, 12.23it/s]
 31%|███       | 872/2814 [01:11<02:39, 12.18it/s]
 31%|███       | 874/2814 [01:11<02:38, 12.26it/s]
 31%|███       | 876/2814 [01:11<02:41, 12.00it/s]
 31%|███       | 878/2814 [01:12<02:38, 12.24it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.06it/s]
 31%|███▏      | 882/2814 [01:12<02:41, 11.94it/s]
 31%|███▏      | 884/2814 [01:12<02:41, 11.93it/s]
 31%|███▏      | 886/2814 [01:12<02:42, 11.88it/s]
 32%|███▏      | 888/2814 [01:12<02:44, 11.69it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.89it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.60it/s]
 32%|███▏      | 896/2814 [01:13<02:41, 11.84it/s]
 32%|███▏      | 898/2814 [01:13<02:34, 12.36it/s]
 32%|███▏      | 900/2814 [01:13<02:34, 12.40it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.80it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.68it/s]
 32%|███▏      | 906/2814 [01:14<02:27, 12.89it/s]
 32%|███▏      | 908/2814 [01:14<02:33, 12.44it/s]
 32%|███▏      | 910/2814 [01:14<02:35, 12.22it/s]
 32%|███▏      | 912/2814 [01:14<02:38, 12.00it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.29it/s]
 33%|███▎      | 916/2814 [01:15<02:37, 12.07it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.02it/s]
 33%|███▎      | 920/2814 [01:15<02:36, 12.13it/s]
 33%|███▎      | 922/2814 [01:15<02:35, 12.18it/s]
 33%|███▎      | 924/2814 [01:15<02:39, 11.83it/s]
 33%|███▎      | 926/2814 [01:16<02:28, 12.68it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.79it/s]
 33%|███▎      | 930/2814 [01:16<02:31, 12.41it/s]
 33%|███▎      | 932/2814 [01:16<02:35, 12.11it/s]
 33%|███▎      | 934/2814 [01:16<02:36, 11.99it/s]
 33%|███▎      | 936/2814 [01:16<02:37, 11.93it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.49it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.49it/s]{'loss': 0.8198, 'learning_rate': 8.861705573181426e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.49it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.46it/s]

 21%|██        | 66/313 [00:00<00:01, 205.87it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.07it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.43it/s]

 40%|████      | 126/313 [00:00<00:01, 185.26it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.11it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.05it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.89it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.04it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.27it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.07it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.55it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.22it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.26it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.26it/s]
 33%|███▎      | 938/2814 [01:18<02:30, 12.49it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 940/2814 [01:19<14:54,  2.10it/s]
 33%|███▎      | 942/2814 [01:20<11:13,  2.78it/s]
 34%|███▎      | 944/2814 [01:20<08:38,  3.61it/s]
 34%|███▎      | 946/2814 [01:20<06:50,  4.55it/s]
 34%|███▎      | 948/2814 [01:20<05:34,  5.58it/s]
 34%|███▍      | 950/2814 [01:20<04:37,  6.72it/s]
 34%|███▍      | 952/2814 [01:20<03:56,  7.88it/s]
 34%|███▍      | 954/2814 [01:21<03:33,  8.70it/s]
 34%|███▍      | 956/2814 [01:21<03:18,  9.35it/s]
 34%|███▍      | 958/2814 [01:21<03:06,  9.95it/s]
 34%|███▍      | 960/2814 [01:21<02:52, 10.74it/s]
 34%|███▍      | 962/2814 [01:21<02:46, 11.10it/s]
 34%|███▍      | 964/2814 [01:21<02:45, 11.15it/s]
 34%|███▍      | 966/2814 [01:22<02:37, 11.72it/s]
 34%|███▍      | 968/2814 [01:22<02:33, 12.06it/s]
 34%|███▍      | 970/2814 [01:22<02:34, 11.90it/s]
 35%|███▍      | 972/2814 [01:22<02:32, 12.08it/s]
 35%|███▍      | 974/2814 [01:22<02:33, 11.96it/s]
 35%|███▍      | 976/2814 [01:22<02:33, 12.01it/s]
 35%|███▍      | 978/2814 [01:22<02:34, 11.90it/s]
 35%|███▍      | 980/2814 [01:23<02:35, 11.82it/s]
 35%|███▍      | 982/2814 [01:23<02:35, 11.79it/s]
 35%|███▍      | 984/2814 [01:23<02:33, 11.93it/s]
 35%|███▌      | 986/2814 [01:23<02:35, 11.79it/s]
 35%|███▌      | 988/2814 [01:23<02:26, 12.49it/s]
 35%|███▌      | 990/2814 [01:23<02:26, 12.46it/s]
 35%|███▌      | 992/2814 [01:24<02:29, 12.18it/s]
 35%|███▌      | 994/2814 [01:24<02:28, 12.28it/s]
 35%|███▌      | 996/2814 [01:24<02:29, 12.13it/s]
 35%|███▌      | 998/2814 [01:24<02:31, 11.96it/s]
 36%|███▌      | 1000/2814 [01:24<02:26, 12.41it/s]
 36%|███▌      | 1002/2814 [01:24<02:24, 12.51it/s]
 36%|███▌      | 1004/2814 [01:25<02:24, 12.56it/s]
 36%|███▌      | 1006/2814 [01:25<02:24, 12.51it/s]
 36%|███▌      | 1008/2814 [01:25<02:23, 12.58it/s]
 36%|███▌      | 1010/2814 [01:25<02:21, 12.75it/s]
 36%|███▌      | 1012/2814 [01:25<02:25, 12.41it/s]
 36%|███▌      | 1014/2814 [01:25<02:29, 12.01it/s]
 36%|███▌      | 1016/2814 [01:26<02:30, 11.98it/s]
 36%|███▌      | 1018/2814 [01:26<02:27, 12.20it/s]
 36%|███▌      | 1020/2814 [01:26<02:28, 12.06it/s]
 36%|███▋      | 1022/2814 [01:26<02:31, 11.82it/s]
 36%|███▋      | 1024/2814 [01:26<02:34, 11.60it/s]
 36%|███▋      | 1026/2814 [01:26<02:31, 11.84it/s]
 37%|███▋      | 1028/2814 [01:27<02:30, 11.90it/s]
 37%|███▋      | 1030/2814 [01:27<02:26, 12.14it/s]
 37%|███▋      | 1032/2814 [01:27<02:24, 12.30it/s]
 37%|███▋      | 1034/2814 [01:27<02:24, 12.35it/s]
 37%|███▋      | 1036/2814 [01:27<02:28, 11.94it/s]
 37%|███▋      | 1038/2814 [01:27<02:30, 11.82it/s]
 37%|███▋      | 1040/2814 [01:28<02:27, 11.99it/s]
 37%|███▋      | 1042/2814 [01:28<02:28, 11.92it/s]
 37%|███▋      | 1044/2814 [01:28<02:31, 11.70it/s]
 37%|███▋      | 1046/2814 [01:28<02:33, 11.54it/s]
 37%|███▋      | 1048/2814 [01:28<02:28, 11.91it/s]
 37%|███▋      | 1050/2814 [01:28<02:18, 12.69it/s]
 37%|███▋      | 1052/2814 [01:29<03:22,  8.72it/s]
 37%|███▋      | 1054/2814 [01:29<02:58,  9.83it/s]
 38%|███▊      | 1056/2814 [01:29<02:50, 10.34it/s]
 38%|███▊      | 1058/2814 [01:29<02:40, 10.92it/s]
 38%|███▊      | 1060/2814 [01:29<02:34, 11.32it/s]
 38%|███▊      | 1062/2814 [01:30<02:34, 11.36it/s]
 38%|███▊      | 1064/2814 [01:30<02:33, 11.40it/s]
 38%|███▊      | 1066/2814 [01:30<02:34, 11.34it/s]
 38%|███▊      | 1068/2814 [01:30<02:29, 11.70it/s]
 38%|███▊      | 1070/2814 [01:30<02:29, 11.68it/s]
 38%|███▊      | 1072/2814 [01:30<02:29, 11.67it/s]
 38%|███▊      | 1074/2814 [01:31<02:30, 11.58it/s]
 38%|███▊      | 1076/2814 [01:31<02:30, 11.58it/s]
 38%|███▊      | 1078/2814 [01:31<02:26, 11.89it/s]
 38%|███▊      | 1080/2814 [01:31<02:27, 11.79it/s]
 38%|███▊      | 1082/2814 [01:31<02:26, 11.79it/s]
 39%|███▊      | 1084/2814 [01:31<02:21, 12.22it/s]
 39%|███▊      | 1086/2814 [01:32<02:16, 12.69it/s]
 39%|███▊      | 1088/2814 [01:32<02:18, 12.50it/s]
 39%|███▊      | 1090/2814 [01:32<02:18, 12.40it/s]
 39%|███▉      | 1092/2814 [01:32<02:23, 12.03it/s]
 39%|███▉      | 1094/2814 [01:32<02:19, 12.33it/s]
 39%|███▉      | 1096/2814 [01:32<02:14, 12.81it/s]
 39%|███▉      | 1098/2814 [01:33<02:10, 13.15it/s]
 39%|███▉      | 1100/2814 [01:33<02:14, 12.72it/s]
 39%|███▉      | 1102/2814 [01:33<02:18, 12.37it/s]
 39%|███▉      | 1104/2814 [01:33<02:17, 12.41it/s]
 39%|███▉      | 1106/2814 [01:33<02:16, 12.48it/s]
 39%|███▉      | 1108/2814 [01:33<02:15, 12.63it/s]
 39%|███▉      | 1110/2814 [01:34<02:19, 12.20it/s]
 40%|███▉      | 1112/2814 [01:34<02:22, 11.98it/s]
 40%|███▉      | 1114/2814 [01:34<02:24, 11.76it/s]
 40%|███▉      | 1116/2814 [01:34<02:25, 11.67it/s]
 40%|███▉      | 1118/2814 [01:34<02:25, 11.62it/s]
 40%|███▉      | 1120/2814 [01:34<02:24, 11.75it/s]
 40%|███▉      | 1122/2814 [01:35<02:23, 11.82it/s]
 40%|███▉      | 1124/2814 [01:35<02:23, 11.76it/s]
 40%|████      | 1126/2814 [01:35<02:20, 11.99it/s]
 40%|████      | 1128/2814 [01:35<02:21, 11.88it/s]
 40%|████      | 1130/2814 [01:35<02:24, 11.64it/s]
 40%|████      | 1132/2814 [01:35<02:18, 12.11it/s]
 40%|████      | 1134/2814 [01:36<02:18, 12.16it/s]
 40%|████      | 1136/2814 [01:36<02:19, 12.04it/s]
 40%|████      | 1138/2814 [01:36<02:16, 12.32it/s]
 41%|████      | 1140/2814 [01:36<02:18, 12.08it/s]
 41%|████      | 1142/2814 [01:36<02:21, 11.82it/s]
 41%|████      | 1144/2814 [01:36<02:21, 11.82it/s]
 41%|████      | 1146/2814 [01:37<02:16, 12.19it/s]
 41%|████      | 1148/2814 [01:37<02:19, 11.98it/s]
 41%|████      | 1150/2814 [01:37<02:21, 11.76it/s]
 41%|████      | 1152/2814 [01:37<02:21, 11.73it/s]
 41%|████      | 1154/2814 [01:37<02:20, 11.83it/s]
 41%|████      | 1156/2814 [01:37<02:16, 12.16it/s]
 41%|████      | 1158/2814 [01:38<02:16, 12.15it/s]
 41%|████      | 1160/2814 [01:38<02:10, 12.68it/s]
 41%|████▏     | 1162/2814 [01:38<02:11, 12.54it/s]
 41%|████▏     | 1164/2814 [01:38<02:14, 12.29it/s]
 41%|████▏     | 1166/2814 [01:38<02:14, 12.28it/s]
 42%|████▏     | 1168/2814 [01:38<02:14, 12.20it/s]
 42%|████▏     | 1170/2814 [01:39<02:17, 11.94it/s]
 42%|████▏     | 1172/2814 [01:39<02:19, 11.74it/s]
 42%|████▏     | 1174/2814 [01:39<02:18, 11.85it/s]
 42%|████▏     | 1176/2814 [01:39<02:20, 11.62it/s]
 42%|████▏     | 1178/2814 [01:39<02:22, 11.48it/s]
 42%|████▏     | 1180/2814 [01:39<02:20, 11.60it/s]
 42%|████▏     | 1182/2814 [01:40<02:16, 11.92it/s]
 42%|████▏     | 1184/2814 [01:40<02:15, 12.07it/s]
 42%|████▏     | 1186/2814 [01:40<02:11, 12.42it/s]
 42%|████▏     | 1188/2814 [01:40<02:10, 12.46it/s]
 42%|████▏     | 1190/2814 [01:40<02:11, 12.32it/s]
 42%|████▏     | 1192/2814 [01:40<02:14, 12.08it/s]
 42%|████▏     | 1194/2814 [01:41<02:08, 12.66it/s]
 43%|████▎     | 1196/2814 [01:41<02:05, 12.91it/s]
 43%|████▎     | 1198/2814 [01:41<02:08, 12.55it/s]
 43%|████▎     | 1200/2814 [01:41<02:06, 12.79it/s]
 43%|████▎     | 1202/2814 [01:41<02:09, 12.43it/s]
 43%|████▎     | 1204/2814 [01:41<02:12, 12.11it/s]
 43%|████▎     | 1206/2814 [01:42<02:11, 12.20it/s]
 43%|████▎     | 1208/2814 [01:42<02:13, 11.99it/s]
 43%|████▎     | 1210/2814 [01:42<02:12, 12.07it/s]
 43%|████▎     | 1212/2814 [01:42<02:11, 12.20it/s]
 43%|████▎     | 1214/2814 [01:42<02:12, 12.10it/s]
 43%|████▎     | 1216/2814 [01:42<02:07, 12.49it/s]
 43%|████▎     | 1218/2814 [01:42<02:01, 13.08it/s]
 43%|████▎     | 1220/2814 [01:43<02:01, 13.11it/s]
 43%|████▎     | 1222/2814 [01:43<02:07, 12.50it/s]
 43%|████▎     | 1224/2814 [01:43<02:10, 12.22it/s]
 44%|████▎     | 1226/2814 [01:43<02:05, 12.70it/s]
 44%|████▎     | 1228/2814 [01:43<02:09, 12.23it/s]
 44%|████▎     | 1230/2814 [01:43<02:09, 12.24it/s]
 44%|████▍     | 1232/2814 [01:44<02:08, 12.35it/s]
 44%|████▍     | 1234/2814 [01:44<02:07, 12.41it/s]
 44%|████▍     | 1236/2814 [01:44<02:09, 12.15it/s]
 44%|████▍     | 1238/2814 [01:44<02:09, 12.21it/s]
 44%|████▍     | 1240/2814 [01:44<02:12, 11.92it/s]
 44%|████▍     | 1242/2814 [01:44<02:04, 12.62it/s]
 44%|████▍     | 1244/2814 [01:45<02:07, 12.29it/s]
 44%|████▍     | 1246/2814 [01:45<02:09, 12.09it/s]
 44%|████▍     | 1248/2814 [01:45<02:12, 11.80it/s]
 44%|████▍     | 1250/2814 [01:45<02:13, 11.71it/s]
 44%|████▍     | 1252/2814 [01:45<02:08, 12.11it/s]
 45%|████▍     | 1254/2814 [01:45<02:01, 12.81it/s]
 45%|████▍     | 1256/2814 [01:46<02:04, 12.47it/s]
 45%|████▍     | 1258/2814 [01:46<02:01, 12.84it/s]
 45%|████▍     | 1260/2814 [01:46<02:00, 12.93it/s]
 45%|████▍     | 1262/2814 [01:46<02:05, 12.41it/s]
 45%|████▍     | 1264/2814 [01:46<02:02, 12.69it/s]
 45%|████▍     | 1266/2814 [01:46<02:05, 12.34it/s]
 45%|████▌     | 1268/2814 [01:47<02:08, 12.06it/s]
 45%|████▌     | 1270/2814 [01:47<02:09, 11.88it/s]
 45%|████▌     | 1272/2814 [01:47<02:07, 12.14it/s]
 45%|████▌     | 1274/2814 [01:47<02:06, 12.15it/s]
 45%|████▌     | 1276/2814 [01:47<02:08, 11.93it/s]
 45%|████▌     | 1278/2814 [01:47<02:10, 11.82it/s]
 45%|████▌     | 1280/2814 [01:48<02:10, 11.74it/s]
 46%|████▌     | 1282/2814 [01:48<02:10, 11.78it/s]
 46%|████▌     | 1284/2814 [01:48<02:08, 11.86it/s]
 46%|████▌     | 1286/2814 [01:48<02:03, 12.33it/s]
 46%|████▌     | 1288/2814 [01:48<02:05, 12.15it/s]
 46%|████▌     | 1290/2814 [01:48<02:07, 11.95it/s]
 46%|████▌     | 1292/2814 [01:49<02:09, 11.74it/s]
 46%|████▌     | 1294/2814 [01:49<02:08, 11.81it/s]
 46%|████▌     | 1296/2814 [01:49<02:06, 11.97it/s]
 46%|████▌     | 1298/2814 [01:49<02:05, 12.11it/s]
 46%|████▌     | 1300/2814 [01:49<02:05, 12.04it/s]
 46%|████▋     | 1302/2814 [01:49<02:07, 11.91it/s]
 46%|████▋     | 1304/2814 [01:50<02:09, 11.62it/s]
 46%|████▋     | 1306/2814 [01:50<02:10, 11.56it/s]
 46%|████▋     | 1308/2814 [01:50<02:06, 11.89it/s]
 47%|████▋     | 1310/2814 [01:50<02:08, 11.71it/s]
 47%|████▋     | 1312/2814 [01:50<02:07, 11.82it/s]
 47%|████▋     | 1314/2814 [01:50<02:07, 11.77it/s]
 47%|████▋     | 1316/2814 [01:51<02:05, 11.95it/s]
 47%|████▋     | 1318/2814 [01:51<02:04, 11.98it/s]
 47%|████▋     | 1320/2814 [01:51<02:07, 11.75it/s]
 47%|████▋     | 1322/2814 [01:51<01:59, 12.49it/s]
 47%|████▋     | 1324/2814 [01:51<02:01, 12.25it/s]
 47%|████▋     | 1326/2814 [01:51<02:03, 12.06it/s]
 47%|████▋     | 1328/2814 [01:52<02:05, 11.87it/s]
 47%|████▋     | 1330/2814 [01:52<01:58, 12.49it/s]
 47%|████▋     | 1332/2814 [01:52<01:57, 12.63it/s]
 47%|████▋     | 1334/2814 [01:52<01:58, 12.48it/s]
 47%|████▋     | 1336/2814 [01:52<01:56, 12.69it/s]
 48%|████▊     | 1338/2814 [01:52<01:57, 12.53it/s]
 48%|████▊     | 1340/2814 [01:53<02:00, 12.21it/s]
 48%|████▊     | 1342/2814 [01:53<01:57, 12.48it/s]
 48%|████▊     | 1344/2814 [01:53<02:00, 12.15it/s]
 48%|████▊     | 1346/2814 [01:53<02:00, 12.18it/s]
 48%|████▊     | 1348/2814 [01:53<01:58, 12.42it/s]
 48%|████▊     | 1350/2814 [01:53<01:52, 12.97it/s]
 48%|████▊     | 1352/2814 [01:53<01:53, 12.93it/s]
 48%|████▊     | 1354/2814 [01:54<01:58, 12.36it/s]
 48%|████▊     | 1356/2814 [01:54<01:58, 12.29it/s]
 48%|████▊     | 1358/2814 [01:54<02:37,  9.26it/s]
 48%|████▊     | 1360/2814 [01:54<02:28,  9.81it/s]
 48%|████▊     | 1362/2814 [01:55<02:22, 10.20it/s]
 48%|████▊     | 1364/2814 [01:55<02:14, 10.74it/s]
 49%|████▊     | 1366/2814 [01:55<02:06, 11.41it/s]
 49%|████▊     | 1368/2814 [01:55<02:06, 11.44it/s]
 49%|████▊     | 1370/2814 [01:55<02:06, 11.45it/s]
 49%|████▉     | 1372/2814 [01:55<02:07, 11.35it/s]
 49%|████▉     | 1374/2814 [01:56<02:03, 11.63it/s]
 49%|████▉     | 1376/2814 [01:56<01:59, 12.08it/s]
 49%|████▉     | 1378/2814 [01:56<01:58, 12.15it/s]
 49%|████▉     | 1380/2814 [01:56<01:59, 11.96it/s]
 49%|████▉     | 1382/2814 [01:56<01:57, 12.15it/s]
 49%|████▉     | 1384/2814 [01:56<01:56, 12.24it/s]
 49%|████▉     | 1386/2814 [01:56<01:56, 12.21it/s]
 49%|████▉     | 1388/2814 [01:57<01:59, 11.97it/s]
 49%|████▉     | 1390/2814 [01:57<02:00, 11.80it/s]
 49%|████▉     | 1392/2814 [01:57<02:00, 11.78it/s]
 50%|████▉     | 1394/2814 [01:57<01:59, 11.85it/s]
 50%|████▉     | 1396/2814 [01:57<01:58, 11.98it/s]
 50%|████▉     | 1398/2814 [01:57<01:59, 11.85it/s]
 50%|████▉     | 1400/2814 [01:58<02:00, 11.75it/s]
 50%|████▉     | 1402/2814 [01:58<02:01, 11.58it/s]
 50%|████▉     | 1404/2814 [01:58<01:59, 11.76it/s]
 50%|████▉     | 1406/2814 [01:58<01:58, 11.85it/s]
 50%|█████     | 1408/2814 [01:58<01:57, 11.96it/s]
 50%|█████     | 1410/2814 [01:59<01:56, 12.06it/s]
 50%|█████     | 1412/2814 [01:59<01:57, 11.92it/s]
 50%|█████     | 1414/2814 [01:59<01:54, 12.18it/s]
 50%|█████     | 1416/2814 [01:59<01:56, 12.03it/s]
 50%|█████     | 1418/2814 [01:59<01:59, 11.71it/s]
 50%|█████     | 1420/2814 [01:59<01:53, 12.33it/s]
 51%|█████     | 1422/2814 [01:59<01:52, 12.39it/s]
 51%|█████     | 1424/2814 [02:00<01:54, 12.16it/s]
 51%|█████     | 1426/2814 [02:00<01:55, 11.98it/s]
 51%|█████     | 1428/2814 [02:00<01:54, 12.07it/s]
 51%|█████     | 1430/2814 [02:00<01:57, 11.82it/s]
 51%|█████     | 1432/2814 [02:00<01:55, 11.95it/s]
 51%|█████     | 1434/2814 [02:00<01:52, 12.27it/s]
 51%|█████     | 1436/2814 [02:01<01:45, 13.07it/s]
 51%|█████     | 1438/2814 [02:01<01:49, 12.60it/s]
 51%|█████     | 1440/2814 [02:01<01:52, 12.26it/s]
 51%|█████     | 1442/2814 [02:01<01:51, 12.34it/s]
 51%|█████▏    | 1444/2814 [02:01<01:44, 13.10it/s]
 51%|█████▏    | 1446/2814 [02:01<01:49, 12.52it/s]
 51%|█████▏    | 1448/2814 [02:02<01:46, 12.80it/s]
 52%|█████▏    | 1450/2814 [02:02<01:50, 12.30it/s]
 52%|█████▏    | 1452/2814 [02:02<01:51, 12.24it/s]
 52%|█████▏    | 1454/2814 [02:02<01:53, 12.01it/s]
 52%|█████▏    | 1456/2814 [02:02<01:50, 12.25it/s]
 52%|█████▏    | 1458/2814 [02:02<01:51, 12.13it/s]
 52%|█████▏    | 1460/2814 [02:03<01:53, 11.96it/s]
 52%|█████▏    | 1462/2814 [02:03<01:54, 11.82it/s]
 52%|█████▏    | 1464/2814 [02:03<01:54, 11.78it/s]
 52%|█████▏    | 1466/2814 [02:03<01:52, 11.95it/s]
 52%|█████▏    | 1468/2814 [02:03<01:53, 11.91it/s]
 52%|█████▏    | 1470/2814 [02:03<01:50, 12.22it/s]
 52%|█████▏    | 1472/2814 [02:04<01:45, 12.73it/s]
 52%|█████▏    | 1474/2814 [02:04<01:45, 12.65it/s]
 52%|█████▏    | 1476/2814 [02:04<01:48, 12.38it/s]
 53%|█████▎    | 1478/2814 [02:04<01:49, 12.21it/s]
 53%|█████▎    | 1480/2814 [02:04<01:45, 12.59it/s]
 53%|█████▎    | 1482/2814 [02:04<01:46, 12.54it/s]
 53%|█████▎    | 1484/2814 [02:05<01:48, 12.28it/s]
 53%|█████▎    | 1486/2814 [02:05<01:47, 12.34it/s]
 53%|█████▎    | 1488/2814 [02:05<01:46, 12.47it/s]
 53%|█████▎    | 1490/2814 [02:05<01:48, 12.21it/s]
 53%|█████▎    | 1492/2814 [02:05<01:51, 11.81it/s]
 53%|█████▎    | 1494/2814 [02:05<01:50, 11.93it/s]
 53%|█████▎    | 1496/2814 [02:06<01:48, 12.20it/s]
 53%|█████▎    | 1498/2814 [02:06<01:47, 12.28it/s]
 53%|█████▎    | 1500/2814 [02:06<01:49, 11.99it/s]
 53%|█████▎    | 1502/2814 [02:06<01:48, 12.09it/s]
 53%|█████▎    | 1504/2814 [02:06<01:44, 12.58it/s]
 54%|█████▎    | 1506/2814 [02:06<01:45, 12.44it/s]
 54%|█████▎    | 1508/2814 [02:07<01:46, 12.21it/s]
 54%|█████▎    | 1510/2814 [02:07<01:46, 12.28it/s]
 54%|█████▎    | 1512/2814 [02:07<01:44, 12.50it/s]
 54%|█████▍    | 1514/2814 [02:07<01:41, 12.86it/s]
 54%|█████▍    | 1516/2814 [02:07<01:40, 12.89it/s]
 54%|█████▍    | 1518/2814 [02:07<01:41, 12.80it/s]
 54%|█████▍    | 1520/2814 [02:07<01:44, 12.37it/s]
 54%|█████▍    | 1522/2814 [02:08<01:47, 12.06it/s]
 54%|█████▍    | 1524/2814 [02:08<01:48, 11.86it/s]
 54%|█████▍    | 1526/2814 [02:08<01:42, 12.56it/s]
 54%|█████▍    | 1528/2814 [02:08<01:41, 12.67it/s]
 54%|█████▍    | 1530/2814 [02:08<01:42, 12.58it/s]
 54%|█████▍    | 1532/2814 [02:08<01:45, 12.10it/s]
 55%|█████▍    | 1534/2814 [02:09<01:45, 12.15it/s]
 55%|█████▍    | 1536/2814 [02:09<01:47, 11.89it/s]
 55%|█████▍    | 1538/2814 [02:09<01:46, 12.03it/s]
 55%|█████▍    | 1540/2814 [02:09<01:41, 12.59it/s]
 55%|█████▍    | 1542/2814 [02:09<01:41, 12.51it/s]
 55%|█████▍    | 1544/2814 [02:09<01:44, 12.13it/s]
 55%|█████▍    | 1546/2814 [02:10<01:43, 12.21it/s]
 55%|█████▌    | 1548/2814 [02:10<01:43, 12.22it/s]
 55%|█████▌    | 1550/2814 [02:10<01:42, 12.29it/s]
 55%|█████▌    | 1552/2814 [02:10<01:42, 12.35it/s]
 55%|█████▌    | 1554/2814 [02:10<01:41, 12.42it/s]
 55%|█████▌    | 1556/2814 [02:10<01:42, 12.28it/s]
 55%|█████▌    | 1558/2814 [02:11<01:44, 12.04it/s]
 55%|█████▌    | 1560/2814 [02:11<01:45, 11.93it/s]
 56%|█████▌    | 1562/2814 [02:11<01:44, 11.93it/s]
 56%|█████▌    | 1564/2814 [02:11<01:44, 11.98it/s]
 56%|█████▌    | 1566/2814 [02:11<01:44, 11.97it/s]
 56%|█████▌    | 1568/2814 [02:11<01:44, 11.87it/s]
 56%|█████▌    | 1570/2814 [02:12<01:46, 11.65it/s]
 56%|█████▌    | 1572/2814 [02:12<01:44, 11.87it/s]
 56%|█████▌    | 1574/2814 [02:12<01:41, 12.26it/s]
 56%|█████▌    | 1576/2814 [02:12<01:40, 12.27it/s]
 56%|█████▌    | 1578/2814 [02:12<01:37, 12.68it/s]
 56%|█████▌    | 1580/2814 [02:12<01:39, 12.34it/s]
 56%|█████▌    | 1582/2814 [02:13<01:42, 11.96it/s]
 56%|█████▋    | 1584/2814 [02:13<01:44, 11.79it/s]
 56%|█████▋    | 1586/2814 [02:13<01:45, 11.59it/s]
 56%|█████▋    | 1588/2814 [02:13<01:46, 11.54it/s]
 57%|█████▋    | 1590/2814 [02:13<01:45, 11.55it/s]
 57%|█████▋    | 1592/2814 [02:13<01:44, 11.72it/s]
 57%|█████▋    | 1594/2814 [02:14<01:44, 11.72it/s]
 57%|█████▋    | 1596/2814 [02:14<01:44, 11.63it/s]
 57%|█████▋    | 1598/2814 [02:14<01:45, 11.52it/s]
 57%|█████▋    | 1600/2814 [02:14<01:42, 11.88it/s]
 57%|█████▋    | 1602/2814 [02:14<01:40, 12.11it/s]
 57%|█████▋    | 1604/2814 [02:14<01:42, 11.83it/s]
 57%|█████▋    | 1606/2814 [02:15<01:39, 12.12it/s]
 57%|█████▋    | 1608/2814 [02:15<01:35, 12.69it/s]
 57%|█████▋    | 1610/2814 [02:15<01:39, 12.16it/s]
 57%|█████▋    | 1612/2814 [02:15<01:37, 12.34it/s]
 57%|█████▋    | 1614/2814 [02:15<01:33, 12.77it/s]
 57%|█████▋    | 1616/2814 [02:15<01:36, 12.40it/s]
 57%|█████▋    | 1618/2814 [02:16<01:35, 12.54it/s]
 58%|█████▊    | 1620/2814 [02:16<01:34, 12.58it/s]
 58%|█████▊    | 1622/2814 [02:16<01:35, 12.49it/s]
 58%|█████▊    | 1624/2814 [02:16<01:34, 12.56it/s]
 58%|█████▊    | 1626/2814 [02:16<01:34, 12.51it/s]
 58%|█████▊    | 1628/2814 [02:16<01:35, 12.43it/s]
 58%|█████▊    | 1630/2814 [02:17<01:34, 12.48it/s]
 58%|█████▊    | 1632/2814 [02:17<01:33, 12.62it/s]
 58%|█████▊    | 1634/2814 [02:17<01:33, 12.60it/s]
 58%|█████▊    | 1636/2814 [02:17<01:36, 12.17it/s]
 58%|█████▊    | 1638/2814 [02:17<01:36, 12.18it/s]
 58%|█████▊    | 1640/2814 [02:17<01:36, 12.11it/s]
 58%|█████▊    | 1642/2814 [02:18<01:38, 11.92it/s]
 58%|█████▊    | 1644/2814 [02:18<01:38, 11.92it/s]
 58%|█████▊    | 1646/2814 [02:18<01:35, 12.26it/s]
 59%|█████▊    | 1648/2814 [02:18<01:36, 12.04it/s]
 59%|█████▊    | 1650/2814 [02:18<01:33, 12.47it/s]
 59%|█████▊    | 1652/2814 [02:18<01:34, 12.28it/s]
 59%|█████▉    | 1654/2814 [02:18<01:33, 12.47it/s]
 59%|█████▉    | 1656/2814 [02:19<01:34, 12.22it/s]
 59%|█████▉    | 1658/2814 [02:19<01:36, 11.96it/s]
 59%|█████▉    | 1660/2814 [02:19<01:37, 11.83it/s]
 59%|█████▉    | 1662/2814 [02:19<01:37, 11.79it/s]
 59%|█████▉    | 1664/2814 [02:19<01:34, 12.19it/s]
 59%|█████▉    | 1666/2814 [02:19<01:35, 11.99it/s]
 59%|█████▉    | 1668/2814 [02:20<01:32, 12.35it/s]
 59%|█████▉    | 1670/2814 [02:20<01:32, 12.38it/s]
 59%|█████▉    | 1672/2814 [02:20<01:29, 12.73it/s]
 59%|█████▉    | 1674/2814 [02:20<01:32, 12.34it/s]
 60%|█████▉    | 1676/2814 [02:20<01:32, 12.35it/s]
 60%|█████▉    | 1678/2814 [02:20<01:33, 12.20it/s]
 60%|█████▉    | 1680/2814 [02:21<01:32, 12.22it/s]
 60%|█████▉    | 1682/2814 [02:21<01:31, 12.39it/s]
 60%|█████▉    | 1684/2814 [02:21<01:32, 12.18it/s]
 60%|█████▉    | 1686/2814 [02:21<01:34, 11.96it/s]
 60%|█████▉    | 1688/2814 [02:21<01:31, 12.27it/s]
 60%|██████    | 1690/2814 [02:21<01:32, 12.22it/s]
 60%|██████    | 1692/2814 [02:22<01:30, 12.39it/s]
 60%|██████    | 1694/2814 [02:22<01:27, 12.74it/s]
 60%|██████    | 1696/2814 [02:22<01:30, 12.38it/s]
 60%|██████    | 1698/2814 [02:22<01:32, 12.11it/s]
 60%|██████    | 1700/2814 [02:22<01:33, 11.90it/s]
 60%|██████    | 1702/2814 [02:22<01:32, 12.06it/s]
 61%|██████    | 1704/2814 [02:23<01:33, 11.83it/s]
 61%|██████    | 1706/2814 [02:23<01:33, 11.90it/s]
 61%|██████    | 1708/2814 [02:23<01:27, 12.67it/s]
 61%|██████    | 1710/2814 [02:23<01:27, 12.55it/s]
 61%|██████    | 1712/2814 [02:23<01:29, 12.31it/s]
 61%|██████    | 1714/2814 [02:23<01:27, 12.58it/s]
 61%|██████    | 1716/2814 [02:24<01:29, 12.28it/s]
 61%|██████    | 1718/2814 [02:24<01:29, 12.25it/s]
 61%|██████    | 1720/2814 [02:24<01:31, 11.99it/s]
 61%|██████    | 1722/2814 [02:24<01:32, 11.75it/s]
 61%|██████▏   | 1724/2814 [02:24<01:29, 12.20it/s]
 61%|██████▏   | 1726/2814 [02:24<01:28, 12.30it/s]
 61%|██████▏   | 1728/2814 [02:25<01:26, 12.59it/s]
 61%|██████▏   | 1730/2814 [02:25<01:27, 12.45it/s]
 62%|██████▏   | 1732/2814 [02:25<01:26, 12.44it/s]
 62%|██████▏   | 1734/2814 [02:25<01:27, 12.39it/s]
 62%|██████▏   | 1736/2814 [02:25<01:25, 12.60it/s]
 62%|██████▏   | 1738/2814 [02:25<01:25, 12.52it/s]
 62%|██████▏   | 1740/2814 [02:25<01:25, 12.53it/s]
 62%|██████▏   | 1742/2814 [02:26<01:23, 12.81it/s]
 62%|██████▏   | 1744/2814 [02:26<01:26, 12.39it/s]
 62%|██████▏   | 1746/2814 [02:26<01:25, 12.43it/s]
 62%|██████▏   | 1748/2814 [02:26<01:27, 12.23it/s]
 62%|██████▏   | 1750/2814 [02:26<01:25, 12.39it/s]
 62%|██████▏   | 1752/2814 [02:26<01:25, 12.39it/s]
 62%|██████▏   | 1754/2814 [02:27<01:23, 12.76it/s]
 62%|██████▏   | 1756/2814 [02:27<01:25, 12.32it/s]
 62%|██████▏   | 1758/2814 [02:27<01:25, 12.31it/s]
 63%|██████▎   | 1760/2814 [02:27<01:27, 12.03it/s]
 63%|██████▎   | 1762/2814 [02:27<01:25, 12.37it/s]
 63%|██████▎   | 1764/2814 [02:27<01:23, 12.62it/s]
 63%|██████▎   | 1766/2814 [02:28<01:25, 12.33it/s]
 63%|██████▎   | 1768/2814 [02:28<01:26, 12.16it/s]
 63%|██████▎   | 1770/2814 [02:28<01:23, 12.45it/s]
 63%|██████▎   | 1772/2814 [02:28<01:24, 12.31it/s]
 63%|██████▎   | 1774/2814 [02:28<01:26, 12.02it/s]
 63%|██████▎   | 1776/2814 [02:28<01:26, 11.98it/s]
 63%|██████▎   | 1778/2814 [02:29<01:27, 11.82it/s]
 63%|██████▎   | 1780/2814 [02:29<01:23, 12.34it/s]
 63%|██████▎   | 1782/2814 [02:29<01:20, 12.84it/s]
 63%|██████▎   | 1784/2814 [02:29<01:22, 12.53it/s]
 63%|██████▎   | 1786/2814 [02:29<01:22, 12.39it/s]
 64%|██████▎   | 1788/2814 [02:29<01:24, 12.08it/s]
 64%|██████▎   | 1790/2814 [02:30<01:25, 11.97it/s]
 64%|██████▎   | 1792/2814 [02:30<01:25, 12.02it/s]
 64%|██████▍   | 1794/2814 [02:30<01:23, 12.15it/s]
 64%|██████▍   | 1796/2814 [02:30<01:25, 11.87it/s]
 64%|██████▍   | 1798/2814 [02:30<01:27, 11.60it/s]
 64%|██████▍   | 1800/2814 [02:30<01:26, 11.74it/s]
 64%|██████▍   | 1802/2814 [02:31<01:26, 11.70it/s]
 64%|██████▍   | 1804/2814 [02:31<01:25, 11.88it/s]
 64%|██████▍   | 1806/2814 [02:31<01:21, 12.32it/s]
 64%|██████▍   | 1808/2814 [02:31<01:21, 12.41it/s]
 64%|██████▍   | 1810/2814 [02:31<01:22, 12.14it/s]
 64%|██████▍   | 1812/2814 [02:31<01:21, 12.23it/s]
 64%|██████▍   | 1814/2814 [02:32<01:20, 12.37it/s]
 65%|██████▍   | 1816/2814 [02:32<01:19, 12.48it/s]
 65%|██████▍   | 1818/2814 [02:32<01:21, 12.23it/s]
 65%|██████▍   | 1820/2814 [02:32<01:16, 13.03it/s]
 65%|██████▍   | 1822/2814 [02:32<01:18, 12.68it/s]
 65%|██████▍   | 1824/2814 [02:32<01:17, 12.75it/s]
 65%|██████▍   | 1826/2814 [02:32<01:20, 12.31it/s]
 65%|██████▍   | 1828/2814 [02:33<01:19, 12.41it/s]
 65%|██████▌   | 1830/2814 [02:33<01:20, 12.16it/s]
 65%|██████▌   | 1832/2814 [02:33<01:21, 12.05it/s]
 65%|██████▌   | 1834/2814 [02:33<01:22, 11.90it/s]
 65%|██████▌   | 1836/2814 [02:33<01:23, 11.78it/s]
 65%|██████▌   | 1838/2814 [02:34<01:23, 11.65it/s]
 65%|██████▌   | 1840/2814 [02:34<01:22, 11.84it/s]
 65%|██████▌   | 1842/2814 [02:34<01:20, 12.01it/s]
 66%|██████▌   | 1844/2814 [02:34<01:22, 11.80it/s]
 66%|██████▌   | 1846/2814 [02:34<01:22, 11.73it/s]
 66%|██████▌   | 1848/2814 [02:34<01:21, 11.90it/s]
 66%|██████▌   | 1850/2814 [02:35<01:21, 11.76it/s]
 66%|██████▌   | 1852/2814 [02:35<01:21, 11.84it/s]
 66%|██████▌   | 1854/2814 [02:35<01:21, 11.83it/s]
 66%|██████▌   | 1856/2814 [02:35<01:19, 12.08it/s]
 66%|██████▌   | 1858/2814 [02:35<01:20, 11.92it/s]
 66%|██████▌   | 1860/2814 [02:35<01:21, 11.64it/s]
 66%|██████▌   | 1862/2814 [02:36<01:19, 12.02it/s]
 66%|██████▌   | 1864/2814 [02:36<01:19, 11.91it/s]
 66%|██████▋   | 1866/2814 [02:36<01:18, 12.12it/s]
 66%|██████▋   | 1868/2814 [02:36<01:18, 12.08it/s]
 66%|██████▋   | 1870/2814 [02:36<01:19, 11.83it/s]
 67%|██████▋   | 1872/2814 [02:36<01:18, 11.94it/s]
 67%|██████▋   | 1874/2814 [02:37<01:18, 11.91it/s]
 67%|██████▋   | 1876/2814 [02:37<01:14, 12.62it/s]
                                                   

 67%|██████▋   | 1876/2814 [02:37<01:14, 12.62it/s]{'eval_loss': 0.6972612142562866, 'eval_accuracy': 0.6968, 'eval_f1': 0.6951376406863021, 'eval_runtime': 1.7329, 'eval_samples_per_second': 1442.689, 'eval_steps_per_second': 180.625, 'epoch': 1.0}
{'loss': 0.6081, 'learning_rate': 4.4355714796541745e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.83it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.68it/s]

 21%|██        | 66/313 [00:00<00:01, 206.19it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.38it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.63it/s]

 40%|████      | 126/313 [00:00<00:01, 185.35it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.19it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.03it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.85it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.06it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.27it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.00it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.75it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.74it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.57it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.57it/s]
 67%|██████▋   | 1876/2814 [02:38<01:14, 12.62it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 1878/2814 [02:39<07:24,  2.10it/s]
 67%|██████▋   | 1880/2814 [02:40<05:33,  2.80it/s]
 67%|██████▋   | 1882/2814 [02:40<04:15,  3.65it/s]
 67%|██████▋   | 1884/2814 [02:40<03:22,  4.60it/s]
 67%|██████▋   | 1886/2814 [02:40<02:45,  5.61it/s]
 67%|██████▋   | 1888/2814 [02:40<02:18,  6.69it/s]
 67%|██████▋   | 1890/2814 [02:40<02:00,  7.67it/s]
 67%|██████▋   | 1892/2814 [02:41<01:45,  8.74it/s]
 67%|██████▋   | 1894/2814 [02:41<01:36,  9.57it/s]
 67%|██████▋   | 1896/2814 [02:41<01:31, 10.02it/s]
 67%|██████▋   | 1898/2814 [02:41<01:23, 10.98it/s]
 68%|██████▊   | 1900/2814 [02:41<01:22, 11.06it/s]
 68%|██████▊   | 1902/2814 [02:41<01:21, 11.23it/s]
 68%|██████▊   | 1904/2814 [02:42<01:18, 11.59it/s]
 68%|██████▊   | 1906/2814 [02:42<01:19, 11.42it/s]
 68%|██████▊   | 1908/2814 [02:42<01:18, 11.52it/s]
 68%|██████▊   | 1910/2814 [02:42<01:16, 11.80it/s]
 68%|██████▊   | 1912/2814 [02:42<01:16, 11.79it/s]
 68%|██████▊   | 1914/2814 [02:42<01:15, 11.95it/s]
 68%|██████▊   | 1916/2814 [02:43<01:16, 11.73it/s]
 68%|██████▊   | 1918/2814 [02:43<01:16, 11.75it/s]
 68%|██████▊   | 1920/2814 [02:43<01:15, 11.91it/s]
 68%|██████▊   | 1922/2814 [02:43<01:15, 11.83it/s]
 68%|██████▊   | 1924/2814 [02:43<01:16, 11.71it/s]
 68%|██████▊   | 1926/2814 [02:43<01:13, 12.05it/s]
 69%|██████▊   | 1928/2814 [02:44<01:14, 11.95it/s]
 69%|██████▊   | 1930/2814 [02:44<01:14, 11.83it/s]
 69%|██████▊   | 1932/2814 [02:44<01:14, 11.88it/s]
 69%|██████▊   | 1934/2814 [02:44<01:11, 12.38it/s]
 69%|██████▉   | 1936/2814 [02:44<01:10, 12.39it/s]
 69%|██████▉   | 1938/2814 [02:44<01:12, 12.01it/s]
 69%|██████▉   | 1940/2814 [02:45<01:13, 11.83it/s]
 69%|██████▉   | 1942/2814 [02:45<01:13, 11.94it/s]
 69%|██████▉   | 1944/2814 [02:45<01:11, 12.14it/s]
 69%|██████▉   | 1946/2814 [02:45<01:11, 12.22it/s]
 69%|██████▉   | 1948/2814 [02:45<01:09, 12.52it/s]
 69%|██████▉   | 1950/2814 [02:45<01:09, 12.38it/s]
 69%|██████▉   | 1952/2814 [02:46<01:09, 12.34it/s]
 69%|██████▉   | 1954/2814 [02:46<01:11, 11.99it/s]
 70%|██████▉   | 1956/2814 [02:46<01:10, 12.19it/s]
 70%|██████▉   | 1958/2814 [02:46<01:09, 12.28it/s]
 70%|██████▉   | 1960/2814 [02:46<01:07, 12.60it/s]
 70%|██████▉   | 1962/2814 [02:46<01:08, 12.43it/s]
 70%|██████▉   | 1964/2814 [02:47<01:06, 12.77it/s]
 70%|██████▉   | 1966/2814 [02:47<01:08, 12.38it/s]
 70%|██████▉   | 1968/2814 [02:47<01:06, 12.74it/s]
 70%|███████   | 1970/2814 [02:47<01:08, 12.23it/s]
 70%|███████   | 1972/2814 [02:47<01:08, 12.34it/s]
 70%|███████   | 1974/2814 [02:47<01:06, 12.65it/s]
 70%|███████   | 1976/2814 [02:48<01:07, 12.36it/s]
 70%|███████   | 1978/2814 [02:48<01:05, 12.82it/s]
 70%|███████   | 1980/2814 [02:48<01:04, 12.90it/s]
 70%|███████   | 1982/2814 [02:48<01:02, 13.26it/s]
 71%|███████   | 1984/2814 [02:48<01:05, 12.60it/s]
 71%|███████   | 1986/2814 [02:48<01:06, 12.44it/s]
 71%|███████   | 1988/2814 [02:48<01:04, 12.78it/s]
 71%|███████   | 1990/2814 [02:49<01:06, 12.31it/s]
 71%|███████   | 1992/2814 [02:49<01:07, 12.20it/s]
 71%|███████   | 1994/2814 [02:49<01:06, 12.42it/s]
 71%|███████   | 1996/2814 [02:49<01:06, 12.32it/s]
 71%|███████   | 1998/2814 [02:49<01:06, 12.25it/s]
 71%|███████   | 2000/2814 [02:49<01:05, 12.41it/s]
 71%|███████   | 2002/2814 [02:50<01:06, 12.15it/s]
 71%|███████   | 2004/2814 [02:50<01:06, 12.18it/s]
 71%|███████▏  | 2006/2814 [02:50<01:04, 12.51it/s]
 71%|███████▏  | 2008/2814 [02:50<01:04, 12.52it/s]
 71%|███████▏  | 2010/2814 [02:50<01:05, 12.24it/s]
 71%|███████▏  | 2012/2814 [02:50<01:05, 12.16it/s]
 72%|███████▏  | 2014/2814 [02:51<01:05, 12.17it/s]
 72%|███████▏  | 2016/2814 [02:51<01:06, 11.95it/s]
 72%|███████▏  | 2018/2814 [02:51<01:04, 12.29it/s]
 72%|███████▏  | 2020/2814 [02:51<01:05, 12.14it/s]
 72%|███████▏  | 2022/2814 [02:51<01:04, 12.22it/s]
 72%|███████▏  | 2024/2814 [02:51<01:03, 12.39it/s]
 72%|███████▏  | 2026/2814 [02:52<01:05, 12.04it/s]
 72%|███████▏  | 2028/2814 [02:52<01:07, 11.71it/s]
 72%|███████▏  | 2030/2814 [02:52<01:07, 11.68it/s]
 72%|███████▏  | 2032/2814 [02:52<01:06, 11.77it/s]
 72%|███████▏  | 2034/2814 [02:52<01:03, 12.33it/s]
 72%|███████▏  | 2036/2814 [02:52<01:04, 12.04it/s]
 72%|███████▏  | 2038/2814 [02:53<01:01, 12.67it/s]
 72%|███████▏  | 2040/2814 [02:53<00:59, 13.01it/s]
 73%|███████▎  | 2042/2814 [02:53<01:01, 12.47it/s]
 73%|███████▎  | 2044/2814 [02:53<01:01, 12.56it/s]
 73%|███████▎  | 2046/2814 [02:53<01:02, 12.21it/s]
 73%|███████▎  | 2048/2814 [02:53<01:03, 11.98it/s]
 73%|███████▎  | 2050/2814 [02:54<01:01, 12.40it/s]
 73%|███████▎  | 2052/2814 [02:54<01:03, 11.94it/s]
 73%|███████▎  | 2054/2814 [02:54<01:00, 12.61it/s]
 73%|███████▎  | 2056/2814 [02:54<01:01, 12.25it/s]
 73%|███████▎  | 2058/2814 [02:54<01:02, 12.02it/s]
 73%|███████▎  | 2060/2814 [02:54<01:02, 12.10it/s]
 73%|███████▎  | 2062/2814 [02:55<01:03, 11.85it/s]
 73%|███████▎  | 2064/2814 [02:55<01:03, 11.84it/s]
 73%|███████▎  | 2066/2814 [02:55<01:02, 12.03it/s]
 73%|███████▎  | 2068/2814 [02:55<01:03, 11.76it/s]
 74%|███████▎  | 2070/2814 [02:55<01:03, 11.72it/s]
 74%|███████▎  | 2072/2814 [02:55<01:01, 12.01it/s]
 74%|███████▎  | 2074/2814 [02:56<01:02, 11.91it/s]
 74%|███████▍  | 2076/2814 [02:56<01:01, 12.02it/s]
 74%|███████▍  | 2078/2814 [02:56<01:02, 11.86it/s]
 74%|███████▍  | 2080/2814 [02:56<01:00, 12.19it/s]
 74%|███████▍  | 2082/2814 [02:56<01:01, 11.98it/s]
 74%|███████▍  | 2084/2814 [02:56<00:57, 12.67it/s]
 74%|███████▍  | 2086/2814 [02:57<00:58, 12.51it/s]
 74%|███████▍  | 2088/2814 [02:57<00:59, 12.22it/s]
 74%|███████▍  | 2090/2814 [02:57<01:00, 12.06it/s]
 74%|███████▍  | 2092/2814 [02:57<01:00, 11.95it/s]
 74%|███████▍  | 2094/2814 [02:57<01:01, 11.79it/s]
 74%|███████▍  | 2096/2814 [02:57<01:00, 11.95it/s]
 75%|███████▍  | 2098/2814 [02:58<00:59, 12.11it/s]
 75%|███████▍  | 2100/2814 [02:58<00:59, 12.06it/s]
 75%|███████▍  | 2102/2814 [02:58<00:58, 12.14it/s]
 75%|███████▍  | 2104/2814 [02:58<00:58, 12.08it/s]
 75%|███████▍  | 2106/2814 [02:58<00:59, 11.91it/s]
 75%|███████▍  | 2108/2814 [02:58<01:00, 11.71it/s]
 75%|███████▍  | 2110/2814 [02:59<01:00, 11.61it/s]
 75%|███████▌  | 2112/2814 [02:59<00:57, 12.31it/s]
 75%|███████▌  | 2114/2814 [02:59<00:54, 12.80it/s]
 75%|███████▌  | 2116/2814 [02:59<00:56, 12.43it/s]
 75%|███████▌  | 2118/2814 [02:59<00:54, 12.85it/s]
 75%|███████▌  | 2120/2814 [02:59<00:55, 12.41it/s]
 75%|███████▌  | 2122/2814 [02:59<00:53, 12.88it/s]
 75%|███████▌  | 2124/2814 [03:00<00:55, 12.33it/s]
 76%|███████▌  | 2126/2814 [03:00<00:53, 12.88it/s]
 76%|███████▌  | 2128/2814 [03:00<00:55, 12.47it/s]
 76%|███████▌  | 2130/2814 [03:00<00:56, 12.09it/s]
 76%|███████▌  | 2132/2814 [03:00<00:56, 12.03it/s]
 76%|███████▌  | 2134/2814 [03:00<00:56, 11.99it/s]
 76%|███████▌  | 2136/2814 [03:01<00:55, 12.11it/s]
 76%|███████▌  | 2138/2814 [03:01<00:56, 12.02it/s]
 76%|███████▌  | 2140/2814 [03:01<00:57, 11.78it/s]
 76%|███████▌  | 2142/2814 [03:01<00:57, 11.59it/s]
 76%|███████▌  | 2144/2814 [03:01<00:56, 11.88it/s]
 76%|███████▋  | 2146/2814 [03:01<00:55, 11.97it/s]
 76%|███████▋  | 2148/2814 [03:02<01:16,  8.66it/s]
 76%|███████▋  | 2150/2814 [03:02<01:10,  9.46it/s]
 76%|███████▋  | 2152/2814 [03:02<01:06,  9.93it/s]
 77%|███████▋  | 2154/2814 [03:02<01:01, 10.73it/s]
 77%|███████▋  | 2156/2814 [03:03<00:58, 11.20it/s]
 77%|███████▋  | 2158/2814 [03:03<00:58, 11.24it/s]
 77%|███████▋  | 2160/2814 [03:03<00:56, 11.50it/s]
 77%|███████▋  | 2162/2814 [03:03<00:56, 11.55it/s]
 77%|███████▋  | 2164/2814 [03:03<00:52, 12.33it/s]
 77%|███████▋  | 2166/2814 [03:03<00:53, 12.04it/s]
 77%|███████▋  | 2168/2814 [03:03<00:52, 12.34it/s]
 77%|███████▋  | 2170/2814 [03:04<00:53, 12.11it/s]
 77%|███████▋  | 2172/2814 [03:04<00:53, 11.90it/s]
 77%|███████▋  | 2174/2814 [03:04<00:52, 12.23it/s]
 77%|███████▋  | 2176/2814 [03:04<00:53, 11.91it/s]
 77%|███████▋  | 2178/2814 [03:04<00:53, 11.92it/s]
 77%|███████▋  | 2180/2814 [03:04<00:51, 12.35it/s]
 78%|███████▊  | 2182/2814 [03:05<00:50, 12.40it/s]
 78%|███████▊  | 2184/2814 [03:05<00:51, 12.18it/s]
 78%|███████▊  | 2186/2814 [03:05<00:52, 11.98it/s]
 78%|███████▊  | 2188/2814 [03:05<00:52, 11.84it/s]
 78%|███████▊  | 2190/2814 [03:05<00:52, 11.80it/s]
 78%|███████▊  | 2192/2814 [03:06<00:52, 11.78it/s]
 78%|███████▊  | 2194/2814 [03:06<00:51, 11.93it/s]
 78%|███████▊  | 2196/2814 [03:06<00:52, 11.86it/s]
 78%|███████▊  | 2198/2814 [03:06<00:52, 11.73it/s]
 78%|███████▊  | 2200/2814 [03:06<00:51, 11.99it/s]
 78%|███████▊  | 2202/2814 [03:06<00:52, 11.71it/s]
 78%|███████▊  | 2204/2814 [03:07<00:50, 11.99it/s]
 78%|███████▊  | 2206/2814 [03:07<00:51, 11.76it/s]
 78%|███████▊  | 2208/2814 [03:07<00:49, 12.27it/s]
 79%|███████▊  | 2210/2814 [03:07<00:49, 12.29it/s]
 79%|███████▊  | 2212/2814 [03:07<00:50, 11.87it/s]
 79%|███████▊  | 2214/2814 [03:07<00:51, 11.61it/s]
 79%|███████▊  | 2216/2814 [03:08<00:50, 11.77it/s]
 79%|███████▉  | 2218/2814 [03:08<00:50, 11.83it/s]
 79%|███████▉  | 2220/2814 [03:08<00:47, 12.40it/s]
 79%|███████▉  | 2222/2814 [03:08<00:48, 12.32it/s]
 79%|███████▉  | 2224/2814 [03:08<00:48, 12.07it/s]
 79%|███████▉  | 2226/2814 [03:08<00:48, 12.20it/s]
 79%|███████▉  | 2228/2814 [03:08<00:47, 12.34it/s]
 79%|███████▉  | 2230/2814 [03:09<00:47, 12.23it/s]
 79%|███████▉  | 2232/2814 [03:09<00:47, 12.30it/s]
 79%|███████▉  | 2234/2814 [03:09<00:47, 12.21it/s]
 79%|███████▉  | 2236/2814 [03:09<00:47, 12.07it/s]
 80%|███████▉  | 2238/2814 [03:09<00:48, 11.91it/s]
 80%|███████▉  | 2240/2814 [03:09<00:47, 11.96it/s]
 80%|███████▉  | 2242/2814 [03:10<00:46, 12.29it/s]
 80%|███████▉  | 2244/2814 [03:10<00:44, 12.71it/s]
 80%|███████▉  | 2246/2814 [03:10<00:46, 12.31it/s]
 80%|███████▉  | 2248/2814 [03:10<00:45, 12.33it/s]
 80%|███████▉  | 2250/2814 [03:10<00:42, 13.15it/s]
 80%|████████  | 2252/2814 [03:10<00:41, 13.49it/s]
 80%|████████  | 2254/2814 [03:11<00:41, 13.42it/s]
 80%|████████  | 2256/2814 [03:11<00:42, 13.03it/s]
 80%|████████  | 2258/2814 [03:11<00:43, 12.67it/s]
 80%|████████  | 2260/2814 [03:11<00:44, 12.39it/s]
 80%|████████  | 2262/2814 [03:11<00:42, 12.85it/s]
 80%|████████  | 2264/2814 [03:11<00:42, 12.85it/s]
 81%|████████  | 2266/2814 [03:12<00:42, 12.75it/s]
 81%|████████  | 2268/2814 [03:12<00:43, 12.65it/s]
 81%|████████  | 2270/2814 [03:12<00:54, 10.02it/s]
 81%|████████  | 2272/2814 [03:12<00:50, 10.76it/s]
 81%|████████  | 2274/2814 [03:12<00:49, 11.01it/s]
 81%|████████  | 2276/2814 [03:12<00:46, 11.59it/s]
 81%|████████  | 2278/2814 [03:13<00:43, 12.29it/s]
 81%|████████  | 2280/2814 [03:13<00:43, 12.39it/s]
 81%|████████  | 2282/2814 [03:13<00:44, 12.07it/s]
 81%|████████  | 2284/2814 [03:13<00:42, 12.48it/s]
 81%|████████  | 2286/2814 [03:13<00:43, 12.24it/s]
 81%|████████▏ | 2288/2814 [03:13<00:42, 12.28it/s]
 81%|████████▏ | 2290/2814 [03:14<00:43, 11.99it/s]
 81%|████████▏ | 2292/2814 [03:14<00:42, 12.35it/s]
 82%|████████▏ | 2294/2814 [03:14<00:43, 12.04it/s]
 82%|████████▏ | 2296/2814 [03:14<00:43, 11.94it/s]
 82%|████████▏ | 2298/2814 [03:14<00:43, 11.86it/s]
 82%|████████▏ | 2300/2814 [03:14<00:42, 12.20it/s]
 82%|████████▏ | 2302/2814 [03:15<00:42, 11.94it/s]
 82%|████████▏ | 2304/2814 [03:15<00:43, 11.69it/s]
 82%|████████▏ | 2306/2814 [03:15<00:43, 11.57it/s]
 82%|████████▏ | 2308/2814 [03:15<00:43, 11.53it/s]
 82%|████████▏ | 2310/2814 [03:15<00:43, 11.46it/s]
 82%|████████▏ | 2312/2814 [03:15<00:42, 11.71it/s]
 82%|████████▏ | 2314/2814 [03:16<00:41, 11.91it/s]
 82%|████████▏ | 2316/2814 [03:16<00:42, 11.82it/s]
 82%|████████▏ | 2318/2814 [03:16<00:41, 11.83it/s]
 82%|████████▏ | 2320/2814 [03:16<00:41, 11.81it/s]
 83%|████████▎ | 2322/2814 [03:16<00:41, 11.99it/s]
 83%|████████▎ | 2324/2814 [03:16<00:41, 11.78it/s]
 83%|████████▎ | 2326/2814 [03:17<00:41, 11.65it/s]
 83%|████████▎ | 2328/2814 [03:17<00:40, 12.08it/s]
 83%|████████▎ | 2330/2814 [03:17<00:45, 10.59it/s]
 83%|████████▎ | 2332/2814 [03:17<00:43, 10.98it/s]
 83%|████████▎ | 2334/2814 [03:17<00:43, 11.14it/s]
 83%|████████▎ | 2336/2814 [03:18<00:42, 11.25it/s]
 83%|████████▎ | 2338/2814 [03:18<00:42, 11.28it/s]
 83%|████████▎ | 2340/2814 [03:18<00:41, 11.35it/s]
 83%|████████▎ | 2342/2814 [03:18<00:41, 11.46it/s]
 83%|████████▎ | 2344/2814 [03:18<00:40, 11.53it/s]
 83%|████████▎ | 2346/2814 [03:18<00:40, 11.69it/s]
 83%|████████▎ | 2348/2814 [03:19<00:39, 11.81it/s]
 84%|████████▎ | 2350/2814 [03:19<00:38, 12.11it/s]
 84%|████████▎ | 2352/2814 [03:19<00:39, 11.80it/s]
 84%|████████▎ | 2354/2814 [03:19<00:39, 11.57it/s]
 84%|████████▎ | 2356/2814 [03:19<00:39, 11.62it/s]
 84%|████████▍ | 2358/2814 [03:19<00:39, 11.66it/s]
 84%|████████▍ | 2360/2814 [03:20<00:39, 11.60it/s]
 84%|████████▍ | 2362/2814 [03:20<00:38, 11.84it/s]
 84%|████████▍ | 2364/2814 [03:20<00:37, 11.86it/s]
 84%|████████▍ | 2366/2814 [03:20<00:36, 12.43it/s]
 84%|████████▍ | 2368/2814 [03:20<00:35, 12.54it/s]
 84%|████████▍ | 2370/2814 [03:20<00:36, 12.12it/s]
 84%|████████▍ | 2372/2814 [03:21<00:37, 11.94it/s]
 84%|████████▍ | 2374/2814 [03:21<00:37, 11.82it/s]
 84%|████████▍ | 2376/2814 [03:21<00:35, 12.33it/s]
 85%|████████▍ | 2378/2814 [03:21<00:36, 12.04it/s]
 85%|████████▍ | 2380/2814 [03:21<00:36, 11.89it/s]
 85%|████████▍ | 2382/2814 [03:21<00:36, 11.76it/s]
 85%|████████▍ | 2384/2814 [03:22<00:35, 12.04it/s]
 85%|████████▍ | 2386/2814 [03:22<00:34, 12.53it/s]
 85%|████████▍ | 2388/2814 [03:22<00:34, 12.37it/s]
 85%|████████▍ | 2390/2814 [03:22<00:34, 12.39it/s]
 85%|████████▌ | 2392/2814 [03:22<00:33, 12.45it/s]
 85%|████████▌ | 2394/2814 [03:22<00:34, 12.17it/s]
 85%|████████▌ | 2396/2814 [03:23<00:33, 12.42it/s]
 85%|████████▌ | 2398/2814 [03:23<00:32, 12.90it/s]
 85%|████████▌ | 2400/2814 [03:23<00:31, 13.08it/s]
 85%|████████▌ | 2402/2814 [03:23<00:30, 13.42it/s]
 85%|████████▌ | 2404/2814 [03:23<00:32, 12.70it/s]
 86%|████████▌ | 2406/2814 [03:23<00:33, 12.29it/s]
 86%|████████▌ | 2408/2814 [03:23<00:31, 12.80it/s]
 86%|████████▌ | 2410/2814 [03:24<00:31, 12.80it/s]
 86%|████████▌ | 2412/2814 [03:24<00:32, 12.33it/s]
 86%|████████▌ | 2414/2814 [03:24<00:32, 12.12it/s]
 86%|████████▌ | 2416/2814 [03:24<00:32, 12.32it/s]
 86%|████████▌ | 2418/2814 [03:24<00:31, 12.40it/s]
 86%|████████▌ | 2420/2814 [03:24<00:32, 12.20it/s]
 86%|████████▌ | 2422/2814 [03:25<00:30, 12.84it/s]
 86%|████████▌ | 2424/2814 [03:25<00:30, 12.93it/s]
 86%|████████▌ | 2426/2814 [03:25<00:31, 12.49it/s]
 86%|████████▋ | 2428/2814 [03:25<00:31, 12.22it/s]
 86%|████████▋ | 2430/2814 [03:25<00:32, 11.89it/s]
 86%|████████▋ | 2432/2814 [03:25<00:31, 11.94it/s]
 86%|████████▋ | 2434/2814 [03:26<00:31, 12.06it/s]
 87%|████████▋ | 2436/2814 [03:26<00:30, 12.26it/s]
 87%|████████▋ | 2438/2814 [03:26<00:29, 12.64it/s]
 87%|████████▋ | 2440/2814 [03:26<00:30, 12.46it/s]
 87%|████████▋ | 2442/2814 [03:26<00:30, 12.22it/s]
 87%|████████▋ | 2444/2814 [03:26<00:30, 12.28it/s]
 87%|████████▋ | 2446/2814 [03:27<00:30, 11.96it/s]
 87%|████████▋ | 2448/2814 [03:27<00:30, 12.07it/s]
 87%|████████▋ | 2450/2814 [03:27<00:29, 12.38it/s]
 87%|████████▋ | 2452/2814 [03:27<00:29, 12.34it/s]
 87%|████████▋ | 2454/2814 [03:27<00:29, 12.09it/s]
 87%|████████▋ | 2456/2814 [03:27<00:30, 11.91it/s]
 87%|████████▋ | 2458/2814 [03:28<00:29, 12.10it/s]
 87%|████████▋ | 2460/2814 [03:28<00:29, 12.08it/s]
 87%|████████▋ | 2462/2814 [03:28<00:28, 12.39it/s]
 88%|████████▊ | 2464/2814 [03:28<00:27, 12.56it/s]
 88%|████████▊ | 2466/2814 [03:28<00:28, 12.27it/s]
 88%|████████▊ | 2468/2814 [03:28<00:28, 11.98it/s]
 88%|████████▊ | 2470/2814 [03:29<00:28, 11.95it/s]
 88%|████████▊ | 2472/2814 [03:29<00:27, 12.57it/s]
 88%|████████▊ | 2474/2814 [03:29<00:26, 12.98it/s]
 88%|████████▊ | 2476/2814 [03:29<00:26, 12.60it/s]
 88%|████████▊ | 2478/2814 [03:29<00:25, 13.06it/s]
 88%|████████▊ | 2480/2814 [03:29<00:25, 12.86it/s]
 88%|████████▊ | 2482/2814 [03:29<00:26, 12.32it/s]
 88%|████████▊ | 2484/2814 [03:30<00:26, 12.41it/s]
 88%|████████▊ | 2486/2814 [03:30<00:26, 12.47it/s]
 88%|████████▊ | 2488/2814 [03:30<00:26, 12.20it/s]
 88%|████████▊ | 2490/2814 [03:30<00:27, 11.99it/s]
 89%|████████▊ | 2492/2814 [03:30<00:25, 12.44it/s]
 89%|████████▊ | 2494/2814 [03:30<00:25, 12.47it/s]
 89%|████████▊ | 2496/2814 [03:31<00:26, 12.18it/s]
 89%|████████▉ | 2498/2814 [03:31<00:24, 12.67it/s]
 89%|████████▉ | 2500/2814 [03:31<00:24, 12.58it/s]
 89%|████████▉ | 2502/2814 [03:31<00:24, 12.73it/s]
 89%|████████▉ | 2504/2814 [03:31<00:25, 12.27it/s]
 89%|████████▉ | 2506/2814 [03:31<00:25, 12.19it/s]
 89%|████████▉ | 2508/2814 [03:32<00:25, 12.01it/s]
 89%|████████▉ | 2510/2814 [03:32<00:24, 12.43it/s]
 89%|████████▉ | 2512/2814 [03:32<00:24, 12.21it/s]
 89%|████████▉ | 2514/2814 [03:32<00:24, 12.47it/s]
 89%|████████▉ | 2516/2814 [03:32<00:24, 12.33it/s]
 89%|████████▉ | 2518/2814 [03:32<00:23, 12.43it/s]
 90%|████████▉ | 2520/2814 [03:33<00:24, 12.10it/s]
 90%|████████▉ | 2522/2814 [03:33<00:23, 12.33it/s]
 90%|████████▉ | 2524/2814 [03:33<00:23, 12.27it/s]
 90%|████████▉ | 2526/2814 [03:33<00:23, 12.28it/s]
 90%|████████▉ | 2528/2814 [03:33<00:23, 12.34it/s]
 90%|████████▉ | 2530/2814 [03:33<00:23, 12.14it/s]
 90%|████████▉ | 2532/2814 [03:33<00:22, 12.49it/s]
 90%|█████████ | 2534/2814 [03:34<00:22, 12.37it/s]
 90%|█████████ | 2536/2814 [03:34<00:23, 11.94it/s]
 90%|█████████ | 2538/2814 [03:34<00:23, 11.83it/s]
 90%|█████████ | 2540/2814 [03:34<00:23, 11.70it/s]
 90%|█████████ | 2542/2814 [03:34<00:23, 11.64it/s]
 90%|█████████ | 2544/2814 [03:35<00:23, 11.60it/s]
 90%|█████████ | 2546/2814 [03:35<00:22, 11.71it/s]
 91%|█████████ | 2548/2814 [03:35<00:22, 11.59it/s]
 91%|█████████ | 2550/2814 [03:35<00:22, 11.68it/s]
 91%|█████████ | 2552/2814 [03:35<00:22, 11.89it/s]
 91%|█████████ | 2554/2814 [03:35<00:19, 13.25it/s]
 91%|█████████ | 2556/2814 [03:35<00:19, 13.07it/s]
 91%|█████████ | 2558/2814 [03:36<00:20, 12.59it/s]
 91%|█████████ | 2560/2814 [03:36<00:20, 12.53it/s]
 91%|█████████ | 2562/2814 [03:36<00:20, 12.27it/s]
 91%|█████████ | 2564/2814 [03:36<00:20, 12.29it/s]
 91%|█████████ | 2566/2814 [03:36<00:20, 11.95it/s]
 91%|█████████▏| 2568/2814 [03:36<00:20, 11.87it/s]
 91%|█████████▏| 2570/2814 [03:37<00:20, 12.16it/s]
 91%|█████████▏| 2572/2814 [03:37<00:20, 11.86it/s]
 91%|█████████▏| 2574/2814 [03:37<00:20, 11.74it/s]
 92%|█████████▏| 2576/2814 [03:37<00:20, 11.74it/s]
 92%|█████████▏| 2578/2814 [03:37<00:20, 11.65it/s]
 92%|█████████▏| 2580/2814 [03:38<00:19, 11.94it/s]
 92%|█████████▏| 2582/2814 [03:38<00:19, 12.03it/s]
 92%|█████████▏| 2584/2814 [03:38<00:19, 11.82it/s]
 92%|█████████▏| 2586/2814 [03:38<00:19, 11.73it/s]
 92%|█████████▏| 2588/2814 [03:38<00:18, 12.05it/s]
 92%|█████████▏| 2590/2814 [03:38<00:18, 12.07it/s]
 92%|█████████▏| 2592/2814 [03:39<00:18, 12.27it/s]
 92%|█████████▏| 2594/2814 [03:39<00:17, 12.31it/s]
 92%|█████████▏| 2596/2814 [03:39<00:18, 12.07it/s]
 92%|█████████▏| 2598/2814 [03:39<00:17, 12.00it/s]
 92%|█████████▏| 2600/2814 [03:39<00:17, 12.11it/s]
 92%|█████████▏| 2602/2814 [03:39<00:17, 12.26it/s]
 93%|█████████▎| 2604/2814 [03:40<00:17, 11.90it/s]
 93%|█████████▎| 2606/2814 [03:40<00:17, 12.07it/s]
 93%|█████████▎| 2608/2814 [03:40<00:16, 12.37it/s]
 93%|█████████▎| 2610/2814 [03:40<00:16, 12.35it/s]
 93%|█████████▎| 2612/2814 [03:40<00:16, 12.06it/s]
 93%|█████████▎| 2614/2814 [03:40<00:16, 11.93it/s]
 93%|█████████▎| 2616/2814 [03:40<00:16, 12.32it/s]
 93%|█████████▎| 2618/2814 [03:41<00:16, 12.07it/s]
 93%|█████████▎| 2620/2814 [03:41<00:16, 11.83it/s]
 93%|█████████▎| 2622/2814 [03:41<00:16, 11.83it/s]
 93%|█████████▎| 2624/2814 [03:41<00:16, 11.79it/s]
 93%|█████████▎| 2626/2814 [03:41<00:15, 11.85it/s]
 93%|█████████▎| 2628/2814 [03:42<00:15, 11.82it/s]
 93%|█████████▎| 2630/2814 [03:42<00:15, 11.72it/s]
 94%|█████████▎| 2632/2814 [03:42<00:15, 12.09it/s]
 94%|█████████▎| 2634/2814 [03:42<00:14, 12.16it/s]
 94%|█████████▎| 2636/2814 [03:42<00:14, 12.54it/s]
 94%|█████████▎| 2638/2814 [03:42<00:14, 12.19it/s]
 94%|█████████▍| 2640/2814 [03:42<00:14, 12.07it/s]
 94%|█████████▍| 2642/2814 [03:43<00:13, 12.37it/s]
 94%|█████████▍| 2644/2814 [03:43<00:14, 11.93it/s]
 94%|█████████▍| 2646/2814 [03:43<00:14, 11.91it/s]
 94%|█████████▍| 2648/2814 [03:43<00:14, 11.78it/s]
 94%|█████████▍| 2650/2814 [03:43<00:13, 11.75it/s]
 94%|█████████▍| 2652/2814 [03:44<00:13, 11.61it/s]
 94%|█████████▍| 2654/2814 [03:44<00:13, 11.76it/s]
 94%|█████████▍| 2656/2814 [03:44<00:13, 12.11it/s]
 94%|█████████▍| 2658/2814 [03:44<00:12, 12.17it/s]
 95%|█████████▍| 2660/2814 [03:44<00:12, 12.17it/s]
 95%|█████████▍| 2662/2814 [03:44<00:12, 12.01it/s]
 95%|█████████▍| 2664/2814 [03:45<00:12, 11.81it/s]
 95%|█████████▍| 2666/2814 [03:45<00:12, 11.76it/s]
 95%|█████████▍| 2668/2814 [03:45<00:12, 11.99it/s]
 95%|█████████▍| 2670/2814 [03:45<00:12, 11.74it/s]
 95%|█████████▍| 2672/2814 [03:45<00:12, 11.67it/s]
 95%|█████████▌| 2674/2814 [03:45<00:12, 11.58it/s]
 95%|█████████▌| 2676/2814 [03:46<00:11, 11.87it/s]
 95%|█████████▌| 2678/2814 [03:46<00:11, 11.75it/s]
 95%|█████████▌| 2680/2814 [03:46<00:11, 11.92it/s]
 95%|█████████▌| 2682/2814 [03:46<00:11, 11.89it/s]
 95%|█████████▌| 2684/2814 [03:46<00:11, 11.74it/s]
 95%|█████████▌| 2686/2814 [03:46<00:10, 11.98it/s]
 96%|█████████▌| 2688/2814 [03:47<00:10, 11.95it/s]
 96%|█████████▌| 2690/2814 [03:47<00:10, 12.08it/s]
 96%|█████████▌| 2692/2814 [03:47<00:09, 12.62it/s]
 96%|█████████▌| 2694/2814 [03:47<00:09, 12.89it/s]
 96%|█████████▌| 2696/2814 [03:47<00:09, 12.35it/s]
 96%|█████████▌| 2698/2814 [03:47<00:09, 12.12it/s]
 96%|█████████▌| 2700/2814 [03:47<00:08, 12.77it/s]
 96%|█████████▌| 2702/2814 [03:48<00:09, 12.29it/s]
 96%|█████████▌| 2704/2814 [03:48<00:09, 12.12it/s]
 96%|█████████▌| 2706/2814 [03:48<00:08, 12.37it/s]
 96%|█████████▌| 2708/2814 [03:48<00:08, 12.01it/s]
 96%|█████████▋| 2710/2814 [03:48<00:08, 12.36it/s]
 96%|█████████▋| 2712/2814 [03:48<00:08, 12.04it/s]
 96%|█████████▋| 2714/2814 [03:49<00:08, 11.80it/s]
 97%|█████████▋| 2716/2814 [03:49<00:08, 11.91it/s]
 97%|█████████▋| 2718/2814 [03:49<00:07, 12.03it/s]
 97%|█████████▋| 2720/2814 [03:49<00:07, 12.04it/s]
 97%|█████████▋| 2722/2814 [03:49<00:07, 11.81it/s]
 97%|█████████▋| 2724/2814 [03:49<00:07, 11.86it/s]
 97%|█████████▋| 2726/2814 [03:50<00:07, 11.77it/s]
 97%|█████████▋| 2728/2814 [03:50<00:07, 12.10it/s]
 97%|█████████▋| 2730/2814 [03:50<00:06, 12.04it/s]
 97%|█████████▋| 2732/2814 [03:50<00:07, 11.71it/s]
 97%|█████████▋| 2734/2814 [03:50<00:06, 11.53it/s]
 97%|█████████▋| 2736/2814 [03:51<00:06, 11.48it/s]
 97%|█████████▋| 2738/2814 [03:51<00:06, 11.53it/s]
 97%|█████████▋| 2740/2814 [03:51<00:06, 11.55it/s]
 97%|█████████▋| 2742/2814 [03:51<00:06, 11.99it/s]
 98%|█████████▊| 2744/2814 [03:51<00:05, 11.84it/s]
 98%|█████████▊| 2746/2814 [03:51<00:05, 11.96it/s]
 98%|█████████▊| 2748/2814 [03:52<00:05, 12.04it/s]
 98%|█████████▊| 2750/2814 [03:52<00:05, 11.71it/s]
 98%|█████████▊| 2752/2814 [03:52<00:05, 11.61it/s]
 98%|█████████▊| 2754/2814 [03:52<00:05, 11.71it/s]
 98%|█████████▊| 2756/2814 [03:52<00:04, 11.61it/s]
 98%|█████████▊| 2758/2814 [03:52<00:04, 12.18it/s]
 98%|█████████▊| 2760/2814 [03:53<00:04, 12.03it/s]
 98%|█████████▊| 2762/2814 [03:53<00:04, 12.22it/s]
 98%|█████████▊| 2764/2814 [03:53<00:04, 12.31it/s]
 98%|█████████▊| 2766/2814 [03:53<00:03, 12.02it/s]
 98%|█████████▊| 2768/2814 [03:53<00:03, 12.19it/s]
 98%|█████████▊| 2770/2814 [03:53<00:03, 12.50it/s]
 99%|█████████▊| 2772/2814 [03:53<00:03, 12.97it/s]
 99%|█████████▊| 2774/2814 [03:54<00:03, 12.43it/s]
 99%|█████████▊| 2776/2814 [03:54<00:03, 12.12it/s]
 99%|█████████▊| 2778/2814 [03:54<00:02, 12.09it/s]
 99%|█████████▉| 2780/2814 [03:54<00:02, 12.12it/s]
 99%|█████████▉| 2782/2814 [03:54<00:02, 12.00it/s]
 99%|█████████▉| 2784/2814 [03:54<00:02, 12.29it/s]
 99%|█████████▉| 2786/2814 [03:55<00:02, 12.06it/s]
 99%|█████████▉| 2788/2814 [03:55<00:02, 12.23it/s]
 99%|█████████▉| 2790/2814 [03:55<00:02, 11.97it/s]
 99%|█████████▉| 2792/2814 [03:55<00:01, 12.15it/s]
 99%|█████████▉| 2794/2814 [03:55<00:01, 12.79it/s]
 99%|█████████▉| 2796/2814 [03:55<00:01, 12.40it/s]
 99%|█████████▉| 2798/2814 [03:56<00:01, 11.95it/s]
100%|█████████▉| 2800/2814 [03:56<00:01, 11.94it/s]
100%|█████████▉| 2802/2814 [03:56<00:01, 11.82it/s]
100%|█████████▉| 2804/2814 [03:56<00:00, 11.68it/s]
100%|█████████▉| 2806/2814 [03:56<00:00, 11.78it/s]
100%|█████████▉| 2808/2814 [03:56<00:00, 12.39it/s]
100%|█████████▉| 2810/2814 [03:57<00:00, 12.16it/s]
100%|█████████▉| 2812/2814 [03:57<00:00, 11.94it/s]
100%|██████████| 2814/2814 [03:57<00:00, 12.39it/s]
                                                   

100%|██████████| 2814/2814 [03:57<00:00, 12.39it/s]{'eval_loss': 0.6747675538063049, 'eval_accuracy': 0.718, 'eval_f1': 0.7143119532678139, 'eval_runtime': 1.7319, 'eval_samples_per_second': 1443.53, 'eval_steps_per_second': 180.73, 'epoch': 2.0}
{'loss': 0.5072, 'learning_rate': 9.437386126923775e-09, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.23it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.48it/s]

 21%|██        | 66/313 [00:00<00:01, 205.93it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.18it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.49it/s]

 40%|████      | 126/313 [00:00<00:01, 185.24it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.10it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.13it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.33it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.48it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.59it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.30it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.12it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.93it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 179.00it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 179.00it/s]
100%|██████████| 2814/2814 [03:59<00:00, 12.39it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 2814/2814 [04:00<00:00, 12.39it/s]
100%|██████████| 2814/2814 [04:00<00:00, 11.72it/s]
[I 2023-10-26 22:23:26,766] Trial 6 finished with value: 0.716991552355688 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 1.19477308366855e-05, 'per_device_train_batch_size': 32, 'weight_decay': 2.001235527475546e-05}. Best is trial 6 with value: 0.716991552355688.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.683558464050293, 'eval_accuracy': 0.718, 'eval_f1': 0.716991552355688, 'eval_runtime': 1.7296, 'eval_samples_per_second': 1445.428, 'eval_steps_per_second': 180.968, 'epoch': 3.0}
{'train_runtime': 240.1433, 'train_samples_per_second': 374.776, 'train_steps_per_second': 11.718, 'train_loss': 0.6450330548533838, 'epoch': 3.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<03:59, 11.76it/s]
  0%|          | 4/2814 [00:00<04:00, 11.68it/s]
  0%|          | 6/2814 [00:00<04:00, 11.68it/s]
  0%|          | 8/2814 [00:00<03:57, 11.82it/s]
  0%|          | 10/2814 [00:00<04:00, 11.66it/s]
  0%|          | 12/2814 [00:01<04:02, 11.55it/s]
  0%|          | 14/2814 [00:01<04:01, 11.58it/s]
  1%|          | 16/2814 [00:01<03:54, 11.93it/s]
  1%|          | 18/2814 [00:01<03:55, 11.89it/s]
  1%|          | 20/2814 [00:01<03:48, 12.20it/s]
  1%|          | 22/2814 [00:01<03:51, 12.05it/s]
  1%|          | 24/2814 [00:01<03:36, 12.88it/s]
  1%|          | 26/2814 [00:02<03:39, 12.69it/s]
  1%|          | 28/2814 [00:02<03:46, 12.29it/s]
  1%|          | 30/2814 [00:02<03:48, 12.17it/s]
  1%|          | 32/2814 [00:02<03:38, 12.71it/s]
  1%|          | 34/2814 [00:02<03:36, 12.84it/s]
  1%|▏         | 36/2814 [00:02<03:37, 12.75it/s]
  1%|▏         | 38/2814 [00:03<03:45, 12.29it/s]
  1%|▏         | 40/2814 [00:03<03:52, 11.94it/s]
  1%|▏         | 42/2814 [00:03<03:46, 12.24it/s]
  2%|▏         | 44/2814 [00:03<03:50, 12.02it/s]
  2%|▏         | 46/2814 [00:03<03:52, 11.88it/s]
  2%|▏         | 48/2814 [00:03<03:52, 11.91it/s]
  2%|▏         | 50/2814 [00:04<03:49, 12.02it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.93it/s]
  2%|▏         | 54/2814 [00:04<03:50, 11.97it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.09it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.06it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.82it/s]
  2%|▏         | 62/2814 [00:05<03:28, 13.17it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.62it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.08it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.90it/s]
  2%|▏         | 70/2814 [00:05<03:56, 11.63it/s]
  3%|▎         | 72/2814 [00:05<03:56, 11.61it/s]
  3%|▎         | 74/2814 [00:06<03:50, 11.90it/s]
  3%|▎         | 76/2814 [00:06<03:52, 11.80it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.75it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.28it/s]
  3%|▎         | 82/2814 [00:06<03:47, 12.00it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.11it/s]
  3%|▎         | 86/2814 [00:07<03:43, 12.19it/s]
  3%|▎         | 88/2814 [00:07<03:42, 12.25it/s]
  3%|▎         | 90/2814 [00:07<03:43, 12.18it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.69it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.18it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.33it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.21it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.02it/s]
  4%|▎         | 102/2814 [00:08<03:41, 12.25it/s]
  4%|▎         | 104/2814 [00:08<03:30, 12.85it/s]
  4%|▍         | 106/2814 [00:08<03:38, 12.40it/s]
  4%|▍         | 108/2814 [00:08<03:40, 12.26it/s]
  4%|▍         | 110/2814 [00:09<03:32, 12.72it/s]
  4%|▍         | 112/2814 [00:09<03:40, 12.27it/s]
  4%|▍         | 114/2814 [00:09<03:42, 12.13it/s]
  4%|▍         | 116/2814 [00:09<03:37, 12.43it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.05it/s]
  4%|▍         | 120/2814 [00:09<03:37, 12.40it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.04it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.20it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.93it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.08it/s]
  5%|▍         | 130/2814 [00:10<03:44, 11.93it/s]
  5%|▍         | 132/2814 [00:10<03:34, 12.50it/s]
  5%|▍         | 134/2814 [00:11<03:32, 12.62it/s]
  5%|▍         | 136/2814 [00:11<03:34, 12.51it/s]
  5%|▍         | 138/2814 [00:11<03:35, 12.43it/s]
  5%|▍         | 140/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 142/2814 [00:11<03:34, 12.46it/s]
  5%|▌         | 144/2814 [00:11<03:39, 12.18it/s]
  5%|▌         | 146/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 148/2814 [00:12<03:41, 12.05it/s]
  5%|▌         | 150/2814 [00:12<03:35, 12.38it/s]
  5%|▌         | 152/2814 [00:12<03:40, 12.10it/s]
  5%|▌         | 154/2814 [00:12<03:43, 11.91it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.41it/s]
  6%|▌         | 158/2814 [00:12<03:34, 12.37it/s]
  6%|▌         | 160/2814 [00:13<03:40, 12.02it/s]
  6%|▌         | 162/2814 [00:13<03:38, 12.13it/s]
  6%|▌         | 164/2814 [00:13<03:38, 12.11it/s]
  6%|▌         | 166/2814 [00:13<03:36, 12.21it/s]
  6%|▌         | 168/2814 [00:13<03:32, 12.43it/s]
  6%|▌         | 170/2814 [00:14<04:17, 10.25it/s]
  6%|▌         | 172/2814 [00:14<04:09, 10.60it/s]
  6%|▌         | 174/2814 [00:14<03:54, 11.27it/s]
  6%|▋         | 176/2814 [00:14<03:43, 11.79it/s]
  6%|▋         | 178/2814 [00:14<03:32, 12.41it/s]
  6%|▋         | 180/2814 [00:14<03:38, 12.07it/s]
  6%|▋         | 182/2814 [00:15<03:42, 11.82it/s]
  7%|▋         | 184/2814 [00:15<03:45, 11.66it/s]
  7%|▋         | 186/2814 [00:15<03:46, 11.60it/s]
  7%|▋         | 188/2814 [00:15<03:41, 11.88it/s]
  7%|▋         | 190/2814 [00:15<03:41, 11.86it/s]
  7%|▋         | 192/2814 [00:15<03:38, 12.00it/s]
  7%|▋         | 194/2814 [00:16<03:40, 11.88it/s]
  7%|▋         | 196/2814 [00:16<03:42, 11.77it/s]
  7%|▋         | 198/2814 [00:16<03:40, 11.88it/s]
  7%|▋         | 200/2814 [00:16<03:38, 11.95it/s]
  7%|▋         | 202/2814 [00:16<03:40, 11.84it/s]
  7%|▋         | 204/2814 [00:16<03:41, 11.76it/s]
  7%|▋         | 206/2814 [00:17<03:46, 11.54it/s]
  7%|▋         | 208/2814 [00:17<03:29, 12.47it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.55it/s]
  8%|▊         | 214/2814 [00:17<03:27, 12.51it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 218/2814 [00:17<03:21, 12.89it/s]
  8%|▊         | 220/2814 [00:18<03:23, 12.73it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.92it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.44it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.10it/s]
  8%|▊         | 228/2814 [00:18<03:23, 12.68it/s]
  8%|▊         | 230/2814 [00:18<03:31, 12.24it/s]
  8%|▊         | 232/2814 [00:19<03:41, 11.63it/s]
  8%|▊         | 234/2814 [00:19<03:36, 11.92it/s]
  8%|▊         | 236/2814 [00:19<03:35, 11.95it/s]
  8%|▊         | 238/2814 [00:19<03:34, 11.98it/s]
  9%|▊         | 240/2814 [00:19<03:30, 12.21it/s]
  9%|▊         | 242/2814 [00:19<03:33, 12.03it/s]
  9%|▊         | 244/2814 [00:20<03:32, 12.09it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.29it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.78it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.53it/s]
  9%|▉         | 252/2814 [00:20<03:30, 12.16it/s]
  9%|▉         | 254/2814 [00:20<03:19, 12.81it/s]
  9%|▉         | 256/2814 [00:21<03:26, 12.39it/s]
  9%|▉         | 258/2814 [00:21<03:31, 12.11it/s]
  9%|▉         | 260/2814 [00:21<03:35, 11.87it/s]
  9%|▉         | 262/2814 [00:21<03:38, 11.66it/s]
  9%|▉         | 264/2814 [00:21<03:32, 12.00it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.78it/s]
 10%|▉         | 268/2814 [00:22<03:38, 11.63it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.99it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.26it/s]
 10%|▉         | 274/2814 [00:22<03:30, 12.07it/s]
 10%|▉         | 276/2814 [00:22<03:31, 11.99it/s]
 10%|▉         | 278/2814 [00:22<03:29, 12.08it/s]
 10%|▉         | 280/2814 [00:23<03:27, 12.23it/s]
 10%|█         | 282/2814 [00:23<03:30, 12.04it/s]
 10%|█         | 284/2814 [00:23<03:31, 11.95it/s]
 10%|█         | 286/2814 [00:23<03:25, 12.29it/s]
 10%|█         | 288/2814 [00:23<03:27, 12.17it/s]
 10%|█         | 290/2814 [00:23<03:28, 12.11it/s]
 10%|█         | 292/2814 [00:24<04:57,  8.49it/s]
 10%|█         | 294/2814 [00:24<04:34,  9.19it/s]
 11%|█         | 296/2814 [00:24<04:11, 10.01it/s]
 11%|█         | 298/2814 [00:24<04:02, 10.37it/s]
 11%|█         | 300/2814 [00:24<03:43, 11.27it/s]
 11%|█         | 302/2814 [00:25<03:43, 11.23it/s]
 11%|█         | 304/2814 [00:25<03:41, 11.33it/s]
 11%|█         | 306/2814 [00:25<03:39, 11.42it/s]
 11%|█         | 308/2814 [00:25<03:39, 11.43it/s]
 11%|█         | 310/2814 [00:25<03:31, 11.83it/s]
 11%|█         | 312/2814 [00:26<03:31, 11.81it/s]
 11%|█         | 314/2814 [00:26<03:28, 11.96it/s]
 11%|█         | 316/2814 [00:26<03:25, 12.17it/s]
 11%|█▏        | 318/2814 [00:26<03:28, 11.95it/s]
 11%|█▏        | 320/2814 [00:26<03:25, 12.13it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.55it/s]
 12%|█▏        | 324/2814 [00:26<03:25, 12.14it/s]
 12%|█▏        | 326/2814 [00:27<03:28, 11.93it/s]
 12%|█▏        | 328/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 332/2814 [00:27<03:24, 12.16it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.02it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.34it/s]
 12%|█▏        | 338/2814 [00:28<03:25, 12.03it/s]
 12%|█▏        | 340/2814 [00:28<03:29, 11.80it/s]
 12%|█▏        | 342/2814 [00:28<03:32, 11.61it/s]
 12%|█▏        | 344/2814 [00:28<03:27, 11.92it/s]
 12%|█▏        | 346/2814 [00:28<03:24, 12.06it/s]
 12%|█▏        | 348/2814 [00:28<03:26, 11.95it/s]
 12%|█▏        | 350/2814 [00:29<03:23, 12.09it/s]
 13%|█▎        | 352/2814 [00:29<03:48, 10.76it/s]
 13%|█▎        | 354/2814 [00:29<03:43, 10.98it/s]
 13%|█▎        | 356/2814 [00:29<03:36, 11.37it/s]
 13%|█▎        | 358/2814 [00:29<03:35, 11.41it/s]
 13%|█▎        | 360/2814 [00:30<03:36, 11.32it/s]
 13%|█▎        | 362/2814 [00:30<03:29, 11.72it/s]
 13%|█▎        | 364/2814 [00:30<03:29, 11.68it/s]
 13%|█▎        | 366/2814 [00:30<03:30, 11.60it/s]
 13%|█▎        | 368/2814 [00:30<03:29, 11.70it/s]
 13%|█▎        | 370/2814 [00:30<03:30, 11.60it/s]
 13%|█▎        | 372/2814 [00:31<03:20, 12.16it/s]
 13%|█▎        | 374/2814 [00:31<03:24, 11.91it/s]
 13%|█▎        | 376/2814 [00:31<03:27, 11.76it/s]
 13%|█▎        | 378/2814 [00:31<03:27, 11.72it/s]
 14%|█▎        | 380/2814 [00:31<03:24, 11.91it/s]
 14%|█▎        | 382/2814 [00:31<03:26, 11.78it/s]
 14%|█▎        | 384/2814 [00:32<03:22, 11.97it/s]
 14%|█▎        | 386/2814 [00:32<03:25, 11.81it/s]
 14%|█▍        | 388/2814 [00:32<03:24, 11.89it/s]
 14%|█▍        | 390/2814 [00:32<03:26, 11.75it/s]
 14%|█▍        | 392/2814 [00:32<03:10, 12.70it/s]
 14%|█▍        | 394/2814 [00:32<03:18, 12.19it/s]
 14%|█▍        | 396/2814 [00:33<03:21, 12.00it/s]
 14%|█▍        | 398/2814 [00:33<03:19, 12.13it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.89it/s]
 14%|█▍        | 402/2814 [00:33<03:17, 12.18it/s]
 14%|█▍        | 404/2814 [00:33<03:19, 12.06it/s]
 14%|█▍        | 406/2814 [00:33<03:23, 11.82it/s]
 14%|█▍        | 408/2814 [00:34<03:16, 12.26it/s]
 15%|█▍        | 410/2814 [00:34<03:20, 11.97it/s]
 15%|█▍        | 412/2814 [00:34<04:06,  9.74it/s]
 15%|█▍        | 414/2814 [00:34<03:56, 10.17it/s]
 15%|█▍        | 416/2814 [00:34<03:35, 11.15it/s]
 15%|█▍        | 418/2814 [00:35<03:28, 11.49it/s]
 15%|█▍        | 420/2814 [00:35<03:26, 11.62it/s]
 15%|█▍        | 422/2814 [00:35<03:19, 11.98it/s]
 15%|█▌        | 424/2814 [00:35<03:21, 11.86it/s]
 15%|█▌        | 426/2814 [00:35<03:16, 12.14it/s]
 15%|█▌        | 428/2814 [00:35<03:16, 12.12it/s]
 15%|█▌        | 430/2814 [00:35<03:10, 12.49it/s]
 15%|█▌        | 432/2814 [00:36<03:16, 12.15it/s]
 15%|█▌        | 434/2814 [00:36<03:11, 12.45it/s]
 15%|█▌        | 436/2814 [00:36<03:11, 12.41it/s]
 16%|█▌        | 438/2814 [00:36<03:14, 12.22it/s]
 16%|█▌        | 440/2814 [00:36<03:17, 12.03it/s]
 16%|█▌        | 442/2814 [00:36<03:19, 11.87it/s]
 16%|█▌        | 444/2814 [00:37<03:13, 12.23it/s]
 16%|█▌        | 446/2814 [00:37<03:15, 12.09it/s]
 16%|█▌        | 448/2814 [00:37<03:21, 11.75it/s]
 16%|█▌        | 450/2814 [00:37<03:08, 12.53it/s]
 16%|█▌        | 452/2814 [00:37<03:06, 12.65it/s]
 16%|█▌        | 454/2814 [00:37<03:12, 12.25it/s]
 16%|█▌        | 456/2814 [00:38<03:08, 12.50it/s]
 16%|█▋        | 458/2814 [00:38<03:03, 12.86it/s]
 16%|█▋        | 460/2814 [00:38<03:11, 12.31it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.99it/s]
 16%|█▋        | 464/2814 [00:38<03:17, 11.89it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.26it/s]
 17%|█▋        | 468/2814 [00:39<03:10, 12.30it/s]
 17%|█▋        | 470/2814 [00:39<03:14, 12.07it/s]
 17%|█▋        | 472/2814 [00:39<03:10, 12.33it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.52it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 12.00it/s]
 17%|█▋        | 480/2814 [00:40<03:15, 11.95it/s]
 17%|█▋        | 482/2814 [00:40<03:14, 11.97it/s]
 17%|█▋        | 484/2814 [00:40<03:16, 11.86it/s]
 17%|█▋        | 486/2814 [00:40<03:19, 11.69it/s]
 17%|█▋        | 488/2814 [00:40<03:19, 11.66it/s]
 17%|█▋        | 490/2814 [00:40<03:13, 12.00it/s]
 17%|█▋        | 492/2814 [00:41<03:15, 11.87it/s]
 18%|█▊        | 494/2814 [00:41<03:15, 11.84it/s]
 18%|█▊        | 496/2814 [00:41<03:07, 12.38it/s]
 18%|█▊        | 498/2814 [00:41<03:11, 12.11it/s]
 18%|█▊        | 500/2814 [00:41<03:08, 12.25it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.43it/s]
 18%|█▊        | 504/2814 [00:42<03:02, 12.68it/s]
 18%|█▊        | 506/2814 [00:42<03:07, 12.34it/s]
 18%|█▊        | 508/2814 [00:42<03:04, 12.47it/s]
 18%|█▊        | 510/2814 [00:42<02:57, 12.99it/s]
 18%|█▊        | 512/2814 [00:42<03:02, 12.59it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.69it/s]
 18%|█▊        | 516/2814 [00:43<03:06, 12.31it/s]
 18%|█▊        | 518/2814 [00:43<03:03, 12.54it/s]
 18%|█▊        | 520/2814 [00:43<03:07, 12.21it/s]
 19%|█▊        | 522/2814 [00:43<03:12, 11.92it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.34it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.67it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.33it/s]
 19%|█▉        | 530/2814 [00:44<03:08, 12.11it/s]
 19%|█▉        | 532/2814 [00:44<03:07, 12.18it/s]
 19%|█▉        | 534/2814 [00:44<03:01, 12.55it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.17it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.02it/s]
 19%|█▉        | 540/2814 [00:45<03:13, 11.77it/s]
 19%|█▉        | 542/2814 [00:45<03:12, 11.81it/s]
 19%|█▉        | 544/2814 [00:45<03:02, 12.43it/s]
 19%|█▉        | 546/2814 [00:45<03:01, 12.49it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.16it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.52it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.31it/s]
 20%|█▉        | 554/2814 [00:46<03:04, 12.25it/s]
 20%|█▉        | 556/2814 [00:46<02:57, 12.70it/s]
 20%|█▉        | 558/2814 [00:46<03:00, 12.49it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.47it/s]
 20%|█▉        | 562/2814 [00:46<03:07, 12.04it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.95it/s]
 20%|██        | 566/2814 [00:47<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:47<03:01, 12.34it/s]
 20%|██        | 570/2814 [00:47<03:06, 12.03it/s]
 20%|██        | 572/2814 [00:47<03:09, 11.82it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.04it/s]
 20%|██        | 576/2814 [00:47<02:57, 12.63it/s]
 21%|██        | 578/2814 [00:48<02:57, 12.59it/s]
 21%|██        | 580/2814 [00:48<03:04, 12.12it/s]
 21%|██        | 582/2814 [00:48<02:55, 12.71it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.48it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.27it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.63it/s]
 21%|██        | 590/2814 [00:49<02:59, 12.40it/s]
 21%|██        | 592/2814 [00:49<02:57, 12.51it/s]
 21%|██        | 594/2814 [00:49<03:01, 12.20it/s]
 21%|██        | 596/2814 [00:49<03:05, 11.99it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.75it/s]
 21%|██▏       | 600/2814 [00:49<02:47, 13.21it/s]
 21%|██▏       | 602/2814 [00:49<02:44, 13.44it/s]
 21%|██▏       | 604/2814 [00:50<02:47, 13.17it/s]
 22%|██▏       | 606/2814 [00:50<02:52, 12.81it/s]
 22%|██▏       | 608/2814 [00:50<02:52, 12.77it/s]
 22%|██▏       | 610/2814 [00:50<02:47, 13.13it/s]
 22%|██▏       | 612/2814 [00:50<02:55, 12.56it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.09it/s]
 22%|██▏       | 616/2814 [00:51<03:05, 11.87it/s]
 22%|██▏       | 618/2814 [00:51<03:00, 12.15it/s]
 22%|██▏       | 620/2814 [00:51<02:59, 12.19it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.09it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.20it/s]
 22%|██▏       | 626/2814 [00:51<02:59, 12.17it/s]
 22%|██▏       | 628/2814 [00:52<02:51, 12.74it/s]
 22%|██▏       | 630/2814 [00:52<02:52, 12.63it/s]
 22%|██▏       | 632/2814 [00:52<02:52, 12.68it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.21it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.96it/s]
 23%|██▎       | 638/2814 [00:52<03:04, 11.78it/s]
 23%|██▎       | 640/2814 [00:53<03:06, 11.68it/s]
 23%|██▎       | 642/2814 [00:53<03:02, 11.92it/s]
 23%|██▎       | 644/2814 [00:53<02:51, 12.62it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.14it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.99it/s]
 23%|██▎       | 650/2814 [00:53<02:56, 12.25it/s]
 23%|██▎       | 652/2814 [00:54<03:01, 11.90it/s]
 23%|██▎       | 654/2814 [00:54<03:02, 11.82it/s]
 23%|██▎       | 656/2814 [00:54<02:54, 12.35it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.29it/s]
 23%|██▎       | 660/2814 [00:54<02:54, 12.37it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.35it/s]
 24%|██▎       | 664/2814 [00:55<02:57, 12.10it/s]
 24%|██▎       | 666/2814 [00:55<02:55, 12.25it/s]
 24%|██▎       | 668/2814 [00:55<02:57, 12.06it/s]
 24%|██▍       | 670/2814 [00:55<03:01, 11.79it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.05it/s]
 24%|██▍       | 674/2814 [00:55<02:55, 12.17it/s]
 24%|██▍       | 676/2814 [00:56<02:54, 12.28it/s]
 24%|██▍       | 678/2814 [00:56<02:53, 12.30it/s]
 24%|██▍       | 680/2814 [00:56<02:55, 12.13it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.10it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.75it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.90it/s]
 24%|██▍       | 688/2814 [00:57<02:56, 12.02it/s]
 25%|██▍       | 690/2814 [00:57<02:57, 11.98it/s]
 25%|██▍       | 692/2814 [00:57<03:00, 11.73it/s]
 25%|██▍       | 694/2814 [00:57<02:52, 12.28it/s]
 25%|██▍       | 696/2814 [00:57<02:52, 12.24it/s]
 25%|██▍       | 698/2814 [00:57<02:49, 12.47it/s]
 25%|██▍       | 700/2814 [00:58<02:49, 12.49it/s]
 25%|██▍       | 702/2814 [00:58<02:49, 12.48it/s]
 25%|██▌       | 704/2814 [00:58<02:53, 12.16it/s]
 25%|██▌       | 706/2814 [00:58<02:47, 12.58it/s]
 25%|██▌       | 708/2814 [00:58<02:43, 12.85it/s]
 25%|██▌       | 710/2814 [00:58<02:49, 12.38it/s]
 25%|██▌       | 712/2814 [00:59<02:52, 12.17it/s]
 25%|██▌       | 714/2814 [00:59<02:51, 12.25it/s]
 25%|██▌       | 716/2814 [00:59<02:50, 12.32it/s]
 26%|██▌       | 718/2814 [00:59<02:51, 12.20it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.88it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.88it/s]
 26%|██▌       | 724/2814 [00:59<02:50, 12.23it/s]
 26%|██▌       | 726/2814 [01:00<02:42, 12.81it/s]
 26%|██▌       | 728/2814 [01:00<02:50, 12.23it/s]
 26%|██▌       | 730/2814 [01:00<02:47, 12.47it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.45it/s]
 26%|██▌       | 734/2814 [01:00<02:50, 12.17it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.26it/s]
 26%|██▌       | 738/2814 [01:01<02:51, 12.09it/s]
 26%|██▋       | 740/2814 [01:01<02:47, 12.39it/s]
 26%|██▋       | 742/2814 [01:01<02:46, 12.41it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.64it/s]
 27%|██▋       | 746/2814 [01:01<02:48, 12.31it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.30it/s]
 27%|██▋       | 750/2814 [01:02<02:52, 11.94it/s]
 27%|██▋       | 752/2814 [01:02<02:52, 11.96it/s]
 27%|██▋       | 754/2814 [01:02<02:53, 11.86it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.07it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.93it/s]
 27%|██▋       | 760/2814 [01:02<02:48, 12.17it/s]
 27%|██▋       | 762/2814 [01:03<02:48, 12.17it/s]
 27%|██▋       | 764/2814 [01:03<02:44, 12.46it/s]
 27%|██▋       | 766/2814 [01:03<02:45, 12.36it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.12it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.92it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.80it/s]
 28%|██▊       | 774/2814 [01:04<02:46, 12.26it/s]
 28%|██▊       | 776/2814 [01:04<02:43, 12.45it/s]
 28%|██▊       | 778/2814 [01:04<02:45, 12.32it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.31it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.12it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 11.99it/s]
 28%|██▊       | 786/2814 [01:05<02:47, 12.14it/s]
 28%|██▊       | 788/2814 [01:05<02:47, 12.13it/s]
 28%|██▊       | 790/2814 [01:05<02:45, 12.23it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.29it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.13it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.52it/s]
 28%|██▊       | 798/2814 [01:06<02:44, 12.26it/s]
 28%|██▊       | 800/2814 [01:06<02:46, 12.09it/s]
 29%|██▊       | 802/2814 [01:06<02:48, 11.95it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.01it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.15it/s]
 29%|██▊       | 808/2814 [01:06<02:46, 12.01it/s]
 29%|██▉       | 810/2814 [01:07<02:43, 12.23it/s]
 29%|██▉       | 812/2814 [01:07<02:38, 12.62it/s]
 29%|██▉       | 814/2814 [01:07<02:41, 12.36it/s]
 29%|██▉       | 816/2814 [01:07<02:39, 12.50it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.65it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.50it/s]
 29%|██▉       | 822/2814 [01:08<02:44, 12.13it/s]
 29%|██▉       | 824/2814 [01:08<02:40, 12.42it/s]
 29%|██▉       | 826/2814 [01:08<02:42, 12.20it/s]
 29%|██▉       | 828/2814 [01:08<02:45, 11.99it/s]
 29%|██▉       | 830/2814 [01:08<02:44, 12.09it/s]
 30%|██▉       | 832/2814 [01:08<02:46, 11.93it/s]
 30%|██▉       | 834/2814 [01:09<02:49, 11.71it/s]
 30%|██▉       | 836/2814 [01:09<02:42, 12.16it/s]
 30%|██▉       | 838/2814 [01:09<02:41, 12.21it/s]
 30%|██▉       | 840/2814 [01:09<02:45, 11.92it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.83it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.75it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.12it/s]
 30%|███       | 848/2814 [01:10<02:37, 12.50it/s]
 30%|███       | 850/2814 [01:10<02:41, 12.18it/s]
 30%|███       | 852/2814 [01:10<02:37, 12.46it/s]
 30%|███       | 854/2814 [01:10<02:39, 12.28it/s]
 30%|███       | 856/2814 [01:10<02:43, 12.00it/s]
 30%|███       | 858/2814 [01:10<02:45, 11.85it/s]
 31%|███       | 860/2814 [01:11<02:42, 11.99it/s]
 31%|███       | 862/2814 [01:11<02:43, 11.96it/s]
 31%|███       | 864/2814 [01:11<02:39, 12.25it/s]
 31%|███       | 866/2814 [01:11<02:34, 12.60it/s]
 31%|███       | 868/2814 [01:11<02:33, 12.64it/s]
 31%|███       | 870/2814 [01:11<02:38, 12.24it/s]
 31%|███       | 872/2814 [01:12<02:39, 12.20it/s]
 31%|███       | 874/2814 [01:12<02:37, 12.28it/s]
 31%|███       | 876/2814 [01:12<02:41, 12.03it/s]
 31%|███       | 878/2814 [01:12<02:37, 12.26it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.08it/s]
 31%|███▏      | 882/2814 [01:12<02:41, 11.94it/s]
 31%|███▏      | 884/2814 [01:13<02:41, 11.94it/s]
 31%|███▏      | 886/2814 [01:13<02:42, 11.88it/s]
 32%|███▏      | 888/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.89it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.61it/s]
 32%|███▏      | 896/2814 [01:14<02:41, 11.85it/s]
 32%|███▏      | 898/2814 [01:14<02:34, 12.36it/s]
 32%|███▏      | 900/2814 [01:14<02:34, 12.39it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.79it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.67it/s]
 32%|███▏      | 906/2814 [01:14<02:28, 12.89it/s]
 32%|███▏      | 908/2814 [01:15<02:33, 12.43it/s]
 32%|███▏      | 910/2814 [01:15<02:35, 12.22it/s]
 32%|███▏      | 912/2814 [01:15<02:38, 12.01it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.31it/s]
 33%|███▎      | 916/2814 [01:15<02:36, 12.10it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.05it/s]
 33%|███▎      | 920/2814 [01:16<02:35, 12.16it/s]
 33%|███▎      | 922/2814 [01:16<02:35, 12.20it/s]
 33%|███▎      | 924/2814 [01:16<02:39, 11.83it/s]
 33%|███▎      | 926/2814 [01:16<02:29, 12.67it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.79it/s]
 33%|███▎      | 930/2814 [01:16<02:31, 12.39it/s]
 33%|███▎      | 932/2814 [01:17<02:35, 12.10it/s]
 33%|███▎      | 934/2814 [01:17<02:36, 11.99it/s]
 33%|███▎      | 936/2814 [01:17<02:37, 11.92it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]{'loss': 0.9868, 'learning_rate': 1.0451012498704019e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.23it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.46it/s]

 21%|██        | 66/313 [00:00<00:01, 205.72it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.99it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.45it/s]

 40%|████      | 126/313 [00:00<00:01, 185.24it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.08it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.16it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.29it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.58it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.60it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.16it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.96it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.91it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.73it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.73it/s]
 33%|███▎      | 938/2814 [01:19<02:30, 12.48it/s]

                                                  
 33%|███▎      | 938/2814 [01:19<02:38, 11.83it/s]
[I 2023-10-26 22:24:46,804] Trial 7 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.8296237587928772, 'eval_accuracy': 0.6128, 'eval_f1': 0.5886341470096741, 'eval_runtime': 1.731, 'eval_samples_per_second': 1444.23, 'eval_steps_per_second': 180.818, 'epoch': 1.0}

  0%|          | 0/1407 [00:00<?, ?it/s]
  0%|          | 1/1407 [00:00<03:32,  6.63it/s]
  0%|          | 2/1407 [00:00<03:25,  6.83it/s]
  0%|          | 3/1407 [00:00<03:25,  6.83it/s]
  0%|          | 4/1407 [00:00<03:31,  6.64it/s]
  0%|          | 5/1407 [00:00<03:33,  6.55it/s]
  0%|          | 6/1407 [00:00<03:35,  6.50it/s]
  0%|          | 7/1407 [00:01<03:36,  6.46it/s]
  1%|          | 8/1407 [00:01<03:29,  6.67it/s]
  1%|          | 9/1407 [00:01<03:25,  6.80it/s]
  1%|          | 10/1407 [00:01<03:26,  6.78it/s]
  1%|          | 11/1407 [00:01<03:23,  6.84it/s]
  1%|          | 12/1407 [00:01<03:06,  7.47it/s]
  1%|          | 13/1407 [00:01<03:12,  7.23it/s]
  1%|          | 14/1407 [00:02<03:16,  7.10it/s]
  1%|          | 15/1407 [00:02<03:17,  7.05it/s]
  1%|          | 16/1407 [00:02<03:16,  7.09it/s]
  1%|          | 17/1407 [00:02<03:18,  7.01it/s]
  1%|▏         | 18/1407 [00:02<03:24,  6.80it/s]
  1%|▏         | 19/1407 [00:02<03:27,  6.71it/s]
  1%|▏         | 20/1407 [00:02<03:30,  6.60it/s]
  1%|▏         | 21/1407 [00:03<03:27,  6.67it/s]
  2%|▏         | 22/1407 [00:03<03:27,  6.68it/s]
  2%|▏         | 23/1407 [00:03<03:24,  6.75it/s]
  2%|▏         | 24/1407 [00:03<03:24,  6.77it/s]
  2%|▏         | 25/1407 [00:03<03:21,  6.86it/s]
  2%|▏         | 26/1407 [00:03<03:20,  6.90it/s]
  2%|▏         | 27/1407 [00:03<03:19,  6.91it/s]
  2%|▏         | 28/1407 [00:04<03:19,  6.90it/s]
  2%|▏         | 29/1407 [00:04<03:23,  6.77it/s]
  2%|▏         | 30/1407 [00:04<03:26,  6.67it/s]
  2%|▏         | 32/1407 [00:04<03:04,  7.47it/s]
  2%|▏         | 33/1407 [00:04<03:11,  7.17it/s]
  2%|▏         | 34/1407 [00:04<03:13,  7.08it/s]
  2%|▏         | 35/1407 [00:05<03:19,  6.87it/s]
  3%|▎         | 36/1407 [00:05<03:19,  6.89it/s]
  3%|▎         | 37/1407 [00:05<03:11,  7.17it/s]
  3%|▎         | 38/1407 [00:05<03:12,  7.10it/s]
  3%|▎         | 39/1407 [00:05<03:13,  7.07it/s]
  3%|▎         | 40/1407 [00:05<03:16,  6.97it/s]
  3%|▎         | 41/1407 [00:05<03:20,  6.83it/s]
  3%|▎         | 42/1407 [00:06<03:18,  6.86it/s]
  3%|▎         | 43/1407 [00:06<03:17,  6.89it/s]
  3%|▎         | 44/1407 [00:06<03:16,  6.95it/s]
  3%|▎         | 45/1407 [00:06<03:21,  6.77it/s]
  3%|▎         | 46/1407 [00:06<03:10,  7.14it/s]
  3%|▎         | 47/1407 [00:06<03:16,  6.91it/s]
  3%|▎         | 48/1407 [00:06<03:08,  7.20it/s]
  3%|▎         | 49/1407 [00:07<03:11,  7.08it/s]
  4%|▎         | 50/1407 [00:07<03:13,  7.01it/s]
  4%|▎         | 51/1407 [00:07<03:18,  6.83it/s]
  4%|▎         | 52/1407 [00:07<03:14,  6.97it/s]
  4%|▍         | 53/1407 [00:07<03:16,  6.90it/s]
  4%|▍         | 54/1407 [00:07<03:20,  6.74it/s]
  4%|▍         | 55/1407 [00:07<03:06,  7.23it/s]
  4%|▍         | 56/1407 [00:08<03:14,  6.96it/s]
  4%|▍         | 57/1407 [00:08<03:12,  7.01it/s]
  4%|▍         | 58/1407 [00:08<03:05,  7.28it/s]
  4%|▍         | 59/1407 [00:08<03:12,  7.00it/s]
  4%|▍         | 60/1407 [00:08<03:03,  7.35it/s]
  4%|▍         | 61/1407 [00:08<03:10,  7.07it/s]
  4%|▍         | 62/1407 [00:08<03:09,  7.09it/s]
  4%|▍         | 63/1407 [00:09<03:14,  6.92it/s]
  5%|▍         | 64/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 65/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 66/1407 [00:09<03:12,  6.98it/s]
  5%|▍         | 67/1407 [00:09<03:17,  6.79it/s]
  5%|▍         | 68/1407 [00:09<03:20,  6.67it/s]
  5%|▍         | 69/1407 [00:09<03:18,  6.74it/s]
  5%|▍         | 70/1407 [00:10<03:16,  6.80it/s]
  5%|▌         | 71/1407 [00:10<03:16,  6.80it/s]
  5%|▌         | 72/1407 [00:10<03:14,  6.85it/s]
  5%|▌         | 73/1407 [00:10<03:11,  6.98it/s]
  5%|▌         | 74/1407 [00:10<03:09,  7.02it/s]
  5%|▌         | 75/1407 [00:10<03:08,  7.05it/s]
  5%|▌         | 76/1407 [00:10<03:13,  6.89it/s]
  5%|▌         | 77/1407 [00:11<03:16,  6.78it/s]
  6%|▌         | 78/1407 [00:11<03:07,  7.10it/s]
  6%|▌         | 79/1407 [00:11<03:08,  7.06it/s]
  6%|▌         | 80/1407 [00:11<03:13,  6.85it/s]
  6%|▌         | 81/1407 [00:11<03:13,  6.85it/s]
  6%|▌         | 82/1407 [00:11<03:16,  6.74it/s]
  6%|▌         | 83/1407 [00:12<03:14,  6.80it/s]
  6%|▌         | 84/1407 [00:12<03:15,  6.77it/s]
  6%|▌         | 85/1407 [00:12<03:18,  6.65it/s]
  6%|▌         | 86/1407 [00:12<03:17,  6.69it/s]
  6%|▌         | 87/1407 [00:12<03:15,  6.75it/s]
  6%|▋         | 88/1407 [00:12<03:04,  7.13it/s]
  6%|▋         | 89/1407 [00:12<03:06,  7.07it/s]
  6%|▋         | 90/1407 [00:13<03:12,  6.85it/s]
  6%|▋         | 91/1407 [00:13<03:16,  6.70it/s]
  7%|▋         | 92/1407 [00:13<03:19,  6.60it/s]
  7%|▋         | 93/1407 [00:13<03:17,  6.64it/s]
  7%|▋         | 94/1407 [00:13<03:15,  6.73it/s]
  7%|▋         | 95/1407 [00:13<03:16,  6.66it/s]
  7%|▋         | 96/1407 [00:13<03:18,  6.62it/s]
  7%|▋         | 97/1407 [00:14<03:16,  6.65it/s]
  7%|▋         | 98/1407 [00:14<03:15,  6.68it/s]
  7%|▋         | 99/1407 [00:14<03:18,  6.59it/s]
  7%|▋         | 100/1407 [00:14<03:17,  6.63it/s]
  7%|▋         | 101/1407 [00:14<03:14,  6.71it/s]
  7%|▋         | 102/1407 [00:14<03:13,  6.75it/s]
  7%|▋         | 103/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 104/1407 [00:15<03:03,  7.09it/s]
  7%|▋         | 105/1407 [00:15<03:03,  7.10it/s]
  8%|▊         | 106/1407 [00:15<03:02,  7.13it/s]
  8%|▊         | 107/1407 [00:15<03:02,  7.13it/s]
  8%|▊         | 108/1407 [00:15<03:04,  7.05it/s]
  8%|▊         | 109/1407 [00:15<02:54,  7.43it/s]
  8%|▊         | 110/1407 [00:15<03:01,  7.14it/s]
  8%|▊         | 111/1407 [00:16<03:03,  7.08it/s]
  8%|▊         | 112/1407 [00:16<03:05,  6.97it/s]
  8%|▊         | 113/1407 [00:16<03:07,  6.90it/s]
  8%|▊         | 114/1407 [00:16<03:05,  6.98it/s]
  8%|▊         | 115/1407 [00:16<03:09,  6.82it/s]
  8%|▊         | 116/1407 [00:16<03:13,  6.68it/s]
  8%|▊         | 117/1407 [00:16<03:09,  6.79it/s]
  8%|▊         | 118/1407 [00:17<03:13,  6.66it/s]
  8%|▊         | 119/1407 [00:17<03:14,  6.62it/s]
  9%|▊         | 120/1407 [00:17<03:12,  6.69it/s]
  9%|▊         | 121/1407 [00:17<03:10,  6.74it/s]
  9%|▊         | 122/1407 [00:17<03:09,  6.79it/s]
  9%|▊         | 123/1407 [00:17<03:00,  7.10it/s]
  9%|▉         | 124/1407 [00:17<02:59,  7.14it/s]
  9%|▉         | 125/1407 [00:18<03:05,  6.91it/s]
  9%|▉         | 126/1407 [00:18<03:08,  6.79it/s]
  9%|▉         | 127/1407 [00:18<02:57,  7.23it/s]
  9%|▉         | 128/1407 [00:18<02:59,  7.11it/s]
  9%|▉         | 129/1407 [00:18<03:02,  6.98it/s]
  9%|▉         | 130/1407 [00:18<03:07,  6.80it/s]
  9%|▉         | 131/1407 [00:19<03:11,  6.67it/s]
  9%|▉         | 132/1407 [00:19<03:09,  6.72it/s]
  9%|▉         | 133/1407 [00:19<03:12,  6.61it/s]
 10%|▉         | 134/1407 [00:19<03:14,  6.54it/s]
 10%|▉         | 135/1407 [00:19<03:09,  6.72it/s]
 10%|▉         | 136/1407 [00:19<03:07,  6.78it/s]
 10%|▉         | 137/1407 [00:19<03:05,  6.83it/s]
 10%|▉         | 138/1407 [00:20<03:03,  6.91it/s]
 10%|▉         | 139/1407 [00:20<03:03,  6.90it/s]
 10%|▉         | 140/1407 [00:20<03:01,  6.98it/s]
 10%|█         | 141/1407 [00:20<03:03,  6.90it/s]
 10%|█         | 142/1407 [00:20<03:03,  6.91it/s]
 10%|█         | 143/1407 [00:20<02:55,  7.21it/s]
 10%|█         | 144/1407 [00:20<02:55,  7.19it/s]
 10%|█         | 145/1407 [00:21<02:57,  7.12it/s]
 10%|█         | 146/1407 [00:21<03:00,  7.00it/s]
 10%|█         | 147/1407 [00:21<03:02,  6.91it/s]
 11%|█         | 148/1407 [00:21<03:02,  6.91it/s]
 11%|█         | 149/1407 [00:21<03:05,  6.78it/s]
 11%|█         | 150/1407 [00:21<03:03,  6.87it/s]
 11%|█         | 151/1407 [00:21<03:06,  6.73it/s]
 11%|█         | 152/1407 [00:22<03:01,  6.92it/s]
 11%|█         | 153/1407 [00:22<03:02,  6.89it/s]
 11%|█         | 154/1407 [00:22<03:05,  6.77it/s]
 11%|█         | 155/1407 [00:22<03:03,  6.82it/s]
 11%|█         | 156/1407 [00:22<03:01,  6.91it/s]
 11%|█         | 157/1407 [00:22<02:59,  6.96it/s]
 11%|█         | 158/1407 [00:22<03:04,  6.78it/s]
 11%|█▏        | 159/1407 [00:23<03:06,  6.71it/s]
 11%|█▏        | 160/1407 [00:23<03:01,  6.87it/s]
 11%|█▏        | 161/1407 [00:23<02:53,  7.17it/s]
 12%|█▏        | 162/1407 [00:23<03:00,  6.91it/s]
 12%|█▏        | 163/1407 [00:23<03:04,  6.74it/s]
 12%|█▏        | 164/1407 [00:23<02:54,  7.12it/s]
 12%|█▏        | 165/1407 [00:23<02:56,  7.04it/s]
 12%|█▏        | 166/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 167/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 168/1407 [00:24<02:55,  7.07it/s]
 12%|█▏        | 169/1407 [00:24<02:59,  6.90it/s]
 12%|█▏        | 170/1407 [00:24<03:00,  6.84it/s]
 12%|█▏        | 171/1407 [00:24<03:04,  6.70it/s]
 12%|█▏        | 172/1407 [00:24<02:59,  6.87it/s]
 12%|█▏        | 173/1407 [00:25<02:59,  6.87it/s]
 12%|█▏        | 174/1407 [00:25<03:02,  6.76it/s]
 12%|█▏        | 175/1407 [00:25<03:04,  6.68it/s]
 13%|█▎        | 176/1407 [00:25<03:03,  6.72it/s]
 13%|█▎        | 177/1407 [00:25<03:02,  6.73it/s]
 13%|█▎        | 178/1407 [00:25<02:53,  7.07it/s]
 13%|█▎        | 179/1407 [00:25<02:56,  6.97it/s]
 13%|█▎        | 180/1407 [00:26<03:00,  6.79it/s]
 13%|█▎        | 181/1407 [00:26<02:57,  6.89it/s]
 13%|█▎        | 182/1407 [00:26<02:57,  6.90it/s]
 13%|█▎        | 183/1407 [00:26<03:00,  6.78it/s]
 13%|█▎        | 184/1407 [00:26<02:59,  6.82it/s]
 13%|█▎        | 185/1407 [00:26<03:02,  6.70it/s]
 13%|█▎        | 186/1407 [00:26<02:50,  7.15it/s]
 13%|█▎        | 187/1407 [00:27<02:55,  6.94it/s]
 13%|█▎        | 188/1407 [00:27<02:59,  6.80it/s]
 13%|█▎        | 189/1407 [00:27<02:58,  6.84it/s]
 14%|█▎        | 190/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 191/1407 [00:27<03:02,  6.67it/s]
 14%|█▎        | 192/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 193/1407 [00:28<03:02,  6.63it/s]
 14%|█▍        | 194/1407 [00:28<03:04,  6.56it/s]
 14%|█▍        | 195/1407 [00:28<03:03,  6.62it/s]
 14%|█▍        | 196/1407 [00:28<02:49,  7.13it/s]
 14%|█▍        | 197/1407 [00:28<02:55,  6.89it/s]
 14%|█▍        | 198/1407 [00:28<02:55,  6.87it/s]
 14%|█▍        | 199/1407 [00:28<02:55,  6.90it/s]
 14%|█▍        | 200/1407 [00:29<02:58,  6.78it/s]
 14%|█▍        | 201/1407 [00:29<03:00,  6.66it/s]
 14%|█▍        | 202/1407 [00:29<03:00,  6.68it/s]
 14%|█▍        | 203/1407 [00:29<03:02,  6.59it/s]
 14%|█▍        | 204/1407 [00:29<02:57,  6.78it/s]
 15%|█▍        | 205/1407 [00:29<02:57,  6.76it/s]
 15%|█▍        | 206/1407 [00:29<02:57,  6.78it/s]
 15%|█▍        | 207/1407 [00:30<02:58,  6.71it/s]
 15%|█▍        | 208/1407 [00:30<02:47,  7.17it/s]
 15%|█▍        | 209/1407 [00:30<02:48,  7.11it/s]
 15%|█▍        | 210/1407 [00:30<02:49,  7.06it/s]
 15%|█▍        | 211/1407 [00:30<02:43,  7.34it/s]
 15%|█▌        | 212/1407 [00:30<02:45,  7.21it/s]
 15%|█▌        | 213/1407 [00:30<02:45,  7.23it/s]
 15%|█▌        | 214/1407 [00:31<02:51,  6.95it/s]
 15%|█▌        | 215/1407 [00:31<02:49,  7.02it/s]
 15%|█▌        | 216/1407 [00:31<02:51,  6.94it/s]
 15%|█▌        | 217/1407 [00:31<02:44,  7.25it/s]
 15%|█▌        | 218/1407 [00:31<02:47,  7.09it/s]
 16%|█▌        | 219/1407 [00:31<02:47,  7.08it/s]
 16%|█▌        | 220/1407 [00:31<02:51,  6.90it/s]
 16%|█▌        | 221/1407 [00:32<02:52,  6.89it/s]
 16%|█▌        | 222/1407 [00:32<02:44,  7.20it/s]
 16%|█▌        | 223/1407 [00:32<02:45,  7.16it/s]
 16%|█▌        | 224/1407 [00:32<02:50,  6.92it/s]
 16%|█▌        | 225/1407 [00:32<02:37,  7.53it/s]
 16%|█▌        | 226/1407 [00:32<02:40,  7.35it/s]
 16%|█▌        | 227/1407 [00:32<02:44,  7.16it/s]
 16%|█▌        | 228/1407 [00:33<02:39,  7.40it/s]
 16%|█▋        | 229/1407 [00:33<02:40,  7.36it/s]
 16%|█▋        | 230/1407 [00:33<02:47,  7.04it/s]
 16%|█▋        | 231/1407 [00:33<02:50,  6.88it/s]
 16%|█▋        | 232/1407 [00:33<02:50,  6.88it/s]
 17%|█▋        | 233/1407 [00:33<02:48,  6.97it/s]
 17%|█▋        | 234/1407 [00:33<02:49,  6.93it/s]
 17%|█▋        | 235/1407 [00:34<02:49,  6.90it/s]
 17%|█▋        | 236/1407 [00:34<02:45,  7.09it/s]
 17%|█▋        | 237/1407 [00:34<02:47,  6.98it/s]
 17%|█▋        | 238/1407 [00:34<02:52,  6.78it/s]
 17%|█▋        | 239/1407 [00:34<02:51,  6.80it/s]
 17%|█▋        | 240/1407 [00:34<02:49,  6.89it/s]
 17%|█▋        | 241/1407 [00:34<02:47,  6.97it/s]
 17%|█▋        | 242/1407 [00:35<02:47,  6.97it/s]
 17%|█▋        | 243/1407 [00:35<02:50,  6.82it/s]
 17%|█▋        | 244/1407 [00:35<02:49,  6.86it/s]
 17%|█▋        | 245/1407 [00:35<02:46,  6.96it/s]
 17%|█▋        | 246/1407 [00:35<02:47,  6.93it/s]
 18%|█▊        | 247/1407 [00:35<02:46,  6.98it/s]
 18%|█▊        | 248/1407 [00:35<02:37,  7.35it/s]
 18%|█▊        | 249/1407 [00:36<02:40,  7.20it/s]
 18%|█▊        | 250/1407 [00:36<02:43,  7.08it/s]
 18%|█▊        | 251/1407 [00:36<02:37,  7.34it/s]
 18%|█▊        | 252/1407 [00:36<02:40,  7.18it/s]
 18%|█▊        | 253/1407 [00:36<02:42,  7.11it/s]
 18%|█▊        | 254/1407 [00:36<02:44,  7.02it/s]
 18%|█▊        | 255/1407 [00:36<02:36,  7.35it/s]
 18%|█▊        | 256/1407 [00:37<02:39,  7.20it/s]
 18%|█▊        | 257/1407 [00:37<02:37,  7.31it/s]
 18%|█▊        | 258/1407 [00:37<02:40,  7.17it/s]
 18%|█▊        | 259/1407 [00:37<02:44,  6.97it/s]
 18%|█▊        | 260/1407 [00:37<02:45,  6.93it/s]
 19%|█▊        | 261/1407 [00:37<02:46,  6.87it/s]
 19%|█▊        | 262/1407 [00:37<02:45,  6.90it/s]
 19%|█▊        | 263/1407 [00:38<02:37,  7.25it/s]
 19%|█▉        | 264/1407 [00:38<02:40,  7.12it/s]
 19%|█▉        | 265/1407 [00:38<02:41,  7.06it/s]
 19%|█▉        | 266/1407 [00:38<02:45,  6.88it/s]
 19%|█▉        | 267/1407 [00:38<02:45,  6.89it/s]
 19%|█▉        | 268/1407 [00:38<02:47,  6.78it/s]
 19%|█▉        | 269/1407 [00:38<02:46,  6.83it/s]
 19%|█▉        | 270/1407 [00:39<02:48,  6.74it/s]
 19%|█▉        | 271/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 272/1407 [00:39<02:45,  6.86it/s]
 19%|█▉        | 273/1407 [00:39<02:44,  6.88it/s]
 19%|█▉        | 274/1407 [00:39<02:45,  6.87it/s]
 20%|█▉        | 275/1407 [00:39<02:42,  6.95it/s]
 20%|█▉        | 276/1407 [00:39<02:43,  6.92it/s]
 20%|█▉        | 277/1407 [00:40<02:47,  6.75it/s]
 20%|█▉        | 278/1407 [00:40<02:36,  7.20it/s]
 20%|█▉        | 279/1407 [00:40<02:42,  6.94it/s]
 20%|█▉        | 280/1407 [00:40<02:43,  6.88it/s]
 20%|█▉        | 281/1407 [00:40<02:47,  6.73it/s]
 20%|██        | 282/1407 [00:40<02:45,  6.80it/s]
 20%|██        | 283/1407 [00:40<02:37,  7.12it/s]
 20%|██        | 284/1407 [00:41<02:34,  7.25it/s]
 20%|██        | 285/1407 [00:41<02:41,  6.96it/s]
 20%|██        | 286/1407 [00:41<02:44,  6.83it/s]
 20%|██        | 287/1407 [00:41<02:43,  6.86it/s]
 20%|██        | 288/1407 [00:41<02:34,  7.25it/s]
 21%|██        | 289/1407 [00:41<02:37,  7.09it/s]
 21%|██        | 290/1407 [00:41<02:42,  6.86it/s]
 21%|██        | 291/1407 [00:42<02:43,  6.82it/s]
 21%|██        | 292/1407 [00:42<02:46,  6.69it/s]
 21%|██        | 293/1407 [00:42<02:43,  6.83it/s]
 21%|██        | 294/1407 [00:42<02:37,  7.04it/s]
 21%|██        | 295/1407 [00:42<02:38,  7.02it/s]
 21%|██        | 296/1407 [00:42<02:32,  7.29it/s]
 21%|██        | 297/1407 [00:42<02:37,  7.05it/s]
 21%|██        | 298/1407 [00:43<02:38,  6.99it/s]
 21%|██▏       | 299/1407 [00:43<02:42,  6.80it/s]
 21%|██▏       | 300/1407 [00:43<02:27,  7.52it/s]
 21%|██▏       | 301/1407 [00:43<02:23,  7.71it/s]
 21%|██▏       | 302/1407 [00:43<02:28,  7.43it/s]
 22%|██▏       | 303/1407 [00:43<02:31,  7.28it/s]
 22%|██▏       | 304/1407 [00:43<02:33,  7.19it/s]
 22%|██▏       | 305/1407 [00:44<02:26,  7.53it/s]
 22%|██▏       | 306/1407 [00:44<02:34,  7.14it/s]
 22%|██▏       | 307/1407 [00:44<02:38,  6.94it/s]
 22%|██▏       | 308/1407 [00:44<02:39,  6.88it/s]
 22%|██▏       | 309/1407 [00:44<02:32,  7.18it/s]
 22%|██▏       | 310/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 311/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 312/1407 [00:45<02:35,  7.05it/s]
 22%|██▏       | 313/1407 [00:45<02:33,  7.12it/s]
 22%|██▏       | 314/1407 [00:45<02:28,  7.38it/s]
 22%|██▏       | 315/1407 [00:45<02:29,  7.29it/s]
 22%|██▏       | 316/1407 [00:45<02:35,  7.04it/s]
 23%|██▎       | 317/1407 [00:45<02:39,  6.83it/s]
 23%|██▎       | 318/1407 [00:45<02:41,  6.73it/s]
 23%|██▎       | 319/1407 [00:46<02:44,  6.63it/s]
 23%|██▎       | 320/1407 [00:46<02:42,  6.70it/s]
 23%|██▎       | 321/1407 [00:46<02:41,  6.71it/s]
 23%|██▎       | 322/1407 [00:46<02:32,  7.13it/s]
 23%|██▎       | 323/1407 [00:46<02:37,  6.90it/s]
 23%|██▎       | 324/1407 [00:46<02:36,  6.92it/s]
 23%|██▎       | 325/1407 [00:46<02:39,  6.80it/s]
 23%|██▎       | 326/1407 [00:47<02:41,  6.70it/s]
 23%|██▎       | 327/1407 [00:47<02:39,  6.78it/s]
 23%|██▎       | 328/1407 [00:47<02:31,  7.12it/s]
 23%|██▎       | 329/1407 [00:47<02:33,  7.04it/s]
 23%|██▎       | 330/1407 [00:47<02:33,  7.02it/s]
 24%|██▎       | 331/1407 [00:47<02:35,  6.93it/s]
 24%|██▎       | 332/1407 [00:47<02:35,  6.92it/s]
 24%|██▎       | 333/1407 [00:48<02:31,  7.11it/s]
 24%|██▎       | 334/1407 [00:48<02:31,  7.07it/s]
 24%|██▍       | 335/1407 [00:48<02:35,  6.90it/s]
 24%|██▍       | 336/1407 [00:48<02:34,  6.92it/s]
 24%|██▍       | 337/1407 [00:48<02:34,  6.94it/s]
 24%|██▍       | 338/1407 [00:48<02:32,  7.00it/s]
 24%|██▍       | 339/1407 [00:48<02:33,  6.95it/s]
 24%|██▍       | 340/1407 [00:49<02:34,  6.89it/s]
 24%|██▍       | 341/1407 [00:49<02:33,  6.94it/s]
 24%|██▍       | 342/1407 [00:49<02:37,  6.77it/s]
 24%|██▍       | 343/1407 [00:49<02:37,  6.76it/s]
 24%|██▍       | 344/1407 [00:49<02:39,  6.65it/s]
 25%|██▍       | 345/1407 [00:49<02:37,  6.74it/s]
 25%|██▍       | 346/1407 [00:49<02:40,  6.63it/s]
 25%|██▍       | 347/1407 [00:50<02:29,  7.07it/s]
 25%|██▍       | 348/1407 [00:50<02:31,  6.97it/s]
 25%|██▍       | 349/1407 [00:50<02:30,  7.04it/s]
 25%|██▍       | 350/1407 [00:50<02:28,  7.12it/s]
 25%|██▍       | 351/1407 [00:50<02:28,  7.11it/s]
 25%|██▌       | 352/1407 [00:50<02:32,  6.93it/s]
 25%|██▌       | 353/1407 [00:50<02:36,  6.75it/s]
 25%|██▌       | 354/1407 [00:51<02:32,  6.90it/s]
 25%|██▌       | 355/1407 [00:51<02:36,  6.73it/s]
 25%|██▌       | 356/1407 [00:51<02:35,  6.76it/s]
 25%|██▌       | 357/1407 [00:51<02:33,  6.86it/s]
 25%|██▌       | 358/1407 [00:51<02:30,  6.95it/s]
 26%|██▌       | 359/1407 [00:51<02:29,  6.99it/s]
 26%|██▌       | 360/1407 [00:51<02:34,  6.80it/s]
 26%|██▌       | 361/1407 [00:52<02:32,  6.84it/s]
 26%|██▌       | 362/1407 [00:52<02:35,  6.74it/s]
 26%|██▌       | 363/1407 [00:52<02:27,  7.07it/s]
 26%|██▌       | 364/1407 [00:52<02:32,  6.85it/s]
 26%|██▌       | 365/1407 [00:52<02:30,  6.92it/s]
 26%|██▌       | 366/1407 [00:52<02:33,  6.77it/s]
 26%|██▌       | 367/1407 [00:53<02:33,  6.76it/s]
 26%|██▌       | 368/1407 [00:53<02:31,  6.87it/s]
 26%|██▌       | 369/1407 [00:53<02:30,  6.88it/s]
 26%|██▋       | 370/1407 [00:53<02:30,  6.87it/s]
 26%|██▋       | 371/1407 [00:53<02:30,  6.90it/s]
 26%|██▋       | 372/1407 [00:53<02:29,  6.92it/s]
 27%|██▋       | 373/1407 [00:53<02:33,  6.75it/s]
 27%|██▋       | 374/1407 [00:54<02:31,  6.80it/s]
 27%|██▋       | 375/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 376/1407 [00:54<02:35,  6.61it/s]
 27%|██▋       | 377/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 378/1407 [00:54<02:31,  6.78it/s]
 27%|██▋       | 379/1407 [00:54<02:30,  6.83it/s]
 27%|██▋       | 380/1407 [00:54<02:29,  6.87it/s]
 27%|██▋       | 381/1407 [00:55<02:30,  6.83it/s]
 27%|██▋       | 382/1407 [00:55<02:22,  7.19it/s]
 27%|██▋       | 383/1407 [00:55<02:22,  7.18it/s]
 27%|██▋       | 384/1407 [00:55<02:25,  7.04it/s]
 27%|██▋       | 385/1407 [00:55<02:26,  6.97it/s]
 27%|██▋       | 386/1407 [00:55<02:29,  6.83it/s]
 28%|██▊       | 387/1407 [00:55<02:21,  7.19it/s]
 28%|██▊       | 388/1407 [00:56<02:24,  7.05it/s]
 28%|██▊       | 389/1407 [00:56<02:24,  7.06it/s]
 28%|██▊       | 390/1407 [00:56<02:20,  7.21it/s]
 28%|██▊       | 391/1407 [00:56<02:21,  7.18it/s]
 28%|██▊       | 392/1407 [00:56<02:23,  7.09it/s]
 28%|██▊       | 393/1407 [00:56<02:23,  7.06it/s]
 28%|██▊       | 394/1407 [00:56<02:25,  6.96it/s]
 28%|██▊       | 395/1407 [00:57<02:25,  6.97it/s]
 28%|██▊       | 396/1407 [00:57<02:25,  6.94it/s]
 28%|██▊       | 397/1407 [00:57<02:25,  6.94it/s]
 28%|██▊       | 398/1407 [00:57<02:19,  7.24it/s]
 28%|██▊       | 399/1407 [00:57<02:20,  7.19it/s]
 28%|██▊       | 400/1407 [00:57<02:20,  7.15it/s]
 29%|██▊       | 401/1407 [00:57<02:22,  7.08it/s]
 29%|██▊       | 402/1407 [00:58<02:23,  7.00it/s]
 29%|██▊       | 403/1407 [00:58<02:24,  6.96it/s]
 29%|██▊       | 404/1407 [00:58<02:25,  6.89it/s]
 29%|██▉       | 405/1407 [00:58<02:19,  7.19it/s]
 29%|██▉       | 406/1407 [00:58<02:15,  7.41it/s]
 29%|██▉       | 407/1407 [00:58<02:20,  7.12it/s]
 29%|██▉       | 408/1407 [00:58<02:15,  7.37it/s]
 29%|██▉       | 409/1407 [00:58<02:11,  7.56it/s]
 29%|██▉       | 410/1407 [00:59<02:18,  7.22it/s]
 29%|██▉       | 411/1407 [00:59<02:21,  7.06it/s]
 29%|██▉       | 412/1407 [00:59<02:22,  6.96it/s]
 29%|██▉       | 413/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 414/1407 [00:59<02:23,  6.91it/s]
 29%|██▉       | 415/1407 [00:59<02:26,  6.76it/s]
 30%|██▉       | 416/1407 [01:00<02:29,  6.64it/s]
 30%|██▉       | 417/1407 [01:00<02:30,  6.57it/s]
 30%|██▉       | 418/1407 [01:00<02:20,  7.02it/s]
 30%|██▉       | 419/1407 [01:00<02:21,  7.01it/s]
 30%|██▉       | 420/1407 [01:00<02:23,  6.86it/s]
 30%|██▉       | 421/1407 [01:00<02:27,  6.71it/s]
 30%|██▉       | 422/1407 [01:00<02:26,  6.74it/s]
 30%|███       | 423/1407 [01:01<02:18,  7.11it/s]
 30%|███       | 424/1407 [01:01<02:17,  7.13it/s]
 30%|███       | 425/1407 [01:01<02:19,  7.04it/s]
 30%|███       | 426/1407 [01:01<02:22,  6.88it/s]
 30%|███       | 427/1407 [01:01<02:22,  6.87it/s]
 30%|███       | 428/1407 [01:01<02:23,  6.83it/s]
 30%|███       | 429/1407 [01:01<02:23,  6.80it/s]
 31%|███       | 430/1407 [01:02<02:26,  6.68it/s]
 31%|███       | 431/1407 [01:02<02:24,  6.77it/s]
 31%|███       | 432/1407 [01:02<02:22,  6.83it/s]
 31%|███       | 433/1407 [01:02<02:15,  7.19it/s]
 31%|███       | 434/1407 [01:02<02:20,  6.92it/s]
 31%|███       | 435/1407 [01:02<02:24,  6.75it/s]
 31%|███       | 436/1407 [01:02<02:26,  6.64it/s]
 31%|███       | 437/1407 [01:03<02:25,  6.66it/s]
 31%|███       | 438/1407 [01:03<02:25,  6.68it/s]
 31%|███       | 439/1407 [01:03<02:21,  6.85it/s]
 31%|███▏      | 440/1407 [01:03<02:20,  6.87it/s]
 31%|███▏      | 441/1407 [01:03<02:20,  6.88it/s]
 31%|███▏      | 442/1407 [01:03<02:19,  6.90it/s]
 31%|███▏      | 443/1407 [01:03<02:19,  6.92it/s]
 32%|███▏      | 444/1407 [01:04<02:21,  6.80it/s]
 32%|███▏      | 445/1407 [01:04<02:19,  6.88it/s]
 32%|███▏      | 446/1407 [01:04<02:23,  6.72it/s]
 32%|███▏      | 447/1407 [01:04<02:22,  6.72it/s]
 32%|███▏      | 448/1407 [01:04<02:21,  6.78it/s]
 32%|███▏      | 449/1407 [01:04<02:12,  7.22it/s]
 32%|███▏      | 450/1407 [01:04<02:14,  7.14it/s]
 32%|███▏      | 451/1407 [01:05<02:18,  6.90it/s]
 32%|███▏      | 452/1407 [01:05<02:20,  6.78it/s]
 32%|███▏      | 453/1407 [01:05<02:13,  7.17it/s]
 32%|███▏      | 454/1407 [01:05<02:14,  7.06it/s]
 32%|███▏      | 455/1407 [01:05<02:15,  7.04it/s]
 32%|███▏      | 456/1407 [01:05<02:16,  6.98it/s]
 32%|███▏      | 457/1407 [01:05<02:17,  6.91it/s]
 33%|███▎      | 458/1407 [01:06<02:20,  6.75it/s]
 33%|███▎      | 459/1407 [01:06<02:19,  6.80it/s]
 33%|███▎      | 460/1407 [01:06<02:17,  6.89it/s]
 33%|███▎      | 461/1407 [01:06<02:15,  6.96it/s]
 33%|███▎      | 462/1407 [01:06<02:19,  6.78it/s]
 33%|███▎      | 463/1407 [01:06<02:07,  7.42it/s]
 33%|███▎      | 464/1407 [01:06<02:08,  7.35it/s]
 33%|███▎      | 465/1407 [01:07<02:11,  7.19it/s]
 33%|███▎      | 466/1407 [01:07<02:13,  7.07it/s]
 33%|███▎      | 467/1407 [01:07<02:13,  7.04it/s]
 33%|███▎      | 468/1407 [01:07<02:15,  6.94it/s]
 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]
                                                  

 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]{'loss': 0.8685, 'learning_rate': 6.483138902064646e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.12it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.35it/s]

 21%|██        | 66/313 [00:00<00:01, 205.94it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.16it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.60it/s]

 40%|████      | 126/313 [00:00<00:01, 185.43it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.26it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.32it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.51it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.53it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.57it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.28it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.18it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 185.10it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.91it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.91it/s]
 33%|███▎      | 469/1407 [01:09<02:07,  7.35it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 470/1407 [01:10<14:42,  1.06it/s]
 33%|███▎      | 471/1407 [01:10<10:57,  1.42it/s]
 34%|███▎      | 472/1407 [01:10<08:20,  1.87it/s]
 34%|███▎      | 473/1407 [01:10<06:30,  2.39it/s]
 34%|███▎      | 474/1407 [01:11<05:12,  2.98it/s]
 34%|███▍      | 475/1407 [01:11<04:22,  3.56it/s]
 34%|███▍      | 476/1407 [01:11<03:44,  4.16it/s]
 34%|███▍      | 477/1407 [01:11<03:17,  4.71it/s]
 34%|███▍      | 478/1407 [01:11<03:01,  5.11it/s]
 34%|███▍      | 479/1407 [01:11<02:49,  5.47it/s]
 34%|███▍      | 480/1407 [01:11<02:39,  5.83it/s]
 34%|███▍      | 481/1407 [01:12<02:31,  6.12it/s]
 34%|███▍      | 482/1407 [01:12<02:29,  6.20it/s]
 34%|███▍      | 483/1407 [01:12<02:24,  6.40it/s]
 34%|███▍      | 484/1407 [01:12<02:21,  6.50it/s]
 34%|███▍      | 485/1407 [01:12<02:19,  6.62it/s]
 35%|███▍      | 486/1407 [01:12<02:16,  6.76it/s]
 35%|███▍      | 487/1407 [01:12<02:14,  6.82it/s]
 35%|███▍      | 488/1407 [01:13<02:12,  6.96it/s]
 35%|███▍      | 489/1407 [01:13<02:14,  6.82it/s]
 35%|███▍      | 490/1407 [01:13<02:17,  6.68it/s]
 35%|███▍      | 491/1407 [01:13<02:16,  6.70it/s]
 35%|███▍      | 492/1407 [01:13<02:15,  6.77it/s]
 35%|███▌      | 493/1407 [01:13<02:17,  6.65it/s]
 35%|███▌      | 494/1407 [01:13<02:06,  7.23it/s]
 35%|███▌      | 495/1407 [01:14<02:06,  7.19it/s]
 35%|███▌      | 496/1407 [01:14<02:09,  7.05it/s]
 35%|███▌      | 497/1407 [01:14<02:09,  7.02it/s]
 35%|███▌      | 498/1407 [01:14<02:11,  6.93it/s]
 35%|███▌      | 499/1407 [01:14<02:14,  6.76it/s]
 36%|███▌      | 500/1407 [01:14<02:08,  7.08it/s]
 36%|███▌      | 501/1407 [01:14<02:03,  7.32it/s]
 36%|███▌      | 502/1407 [01:15<02:04,  7.25it/s]
 36%|███▌      | 503/1407 [01:15<02:06,  7.13it/s]
 36%|███▌      | 504/1407 [01:15<02:02,  7.36it/s]
 36%|███▌      | 505/1407 [01:15<01:59,  7.55it/s]
 36%|███▌      | 506/1407 [01:15<02:02,  7.35it/s]
 36%|███▌      | 507/1407 [01:15<02:07,  7.04it/s]
 36%|███▌      | 508/1407 [01:15<02:08,  7.00it/s]
 36%|███▌      | 509/1407 [01:16<02:08,  6.99it/s]
 36%|███▌      | 510/1407 [01:16<02:07,  7.02it/s]
 36%|███▋      | 511/1407 [01:16<02:11,  6.82it/s]
 36%|███▋      | 512/1407 [01:16<02:13,  6.68it/s]
 36%|███▋      | 513/1407 [01:16<02:11,  6.80it/s]
 37%|███▋      | 514/1407 [01:16<02:10,  6.84it/s]
 37%|███▋      | 515/1407 [01:16<02:04,  7.15it/s]
 37%|███▋      | 516/1407 [01:17<02:00,  7.38it/s]
 37%|███▋      | 517/1407 [01:17<02:05,  7.10it/s]
 37%|███▋      | 518/1407 [01:17<02:09,  6.88it/s]
 37%|███▋      | 519/1407 [01:17<02:08,  6.89it/s]
 37%|███▋      | 520/1407 [01:17<02:08,  6.91it/s]
 37%|███▋      | 521/1407 [01:17<02:07,  6.96it/s]
 37%|███▋      | 522/1407 [01:17<02:10,  6.78it/s]
 37%|███▋      | 523/1407 [01:18<02:12,  6.69it/s]
 37%|███▋      | 524/1407 [01:18<02:08,  6.86it/s]
 37%|███▋      | 525/1407 [01:18<01:58,  7.42it/s]
 37%|███▋      | 526/1407 [01:18<02:03,  7.13it/s]
 37%|███▋      | 527/1407 [01:18<01:57,  7.49it/s]
 38%|███▊      | 528/1407 [01:18<01:59,  7.33it/s]
 38%|███▊      | 529/1407 [01:18<02:00,  7.29it/s]
 38%|███▊      | 530/1407 [01:19<02:04,  7.04it/s]
 38%|███▊      | 531/1407 [01:19<02:06,  6.95it/s]
 38%|███▊      | 532/1407 [01:19<02:06,  6.92it/s]
 38%|███▊      | 533/1407 [01:19<02:09,  6.76it/s]
 38%|███▊      | 534/1407 [01:19<02:08,  6.80it/s]
 38%|███▊      | 535/1407 [01:19<02:10,  6.67it/s]
 38%|███▊      | 536/1407 [01:19<02:09,  6.71it/s]
 38%|███▊      | 537/1407 [01:20<02:11,  6.61it/s]
 38%|███▊      | 538/1407 [01:20<02:10,  6.64it/s]
 38%|███▊      | 539/1407 [01:20<02:08,  6.73it/s]
 38%|███▊      | 540/1407 [01:20<02:07,  6.79it/s]
 38%|███▊      | 541/1407 [01:20<02:05,  6.88it/s]
 39%|███▊      | 542/1407 [01:20<02:04,  6.94it/s]
 39%|███▊      | 543/1407 [01:21<02:04,  6.95it/s]
 39%|███▊      | 544/1407 [01:21<02:03,  7.01it/s]
 39%|███▊      | 545/1407 [01:21<02:03,  6.95it/s]
 39%|███▉      | 546/1407 [01:21<02:06,  6.79it/s]
 39%|███▉      | 547/1407 [01:21<02:05,  6.84it/s]
 39%|███▉      | 548/1407 [01:21<01:59,  7.22it/s]
 39%|███▉      | 549/1407 [01:21<01:52,  7.61it/s]
 39%|███▉      | 550/1407 [01:21<01:54,  7.48it/s]
 39%|███▉      | 551/1407 [01:22<01:56,  7.32it/s]
 39%|███▉      | 552/1407 [01:22<01:58,  7.22it/s]
 39%|███▉      | 553/1407 [01:22<01:59,  7.13it/s]
 39%|███▉      | 554/1407 [01:22<01:57,  7.25it/s]
 39%|███▉      | 555/1407 [01:22<02:02,  6.98it/s]
 40%|███▉      | 556/1407 [01:22<02:02,  6.94it/s]
 40%|███▉      | 557/1407 [01:22<02:05,  6.76it/s]
 40%|███▉      | 558/1407 [01:23<02:05,  6.76it/s]
 40%|███▉      | 559/1407 [01:23<02:05,  6.78it/s]
 40%|███▉      | 560/1407 [01:23<02:06,  6.70it/s]
 40%|███▉      | 561/1407 [01:23<02:07,  6.64it/s]
 40%|███▉      | 562/1407 [01:23<02:05,  6.74it/s]
 40%|████      | 563/1407 [01:23<02:01,  6.97it/s]
 40%|████      | 564/1407 [01:24<02:01,  6.94it/s]
 40%|████      | 565/1407 [01:24<02:03,  6.80it/s]
 40%|████      | 566/1407 [01:24<02:00,  6.95it/s]
 40%|████      | 567/1407 [01:24<02:00,  6.95it/s]
 40%|████      | 568/1407 [01:24<02:03,  6.82it/s]
 40%|████      | 569/1407 [01:24<02:01,  6.91it/s]
 41%|████      | 570/1407 [01:24<02:01,  6.89it/s]
 41%|████      | 571/1407 [01:25<02:03,  6.75it/s]
 41%|████      | 572/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 573/1407 [01:25<02:01,  6.85it/s]
 41%|████      | 574/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 575/1407 [01:25<02:04,  6.70it/s]
 41%|████      | 576/1407 [01:25<02:02,  6.78it/s]
 41%|████      | 577/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 578/1407 [01:26<02:01,  6.84it/s]
 41%|████      | 579/1407 [01:26<01:59,  6.92it/s]
 41%|████      | 580/1407 [01:26<01:53,  7.27it/s]
 41%|████▏     | 581/1407 [01:26<01:57,  7.04it/s]
 41%|████▏     | 582/1407 [01:26<01:56,  7.06it/s]
 41%|████▏     | 583/1407 [01:26<01:54,  7.20it/s]
 42%|████▏     | 584/1407 [01:26<01:54,  7.17it/s]
 42%|████▏     | 585/1407 [01:27<01:56,  7.03it/s]
 42%|████▏     | 586/1407 [01:27<01:59,  6.86it/s]
 42%|████▏     | 587/1407 [01:27<02:01,  6.76it/s]
 42%|████▏     | 588/1407 [01:27<02:03,  6.65it/s]
 42%|████▏     | 589/1407 [01:27<02:03,  6.62it/s]
 42%|████▏     | 590/1407 [01:27<02:01,  6.70it/s]
 42%|████▏     | 591/1407 [01:27<01:55,  7.05it/s]
 42%|████▏     | 592/1407 [01:28<01:54,  7.09it/s]
 42%|████▏     | 593/1407 [01:28<01:50,  7.36it/s]
 42%|████▏     | 594/1407 [01:28<01:50,  7.34it/s]
 42%|████▏     | 595/1407 [01:28<01:54,  7.07it/s]
 42%|████▏     | 596/1407 [01:28<02:14,  6.03it/s]
 42%|████▏     | 597/1407 [01:28<02:03,  6.57it/s]
 43%|████▎     | 598/1407 [01:28<01:55,  6.98it/s]
 43%|████▎     | 599/1407 [01:29<01:56,  6.94it/s]
 43%|████▎     | 600/1407 [01:29<01:54,  7.04it/s]
 43%|████▎     | 601/1407 [01:29<01:55,  6.97it/s]
 43%|████▎     | 602/1407 [01:29<01:56,  6.90it/s]
 43%|████▎     | 603/1407 [01:29<01:55,  6.96it/s]
 43%|████▎     | 604/1407 [01:29<01:57,  6.82it/s]
 43%|████▎     | 605/1407 [01:29<01:57,  6.85it/s]
 43%|████▎     | 606/1407 [01:30<01:51,  7.16it/s]
 43%|████▎     | 607/1407 [01:30<01:51,  7.17it/s]
 43%|████▎     | 608/1407 [01:30<01:51,  7.15it/s]
 43%|████▎     | 609/1407 [01:30<01:45,  7.57it/s]
 43%|████▎     | 610/1407 [01:30<01:48,  7.33it/s]
 43%|████▎     | 611/1407 [01:30<01:51,  7.14it/s]
 43%|████▎     | 612/1407 [01:30<01:55,  6.90it/s]
 44%|████▎     | 613/1407 [01:31<01:48,  7.29it/s]
 44%|████▎     | 614/1407 [01:31<01:53,  6.99it/s]
 44%|████▎     | 615/1407 [01:31<01:53,  6.95it/s]
 44%|████▍     | 616/1407 [01:31<01:54,  6.92it/s]
 44%|████▍     | 617/1407 [01:31<01:54,  6.90it/s]
 44%|████▍     | 618/1407 [01:31<01:57,  6.73it/s]
 44%|████▍     | 619/1407 [01:31<01:56,  6.79it/s]
 44%|████▍     | 620/1407 [01:32<01:56,  6.77it/s]
 44%|████▍     | 621/1407 [01:32<01:49,  7.17it/s]
 44%|████▍     | 622/1407 [01:32<01:52,  6.97it/s]
 44%|████▍     | 623/1407 [01:32<01:52,  6.95it/s]
 44%|████▍     | 624/1407 [01:32<01:54,  6.81it/s]
 44%|████▍     | 625/1407 [01:32<01:55,  6.80it/s]
 44%|████▍     | 626/1407 [01:32<01:49,  7.16it/s]
 45%|████▍     | 627/1407 [01:33<01:42,  7.63it/s]
 45%|████▍     | 628/1407 [01:33<01:44,  7.46it/s]
 45%|████▍     | 629/1407 [01:33<01:49,  7.12it/s]
 45%|████▍     | 630/1407 [01:33<01:48,  7.18it/s]
 45%|████▍     | 631/1407 [01:33<01:51,  6.97it/s]
 45%|████▍     | 632/1407 [01:33<02:18,  5.58it/s]
 45%|████▍     | 633/1407 [01:34<02:10,  5.93it/s]
 45%|████▌     | 634/1407 [01:34<02:07,  6.06it/s]
 45%|████▌     | 635/1407 [01:34<02:03,  6.27it/s]
 45%|████▌     | 636/1407 [01:34<02:02,  6.31it/s]
 45%|████▌     | 637/1407 [01:34<01:59,  6.43it/s]
 45%|████▌     | 638/1407 [01:34<01:59,  6.42it/s]
 45%|████▌     | 639/1407 [01:34<01:56,  6.57it/s]
 45%|████▌     | 640/1407 [01:35<01:54,  6.67it/s]
 46%|████▌     | 641/1407 [01:35<01:53,  6.72it/s]
 46%|████▌     | 642/1407 [01:35<01:53,  6.72it/s]
 46%|████▌     | 643/1407 [01:35<01:51,  6.87it/s]
 46%|████▌     | 644/1407 [01:35<01:53,  6.72it/s]
 46%|████▌     | 645/1407 [01:35<01:54,  6.66it/s]
 46%|████▌     | 646/1407 [01:35<01:55,  6.58it/s]
 46%|████▌     | 647/1407 [01:36<01:55,  6.56it/s]
 46%|████▌     | 648/1407 [01:36<01:54,  6.65it/s]
 46%|████▌     | 649/1407 [01:36<01:51,  6.82it/s]
 46%|████▌     | 650/1407 [01:36<01:50,  6.83it/s]
 46%|████▋     | 651/1407 [01:36<01:50,  6.86it/s]
 46%|████▋     | 652/1407 [01:36<01:52,  6.71it/s]
 46%|████▋     | 653/1407 [01:37<01:53,  6.65it/s]
 46%|████▋     | 654/1407 [01:37<01:52,  6.67it/s]
 47%|████▋     | 655/1407 [01:37<01:54,  6.58it/s]
 47%|████▋     | 656/1407 [01:37<01:51,  6.72it/s]
 47%|████▋     | 657/1407 [01:37<01:50,  6.79it/s]
 47%|████▋     | 658/1407 [01:37<01:50,  6.81it/s]
 47%|████▋     | 659/1407 [01:37<01:51,  6.69it/s]
 47%|████▋     | 660/1407 [01:38<01:52,  6.65it/s]
 47%|████▋     | 661/1407 [01:38<01:43,  7.24it/s]
 47%|████▋     | 662/1407 [01:38<01:47,  6.96it/s]
 47%|████▋     | 663/1407 [01:38<01:46,  6.95it/s]
 47%|████▋     | 664/1407 [01:38<01:49,  6.81it/s]
 47%|████▋     | 665/1407 [01:38<02:12,  5.61it/s]
 47%|████▋     | 666/1407 [01:39<02:02,  6.03it/s]
 47%|████▋     | 667/1407 [01:39<02:00,  6.15it/s]
 47%|████▋     | 668/1407 [01:39<01:55,  6.41it/s]
 48%|████▊     | 669/1407 [01:39<01:52,  6.54it/s]
 48%|████▊     | 670/1407 [01:39<01:51,  6.60it/s]
 48%|████▊     | 671/1407 [01:39<01:49,  6.71it/s]
 48%|████▊     | 672/1407 [01:39<01:50,  6.63it/s]
 48%|████▊     | 673/1407 [01:40<01:49,  6.69it/s]
 48%|████▊     | 674/1407 [01:40<01:48,  6.73it/s]
 48%|████▊     | 675/1407 [01:40<01:42,  7.15it/s]
 48%|████▊     | 676/1407 [01:40<01:41,  7.19it/s]
 48%|████▊     | 677/1407 [01:40<01:45,  6.92it/s]
 48%|████▊     | 678/1407 [01:40<01:46,  6.87it/s]
 48%|████▊     | 679/1407 [01:40<01:48,  6.72it/s]
 48%|████▊     | 680/1407 [01:41<01:48,  6.72it/s]
 48%|████▊     | 681/1407 [01:41<01:49,  6.62it/s]
 48%|████▊     | 682/1407 [01:41<01:45,  6.88it/s]
 49%|████▊     | 683/1407 [01:41<01:42,  7.08it/s]
 49%|████▊     | 684/1407 [01:41<01:43,  7.00it/s]
 49%|████▊     | 685/1407 [01:41<01:44,  6.93it/s]
 49%|████▉     | 686/1407 [01:41<01:46,  6.75it/s]
 49%|████▉     | 687/1407 [01:42<01:48,  6.64it/s]
 49%|████▉     | 688/1407 [01:42<01:46,  6.77it/s]
 49%|████▉     | 689/1407 [01:42<01:45,  6.83it/s]
 49%|████▉     | 690/1407 [01:42<01:44,  6.83it/s]
 49%|████▉     | 691/1407 [01:42<01:44,  6.86it/s]
 49%|████▉     | 692/1407 [01:42<01:43,  6.89it/s]
 49%|████▉     | 693/1407 [01:42<01:43,  6.87it/s]
 49%|████▉     | 694/1407 [01:43<01:45,  6.76it/s]
 49%|████▉     | 695/1407 [01:43<01:45,  6.76it/s]
 49%|████▉     | 696/1407 [01:43<01:44,  6.83it/s]
 50%|████▉     | 697/1407 [01:43<01:42,  6.91it/s]
 50%|████▉     | 698/1407 [01:43<01:45,  6.74it/s]
 50%|████▉     | 699/1407 [01:43<01:44,  6.80it/s]
 50%|████▉     | 700/1407 [01:44<01:45,  6.72it/s]
 50%|████▉     | 701/1407 [01:44<01:46,  6.61it/s]
 50%|████▉     | 702/1407 [01:44<01:45,  6.70it/s]
 50%|████▉     | 703/1407 [01:44<01:43,  6.83it/s]
 50%|█████     | 704/1407 [01:44<01:43,  6.80it/s]
 50%|█████     | 705/1407 [01:44<01:42,  6.84it/s]
 50%|█████     | 706/1407 [01:44<01:44,  6.70it/s]
 50%|█████     | 707/1407 [01:45<01:42,  6.81it/s]
 50%|█████     | 708/1407 [01:45<01:41,  6.86it/s]
 50%|█████     | 709/1407 [01:45<01:44,  6.71it/s]
 50%|█████     | 710/1407 [01:45<01:42,  6.82it/s]
 51%|█████     | 711/1407 [01:45<01:42,  6.80it/s]
 51%|█████     | 712/1407 [01:45<01:43,  6.71it/s]
 51%|█████     | 713/1407 [01:45<01:45,  6.61it/s]
 51%|█████     | 714/1407 [01:46<01:40,  6.87it/s]
 51%|█████     | 715/1407 [01:46<01:43,  6.72it/s]
 51%|█████     | 716/1407 [01:46<01:42,  6.72it/s]
 51%|█████     | 717/1407 [01:46<01:37,  7.05it/s]
 51%|█████     | 718/1407 [01:46<01:32,  7.43it/s]
 51%|█████     | 719/1407 [01:46<01:35,  7.21it/s]
 51%|█████     | 720/1407 [01:46<01:38,  6.95it/s]
 51%|█████     | 721/1407 [01:47<01:39,  6.89it/s]
 51%|█████▏    | 722/1407 [01:47<01:34,  7.24it/s]
 51%|█████▏    | 723/1407 [01:47<01:37,  7.00it/s]
 51%|█████▏    | 724/1407 [01:47<01:40,  6.81it/s]
 52%|█████▏    | 725/1407 [01:47<01:42,  6.68it/s]
 52%|█████▏    | 726/1407 [01:47<01:43,  6.60it/s]
 52%|█████▏    | 727/1407 [01:47<01:42,  6.64it/s]
 52%|█████▏    | 728/1407 [01:48<01:43,  6.57it/s]
 52%|█████▏    | 729/1407 [01:48<01:40,  6.75it/s]
 52%|█████▏    | 730/1407 [01:48<01:39,  6.80it/s]
 52%|█████▏    | 731/1407 [01:48<01:39,  6.79it/s]
 52%|█████▏    | 732/1407 [01:48<01:38,  6.88it/s]
 52%|█████▏    | 733/1407 [01:48<01:37,  6.89it/s]
 52%|█████▏    | 734/1407 [01:48<01:36,  6.95it/s]
 52%|█████▏    | 735/1407 [01:49<01:37,  6.89it/s]
 52%|█████▏    | 736/1407 [01:49<01:32,  7.22it/s]
 52%|█████▏    | 737/1407 [01:49<01:34,  7.07it/s]
 52%|█████▏    | 738/1407 [01:49<01:34,  7.07it/s]
 53%|█████▎    | 739/1407 [01:49<01:35,  7.01it/s]
 53%|█████▎    | 740/1407 [01:49<01:31,  7.30it/s]
 53%|█████▎    | 741/1407 [01:49<01:32,  7.19it/s]
 53%|█████▎    | 742/1407 [01:50<01:35,  6.93it/s]
 53%|█████▎    | 743/1407 [01:50<01:35,  6.98it/s]
 53%|█████▎    | 744/1407 [01:50<01:36,  6.90it/s]
 53%|█████▎    | 745/1407 [01:50<01:35,  6.92it/s]
 53%|█████▎    | 746/1407 [01:50<01:37,  6.75it/s]
 53%|█████▎    | 747/1407 [01:50<01:37,  6.79it/s]
 53%|█████▎    | 748/1407 [01:50<01:32,  7.11it/s]
 53%|█████▎    | 749/1407 [01:51<01:34,  6.99it/s]
 53%|█████▎    | 750/1407 [01:51<01:36,  6.80it/s]
 53%|█████▎    | 751/1407 [01:51<01:35,  6.84it/s]
 53%|█████▎    | 752/1407 [01:51<01:31,  7.15it/s]
 54%|█████▎    | 753/1407 [01:51<01:31,  7.14it/s]
 54%|█████▎    | 754/1407 [01:51<01:33,  7.01it/s]
 54%|█████▎    | 755/1407 [01:51<01:32,  7.05it/s]
 54%|█████▎    | 756/1407 [01:52<01:33,  6.99it/s]
 54%|█████▍    | 757/1407 [01:52<01:29,  7.28it/s]
 54%|█████▍    | 758/1407 [01:52<01:29,  7.28it/s]
 54%|█████▍    | 759/1407 [01:52<01:30,  7.13it/s]
 54%|█████▍    | 760/1407 [01:52<01:31,  7.04it/s]
 54%|█████▍    | 761/1407 [01:52<01:33,  6.94it/s]
 54%|█████▍    | 762/1407 [01:52<01:33,  6.88it/s]
 54%|█████▍    | 763/1407 [01:53<01:28,  7.30it/s]
 54%|█████▍    | 764/1407 [01:53<01:25,  7.50it/s]
 54%|█████▍    | 765/1407 [01:53<01:27,  7.32it/s]
 54%|█████▍    | 766/1407 [01:53<01:31,  7.01it/s]
 55%|█████▍    | 767/1407 [01:53<01:32,  6.94it/s]
 55%|█████▍    | 768/1407 [01:53<01:33,  6.81it/s]
 55%|█████▍    | 769/1407 [01:53<01:35,  6.68it/s]
 55%|█████▍    | 770/1407 [01:54<01:33,  6.82it/s]
 55%|█████▍    | 771/1407 [01:54<01:32,  6.84it/s]
 55%|█████▍    | 772/1407 [01:54<01:34,  6.73it/s]
 55%|█████▍    | 773/1407 [01:54<01:32,  6.83it/s]
 55%|█████▌    | 774/1407 [01:54<01:34,  6.69it/s]
 55%|█████▌    | 775/1407 [01:54<01:32,  6.85it/s]
 55%|█████▌    | 776/1407 [01:54<01:31,  6.87it/s]
 55%|█████▌    | 777/1407 [01:55<01:30,  6.95it/s]
 55%|█████▌    | 778/1407 [01:55<01:29,  7.05it/s]
 55%|█████▌    | 779/1407 [01:55<01:30,  6.95it/s]
 55%|█████▌    | 780/1407 [01:55<01:29,  7.00it/s]
 56%|█████▌    | 781/1407 [01:55<01:32,  6.80it/s]
 56%|█████▌    | 782/1407 [01:55<01:30,  6.94it/s]
 56%|█████▌    | 783/1407 [01:55<01:29,  6.93it/s]
 56%|█████▌    | 784/1407 [01:56<01:29,  6.93it/s]
 56%|█████▌    | 785/1407 [01:56<01:31,  6.80it/s]
 56%|█████▌    | 786/1407 [01:56<01:30,  6.83it/s]
 56%|█████▌    | 787/1407 [01:56<01:29,  6.91it/s]
 56%|█████▌    | 788/1407 [01:56<01:30,  6.87it/s]
 56%|█████▌    | 789/1407 [01:56<01:31,  6.75it/s]
 56%|█████▌    | 790/1407 [01:57<01:30,  6.81it/s]
 56%|█████▌    | 791/1407 [01:57<01:32,  6.67it/s]
 56%|█████▋    | 792/1407 [01:57<01:31,  6.69it/s]
 56%|█████▋    | 793/1407 [01:57<01:33,  6.60it/s]
 56%|█████▋    | 794/1407 [01:57<01:33,  6.57it/s]
 57%|█████▋    | 795/1407 [01:57<01:31,  6.68it/s]
 57%|█████▋    | 796/1407 [01:57<01:29,  6.82it/s]
 57%|█████▋    | 797/1407 [01:58<01:29,  6.79it/s]
 57%|█████▋    | 798/1407 [01:58<01:29,  6.77it/s]
 57%|█████▋    | 799/1407 [01:58<01:30,  6.69it/s]
 57%|█████▋    | 800/1407 [01:58<01:26,  7.04it/s]
 57%|█████▋    | 801/1407 [01:58<01:25,  7.05it/s]
 57%|█████▋    | 802/1407 [01:58<01:28,  6.83it/s]
 57%|█████▋    | 803/1407 [01:58<01:28,  6.85it/s]
 57%|█████▋    | 804/1407 [01:59<01:23,  7.22it/s]
 57%|█████▋    | 805/1407 [01:59<01:26,  6.94it/s]
 57%|█████▋    | 806/1407 [01:59<01:24,  7.13it/s]
 57%|█████▋    | 807/1407 [01:59<01:20,  7.42it/s]
 57%|█████▋    | 808/1407 [01:59<01:22,  7.27it/s]
 57%|█████▋    | 809/1407 [01:59<01:24,  7.10it/s]
 58%|█████▊    | 810/1407 [01:59<01:22,  7.24it/s]
 58%|█████▊    | 811/1407 [02:00<01:25,  6.97it/s]
 58%|█████▊    | 812/1407 [02:00<01:23,  7.14it/s]
 58%|█████▊    | 813/1407 [02:00<01:23,  7.15it/s]
 58%|█████▊    | 814/1407 [02:00<01:23,  7.07it/s]
 58%|█████▊    | 815/1407 [02:00<01:24,  7.01it/s]
 58%|█████▊    | 816/1407 [02:00<01:25,  6.92it/s]
 58%|█████▊    | 817/1407 [02:00<01:25,  6.89it/s]
 58%|█████▊    | 818/1407 [02:01<01:27,  6.74it/s]
 58%|█████▊    | 819/1407 [02:01<01:26,  6.78it/s]
 58%|█████▊    | 820/1407 [02:01<01:27,  6.69it/s]
 58%|█████▊    | 821/1407 [02:01<01:27,  6.73it/s]
 58%|█████▊    | 822/1407 [02:01<01:24,  6.89it/s]
 58%|█████▊    | 823/1407 [02:01<01:24,  6.88it/s]
 59%|█████▊    | 824/1407 [02:01<01:24,  6.89it/s]
 59%|█████▊    | 825/1407 [02:02<01:20,  7.19it/s]
 59%|█████▊    | 826/1407 [02:02<01:22,  7.04it/s]
 59%|█████▉    | 827/1407 [02:02<01:22,  7.01it/s]
 59%|█████▉    | 828/1407 [02:02<01:24,  6.85it/s]
 59%|█████▉    | 829/1407 [02:02<01:24,  6.81it/s]
 59%|█████▉    | 830/1407 [02:02<01:24,  6.82it/s]
 59%|█████▉    | 831/1407 [02:02<01:23,  6.86it/s]
 59%|█████▉    | 832/1407 [02:03<01:20,  7.19it/s]
 59%|█████▉    | 833/1407 [02:03<01:20,  7.09it/s]
 59%|█████▉    | 834/1407 [02:03<01:19,  7.23it/s]
 59%|█████▉    | 835/1407 [02:03<01:19,  7.19it/s]
 59%|█████▉    | 836/1407 [02:03<01:18,  7.31it/s]
 59%|█████▉    | 837/1407 [02:03<01:19,  7.17it/s]
 60%|█████▉    | 838/1407 [02:03<01:19,  7.14it/s]
 60%|█████▉    | 839/1407 [02:04<01:20,  7.05it/s]
 60%|█████▉    | 840/1407 [02:04<01:20,  7.02it/s]
 60%|█████▉    | 841/1407 [02:04<01:22,  6.86it/s]
 60%|█████▉    | 842/1407 [02:04<01:21,  6.93it/s]
 60%|█████▉    | 843/1407 [02:04<01:22,  6.88it/s]
 60%|█████▉    | 844/1407 [02:04<01:22,  6.83it/s]
 60%|██████    | 845/1407 [02:04<01:24,  6.69it/s]
 60%|██████    | 846/1407 [02:05<01:19,  7.03it/s]
 60%|██████    | 847/1407 [02:05<01:21,  6.88it/s]
 60%|██████    | 848/1407 [02:05<01:21,  6.86it/s]
 60%|██████    | 849/1407 [02:05<01:21,  6.87it/s]
 60%|██████    | 850/1407 [02:05<01:21,  6.86it/s]
 60%|██████    | 851/1407 [02:05<01:20,  6.93it/s]
 61%|██████    | 852/1407 [02:05<01:21,  6.79it/s]
 61%|██████    | 853/1407 [02:06<01:20,  6.90it/s]
 61%|██████    | 854/1407 [02:06<01:13,  7.53it/s]
 61%|██████    | 855/1407 [02:06<01:17,  7.14it/s]
 61%|██████    | 856/1407 [02:06<01:17,  7.08it/s]
 61%|██████    | 857/1407 [02:06<01:17,  7.11it/s]
 61%|██████    | 858/1407 [02:06<01:17,  7.05it/s]
 61%|██████    | 859/1407 [02:06<01:18,  6.95it/s]
 61%|██████    | 860/1407 [02:07<01:19,  6.88it/s]
 61%|██████    | 861/1407 [02:07<01:21,  6.72it/s]
 61%|██████▏   | 862/1407 [02:07<01:19,  6.83it/s]
 61%|██████▏   | 863/1407 [02:07<01:19,  6.84it/s]
 61%|██████▏   | 864/1407 [02:07<01:18,  6.91it/s]
 61%|██████▏   | 865/1407 [02:07<01:19,  6.78it/s]
 62%|██████▏   | 866/1407 [02:07<01:20,  6.71it/s]
 62%|██████▏   | 867/1407 [02:08<01:19,  6.77it/s]
 62%|██████▏   | 868/1407 [02:08<01:15,  7.09it/s]
 62%|██████▏   | 869/1407 [02:08<01:15,  7.08it/s]
 62%|██████▏   | 870/1407 [02:08<01:16,  7.01it/s]
 62%|██████▏   | 871/1407 [02:08<01:16,  6.99it/s]
 62%|██████▏   | 872/1407 [02:08<01:18,  6.84it/s]
 62%|██████▏   | 873/1407 [02:08<01:18,  6.85it/s]
 62%|██████▏   | 874/1407 [02:09<01:18,  6.81it/s]
 62%|██████▏   | 875/1407 [02:09<01:16,  6.95it/s]
 62%|██████▏   | 876/1407 [02:09<01:17,  6.82it/s]
 62%|██████▏   | 877/1407 [02:09<01:13,  7.25it/s]
 62%|██████▏   | 878/1407 [02:09<01:15,  6.98it/s]
 62%|██████▏   | 879/1407 [02:09<01:17,  6.79it/s]
 63%|██████▎   | 880/1407 [02:10<01:19,  6.66it/s]
 63%|██████▎   | 881/1407 [02:10<01:18,  6.71it/s]
 63%|██████▎   | 882/1407 [02:10<01:18,  6.73it/s]
 63%|██████▎   | 883/1407 [02:10<01:16,  6.83it/s]
 63%|██████▎   | 884/1407 [02:10<01:15,  6.91it/s]
 63%|██████▎   | 885/1407 [02:10<01:15,  6.92it/s]
 63%|██████▎   | 886/1407 [02:10<01:17,  6.75it/s]
 63%|██████▎   | 887/1407 [02:11<01:17,  6.67it/s]
 63%|██████▎   | 888/1407 [02:11<01:16,  6.75it/s]
 63%|██████▎   | 889/1407 [02:11<01:16,  6.75it/s]
 63%|██████▎   | 890/1407 [02:11<01:13,  7.08it/s]
 63%|██████▎   | 891/1407 [02:11<01:12,  7.12it/s]
 63%|██████▎   | 892/1407 [02:11<01:13,  7.03it/s]
 63%|██████▎   | 893/1407 [02:11<01:12,  7.07it/s]
 64%|██████▎   | 894/1407 [02:12<01:13,  6.96it/s]
 64%|██████▎   | 895/1407 [02:12<01:13,  6.95it/s]
 64%|██████▎   | 896/1407 [02:12<01:12,  7.06it/s]
 64%|██████▍   | 897/1407 [02:12<01:12,  7.02it/s]
 64%|██████▍   | 898/1407 [02:12<01:14,  6.85it/s]
 64%|██████▍   | 899/1407 [02:12<01:15,  6.70it/s]
 64%|██████▍   | 900/1407 [02:12<01:15,  6.71it/s]
 64%|██████▍   | 901/1407 [02:13<01:15,  6.72it/s]
 64%|██████▍   | 902/1407 [02:13<01:14,  6.78it/s]
 64%|██████▍   | 903/1407 [02:13<01:12,  6.93it/s]
 64%|██████▍   | 904/1407 [02:13<01:10,  7.11it/s]
 64%|██████▍   | 905/1407 [02:13<01:11,  7.07it/s]
 64%|██████▍   | 906/1407 [02:13<01:11,  7.02it/s]
 64%|██████▍   | 907/1407 [02:13<01:11,  7.00it/s]
 65%|██████▍   | 908/1407 [02:14<01:11,  7.02it/s]
 65%|██████▍   | 909/1407 [02:14<01:12,  6.87it/s]
 65%|██████▍   | 910/1407 [02:14<01:06,  7.51it/s]
 65%|██████▍   | 911/1407 [02:14<01:08,  7.29it/s]
 65%|██████▍   | 912/1407 [02:14<01:09,  7.11it/s]
 65%|██████▍   | 913/1407 [02:14<01:10,  7.00it/s]
 65%|██████▍   | 914/1407 [02:14<01:11,  6.85it/s]
 65%|██████▌   | 915/1407 [02:15<01:12,  6.82it/s]
 65%|██████▌   | 916/1407 [02:15<01:12,  6.79it/s]
 65%|██████▌   | 917/1407 [02:15<01:12,  6.80it/s]
 65%|██████▌   | 918/1407 [02:15<01:12,  6.72it/s]
 65%|██████▌   | 919/1407 [02:15<01:13,  6.66it/s]
 65%|██████▌   | 920/1407 [02:15<01:13,  6.61it/s]
 65%|██████▌   | 921/1407 [02:15<01:12,  6.75it/s]
 66%|██████▌   | 922/1407 [02:16<01:12,  6.67it/s]
 66%|██████▌   | 923/1407 [02:16<01:11,  6.75it/s]
 66%|██████▌   | 924/1407 [02:16<01:10,  6.84it/s]
 66%|██████▌   | 925/1407 [02:16<01:11,  6.70it/s]
 66%|██████▌   | 926/1407 [02:16<01:12,  6.60it/s]
 66%|██████▌   | 927/1407 [02:16<01:12,  6.66it/s]
 66%|██████▌   | 928/1407 [02:16<01:10,  6.78it/s]
 66%|██████▌   | 929/1407 [02:17<01:10,  6.79it/s]
 66%|██████▌   | 930/1407 [02:17<01:11,  6.66it/s]
 66%|██████▌   | 931/1407 [02:17<01:12,  6.58it/s]
 66%|██████▌   | 932/1407 [02:17<01:11,  6.66it/s]
 66%|██████▋   | 933/1407 [02:17<01:09,  6.84it/s]
 66%|██████▋   | 934/1407 [02:17<01:10,  6.70it/s]
 66%|██████▋   | 935/1407 [02:18<01:11,  6.61it/s]
 67%|██████▋   | 936/1407 [02:18<01:10,  6.67it/s]
 67%|██████▋   | 937/1407 [02:18<01:09,  6.80it/s]
 67%|██████▋   | 938/1407 [02:18<01:05,  7.20it/s]
                                                  

 67%|██████▋   | 938/1407 [02:18<01:05,  7.20it/s]{'eval_loss': 0.7165336012840271, 'eval_accuracy': 0.6832, 'eval_f1': 0.6802569271198566, 'eval_runtime': 1.7302, 'eval_samples_per_second': 1444.893, 'eval_steps_per_second': 180.901, 'epoch': 1.0}
{'loss': 0.6754, 'learning_rate': 2.3286059669051312e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.24it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.63it/s]

 21%|██        | 66/313 [00:00<00:01, 206.10it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.30it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.66it/s]

 40%|████      | 126/313 [00:00<00:01, 185.47it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.28it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.20it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.34it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.47it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.51it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.12it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.70it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.34it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.44it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.44it/s]
 67%|██████▋   | 938/1407 [02:20<01:05,  7.20it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 939/1407 [02:21<07:22,  1.06it/s]
 67%|██████▋   | 940/1407 [02:21<05:30,  1.41it/s]
 67%|██████▋   | 941/1407 [02:21<04:11,  1.85it/s]
 67%|██████▋   | 942/1407 [02:21<03:15,  2.37it/s]
 67%|██████▋   | 943/1407 [02:21<02:37,  2.95it/s]
 67%|██████▋   | 944/1407 [02:22<02:10,  3.55it/s]
 67%|██████▋   | 945/1407 [02:22<01:51,  4.15it/s]
 67%|██████▋   | 946/1407 [02:22<01:37,  4.74it/s]
 67%|██████▋   | 947/1407 [02:22<01:28,  5.20it/s]
 67%|██████▋   | 948/1407 [02:22<01:22,  5.54it/s]
 67%|██████▋   | 949/1407 [02:22<01:17,  5.94it/s]
 68%|██████▊   | 950/1407 [02:22<01:15,  6.07it/s]
 68%|██████▊   | 951/1407 [02:23<01:13,  6.17it/s]
 68%|██████▊   | 952/1407 [02:23<01:11,  6.35it/s]
 68%|██████▊   | 953/1407 [02:23<01:11,  6.36it/s]
 68%|██████▊   | 954/1407 [02:23<01:10,  6.46it/s]
 68%|██████▊   | 955/1407 [02:23<01:08,  6.60it/s]
 68%|██████▊   | 956/1407 [02:23<01:07,  6.64it/s]
 68%|██████▊   | 957/1407 [02:23<01:08,  6.60it/s]
 68%|██████▊   | 958/1407 [02:24<01:08,  6.58it/s]
 68%|██████▊   | 959/1407 [02:24<01:06,  6.70it/s]
 68%|██████▊   | 960/1407 [02:24<01:06,  6.77it/s]
 68%|██████▊   | 961/1407 [02:24<01:05,  6.83it/s]
 68%|██████▊   | 962/1407 [02:24<01:06,  6.69it/s]
 68%|██████▊   | 963/1407 [02:24<01:06,  6.64it/s]
 69%|██████▊   | 964/1407 [02:24<01:05,  6.73it/s]
 69%|██████▊   | 965/1407 [02:25<01:06,  6.62it/s]
 69%|██████▊   | 966/1407 [02:25<01:07,  6.57it/s]
 69%|██████▊   | 967/1407 [02:25<01:03,  6.95it/s]
 69%|██████▉   | 968/1407 [02:25<01:02,  7.00it/s]
 69%|██████▉   | 969/1407 [02:25<01:03,  6.85it/s]
 69%|██████▉   | 970/1407 [02:25<01:04,  6.75it/s]
 69%|██████▉   | 971/1407 [02:26<01:05,  6.68it/s]
 69%|██████▉   | 972/1407 [02:26<01:04,  6.76it/s]
 69%|██████▉   | 973/1407 [02:26<01:03,  6.83it/s]
 69%|██████▉   | 974/1407 [02:26<01:01,  7.04it/s]
 69%|██████▉   | 975/1407 [02:26<01:03,  6.83it/s]
 69%|██████▉   | 976/1407 [02:26<01:04,  6.69it/s]
 69%|██████▉   | 977/1407 [02:26<01:04,  6.64it/s]
 70%|██████▉   | 978/1407 [02:27<01:03,  6.78it/s]
 70%|██████▉   | 979/1407 [02:27<01:02,  6.83it/s]
 70%|██████▉   | 980/1407 [02:27<00:59,  7.21it/s]
 70%|██████▉   | 981/1407 [02:27<01:00,  7.06it/s]
 70%|██████▉   | 982/1407 [02:27<01:02,  6.85it/s]
 70%|██████▉   | 983/1407 [02:27<01:01,  6.87it/s]
 70%|██████▉   | 984/1407 [02:27<01:02,  6.77it/s]
 70%|███████   | 985/1407 [02:28<01:03,  6.65it/s]
 70%|███████   | 986/1407 [02:28<01:02,  6.74it/s]
 70%|███████   | 987/1407 [02:28<00:59,  7.07it/s]
 70%|███████   | 988/1407 [02:28<00:59,  7.08it/s]
 70%|███████   | 989/1407 [02:28<00:59,  7.02it/s]
 70%|███████   | 990/1407 [02:28<00:59,  6.97it/s]
 70%|███████   | 991/1407 [02:28<00:59,  7.00it/s]
 71%|███████   | 992/1407 [02:29<01:01,  6.80it/s]
 71%|███████   | 993/1407 [02:29<01:00,  6.89it/s]
 71%|███████   | 994/1407 [02:29<00:57,  7.18it/s]
 71%|███████   | 995/1407 [02:29<00:58,  7.04it/s]
 71%|███████   | 996/1407 [02:29<00:58,  7.02it/s]
 71%|███████   | 997/1407 [02:29<00:58,  6.98it/s]
 71%|███████   | 998/1407 [02:29<00:58,  7.01it/s]
 71%|███████   | 999/1407 [02:30<00:57,  7.04it/s]
 71%|███████   | 1000/1407 [02:30<00:58,  6.95it/s]
 71%|███████   | 1001/1407 [02:30<00:58,  6.89it/s]
 71%|███████   | 1002/1407 [02:30<00:57,  7.00it/s]
 71%|███████▏  | 1003/1407 [02:30<00:57,  7.08it/s]
 71%|███████▏  | 1004/1407 [02:30<00:57,  6.97it/s]
 71%|███████▏  | 1005/1407 [02:30<00:57,  6.96it/s]
 71%|███████▏  | 1006/1407 [02:31<00:59,  6.78it/s]
 72%|███████▏  | 1007/1407 [02:31<00:58,  6.80it/s]
 72%|███████▏  | 1008/1407 [02:31<00:59,  6.71it/s]
 72%|███████▏  | 1009/1407 [02:31<00:56,  7.09it/s]
 72%|███████▏  | 1010/1407 [02:31<00:56,  6.98it/s]
 72%|███████▏  | 1011/1407 [02:31<00:57,  6.95it/s]
 72%|███████▏  | 1012/1407 [02:31<00:57,  6.92it/s]
 72%|███████▏  | 1013/1407 [02:32<00:58,  6.78it/s]
 72%|███████▏  | 1014/1407 [02:32<00:59,  6.66it/s]
 72%|███████▏  | 1015/1407 [02:32<00:58,  6.73it/s]
 72%|███████▏  | 1016/1407 [02:32<00:57,  6.85it/s]
 72%|███████▏  | 1017/1407 [02:32<00:57,  6.81it/s]
 72%|███████▏  | 1018/1407 [02:32<00:58,  6.69it/s]
 72%|███████▏  | 1019/1407 [02:32<00:54,  7.11it/s]
 72%|███████▏  | 1020/1407 [02:33<00:55,  7.03it/s]
 73%|███████▎  | 1021/1407 [02:33<00:55,  6.94it/s]
 73%|███████▎  | 1022/1407 [02:33<00:53,  7.23it/s]
 73%|███████▎  | 1023/1407 [02:33<00:54,  7.07it/s]
 73%|███████▎  | 1024/1407 [02:33<00:54,  7.00it/s]
 73%|███████▎  | 1025/1407 [02:33<00:54,  7.07it/s]
 73%|███████▎  | 1026/1407 [02:33<00:55,  6.85it/s]
 73%|███████▎  | 1027/1407 [02:34<00:54,  6.98it/s]
 73%|███████▎  | 1028/1407 [02:34<00:54,  6.91it/s]
 73%|███████▎  | 1029/1407 [02:34<00:55,  6.85it/s]
 73%|███████▎  | 1030/1407 [02:34<00:55,  6.75it/s]
 73%|███████▎  | 1031/1407 [02:34<00:56,  6.67it/s]
 73%|███████▎  | 1032/1407 [02:34<00:54,  6.82it/s]
 73%|███████▎  | 1033/1407 [02:34<00:54,  6.87it/s]
 73%|███████▎  | 1034/1407 [02:35<00:55,  6.76it/s]
 74%|███████▎  | 1035/1407 [02:35<00:54,  6.79it/s]
 74%|███████▎  | 1036/1407 [02:35<00:52,  7.01it/s]
 74%|███████▎  | 1037/1407 [02:35<00:52,  6.99it/s]
 74%|███████▍  | 1038/1407 [02:35<00:52,  7.02it/s]
 74%|███████▍  | 1039/1407 [02:35<00:52,  6.97it/s]
 74%|███████▍  | 1040/1407 [02:36<00:52,  6.93it/s]
 74%|███████▍  | 1041/1407 [02:36<00:52,  6.91it/s]
 74%|███████▍  | 1042/1407 [02:36<00:49,  7.33it/s]
 74%|███████▍  | 1043/1407 [02:36<00:50,  7.14it/s]
 74%|███████▍  | 1044/1407 [02:36<00:51,  7.07it/s]
 74%|███████▍  | 1045/1407 [02:36<00:51,  7.04it/s]
 74%|███████▍  | 1046/1407 [02:36<00:51,  7.00it/s]
 74%|███████▍  | 1047/1407 [02:36<00:52,  6.92it/s]
 74%|███████▍  | 1048/1407 [02:37<00:51,  6.93it/s]
 75%|███████▍  | 1049/1407 [02:37<00:52,  6.87it/s]
 75%|███████▍  | 1050/1407 [02:37<00:53,  6.72it/s]
 75%|███████▍  | 1051/1407 [02:37<00:53,  6.63it/s]
 75%|███████▍  | 1052/1407 [02:37<00:54,  6.55it/s]
 75%|███████▍  | 1053/1407 [02:37<00:53,  6.63it/s]
 75%|███████▍  | 1054/1407 [02:38<00:53,  6.56it/s]
 75%|███████▍  | 1055/1407 [02:38<00:53,  6.61it/s]
 75%|███████▌  | 1056/1407 [02:38<00:49,  7.03it/s]
 75%|███████▌  | 1057/1407 [02:38<00:47,  7.33it/s]
 75%|███████▌  | 1058/1407 [02:38<00:48,  7.21it/s]
 75%|███████▌  | 1059/1407 [02:38<00:48,  7.12it/s]
 75%|███████▌  | 1060/1407 [02:38<00:49,  7.03it/s]
 75%|███████▌  | 1061/1407 [02:39<00:47,  7.35it/s]
 75%|███████▌  | 1062/1407 [02:39<00:49,  7.03it/s]
 76%|███████▌  | 1063/1407 [02:39<00:49,  6.97it/s]
 76%|███████▌  | 1064/1407 [02:39<00:49,  6.95it/s]
 76%|███████▌  | 1065/1407 [02:39<00:50,  6.78it/s]
 76%|███████▌  | 1066/1407 [02:39<00:50,  6.82it/s]
 76%|███████▌  | 1067/1407 [02:39<00:49,  6.86it/s]
 76%|███████▌  | 1068/1407 [02:40<00:48,  6.95it/s]
 76%|███████▌  | 1069/1407 [02:40<00:49,  6.89it/s]
 76%|███████▌  | 1070/1407 [02:40<00:50,  6.73it/s]
 76%|███████▌  | 1071/1407 [02:40<00:50,  6.66it/s]
 76%|███████▌  | 1072/1407 [02:40<00:49,  6.70it/s]
 76%|███████▋  | 1073/1407 [02:40<00:48,  6.84it/s]
 76%|███████▋  | 1074/1407 [02:40<00:49,  6.70it/s]
 76%|███████▋  | 1075/1407 [02:41<00:49,  6.70it/s]
 76%|███████▋  | 1076/1407 [02:41<00:50,  6.60it/s]
 77%|███████▋  | 1077/1407 [02:41<00:49,  6.69it/s]
 77%|███████▋  | 1078/1407 [02:41<00:48,  6.76it/s]
 77%|███████▋  | 1079/1407 [02:41<00:49,  6.69it/s]
 77%|███████▋  | 1080/1407 [02:41<00:49,  6.64it/s]
 77%|███████▋  | 1081/1407 [02:41<00:48,  6.75it/s]
 77%|███████▋  | 1082/1407 [02:42<00:44,  7.33it/s]
 77%|███████▋  | 1083/1407 [02:42<00:46,  7.03it/s]
 77%|███████▋  | 1084/1407 [02:42<00:46,  7.02it/s]
 77%|███████▋  | 1085/1407 [02:42<00:46,  6.97it/s]
 77%|███████▋  | 1086/1407 [02:42<00:47,  6.83it/s]
 77%|███████▋  | 1087/1407 [02:42<00:44,  7.13it/s]
 77%|███████▋  | 1088/1407 [02:42<00:46,  6.89it/s]
 77%|███████▋  | 1089/1407 [02:43<00:46,  6.90it/s]
 77%|███████▋  | 1090/1407 [02:43<00:43,  7.24it/s]
 78%|███████▊  | 1091/1407 [02:43<00:44,  7.12it/s]
 78%|███████▊  | 1092/1407 [02:43<00:44,  7.08it/s]
 78%|███████▊  | 1093/1407 [02:43<00:44,  7.00it/s]
 78%|███████▊  | 1094/1407 [02:43<00:45,  6.96it/s]
 78%|███████▊  | 1095/1407 [02:43<00:44,  6.95it/s]
 78%|███████▊  | 1096/1407 [02:44<00:44,  7.00it/s]
 78%|███████▊  | 1097/1407 [02:44<00:42,  7.27it/s]
 78%|███████▊  | 1098/1407 [02:44<00:43,  7.14it/s]
 78%|███████▊  | 1099/1407 [02:44<00:43,  7.01it/s]
 78%|███████▊  | 1100/1407 [02:44<00:43,  7.04it/s]
 78%|███████▊  | 1101/1407 [02:44<00:44,  6.87it/s]
 78%|███████▊  | 1102/1407 [02:44<00:44,  6.83it/s]
 78%|███████▊  | 1103/1407 [02:45<00:45,  6.69it/s]
 78%|███████▊  | 1104/1407 [02:45<00:42,  7.12it/s]
 79%|███████▊  | 1105/1407 [02:45<00:42,  7.03it/s]
 79%|███████▊  | 1106/1407 [02:45<00:44,  6.82it/s]
 79%|███████▊  | 1107/1407 [02:45<00:44,  6.68it/s]
 79%|███████▊  | 1108/1407 [02:45<00:44,  6.70it/s]
 79%|███████▉  | 1109/1407 [02:45<00:43,  6.83it/s]
 79%|███████▉  | 1110/1407 [02:46<00:40,  7.31it/s]
 79%|███████▉  | 1111/1407 [02:46<00:40,  7.30it/s]
 79%|███████▉  | 1112/1407 [02:46<00:41,  7.13it/s]
 79%|███████▉  | 1113/1407 [02:46<00:41,  7.04it/s]
 79%|███████▉  | 1114/1407 [02:46<00:41,  7.01it/s]
 79%|███████▉  | 1115/1407 [02:46<00:42,  6.85it/s]
 79%|███████▉  | 1116/1407 [02:46<00:41,  6.94it/s]
 79%|███████▉  | 1117/1407 [02:47<00:41,  6.92it/s]
 79%|███████▉  | 1118/1407 [02:47<00:41,  6.93it/s]
 80%|███████▉  | 1119/1407 [02:47<00:41,  6.93it/s]
 80%|███████▉  | 1120/1407 [02:47<00:41,  6.98it/s]
 80%|███████▉  | 1121/1407 [02:47<00:39,  7.25it/s]
 80%|███████▉  | 1122/1407 [02:47<00:38,  7.46it/s]
 80%|███████▉  | 1123/1407 [02:47<00:39,  7.25it/s]
 80%|███████▉  | 1124/1407 [02:48<00:39,  7.24it/s]
 80%|███████▉  | 1125/1407 [02:48<00:36,  7.63it/s]
 80%|████████  | 1126/1407 [02:48<00:35,  7.81it/s]
 80%|████████  | 1127/1407 [02:48<00:36,  7.74it/s]
 80%|████████  | 1128/1407 [02:48<00:36,  7.58it/s]
 80%|████████  | 1129/1407 [02:48<00:38,  7.18it/s]
 80%|████████  | 1130/1407 [02:48<00:38,  7.11it/s]
 80%|████████  | 1131/1407 [02:49<00:39,  7.05it/s]
 80%|████████  | 1132/1407 [02:49<00:39,  6.88it/s]
 81%|████████  | 1133/1407 [02:49<00:39,  6.86it/s]
 81%|████████  | 1134/1407 [02:49<00:39,  6.87it/s]
 81%|████████  | 1135/1407 [02:49<00:39,  6.94it/s]
 81%|████████  | 1136/1407 [02:49<00:38,  6.98it/s]
 81%|████████  | 1137/1407 [02:49<00:38,  6.97it/s]
 81%|████████  | 1138/1407 [02:50<00:38,  6.96it/s]
 81%|████████  | 1139/1407 [02:50<00:36,  7.30it/s]
 81%|████████  | 1140/1407 [02:50<00:37,  7.17it/s]
 81%|████████  | 1141/1407 [02:50<00:38,  6.92it/s]
 81%|████████  | 1142/1407 [02:50<00:36,  7.20it/s]
 81%|████████  | 1143/1407 [02:50<00:38,  6.93it/s]
 81%|████████▏ | 1144/1407 [02:50<00:38,  6.90it/s]
 81%|████████▏ | 1145/1407 [02:51<00:38,  6.78it/s]
 81%|████████▏ | 1146/1407 [02:51<00:36,  7.11it/s]
 82%|████████▏ | 1147/1407 [02:51<00:37,  6.99it/s]
 82%|████████▏ | 1148/1407 [02:51<00:37,  6.97it/s]
 82%|████████▏ | 1149/1407 [02:51<00:37,  6.97it/s]
 82%|████████▏ | 1150/1407 [02:51<00:36,  6.97it/s]
 82%|████████▏ | 1151/1407 [02:51<00:37,  6.90it/s]
 82%|████████▏ | 1152/1407 [02:52<00:37,  6.78it/s]
 82%|████████▏ | 1153/1407 [02:52<00:37,  6.69it/s]
 82%|████████▏ | 1154/1407 [02:52<00:37,  6.71it/s]
 82%|████████▏ | 1155/1407 [02:52<00:38,  6.61it/s]
 82%|████████▏ | 1156/1407 [02:52<00:36,  6.97it/s]
 82%|████████▏ | 1157/1407 [02:52<00:35,  6.95it/s]
 82%|████████▏ | 1158/1407 [02:52<00:36,  6.77it/s]
 82%|████████▏ | 1159/1407 [02:53<00:36,  6.82it/s]
 82%|████████▏ | 1160/1407 [02:53<00:35,  6.90it/s]
 83%|████████▎ | 1161/1407 [02:53<00:36,  6.78it/s]
 83%|████████▎ | 1162/1407 [02:53<00:36,  6.66it/s]
 83%|████████▎ | 1163/1407 [02:53<00:37,  6.57it/s]
 83%|████████▎ | 1164/1407 [02:53<00:34,  6.98it/s]
 83%|████████▎ | 1165/1407 [02:53<00:34,  7.01it/s]
 83%|████████▎ | 1166/1407 [02:54<00:34,  6.99it/s]
 83%|████████▎ | 1167/1407 [02:54<00:34,  6.91it/s]
 83%|████████▎ | 1168/1407 [02:54<00:34,  6.89it/s]
 83%|████████▎ | 1169/1407 [02:54<00:34,  6.84it/s]
 83%|████████▎ | 1170/1407 [02:54<00:34,  6.81it/s]
 83%|████████▎ | 1171/1407 [02:54<00:34,  6.86it/s]
 83%|████████▎ | 1172/1407 [02:54<00:34,  6.82it/s]
 83%|████████▎ | 1173/1407 [02:55<00:34,  6.72it/s]
 83%|████████▎ | 1174/1407 [02:55<00:33,  6.88it/s]
 84%|████████▎ | 1175/1407 [02:55<00:32,  7.18it/s]
 84%|████████▎ | 1176/1407 [02:55<00:33,  6.93it/s]
 84%|████████▎ | 1177/1407 [02:55<00:34,  6.75it/s]
 84%|████████▎ | 1178/1407 [02:55<00:33,  6.85it/s]
 84%|████████▍ | 1179/1407 [02:56<00:33,  6.88it/s]
 84%|████████▍ | 1180/1407 [02:56<00:33,  6.72it/s]
 84%|████████▍ | 1181/1407 [02:56<00:32,  6.86it/s]
 84%|████████▍ | 1182/1407 [02:56<00:32,  6.89it/s]
 84%|████████▍ | 1183/1407 [02:56<00:30,  7.26it/s]
 84%|████████▍ | 1184/1407 [02:56<00:31,  6.98it/s]
 84%|████████▍ | 1185/1407 [02:56<00:32,  6.80it/s]
 84%|████████▍ | 1186/1407 [02:57<00:32,  6.81it/s]
 84%|████████▍ | 1187/1407 [02:57<00:32,  6.85it/s]
 84%|████████▍ | 1188/1407 [02:57<00:30,  7.15it/s]
 85%|████████▍ | 1189/1407 [02:57<00:31,  6.95it/s]
 85%|████████▍ | 1190/1407 [02:57<00:31,  6.95it/s]
 85%|████████▍ | 1191/1407 [02:57<00:31,  6.88it/s]
 85%|████████▍ | 1192/1407 [02:57<00:30,  6.94it/s]
 85%|████████▍ | 1193/1407 [02:58<00:30,  6.90it/s]
 85%|████████▍ | 1194/1407 [02:58<00:31,  6.75it/s]
 85%|████████▍ | 1195/1407 [02:58<00:30,  6.85it/s]
 85%|████████▌ | 1196/1407 [02:58<00:30,  6.98it/s]
 85%|████████▌ | 1197/1407 [02:58<00:30,  6.95it/s]
 85%|████████▌ | 1198/1407 [02:58<00:30,  6.83it/s]
 85%|████████▌ | 1199/1407 [02:58<00:28,  7.20it/s]
 85%|████████▌ | 1200/1407 [02:59<00:27,  7.53it/s]
 85%|████████▌ | 1201/1407 [02:59<00:27,  7.39it/s]
 85%|████████▌ | 1202/1407 [02:59<00:29,  7.05it/s]
 86%|████████▌ | 1203/1407 [02:59<00:29,  6.95it/s]
 86%|████████▌ | 1204/1407 [02:59<00:29,  6.99it/s]
 86%|████████▌ | 1205/1407 [02:59<00:28,  7.02it/s]
 86%|████████▌ | 1206/1407 [02:59<00:29,  6.93it/s]
 86%|████████▌ | 1207/1407 [03:00<00:28,  6.93it/s]
 86%|████████▌ | 1208/1407 [03:00<00:28,  6.91it/s]
 86%|████████▌ | 1209/1407 [03:00<00:29,  6.75it/s]
 86%|████████▌ | 1210/1407 [03:00<00:28,  6.82it/s]
 86%|████████▌ | 1211/1407 [03:00<00:26,  7.35it/s]
 86%|████████▌ | 1212/1407 [03:00<00:25,  7.55it/s]
 86%|████████▌ | 1213/1407 [03:00<00:26,  7.35it/s]
 86%|████████▋ | 1214/1407 [03:00<00:26,  7.15it/s]
 86%|████████▋ | 1215/1407 [03:01<00:27,  6.95it/s]
 86%|████████▋ | 1216/1407 [03:01<00:28,  6.77it/s]
 86%|████████▋ | 1217/1407 [03:01<00:27,  6.86it/s]
 87%|████████▋ | 1218/1407 [03:01<00:27,  6.95it/s]
 87%|████████▋ | 1219/1407 [03:01<00:25,  7.32it/s]
 87%|████████▋ | 1220/1407 [03:01<00:25,  7.27it/s]
 87%|████████▋ | 1221/1407 [03:01<00:26,  7.13it/s]
 87%|████████▋ | 1222/1407 [03:02<00:26,  7.11it/s]
 87%|████████▋ | 1223/1407 [03:02<00:26,  6.88it/s]
 87%|████████▋ | 1224/1407 [03:02<00:26,  6.84it/s]
 87%|████████▋ | 1225/1407 [03:02<00:25,  7.17it/s]
 87%|████████▋ | 1226/1407 [03:02<00:25,  7.08it/s]
 87%|████████▋ | 1227/1407 [03:02<00:25,  7.00it/s]
 87%|████████▋ | 1228/1407 [03:03<00:25,  6.95it/s]
 87%|████████▋ | 1229/1407 [03:03<00:25,  7.00it/s]
 87%|████████▋ | 1230/1407 [03:03<00:25,  6.98it/s]
 87%|████████▋ | 1231/1407 [03:03<00:24,  7.26it/s]
 88%|████████▊ | 1232/1407 [03:03<00:24,  7.21it/s]
 88%|████████▊ | 1233/1407 [03:03<00:24,  7.10it/s]
 88%|████████▊ | 1234/1407 [03:03<00:24,  6.92it/s]
 88%|████████▊ | 1235/1407 [03:03<00:24,  7.00it/s]
 88%|████████▊ | 1236/1407 [03:04<00:22,  7.44it/s]
 88%|████████▊ | 1237/1407 [03:04<00:22,  7.62it/s]
 88%|████████▊ | 1238/1407 [03:04<00:23,  7.33it/s]
 88%|████████▊ | 1239/1407 [03:04<00:22,  7.32it/s]
 88%|████████▊ | 1240/1407 [03:04<00:23,  7.21it/s]
 88%|████████▊ | 1241/1407 [03:04<00:23,  6.94it/s]
 88%|████████▊ | 1242/1407 [03:04<00:23,  6.94it/s]
 88%|████████▊ | 1243/1407 [03:05<00:23,  7.05it/s]
 88%|████████▊ | 1244/1407 [03:05<00:23,  6.96it/s]
 88%|████████▊ | 1245/1407 [03:05<00:23,  6.93it/s]
 89%|████████▊ | 1246/1407 [03:05<00:22,  7.21it/s]
 89%|████████▊ | 1247/1407 [03:05<00:22,  7.06it/s]
 89%|████████▊ | 1248/1407 [03:05<00:22,  7.00it/s]
 89%|████████▉ | 1249/1407 [03:05<00:22,  6.92it/s]
 89%|████████▉ | 1250/1407 [03:06<00:22,  6.93it/s]
 89%|████████▉ | 1251/1407 [03:06<00:22,  6.93it/s]
 89%|████████▉ | 1252/1407 [03:06<00:22,  6.77it/s]
 89%|████████▉ | 1253/1407 [03:06<00:22,  6.86it/s]
 89%|████████▉ | 1254/1407 [03:06<00:27,  5.60it/s]
 89%|████████▉ | 1255/1407 [03:06<00:24,  6.22it/s]
 89%|████████▉ | 1256/1407 [03:07<00:23,  6.37it/s]
 89%|████████▉ | 1257/1407 [03:07<00:23,  6.51it/s]
 89%|████████▉ | 1258/1407 [03:07<00:22,  6.50it/s]
 89%|████████▉ | 1259/1407 [03:07<00:22,  6.60it/s]
 90%|████████▉ | 1260/1407 [03:07<00:22,  6.53it/s]
 90%|████████▉ | 1261/1407 [03:07<00:22,  6.49it/s]
 90%|████████▉ | 1262/1407 [03:07<00:22,  6.56it/s]
 90%|████████▉ | 1263/1407 [03:08<00:21,  6.66it/s]
 90%|████████▉ | 1264/1407 [03:08<00:21,  6.75it/s]
 90%|████████▉ | 1265/1407 [03:08<00:20,  6.81it/s]
 90%|████████▉ | 1266/1407 [03:08<00:20,  6.92it/s]
 90%|█████████ | 1267/1407 [03:08<00:19,  7.03it/s]
 90%|█████████ | 1268/1407 [03:08<00:20,  6.82it/s]
 90%|█████████ | 1269/1407 [03:08<00:20,  6.85it/s]
 90%|█████████ | 1270/1407 [03:09<00:20,  6.82it/s]
 90%|█████████ | 1271/1407 [03:09<00:20,  6.73it/s]
 90%|█████████ | 1272/1407 [03:09<00:19,  6.76it/s]
 90%|█████████ | 1273/1407 [03:09<00:19,  6.86it/s]
 91%|█████████ | 1274/1407 [03:09<00:19,  6.74it/s]
 91%|█████████ | 1275/1407 [03:09<00:19,  6.77it/s]
 91%|█████████ | 1276/1407 [03:10<00:19,  6.86it/s]
 91%|█████████ | 1278/1407 [03:10<00:16,  7.74it/s]
 91%|█████████ | 1279/1407 [03:10<00:17,  7.47it/s]
 91%|█████████ | 1280/1407 [03:10<00:17,  7.38it/s]
 91%|█████████ | 1281/1407 [03:10<00:17,  7.30it/s]
 91%|█████████ | 1282/1407 [03:10<00:17,  7.25it/s]
 91%|█████████ | 1283/1407 [03:10<00:17,  6.99it/s]
 91%|█████████▏| 1284/1407 [03:11<00:17,  6.97it/s]
 91%|█████████▏| 1285/1407 [03:11<00:17,  6.80it/s]
 91%|█████████▏| 1286/1407 [03:11<00:18,  6.72it/s]
 91%|█████████▏| 1287/1407 [03:11<00:18,  6.65it/s]
 92%|█████████▏| 1288/1407 [03:11<00:17,  6.77it/s]
 92%|█████████▏| 1289/1407 [03:11<00:21,  5.56it/s]
 92%|█████████▏| 1290/1407 [03:12<00:19,  5.99it/s]
 92%|█████████▏| 1291/1407 [03:12<00:18,  6.39it/s]
 92%|█████████▏| 1292/1407 [03:12<00:18,  6.39it/s]
 92%|█████████▏| 1293/1407 [03:12<00:17,  6.52it/s]
 92%|█████████▏| 1294/1407 [03:12<00:16,  6.74it/s]
 92%|█████████▏| 1295/1407 [03:12<00:16,  6.73it/s]
 92%|█████████▏| 1296/1407 [03:12<00:15,  7.06it/s]
 92%|█████████▏| 1297/1407 [03:13<00:15,  6.99it/s]
 92%|█████████▏| 1298/1407 [03:13<00:15,  6.95it/s]
 92%|█████████▏| 1299/1407 [03:13<00:15,  6.91it/s]
 92%|█████████▏| 1300/1407 [03:13<00:15,  6.85it/s]
 92%|█████████▏| 1301/1407 [03:13<00:15,  6.89it/s]
 93%|█████████▎| 1302/1407 [03:13<00:15,  6.73it/s]
 93%|█████████▎| 1303/1407 [03:13<00:15,  6.86it/s]
 93%|█████████▎| 1304/1407 [03:14<00:14,  7.18it/s]
 93%|█████████▎| 1305/1407 [03:14<00:14,  7.12it/s]
 93%|█████████▎| 1306/1407 [03:14<00:14,  7.00it/s]
 93%|█████████▎| 1307/1407 [03:14<00:14,  6.80it/s]
 93%|█████████▎| 1308/1407 [03:14<00:13,  7.19it/s]
 93%|█████████▎| 1309/1407 [03:14<00:13,  7.08it/s]
 93%|█████████▎| 1310/1407 [03:14<00:13,  6.97it/s]
 93%|█████████▎| 1311/1407 [03:15<00:13,  7.01it/s]
 93%|█████████▎| 1312/1407 [03:15<00:13,  6.96it/s]
 93%|█████████▎| 1313/1407 [03:15<00:13,  6.94it/s]
 93%|█████████▎| 1314/1407 [03:15<00:13,  6.99it/s]
 93%|█████████▎| 1315/1407 [03:15<00:13,  6.85it/s]
 94%|█████████▎| 1316/1407 [03:15<00:13,  6.95it/s]
 94%|█████████▎| 1317/1407 [03:15<00:12,  6.95it/s]
 94%|█████████▎| 1318/1407 [03:16<00:12,  7.30it/s]
 94%|█████████▎| 1319/1407 [03:16<00:12,  7.12it/s]
 94%|█████████▍| 1320/1407 [03:16<00:12,  7.11it/s]
 94%|█████████▍| 1321/1407 [03:16<00:11,  7.35it/s]
 94%|█████████▍| 1322/1407 [03:16<00:12,  7.03it/s]
 94%|█████████▍| 1323/1407 [03:16<00:11,  7.08it/s]
 94%|█████████▍| 1324/1407 [03:17<00:16,  4.99it/s]
 94%|█████████▍| 1325/1407 [03:17<00:15,  5.45it/s]
 94%|█████████▍| 1326/1407 [03:17<00:14,  5.71it/s]
 94%|█████████▍| 1327/1407 [03:17<00:13,  6.11it/s]
 94%|█████████▍| 1328/1407 [03:17<00:11,  6.60it/s]
 94%|█████████▍| 1329/1407 [03:17<00:11,  6.70it/s]
 95%|█████████▍| 1330/1407 [03:17<00:11,  6.71it/s]
 95%|█████████▍| 1331/1407 [03:18<00:11,  6.65it/s]
 95%|█████████▍| 1332/1407 [03:18<00:11,  6.61it/s]
 95%|█████████▍| 1333/1407 [03:18<00:11,  6.67it/s]
 95%|█████████▍| 1334/1407 [03:18<00:10,  6.82it/s]
 95%|█████████▍| 1335/1407 [03:18<00:10,  6.69it/s]
 95%|█████████▍| 1336/1407 [03:18<00:10,  6.74it/s]
 95%|█████████▌| 1337/1407 [03:19<00:10,  6.74it/s]
 95%|█████████▌| 1338/1407 [03:19<00:09,  6.90it/s]
 95%|█████████▌| 1339/1407 [03:19<00:09,  6.85it/s]
 95%|█████████▌| 1340/1407 [03:19<00:09,  6.84it/s]
 95%|█████████▌| 1341/1407 [03:19<00:09,  6.80it/s]
 95%|█████████▌| 1342/1407 [03:19<00:09,  6.71it/s]
 95%|█████████▌| 1343/1407 [03:19<00:09,  6.79it/s]
 96%|█████████▌| 1344/1407 [03:20<00:09,  6.84it/s]
 96%|█████████▌| 1345/1407 [03:20<00:08,  6.92it/s]
 96%|█████████▌| 1346/1407 [03:20<00:08,  7.27it/s]
 96%|█████████▌| 1347/1407 [03:20<00:08,  7.36it/s]
 96%|█████████▌| 1348/1407 [03:20<00:08,  7.04it/s]
 96%|█████████▌| 1349/1407 [03:20<00:08,  7.00it/s]
 96%|█████████▌| 1350/1407 [03:20<00:07,  7.44it/s]
 96%|█████████▌| 1351/1407 [03:21<00:07,  7.10it/s]
 96%|█████████▌| 1352/1407 [03:21<00:07,  7.04it/s]
 96%|█████████▌| 1353/1407 [03:21<00:07,  7.19it/s]
 96%|█████████▌| 1354/1407 [03:21<00:07,  6.93it/s]
 96%|█████████▋| 1355/1407 [03:21<00:07,  6.98it/s]
 96%|█████████▋| 1356/1407 [03:21<00:07,  6.83it/s]
 96%|█████████▋| 1357/1407 [03:21<00:07,  6.73it/s]
 97%|█████████▋| 1358/1407 [03:22<00:07,  6.73it/s]
 97%|█████████▋| 1359/1407 [03:22<00:07,  6.80it/s]
 97%|█████████▋| 1360/1407 [03:22<00:07,  6.68it/s]
 97%|█████████▋| 1361/1407 [03:22<00:06,  6.62it/s]
 97%|█████████▋| 1362/1407 [03:22<00:06,  6.58it/s]
 97%|█████████▋| 1363/1407 [03:22<00:06,  6.69it/s]
 97%|█████████▋| 1364/1407 [03:22<00:06,  6.70it/s]
 97%|█████████▋| 1365/1407 [03:23<00:06,  6.76it/s]
 97%|█████████▋| 1366/1407 [03:23<00:06,  6.64it/s]
 97%|█████████▋| 1367/1407 [03:23<00:06,  6.56it/s]
 97%|█████████▋| 1368/1407 [03:23<00:05,  6.55it/s]
 97%|█████████▋| 1369/1407 [03:23<00:05,  6.54it/s]
 97%|█████████▋| 1370/1407 [03:23<00:05,  6.63it/s]
 97%|█████████▋| 1371/1407 [03:24<00:05,  6.71it/s]
 98%|█████████▊| 1372/1407 [03:24<00:05,  6.74it/s]
 98%|█████████▊| 1373/1407 [03:24<00:04,  6.82it/s]
 98%|█████████▊| 1374/1407 [03:24<00:04,  6.86it/s]
 98%|█████████▊| 1375/1407 [03:24<00:04,  6.71it/s]
 98%|█████████▊| 1376/1407 [03:24<00:04,  6.62it/s]
 98%|█████████▊| 1377/1407 [03:24<00:04,  6.60it/s]
 98%|█████████▊| 1378/1407 [03:25<00:04,  6.57it/s]
 98%|█████████▊| 1379/1407 [03:25<00:04,  6.74it/s]
 98%|█████████▊| 1380/1407 [03:25<00:03,  6.81it/s]
 98%|█████████▊| 1381/1407 [03:25<00:03,  7.02it/s]
 98%|█████████▊| 1382/1407 [03:25<00:03,  6.95it/s]
 98%|█████████▊| 1383/1407 [03:25<00:03,  6.76it/s]
 98%|█████████▊| 1384/1407 [03:25<00:03,  6.70it/s]
 98%|█████████▊| 1385/1407 [03:26<00:03,  6.76it/s]
 99%|█████████▊| 1386/1407 [03:26<00:03,  6.86it/s]
 99%|█████████▊| 1387/1407 [03:26<00:02,  6.75it/s]
 99%|█████████▊| 1388/1407 [03:26<00:02,  6.63it/s]
 99%|█████████▊| 1389/1407 [03:26<00:02,  6.55it/s]
 99%|█████████▉| 1390/1407 [03:26<00:02,  6.55it/s]
 99%|█████████▉| 1391/1407 [03:26<00:02,  6.70it/s]
 99%|█████████▉| 1392/1407 [03:27<00:02,  7.05it/s]
 99%|█████████▉| 1393/1407 [03:27<00:01,  7.01it/s]
 99%|█████████▉| 1394/1407 [03:27<00:01,  7.00it/s]
 99%|█████████▉| 1395/1407 [03:27<00:01,  6.86it/s]
 99%|█████████▉| 1396/1407 [03:27<00:01,  6.82it/s]
 99%|█████████▉| 1397/1407 [03:27<00:01,  7.37it/s]
 99%|█████████▉| 1398/1407 [03:27<00:01,  7.19it/s]
 99%|█████████▉| 1399/1407 [03:28<00:01,  6.93it/s]
100%|█████████▉| 1400/1407 [03:28<00:01,  6.99it/s]
100%|█████████▉| 1401/1407 [03:28<00:00,  6.99it/s]
100%|█████████▉| 1402/1407 [03:28<00:00,  6.81it/s]
100%|█████████▉| 1403/1407 [03:28<00:00,  6.69it/s]
100%|█████████▉| 1404/1407 [03:28<00:00,  7.14it/s]
100%|█████████▉| 1405/1407 [03:28<00:00,  7.09it/s]
100%|█████████▉| 1406/1407 [03:29<00:00,  7.02it/s]
100%|██████████| 1407/1407 [03:29<00:00,  7.36it/s]
                                                   

100%|██████████| 1407/1407 [03:29<00:00,  7.36it/s]{'eval_loss': 0.6888552904129028, 'eval_accuracy': 0.7024, 'eval_f1': 0.6992650642088528, 'eval_runtime': 1.7311, 'eval_samples_per_second': 1444.168, 'eval_steps_per_second': 180.81, 'epoch': 2.0}
{'loss': 0.6145, 'learning_rate': 1.1822263472336435e-11, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.38it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.64it/s]

 21%|██        | 66/313 [00:00<00:01, 206.16it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.53it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.88it/s]

 40%|████      | 126/313 [00:00<00:01, 185.66it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.47it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.37it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.40it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.56it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.76it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.51it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.15it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.96it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.89it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.89it/s]
100%|██████████| 1407/1407 [03:30<00:00,  7.36it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 1407/1407 [03:32<00:00,  7.36it/s]
100%|██████████| 1407/1407 [03:32<00:00,  6.64it/s]
[I 2023-10-26 22:28:19,534] Trial 8 finished with value: 0.7018201922749657 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 7.679421653596784e-06, 'per_device_train_batch_size': 64, 'weight_decay': 0.034936438383221254}. Best is trial 6 with value: 0.716991552355688.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6829062700271606, 'eval_accuracy': 0.7028, 'eval_f1': 0.7018201922749657, 'eval_runtime': 1.7287, 'eval_samples_per_second': 1446.212, 'eval_steps_per_second': 181.066, 'epoch': 3.0}
{'train_runtime': 212.0074, 'train_samples_per_second': 424.514, 'train_steps_per_second': 6.637, 'train_loss': 0.7194787346054327, 'epoch': 3.0}

  0%|          | 0/5625 [00:00<?, ?it/s]
  0%|          | 2/5625 [00:00<04:52, 19.20it/s]
  0%|          | 4/5625 [00:00<04:57, 18.91it/s]
  0%|          | 6/5625 [00:00<04:53, 19.17it/s]
  0%|          | 8/5625 [00:00<04:56, 18.97it/s]
  0%|          | 10/5625 [00:00<04:58, 18.80it/s]
  0%|          | 12/5625 [00:00<04:53, 19.14it/s]
  0%|          | 14/5625 [00:00<05:03, 18.51it/s]
  0%|          | 17/5625 [00:00<04:48, 19.43it/s]
  0%|          | 20/5625 [00:01<04:47, 19.51it/s]
  0%|          | 22/5625 [00:01<04:53, 19.12it/s]
  0%|          | 24/5625 [00:01<04:57, 18.86it/s]
  0%|          | 26/5625 [00:01<05:04, 18.37it/s]
  0%|          | 28/5625 [00:01<05:05, 18.32it/s]
  1%|          | 30/5625 [00:01<04:59, 18.69it/s]
  1%|          | 33/5625 [00:01<04:51, 19.22it/s]
  1%|          | 36/5625 [00:01<04:37, 20.11it/s]
  1%|          | 39/5625 [00:02<04:29, 20.72it/s]
  1%|          | 42/5625 [00:02<04:40, 19.93it/s]
  1%|          | 45/5625 [00:02<04:32, 20.47it/s]
  1%|          | 48/5625 [00:02<04:30, 20.64it/s]
  1%|          | 51/5625 [00:02<04:33, 20.35it/s]
  1%|          | 54/5625 [00:02<04:37, 20.05it/s]
  1%|          | 57/5625 [00:02<04:44, 19.54it/s]
  1%|          | 60/5625 [00:03<04:45, 19.47it/s]
  1%|          | 63/5625 [00:03<04:38, 19.94it/s]
  1%|          | 65/5625 [00:03<04:41, 19.74it/s]
  1%|          | 68/5625 [00:03<04:35, 20.13it/s]
  1%|▏         | 71/5625 [00:03<04:43, 19.62it/s]
  1%|▏         | 73/5625 [00:03<04:43, 19.57it/s]
  1%|▏         | 75/5625 [00:03<04:46, 19.39it/s]
  1%|▏         | 77/5625 [00:03<04:55, 18.79it/s]
  1%|▏         | 79/5625 [00:04<05:02, 18.35it/s]
  1%|▏         | 82/5625 [00:04<04:50, 19.11it/s]
  1%|▏         | 84/5625 [00:04<04:47, 19.25it/s]
  2%|▏         | 86/5625 [00:04<04:45, 19.41it/s]
  2%|▏         | 88/5625 [00:04<04:45, 19.38it/s]
  2%|▏         | 90/5625 [00:04<04:48, 19.21it/s]
  2%|▏         | 92/5625 [00:04<04:51, 19.00it/s]
  2%|▏         | 94/5625 [00:04<04:51, 19.00it/s]
  2%|▏         | 96/5625 [00:04<04:58, 18.55it/s]
  2%|▏         | 99/5625 [00:05<04:50, 19.04it/s]
  2%|▏         | 101/5625 [00:05<04:47, 19.23it/s]
  2%|▏         | 103/5625 [00:05<04:44, 19.41it/s]
  2%|▏         | 105/5625 [00:05<04:47, 19.21it/s]
  2%|▏         | 107/5625 [00:05<04:48, 19.15it/s]
  2%|▏         | 109/5625 [00:05<04:50, 18.98it/s]
  2%|▏         | 112/5625 [00:05<04:39, 19.70it/s]
  2%|▏         | 114/5625 [00:05<04:47, 19.14it/s]
  2%|▏         | 117/5625 [00:06<04:44, 19.38it/s]
  2%|▏         | 119/5625 [00:06<04:42, 19.46it/s]
  2%|▏         | 122/5625 [00:06<04:34, 20.01it/s]
  2%|▏         | 125/5625 [00:06<04:27, 20.58it/s]
  2%|▏         | 128/5625 [00:06<04:39, 19.66it/s]
  2%|▏         | 130/5625 [00:06<04:40, 19.59it/s]
  2%|▏         | 132/5625 [00:06<04:40, 19.59it/s]
  2%|▏         | 134/5625 [00:06<04:46, 19.15it/s]
  2%|▏         | 136/5625 [00:07<04:52, 18.75it/s]
  2%|▏         | 139/5625 [00:07<04:48, 19.01it/s]
  3%|▎         | 141/5625 [00:07<04:55, 18.57it/s]
  3%|▎         | 143/5625 [00:07<04:54, 18.60it/s]
  3%|▎         | 145/5625 [00:07<04:59, 18.30it/s]
  3%|▎         | 147/5625 [00:07<04:53, 18.67it/s]
  3%|▎         | 149/5625 [00:07<04:53, 18.66it/s]
  3%|▎         | 151/5625 [00:07<04:49, 18.91it/s]
  3%|▎         | 154/5625 [00:07<04:44, 19.20it/s]
  3%|▎         | 156/5625 [00:08<04:45, 19.12it/s]
  3%|▎         | 158/5625 [00:08<04:52, 18.68it/s]
  3%|▎         | 161/5625 [00:08<04:36, 19.77it/s]
  3%|▎         | 163/5625 [00:08<04:37, 19.70it/s]
  3%|▎         | 165/5625 [00:08<04:46, 19.05it/s]
  3%|▎         | 167/5625 [00:08<04:46, 19.03it/s]
  3%|▎         | 169/5625 [00:08<04:46, 19.06it/s]
  3%|▎         | 171/5625 [00:08<04:43, 19.26it/s]
  3%|▎         | 173/5625 [00:08<04:44, 19.17it/s]
  3%|▎         | 176/5625 [00:09<04:34, 19.84it/s]
  3%|▎         | 179/5625 [00:09<04:28, 20.27it/s]
  3%|▎         | 182/5625 [00:09<04:29, 20.17it/s]
  3%|▎         | 185/5625 [00:09<04:35, 19.73it/s]
  3%|▎         | 187/5625 [00:09<04:39, 19.46it/s]
  3%|▎         | 190/5625 [00:09<04:39, 19.45it/s]
  3%|▎         | 193/5625 [00:09<04:36, 19.62it/s]
  3%|▎         | 195/5625 [00:10<04:41, 19.31it/s]
  4%|▎         | 197/5625 [00:10<04:42, 19.23it/s]
  4%|▎         | 200/5625 [00:10<04:35, 19.70it/s]
  4%|▎         | 202/5625 [00:10<04:39, 19.39it/s]
  4%|▎         | 205/5625 [00:10<04:22, 20.62it/s]
  4%|▎         | 208/5625 [00:10<04:24, 20.52it/s]
  4%|▍         | 211/5625 [00:10<04:31, 19.97it/s]
  4%|▍         | 213/5625 [00:10<04:34, 19.71it/s]
  4%|▍         | 215/5625 [00:11<04:39, 19.38it/s]
  4%|▍         | 217/5625 [00:11<04:43, 19.08it/s]
  4%|▍         | 220/5625 [00:11<04:36, 19.53it/s]
  4%|▍         | 222/5625 [00:11<04:37, 19.47it/s]
  4%|▍         | 224/5625 [00:11<04:41, 19.16it/s]
  4%|▍         | 227/5625 [00:11<04:40, 19.21it/s]
  4%|▍         | 229/5625 [00:11<04:38, 19.38it/s]
  4%|▍         | 231/5625 [00:11<04:37, 19.41it/s]
  4%|▍         | 234/5625 [00:12<04:35, 19.58it/s]
  4%|▍         | 236/5625 [00:12<04:38, 19.34it/s]
  4%|▍         | 238/5625 [00:12<04:36, 19.48it/s]
  4%|▍         | 240/5625 [00:12<04:37, 19.40it/s]
  4%|▍         | 242/5625 [00:12<04:45, 18.85it/s]
  4%|▍         | 244/5625 [00:12<04:49, 18.62it/s]
  4%|▍         | 247/5625 [00:12<04:36, 19.43it/s]
  4%|▍         | 249/5625 [00:12<04:35, 19.54it/s]
  4%|▍         | 251/5625 [00:12<04:42, 18.99it/s]
  4%|▍         | 253/5625 [00:13<04:46, 18.75it/s]
  5%|▍         | 255/5625 [00:13<04:42, 19.04it/s]
  5%|▍         | 257/5625 [00:13<04:47, 18.70it/s]
  5%|▍         | 260/5625 [00:13<04:43, 18.95it/s]
  5%|▍         | 263/5625 [00:13<04:32, 19.69it/s]
  5%|▍         | 266/5625 [00:13<04:27, 20.04it/s]
  5%|▍         | 268/5625 [00:13<04:33, 19.56it/s]
  5%|▍         | 271/5625 [00:13<04:33, 19.56it/s]
  5%|▍         | 273/5625 [00:14<04:37, 19.27it/s]
  5%|▍         | 275/5625 [00:14<04:40, 19.07it/s]
  5%|▍         | 277/5625 [00:14<04:42, 18.95it/s]
  5%|▍         | 280/5625 [00:14<04:32, 19.64it/s]
  5%|▌         | 283/5625 [00:14<04:24, 20.17it/s]
  5%|▌         | 286/5625 [00:14<04:32, 19.57it/s]
  5%|▌         | 288/5625 [00:14<04:35, 19.36it/s]
  5%|▌         | 291/5625 [00:15<04:36, 19.26it/s]
  5%|▌         | 294/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 296/5625 [00:15<04:37, 19.24it/s]
  5%|▌         | 299/5625 [00:15<04:30, 19.71it/s]
  5%|▌         | 301/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 303/5625 [00:15<04:40, 18.98it/s]
  5%|▌         | 305/5625 [00:15<04:43, 18.79it/s]
  5%|▌         | 308/5625 [00:15<04:35, 19.33it/s]
  6%|▌         | 311/5625 [00:16<04:30, 19.66it/s]
  6%|▌         | 313/5625 [00:16<04:30, 19.63it/s]
  6%|▌         | 315/5625 [00:16<04:30, 19.61it/s]
  6%|▌         | 317/5625 [00:16<04:33, 19.40it/s]
  6%|▌         | 319/5625 [00:16<04:38, 19.04it/s]
  6%|▌         | 321/5625 [00:16<04:36, 19.20it/s]
  6%|▌         | 323/5625 [00:16<04:39, 18.99it/s]
  6%|▌         | 326/5625 [00:16<04:22, 20.18it/s]
  6%|▌         | 329/5625 [00:16<04:22, 20.21it/s]
  6%|▌         | 332/5625 [00:17<04:27, 19.76it/s]
  6%|▌         | 334/5625 [00:17<04:27, 19.78it/s]
  6%|▌         | 337/5625 [00:17<04:23, 20.06it/s]
  6%|▌         | 340/5625 [00:17<04:29, 19.64it/s]
  6%|▌         | 342/5625 [00:17<04:36, 19.13it/s]
  6%|▌         | 344/5625 [00:17<04:40, 18.85it/s]
  6%|▌         | 346/5625 [00:17<04:43, 18.62it/s]
  6%|▌         | 349/5625 [00:17<04:31, 19.44it/s]
  6%|▋         | 352/5625 [00:18<04:29, 19.59it/s]
  6%|▋         | 354/5625 [00:18<04:31, 19.39it/s]
  6%|▋         | 357/5625 [00:18<04:18, 20.38it/s]
  6%|▋         | 360/5625 [00:18<04:31, 19.36it/s]
  6%|▋         | 362/5625 [00:18<04:30, 19.45it/s]
  6%|▋         | 364/5625 [00:18<04:38, 18.87it/s]
  7%|▋         | 366/5625 [00:18<04:39, 18.80it/s]
  7%|▋         | 368/5625 [00:18<04:46, 18.37it/s]
  7%|▋         | 370/5625 [00:19<04:44, 18.45it/s]
  7%|▋         | 372/5625 [00:19<04:39, 18.80it/s]
  7%|▋         | 374/5625 [00:19<04:35, 19.08it/s]
  7%|▋         | 376/5625 [00:19<04:41, 18.64it/s]
  7%|▋         | 378/5625 [00:19<04:37, 18.89it/s]
  7%|▋         | 380/5625 [00:19<04:36, 19.00it/s]
  7%|▋         | 382/5625 [00:19<04:38, 18.83it/s]
  7%|▋         | 385/5625 [00:19<04:25, 19.75it/s]
  7%|▋         | 387/5625 [00:19<04:32, 19.21it/s]
  7%|▋         | 389/5625 [00:20<04:35, 19.03it/s]
  7%|▋         | 391/5625 [00:20<04:31, 19.26it/s]
  7%|▋         | 393/5625 [00:20<04:38, 18.79it/s]
  7%|▋         | 395/5625 [00:20<04:34, 19.06it/s]
  7%|▋         | 397/5625 [00:20<04:32, 19.22it/s]
  7%|▋         | 399/5625 [00:20<04:32, 19.16it/s]
  7%|▋         | 401/5625 [00:20<04:29, 19.39it/s]
  7%|▋         | 403/5625 [00:20<04:30, 19.28it/s]
  7%|▋         | 405/5625 [00:20<04:37, 18.81it/s]
  7%|▋         | 407/5625 [00:21<04:37, 18.81it/s]
  7%|▋         | 409/5625 [00:21<04:33, 19.06it/s]
  7%|▋         | 411/5625 [00:21<04:39, 18.65it/s]
  7%|▋         | 413/5625 [00:21<04:34, 18.96it/s]
  7%|▋         | 416/5625 [00:21<04:23, 19.80it/s]
  7%|▋         | 419/5625 [00:21<04:24, 19.70it/s]
  7%|▋         | 421/5625 [00:21<04:28, 19.40it/s]
  8%|▊         | 423/5625 [00:21<04:26, 19.55it/s]
  8%|▊         | 425/5625 [00:21<04:31, 19.14it/s]
  8%|▊         | 427/5625 [00:22<04:33, 19.03it/s]
  8%|▊         | 429/5625 [00:22<04:30, 19.22it/s]
  8%|▊         | 431/5625 [00:22<04:33, 19.01it/s]
  8%|▊         | 434/5625 [00:22<04:24, 19.64it/s]
  8%|▊         | 437/5625 [00:22<04:15, 20.31it/s]
  8%|▊         | 440/5625 [00:22<04:18, 20.04it/s]
  8%|▊         | 442/5625 [00:22<04:25, 19.49it/s]
  8%|▊         | 445/5625 [00:22<04:21, 19.79it/s]
  8%|▊         | 447/5625 [00:23<04:22, 19.75it/s]
  8%|▊         | 449/5625 [00:23<04:25, 19.47it/s]
  8%|▊         | 451/5625 [00:23<04:30, 19.10it/s]
  8%|▊         | 453/5625 [00:23<04:27, 19.33it/s]
  8%|▊         | 456/5625 [00:23<04:15, 20.24it/s]
  8%|▊         | 459/5625 [00:23<04:29, 19.20it/s]
  8%|▊         | 461/5625 [00:23<04:32, 18.94it/s]
  8%|▊         | 463/5625 [00:23<04:29, 19.15it/s]
  8%|▊         | 465/5625 [00:24<04:34, 18.78it/s]
  8%|▊         | 468/5625 [00:24<04:22, 19.64it/s]
  8%|▊         | 470/5625 [00:24<04:27, 19.24it/s]
  8%|▊         | 473/5625 [00:24<04:22, 19.59it/s]
  8%|▊         | 475/5625 [00:24<04:22, 19.60it/s]
  8%|▊         | 477/5625 [00:24<04:26, 19.31it/s]
  9%|▊         | 480/5625 [00:24<04:20, 19.73it/s]
  9%|▊         | 482/5625 [00:24<04:20, 19.76it/s]
  9%|▊         | 484/5625 [00:24<04:24, 19.45it/s]
  9%|▊         | 486/5625 [00:25<04:30, 18.98it/s]
  9%|▊         | 489/5625 [00:25<04:18, 19.87it/s]
  9%|▊         | 491/5625 [00:25<04:22, 19.52it/s]
  9%|▉         | 494/5625 [00:25<04:09, 20.56it/s]
  9%|▉         | 497/5625 [00:25<04:14, 20.16it/s]
  9%|▉         | 500/5625 [00:25<04:20, 19.69it/s]
  9%|▉         | 502/5625 [00:25<04:27, 19.14it/s]
  9%|▉         | 504/5625 [00:26<04:28, 19.10it/s]
  9%|▉         | 507/5625 [00:26<04:17, 19.85it/s]
  9%|▉         | 510/5625 [00:26<04:14, 20.09it/s]
  9%|▉         | 512/5625 [00:26<04:23, 19.40it/s]
  9%|▉         | 514/5625 [00:26<04:24, 19.33it/s]
  9%|▉         | 516/5625 [00:26<04:31, 18.83it/s]
  9%|▉         | 518/5625 [00:26<04:28, 19.03it/s]
  9%|▉         | 520/5625 [00:26<04:30, 18.84it/s]
  9%|▉         | 522/5625 [00:26<04:29, 18.92it/s]
  9%|▉         | 524/5625 [00:27<04:32, 18.74it/s]
  9%|▉         | 526/5625 [00:27<04:36, 18.46it/s]
  9%|▉         | 529/5625 [00:27<04:28, 18.99it/s]
  9%|▉         | 531/5625 [00:27<04:33, 18.65it/s]
  9%|▉         | 533/5625 [00:27<04:39, 18.20it/s]
 10%|▉         | 536/5625 [00:27<04:24, 19.24it/s]
 10%|▉         | 539/5625 [00:27<04:20, 19.55it/s]
 10%|▉         | 541/5625 [00:27<04:19, 19.62it/s]
 10%|▉         | 544/5625 [00:28<04:20, 19.50it/s]
 10%|▉         | 546/5625 [00:28<04:21, 19.43it/s]
 10%|▉         | 548/5625 [00:28<04:25, 19.11it/s]
 10%|▉         | 550/5625 [00:28<04:27, 18.99it/s]
 10%|▉         | 553/5625 [00:28<04:21, 19.37it/s]
 10%|▉         | 555/5625 [00:28<04:20, 19.44it/s]
 10%|▉         | 557/5625 [00:28<04:24, 19.16it/s]
 10%|▉         | 559/5625 [00:28<04:24, 19.17it/s]
 10%|▉         | 562/5625 [00:29<04:19, 19.55it/s]
 10%|█         | 564/5625 [00:29<04:25, 19.06it/s]
 10%|█         | 566/5625 [00:29<04:30, 18.72it/s]
 10%|█         | 568/5625 [00:29<04:33, 18.50it/s]
 10%|█         | 570/5625 [00:29<04:33, 18.49it/s]
 10%|█         | 573/5625 [00:29<04:25, 19.06it/s]
 10%|█         | 576/5625 [00:29<04:18, 19.52it/s]
 10%|█         | 578/5625 [00:29<04:22, 19.26it/s]
 10%|█         | 580/5625 [00:29<04:27, 18.83it/s]
 10%|█         | 583/5625 [00:30<04:25, 18.99it/s]
 10%|█         | 585/5625 [00:30<04:30, 18.64it/s]
 10%|█         | 587/5625 [00:30<04:31, 18.59it/s]
 10%|█         | 589/5625 [00:30<04:29, 18.71it/s]
 11%|█         | 592/5625 [00:30<04:20, 19.31it/s]
 11%|█         | 594/5625 [00:30<04:26, 18.90it/s]
 11%|█         | 596/5625 [00:30<04:25, 18.92it/s]
 11%|█         | 598/5625 [00:30<04:23, 19.09it/s]
 11%|█         | 601/5625 [00:31<04:15, 19.66it/s]
 11%|█         | 603/5625 [00:31<04:17, 19.53it/s]
 11%|█         | 605/5625 [00:31<04:24, 18.96it/s]
 11%|█         | 608/5625 [00:31<04:16, 19.59it/s]
 11%|█         | 610/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 612/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 614/5625 [00:31<04:23, 19.05it/s]
 11%|█         | 616/5625 [00:31<04:19, 19.28it/s]
 11%|█         | 618/5625 [00:31<04:24, 18.91it/s]
 11%|█         | 621/5625 [00:32<04:08, 20.17it/s]
 11%|█         | 624/5625 [00:32<04:15, 19.55it/s]
 11%|█         | 626/5625 [00:32<04:21, 19.14it/s]
 11%|█         | 628/5625 [00:32<04:18, 19.34it/s]
 11%|█         | 631/5625 [00:32<04:10, 19.90it/s]
 11%|█▏        | 633/5625 [00:32<04:21, 19.12it/s]
 11%|█▏        | 635/5625 [00:32<04:23, 18.95it/s]
 11%|█▏        | 637/5625 [00:32<04:22, 19.00it/s]
 11%|█▏        | 640/5625 [00:33<04:16, 19.41it/s]
 11%|█▏        | 642/5625 [00:33<04:16, 19.40it/s]
 11%|█▏        | 645/5625 [00:33<04:11, 19.79it/s]
 12%|█▏        | 647/5625 [00:33<04:20, 19.10it/s]
 12%|█▏        | 649/5625 [00:33<04:20, 19.13it/s]
 12%|█▏        | 651/5625 [00:33<04:25, 18.72it/s]
 12%|█▏        | 653/5625 [00:33<04:22, 18.92it/s]
 12%|█▏        | 656/5625 [00:33<04:11, 19.79it/s]
 12%|█▏        | 658/5625 [00:34<04:12, 19.64it/s]
 12%|█▏        | 661/5625 [00:34<04:13, 19.58it/s]
 12%|█▏        | 663/5625 [00:34<04:17, 19.30it/s]
 12%|█▏        | 665/5625 [00:34<04:21, 18.94it/s]
 12%|█▏        | 667/5625 [00:34<04:25, 18.68it/s]
 12%|█▏        | 669/5625 [00:34<04:26, 18.57it/s]
 12%|█▏        | 671/5625 [00:34<04:21, 18.93it/s]
 12%|█▏        | 673/5625 [00:34<04:21, 18.96it/s]
 12%|█▏        | 675/5625 [00:34<04:22, 18.85it/s]
 12%|█▏        | 677/5625 [00:35<04:29, 18.36it/s]
 12%|█▏        | 679/5625 [00:35<04:28, 18.41it/s]
 12%|█▏        | 681/5625 [00:35<04:27, 18.47it/s]
 12%|█▏        | 683/5625 [00:35<04:32, 18.12it/s]
 12%|█▏        | 685/5625 [00:35<04:28, 18.39it/s]
 12%|█▏        | 687/5625 [00:35<04:25, 18.60it/s]
 12%|█▏        | 689/5625 [00:35<04:21, 18.85it/s]
 12%|█▏        | 691/5625 [00:35<04:18, 19.12it/s]
 12%|█▏        | 693/5625 [00:35<04:21, 18.87it/s]
 12%|█▏        | 696/5625 [00:36<04:14, 19.34it/s]
 12%|█▏        | 699/5625 [00:36<04:14, 19.39it/s]
 12%|█▏        | 701/5625 [00:36<04:19, 18.97it/s]
 12%|█▏        | 703/5625 [00:36<04:23, 18.68it/s]
 13%|█▎        | 705/5625 [00:36<04:19, 18.93it/s]
 13%|█▎        | 707/5625 [00:36<04:20, 18.86it/s]
 13%|█▎        | 709/5625 [00:36<04:21, 18.77it/s]
 13%|█▎        | 711/5625 [00:36<04:24, 18.55it/s]
 13%|█▎        | 714/5625 [00:37<04:18, 19.01it/s]
 13%|█▎        | 716/5625 [00:37<04:16, 19.14it/s]
 13%|█▎        | 718/5625 [00:37<04:15, 19.18it/s]
 13%|█▎        | 720/5625 [00:37<04:16, 19.14it/s]
 13%|█▎        | 722/5625 [00:37<04:17, 19.04it/s]
 13%|█▎        | 725/5625 [00:37<04:14, 19.29it/s]
 13%|█▎        | 728/5625 [00:37<04:04, 20.01it/s]
 13%|█▎        | 730/5625 [00:37<04:12, 19.37it/s]
 13%|█▎        | 733/5625 [00:37<04:11, 19.43it/s]
 13%|█▎        | 735/5625 [00:38<04:13, 19.30it/s]
 13%|█▎        | 737/5625 [00:38<04:11, 19.47it/s]
 13%|█▎        | 739/5625 [00:38<04:18, 18.89it/s]
 13%|█▎        | 742/5625 [00:38<04:09, 19.54it/s]
 13%|█▎        | 745/5625 [00:38<04:08, 19.61it/s]
 13%|█▎        | 747/5625 [00:38<04:15, 19.07it/s]
 13%|█▎        | 750/5625 [00:38<04:08, 19.62it/s]
 13%|█▎        | 752/5625 [00:38<04:09, 19.50it/s]
 13%|█▎        | 754/5625 [00:39<04:12, 19.26it/s]
 13%|█▎        | 756/5625 [00:39<04:18, 18.85it/s]
 13%|█▎        | 758/5625 [00:39<04:16, 18.98it/s]
 14%|█▎        | 761/5625 [00:39<04:11, 19.30it/s]
 14%|█▎        | 763/5625 [00:39<04:12, 19.26it/s]
 14%|█▎        | 765/5625 [00:39<04:14, 19.13it/s]
 14%|█▎        | 767/5625 [00:39<04:16, 18.95it/s]
 14%|█▎        | 769/5625 [00:39<04:13, 19.18it/s]
 14%|█▎        | 771/5625 [00:39<04:14, 19.07it/s]
 14%|█▍        | 774/5625 [00:40<04:10, 19.33it/s]
 14%|█▍        | 776/5625 [00:40<04:15, 18.97it/s]
 14%|█▍        | 779/5625 [00:40<04:14, 19.03it/s]
 14%|█▍        | 782/5625 [00:40<04:07, 19.59it/s]
 14%|█▍        | 785/5625 [00:40<04:03, 19.89it/s]
 14%|█▍        | 787/5625 [00:40<04:11, 19.27it/s]
 14%|█▍        | 789/5625 [00:40<04:13, 19.06it/s]
 14%|█▍        | 791/5625 [00:41<04:18, 18.71it/s]
 14%|█▍        | 794/5625 [00:41<04:05, 19.65it/s]
 14%|█▍        | 796/5625 [00:41<04:11, 19.18it/s]
 14%|█▍        | 798/5625 [00:41<05:23, 14.91it/s]
 14%|█▍        | 800/5625 [00:41<05:08, 15.62it/s]
 14%|█▍        | 803/5625 [00:41<04:39, 17.23it/s]
 14%|█▍        | 805/5625 [00:41<04:38, 17.31it/s]
 14%|█▍        | 808/5625 [00:41<04:21, 18.40it/s]
 14%|█▍        | 810/5625 [00:42<04:21, 18.40it/s]
 14%|█▍        | 812/5625 [00:42<04:24, 18.23it/s]
 14%|█▍        | 815/5625 [00:42<04:11, 19.16it/s]
 15%|█▍        | 817/5625 [00:42<04:13, 18.95it/s]
 15%|█▍        | 819/5625 [00:42<04:19, 18.53it/s]
 15%|█▍        | 821/5625 [00:42<04:14, 18.85it/s]
 15%|█▍        | 823/5625 [00:42<04:15, 18.78it/s]
 15%|█▍        | 826/5625 [00:42<04:07, 19.41it/s]
 15%|█▍        | 829/5625 [00:43<04:05, 19.57it/s]
 15%|█▍        | 832/5625 [00:43<03:56, 20.30it/s]
 15%|█▍        | 835/5625 [00:43<03:58, 20.11it/s]
 15%|█▍        | 838/5625 [00:43<04:02, 19.73it/s]
 15%|█▍        | 840/5625 [00:43<04:06, 19.42it/s]
 15%|█▍        | 842/5625 [00:43<04:11, 19.02it/s]
 15%|█▌        | 844/5625 [00:43<04:09, 19.17it/s]
 15%|█▌        | 846/5625 [00:43<04:10, 19.08it/s]
 15%|█▌        | 848/5625 [00:44<04:16, 18.62it/s]
 15%|█▌        | 851/5625 [00:44<04:10, 19.04it/s]
 15%|█▌        | 854/5625 [00:44<04:08, 19.16it/s]
 15%|█▌        | 856/5625 [00:44<04:07, 19.25it/s]
 15%|█▌        | 859/5625 [00:44<04:01, 19.73it/s]
 15%|█▌        | 862/5625 [00:44<04:01, 19.70it/s]
 15%|█▌        | 864/5625 [00:44<04:08, 19.18it/s]
 15%|█▌        | 867/5625 [00:45<03:56, 20.11it/s]
 15%|█▌        | 870/5625 [00:45<03:58, 19.96it/s]
 16%|█▌        | 872/5625 [00:45<03:59, 19.86it/s]
 16%|█▌        | 874/5625 [00:45<04:02, 19.62it/s]
 16%|█▌        | 876/5625 [00:45<04:04, 19.46it/s]
 16%|█▌        | 879/5625 [00:45<04:02, 19.59it/s]
 16%|█▌        | 882/5625 [00:45<03:59, 19.78it/s]
 16%|█▌        | 885/5625 [00:45<03:58, 19.84it/s]
 16%|█▌        | 888/5625 [00:46<03:57, 19.93it/s]
 16%|█▌        | 890/5625 [00:46<04:01, 19.60it/s]
 16%|█▌        | 893/5625 [00:46<04:02, 19.54it/s]
 16%|█▌        | 895/5625 [00:46<05:49, 13.52it/s]
 16%|█▌        | 898/5625 [00:46<05:03, 15.57it/s]
 16%|█▌        | 901/5625 [00:46<04:39, 16.91it/s]
 16%|█▌        | 904/5625 [00:47<04:21, 18.07it/s]
 16%|█▌        | 906/5625 [00:47<04:19, 18.15it/s]
 16%|█▌        | 908/5625 [00:47<04:17, 18.33it/s]
 16%|█▌        | 911/5625 [00:47<04:07, 19.08it/s]
 16%|█▌        | 914/5625 [00:47<04:04, 19.29it/s]
 16%|█▋        | 917/5625 [00:47<03:58, 19.71it/s]
 16%|█▋        | 919/5625 [00:47<04:04, 19.27it/s]
 16%|█▋        | 921/5625 [00:47<04:10, 18.81it/s]
 16%|█▋        | 923/5625 [00:48<04:07, 18.96it/s]
 16%|█▋        | 925/5625 [00:48<04:08, 18.90it/s]
 16%|█▋        | 928/5625 [00:48<04:01, 19.46it/s]
 17%|█▋        | 930/5625 [00:48<04:02, 19.40it/s]
 17%|█▋        | 933/5625 [00:48<03:52, 20.21it/s]
 17%|█▋        | 936/5625 [00:48<03:53, 20.07it/s]
 17%|█▋        | 939/5625 [00:48<03:52, 20.18it/s]
 17%|█▋        | 942/5625 [00:49<03:51, 20.23it/s]
 17%|█▋        | 945/5625 [00:49<03:55, 19.86it/s]
 17%|█▋        | 947/5625 [00:49<03:56, 19.74it/s]
 17%|█▋        | 950/5625 [00:49<03:52, 20.11it/s]
 17%|█▋        | 953/5625 [00:49<04:00, 19.41it/s]
 17%|█▋        | 955/5625 [00:49<03:59, 19.51it/s]
 17%|█▋        | 958/5625 [00:49<03:54, 19.89it/s]
 17%|█▋        | 960/5625 [00:49<03:57, 19.60it/s]
 17%|█▋        | 962/5625 [00:50<04:03, 19.17it/s]
 17%|█▋        | 964/5625 [00:50<04:01, 19.34it/s]
 17%|█▋        | 966/5625 [00:50<03:58, 19.51it/s]
 17%|█▋        | 968/5625 [00:50<03:57, 19.57it/s]
 17%|█▋        | 970/5625 [00:50<03:58, 19.51it/s]
 17%|█▋        | 972/5625 [00:50<04:02, 19.22it/s]
 17%|█▋        | 974/5625 [00:50<03:59, 19.43it/s]
 17%|█▋        | 976/5625 [00:50<04:01, 19.28it/s]
 17%|█▋        | 979/5625 [00:50<03:57, 19.53it/s]
 17%|█▋        | 982/5625 [00:51<03:57, 19.58it/s]
 17%|█▋        | 984/5625 [00:51<04:02, 19.13it/s]
 18%|█▊        | 986/5625 [00:51<04:03, 19.03it/s]
 18%|█▊        | 988/5625 [00:51<04:05, 18.90it/s]
 18%|█▊        | 991/5625 [00:51<03:56, 19.58it/s]
 18%|█▊        | 993/5625 [00:51<05:54, 13.07it/s]
 18%|█▊        | 995/5625 [00:51<05:29, 14.05it/s]
 18%|█▊        | 998/5625 [00:52<04:52, 15.81it/s]
 18%|█▊        | 1000/5625 [00:52<04:37, 16.64it/s]
 18%|█▊        | 1002/5625 [00:52<04:27, 17.27it/s]
 18%|█▊        | 1005/5625 [00:52<04:15, 18.11it/s]
 18%|█▊        | 1008/5625 [00:52<04:01, 19.14it/s]
 18%|█▊        | 1011/5625 [00:52<03:58, 19.34it/s]
 18%|█▊        | 1013/5625 [00:52<03:59, 19.26it/s]
 18%|█▊        | 1015/5625 [00:52<03:58, 19.33it/s]
 18%|█▊        | 1017/5625 [00:53<03:59, 19.21it/s]
 18%|█▊        | 1020/5625 [00:53<03:51, 19.92it/s]
 18%|█▊        | 1022/5625 [00:53<03:55, 19.52it/s]
 18%|█▊        | 1024/5625 [00:53<04:01, 19.08it/s]
 18%|█▊        | 1027/5625 [00:53<03:57, 19.37it/s]
 18%|█▊        | 1030/5625 [00:53<03:57, 19.36it/s]
 18%|█▊        | 1032/5625 [00:53<03:59, 19.15it/s]
 18%|█▊        | 1034/5625 [00:53<04:05, 18.71it/s]
 18%|█▊        | 1037/5625 [00:54<03:57, 19.31it/s]
 18%|█▊        | 1040/5625 [00:54<03:57, 19.28it/s]
 19%|█▊        | 1042/5625 [00:54<03:57, 19.27it/s]
 19%|█▊        | 1044/5625 [00:54<04:03, 18.85it/s]
 19%|█▊        | 1047/5625 [00:54<03:53, 19.64it/s]
 19%|█▊        | 1050/5625 [00:54<03:45, 20.27it/s]
 19%|█▊        | 1053/5625 [00:54<03:41, 20.65it/s]
 19%|█▉        | 1056/5625 [00:55<03:43, 20.47it/s]
 19%|█▉        | 1059/5625 [00:55<03:48, 19.95it/s]
 19%|█▉        | 1061/5625 [00:55<03:49, 19.89it/s]
 19%|█▉        | 1063/5625 [00:55<03:54, 19.46it/s]
 19%|█▉        | 1066/5625 [00:55<03:48, 19.99it/s]
 19%|█▉        | 1068/5625 [00:55<03:52, 19.64it/s]
 19%|█▉        | 1070/5625 [00:55<03:57, 19.19it/s]
 19%|█▉        | 1072/5625 [00:55<03:59, 19.03it/s]
 19%|█▉        | 1074/5625 [00:55<03:58, 19.05it/s]
 19%|█▉        | 1076/5625 [00:56<04:01, 18.88it/s]
 19%|█▉        | 1078/5625 [00:56<04:05, 18.56it/s]
 19%|█▉        | 1081/5625 [00:56<04:00, 18.86it/s]
 19%|█▉        | 1084/5625 [00:56<03:56, 19.22it/s]
 19%|█▉        | 1086/5625 [00:56<03:54, 19.37it/s]
 19%|█▉        | 1089/5625 [00:56<03:45, 20.11it/s]
 19%|█▉        | 1092/5625 [00:56<03:50, 19.70it/s]
 19%|█▉        | 1094/5625 [00:57<03:53, 19.38it/s]
 19%|█▉        | 1096/5625 [00:57<03:52, 19.46it/s]
 20%|█▉        | 1099/5625 [00:57<03:46, 19.96it/s]
 20%|█▉        | 1101/5625 [00:57<03:48, 19.78it/s]
 20%|█▉        | 1104/5625 [00:57<03:50, 19.60it/s]
 20%|█▉        | 1107/5625 [00:57<03:51, 19.49it/s]
 20%|█▉        | 1110/5625 [00:57<03:47, 19.89it/s]
 20%|█▉        | 1113/5625 [00:57<03:42, 20.30it/s]
 20%|█▉        | 1116/5625 [00:58<03:48, 19.70it/s]
 20%|█▉        | 1119/5625 [00:58<03:43, 20.12it/s]
 20%|█▉        | 1122/5625 [00:58<03:54, 19.21it/s]
 20%|█▉        | 1124/5625 [00:58<03:54, 19.22it/s]
 20%|██        | 1126/5625 [00:58<03:53, 19.29it/s]
 20%|██        | 1128/5625 [00:58<03:57, 18.90it/s]
 20%|██        | 1130/5625 [00:58<03:58, 18.86it/s]
 20%|██        | 1133/5625 [00:58<03:47, 19.78it/s]
 20%|██        | 1135/5625 [00:59<03:50, 19.47it/s]
 20%|██        | 1137/5625 [00:59<03:56, 18.98it/s]
 20%|██        | 1139/5625 [00:59<04:00, 18.64it/s]
 20%|██        | 1141/5625 [00:59<03:57, 18.85it/s]
 20%|██        | 1143/5625 [00:59<04:01, 18.54it/s]
 20%|██        | 1146/5625 [00:59<03:48, 19.64it/s]
 20%|██        | 1148/5625 [00:59<03:51, 19.36it/s]
 20%|██        | 1150/5625 [00:59<03:51, 19.34it/s]
 20%|██        | 1153/5625 [01:00<03:42, 20.09it/s]
 21%|██        | 1155/5625 [01:00<03:44, 19.90it/s]
 21%|██        | 1157/5625 [01:00<03:53, 19.11it/s]
 21%|██        | 1159/5625 [01:00<03:59, 18.66it/s]
 21%|██        | 1162/5625 [01:00<03:47, 19.64it/s]
 21%|██        | 1164/5625 [01:00<03:53, 19.10it/s]
 21%|██        | 1166/5625 [01:00<03:55, 18.89it/s]
 21%|██        | 1169/5625 [01:00<03:46, 19.68it/s]
 21%|██        | 1171/5625 [01:00<03:49, 19.41it/s]
 21%|██        | 1173/5625 [01:01<03:52, 19.13it/s]
 21%|██        | 1176/5625 [01:01<03:42, 19.97it/s]
 21%|██        | 1178/5625 [01:01<03:42, 19.97it/s]
 21%|██        | 1180/5625 [01:01<03:44, 19.78it/s]
 21%|██        | 1182/5625 [01:01<03:47, 19.54it/s]
 21%|██        | 1185/5625 [01:01<03:43, 19.84it/s]
 21%|██        | 1188/5625 [01:01<03:44, 19.80it/s]
 21%|██        | 1190/5625 [01:01<03:44, 19.73it/s]
 21%|██        | 1192/5625 [01:02<03:45, 19.63it/s]
 21%|██        | 1194/5625 [01:02<03:49, 19.32it/s]
 21%|██▏       | 1196/5625 [01:02<03:52, 19.04it/s]
 21%|██▏       | 1199/5625 [01:02<03:38, 20.26it/s]
 21%|██▏       | 1202/5625 [01:02<03:31, 20.88it/s]
 21%|██▏       | 1205/5625 [01:02<03:34, 20.59it/s]
 21%|██▏       | 1208/5625 [01:02<03:39, 20.09it/s]
 22%|██▏       | 1211/5625 [01:02<03:39, 20.10it/s]
 22%|██▏       | 1214/5625 [01:03<03:38, 20.17it/s]
 22%|██▏       | 1217/5625 [01:03<03:39, 20.06it/s]
 22%|██▏       | 1220/5625 [01:03<03:34, 20.50it/s]
 22%|██▏       | 1223/5625 [01:03<03:42, 19.81it/s]
 22%|██▏       | 1225/5625 [01:03<03:44, 19.61it/s]
 22%|██▏       | 1227/5625 [01:03<03:51, 18.98it/s]
 22%|██▏       | 1229/5625 [01:03<03:57, 18.51it/s]
 22%|██▏       | 1231/5625 [01:04<03:56, 18.55it/s]
 22%|██▏       | 1233/5625 [01:04<03:57, 18.46it/s]
 22%|██▏       | 1236/5625 [01:04<03:46, 19.40it/s]
 22%|██▏       | 1238/5625 [01:04<03:51, 18.98it/s]
 22%|██▏       | 1241/5625 [01:04<03:43, 19.60it/s]
 22%|██▏       | 1243/5625 [01:04<03:43, 19.65it/s]
 22%|██▏       | 1245/5625 [01:04<03:45, 19.44it/s]
 22%|██▏       | 1248/5625 [01:04<03:42, 19.63it/s]
 22%|██▏       | 1250/5625 [01:04<03:46, 19.31it/s]
 22%|██▏       | 1253/5625 [01:05<03:38, 19.98it/s]
 22%|██▏       | 1256/5625 [01:05<03:34, 20.37it/s]
 22%|██▏       | 1259/5625 [01:05<03:34, 20.33it/s]
 22%|██▏       | 1262/5625 [01:05<03:32, 20.57it/s]
 22%|██▏       | 1265/5625 [01:05<03:36, 20.11it/s]
 23%|██▎       | 1268/5625 [01:05<03:40, 19.76it/s]
 23%|██▎       | 1270/5625 [01:05<03:42, 19.57it/s]
 23%|██▎       | 1272/5625 [01:06<03:41, 19.61it/s]
 23%|██▎       | 1274/5625 [01:06<03:43, 19.45it/s]
 23%|██▎       | 1276/5625 [01:06<03:51, 18.81it/s]
 23%|██▎       | 1278/5625 [01:06<03:56, 18.41it/s]
 23%|██▎       | 1280/5625 [01:06<03:54, 18.50it/s]
 23%|██▎       | 1283/5625 [01:06<03:46, 19.18it/s]
 23%|██▎       | 1286/5625 [01:06<03:38, 19.84it/s]
 23%|██▎       | 1289/5625 [01:06<03:37, 19.93it/s]
 23%|██▎       | 1291/5625 [01:07<03:45, 19.21it/s]
 23%|██▎       | 1293/5625 [01:07<03:48, 18.93it/s]
 23%|██▎       | 1295/5625 [01:07<03:47, 19.03it/s]
 23%|██▎       | 1297/5625 [01:07<03:45, 19.20it/s]
 23%|██▎       | 1299/5625 [01:07<03:44, 19.28it/s]
 23%|██▎       | 1301/5625 [01:07<03:51, 18.72it/s]
 23%|██▎       | 1303/5625 [01:07<03:56, 18.27it/s]
 23%|██▎       | 1305/5625 [01:07<03:56, 18.28it/s]
 23%|██▎       | 1307/5625 [01:07<03:54, 18.41it/s]
 23%|██▎       | 1309/5625 [01:08<03:52, 18.57it/s]
 23%|██▎       | 1312/5625 [01:08<03:41, 19.45it/s]
 23%|██▎       | 1314/5625 [01:08<03:41, 19.47it/s]
 23%|██▎       | 1317/5625 [01:08<03:37, 19.83it/s]
 23%|██▎       | 1319/5625 [01:08<03:40, 19.51it/s]
 23%|██▎       | 1321/5625 [01:08<03:40, 19.52it/s]
 24%|██▎       | 1323/5625 [01:08<03:40, 19.50it/s]
 24%|██▎       | 1325/5625 [01:08<03:43, 19.25it/s]
 24%|██▎       | 1328/5625 [01:09<03:39, 19.62it/s]
 24%|██▎       | 1331/5625 [01:09<03:35, 19.89it/s]
 24%|██▎       | 1333/5625 [01:09<03:40, 19.45it/s]
 24%|██▎       | 1335/5625 [01:09<03:42, 19.30it/s]
 24%|██▍       | 1337/5625 [01:09<03:40, 19.45it/s]
 24%|██▍       | 1339/5625 [01:09<03:38, 19.60it/s]
 24%|██▍       | 1341/5625 [01:09<03:40, 19.39it/s]
 24%|██▍       | 1343/5625 [01:09<03:43, 19.18it/s]
 24%|██▍       | 1346/5625 [01:09<03:39, 19.53it/s]
 24%|██▍       | 1348/5625 [01:10<03:38, 19.56it/s]
 24%|██▍       | 1351/5625 [01:10<03:38, 19.57it/s]
 24%|██▍       | 1354/5625 [01:10<03:31, 20.19it/s]
 24%|██▍       | 1357/5625 [01:10<03:29, 20.37it/s]
 24%|██▍       | 1360/5625 [01:10<03:35, 19.82it/s]
 24%|██▍       | 1362/5625 [01:10<03:34, 19.86it/s]
 24%|██▍       | 1365/5625 [01:10<03:36, 19.64it/s]
 24%|██▍       | 1367/5625 [01:10<03:37, 19.61it/s]
 24%|██▍       | 1369/5625 [01:11<03:40, 19.31it/s]
 24%|██▍       | 1371/5625 [01:11<03:43, 19.02it/s]
 24%|██▍       | 1373/5625 [01:11<03:45, 18.85it/s]
 24%|██▍       | 1375/5625 [01:11<03:42, 19.10it/s]
 24%|██▍       | 1377/5625 [01:11<03:40, 19.23it/s]
 25%|██▍       | 1379/5625 [01:11<03:44, 18.95it/s]
 25%|██▍       | 1381/5625 [01:11<03:43, 19.01it/s]
 25%|██▍       | 1384/5625 [01:11<03:42, 19.10it/s]
 25%|██▍       | 1386/5625 [01:11<03:39, 19.30it/s]
 25%|██▍       | 1389/5625 [01:12<03:32, 19.92it/s]
 25%|██▍       | 1391/5625 [01:12<03:36, 19.59it/s]
 25%|██▍       | 1393/5625 [01:12<03:35, 19.60it/s]
 25%|██▍       | 1396/5625 [01:12<03:34, 19.76it/s]
 25%|██▍       | 1399/5625 [01:12<03:35, 19.64it/s]
 25%|██▍       | 1402/5625 [01:12<03:28, 20.25it/s]
 25%|██▍       | 1405/5625 [01:12<03:29, 20.11it/s]
 25%|██▌       | 1408/5625 [01:13<03:37, 19.37it/s]
 25%|██▌       | 1410/5625 [01:13<03:36, 19.44it/s]
 25%|██▌       | 1413/5625 [01:13<03:25, 20.49it/s]
 25%|██▌       | 1416/5625 [01:13<03:27, 20.31it/s]
 25%|██▌       | 1419/5625 [01:13<03:35, 19.49it/s]
 25%|██▌       | 1421/5625 [01:13<03:34, 19.60it/s]
 25%|██▌       | 1423/5625 [01:13<03:35, 19.52it/s]
 25%|██▌       | 1426/5625 [01:14<03:33, 19.71it/s]
 25%|██▌       | 1428/5625 [01:14<03:34, 19.53it/s]
 25%|██▌       | 1430/5625 [01:14<03:33, 19.61it/s]
 25%|██▌       | 1432/5625 [01:14<03:33, 19.64it/s]
 25%|██▌       | 1434/5625 [01:14<03:36, 19.33it/s]
 26%|██▌       | 1436/5625 [01:14<03:37, 19.25it/s]
 26%|██▌       | 1438/5625 [01:14<03:43, 18.77it/s]
 26%|██▌       | 1440/5625 [01:14<03:47, 18.43it/s]
 26%|██▌       | 1442/5625 [01:14<03:45, 18.51it/s]
 26%|██▌       | 1444/5625 [01:14<03:44, 18.61it/s]
 26%|██▌       | 1446/5625 [01:15<03:42, 18.82it/s]
 26%|██▌       | 1449/5625 [01:15<03:24, 20.41it/s]
 26%|██▌       | 1452/5625 [01:15<03:24, 20.38it/s]
 26%|██▌       | 1455/5625 [01:15<03:33, 19.54it/s]
 26%|██▌       | 1457/5625 [01:15<03:33, 19.56it/s]
 26%|██▌       | 1459/5625 [01:15<03:32, 19.63it/s]
 26%|██▌       | 1461/5625 [01:15<03:34, 19.45it/s]
 26%|██▌       | 1464/5625 [01:15<03:29, 19.83it/s]
 26%|██▌       | 1466/5625 [01:16<03:31, 19.70it/s]
 26%|██▌       | 1468/5625 [01:16<03:32, 19.57it/s]
 26%|██▌       | 1470/5625 [01:16<03:33, 19.44it/s]
 26%|██▌       | 1472/5625 [01:16<03:32, 19.52it/s]
 26%|██▌       | 1474/5625 [01:16<03:33, 19.48it/s]
 26%|██▌       | 1476/5625 [01:16<03:37, 19.07it/s]
 26%|██▋       | 1479/5625 [01:16<03:26, 20.09it/s]
 26%|██▋       | 1481/5625 [01:16<03:31, 19.62it/s]
 26%|██▋       | 1484/5625 [01:16<03:27, 19.93it/s]
 26%|██▋       | 1487/5625 [01:17<03:20, 20.65it/s]
 26%|██▋       | 1490/5625 [01:17<03:28, 19.84it/s]
 27%|██▋       | 1492/5625 [01:17<03:34, 19.24it/s]
 27%|██▋       | 1494/5625 [01:17<03:33, 19.36it/s]
 27%|██▋       | 1496/5625 [01:17<03:35, 19.16it/s]
 27%|██▋       | 1498/5625 [01:17<03:39, 18.76it/s]
 27%|██▋       | 1500/5625 [01:17<03:36, 19.09it/s]
 27%|██▋       | 1502/5625 [01:17<03:33, 19.29it/s]
 27%|██▋       | 1504/5625 [01:18<03:37, 18.94it/s]
 27%|██▋       | 1506/5625 [01:18<03:38, 18.89it/s]
 27%|██▋       | 1508/5625 [01:18<03:40, 18.64it/s]
 27%|██▋       | 1511/5625 [01:18<03:36, 19.04it/s]
 27%|██▋       | 1513/5625 [01:18<03:40, 18.69it/s]
 27%|██▋       | 1515/5625 [01:18<03:40, 18.66it/s]
 27%|██▋       | 1517/5625 [01:18<03:42, 18.49it/s]
 27%|██▋       | 1520/5625 [01:18<03:32, 19.36it/s]
 27%|██▋       | 1523/5625 [01:19<03:30, 19.51it/s]
 27%|██▋       | 1526/5625 [01:19<03:28, 19.66it/s]
 27%|██▋       | 1529/5625 [01:19<03:23, 20.12it/s]
 27%|██▋       | 1532/5625 [01:19<03:27, 19.68it/s]
 27%|██▋       | 1535/5625 [01:19<03:28, 19.59it/s]
 27%|██▋       | 1538/5625 [01:19<03:26, 19.78it/s]
 27%|██▋       | 1540/5625 [01:19<03:27, 19.70it/s]
 27%|██▋       | 1542/5625 [01:19<03:30, 19.37it/s]
 27%|██▋       | 1544/5625 [01:20<03:33, 19.15it/s]
 27%|██▋       | 1546/5625 [01:20<03:31, 19.30it/s]
 28%|██▊       | 1549/5625 [01:20<03:30, 19.37it/s]
 28%|██▊       | 1551/5625 [01:20<03:30, 19.39it/s]
 28%|██▊       | 1554/5625 [01:20<03:25, 19.79it/s]
 28%|██▊       | 1556/5625 [01:20<03:32, 19.12it/s]
 28%|██▊       | 1558/5625 [01:20<03:34, 18.97it/s]
 28%|██▊       | 1560/5625 [01:20<03:33, 19.06it/s]
 28%|██▊       | 1562/5625 [01:21<03:33, 19.02it/s]
 28%|██▊       | 1564/5625 [01:21<03:30, 19.27it/s]
 28%|██▊       | 1566/5625 [01:21<03:34, 18.89it/s]
 28%|██▊       | 1569/5625 [01:21<03:27, 19.53it/s]
 28%|██▊       | 1571/5625 [01:21<03:30, 19.29it/s]
 28%|██▊       | 1573/5625 [01:21<03:28, 19.47it/s]
 28%|██▊       | 1575/5625 [01:21<03:30, 19.26it/s]
 28%|██▊       | 1578/5625 [01:21<03:27, 19.50it/s]
 28%|██▊       | 1581/5625 [01:21<03:19, 20.25it/s]
 28%|██▊       | 1584/5625 [01:22<03:24, 19.76it/s]
 28%|██▊       | 1587/5625 [01:22<03:23, 19.85it/s]
 28%|██▊       | 1589/5625 [01:22<03:25, 19.62it/s]
 28%|██▊       | 1592/5625 [01:22<03:22, 19.93it/s]
 28%|██▊       | 1594/5625 [01:22<03:27, 19.44it/s]
 28%|██▊       | 1596/5625 [01:22<03:29, 19.20it/s]
 28%|██▊       | 1598/5625 [01:22<03:30, 19.14it/s]
 28%|██▊       | 1600/5625 [01:22<03:30, 19.13it/s]
 28%|██▊       | 1602/5625 [01:23<03:34, 18.76it/s]
 29%|██▊       | 1604/5625 [01:23<03:30, 19.07it/s]
 29%|██▊       | 1606/5625 [01:23<03:28, 19.24it/s]
 29%|██▊       | 1608/5625 [01:23<03:27, 19.39it/s]
 29%|██▊       | 1610/5625 [01:23<03:30, 19.07it/s]
 29%|██▊       | 1613/5625 [01:23<03:28, 19.20it/s]
 29%|██▊       | 1616/5625 [01:23<03:22, 19.81it/s]
 29%|██▉       | 1619/5625 [01:23<03:18, 20.16it/s]
 29%|██▉       | 1622/5625 [01:24<03:18, 20.12it/s]
 29%|██▉       | 1625/5625 [01:24<03:23, 19.64it/s]
 29%|██▉       | 1628/5625 [01:24<03:21, 19.88it/s]
 29%|██▉       | 1630/5625 [01:24<03:22, 19.75it/s]
 29%|██▉       | 1633/5625 [01:24<03:16, 20.28it/s]
 29%|██▉       | 1636/5625 [01:24<03:18, 20.09it/s]
 29%|██▉       | 1639/5625 [01:24<03:20, 19.92it/s]
 29%|██▉       | 1641/5625 [01:25<03:21, 19.78it/s]
 29%|██▉       | 1643/5625 [01:25<03:26, 19.25it/s]
 29%|██▉       | 1645/5625 [01:25<03:32, 18.74it/s]
 29%|██▉       | 1648/5625 [01:25<03:24, 19.43it/s]
 29%|██▉       | 1650/5625 [01:25<03:28, 19.02it/s]
 29%|██▉       | 1652/5625 [01:25<03:31, 18.76it/s]
 29%|██▉       | 1654/5625 [01:25<03:33, 18.59it/s]
 29%|██▉       | 1656/5625 [01:25<03:35, 18.38it/s]
 29%|██▉       | 1658/5625 [01:25<03:32, 18.70it/s]
 30%|██▉       | 1660/5625 [01:26<03:32, 18.62it/s]
 30%|██▉       | 1662/5625 [01:26<03:34, 18.47it/s]
 30%|██▉       | 1665/5625 [01:26<03:31, 18.76it/s]
 30%|██▉       | 1667/5625 [01:26<03:31, 18.69it/s]
 30%|██▉       | 1669/5625 [01:26<03:31, 18.74it/s]
 30%|██▉       | 1672/5625 [01:26<03:21, 19.57it/s]
 30%|██▉       | 1674/5625 [01:26<03:25, 19.20it/s]
 30%|██▉       | 1677/5625 [01:26<03:17, 20.04it/s]
 30%|██▉       | 1679/5625 [01:27<03:24, 19.30it/s]
 30%|██▉       | 1681/5625 [01:27<03:23, 19.38it/s]
 30%|██▉       | 1683/5625 [01:27<03:30, 18.74it/s]
 30%|██▉       | 1685/5625 [01:27<03:34, 18.38it/s]
 30%|██▉       | 1687/5625 [01:27<03:32, 18.55it/s]
 30%|███       | 1689/5625 [01:27<03:30, 18.68it/s]
 30%|███       | 1691/5625 [01:27<03:27, 18.96it/s]
 30%|███       | 1694/5625 [01:27<03:18, 19.82it/s]
 30%|███       | 1697/5625 [01:28<03:20, 19.60it/s]
 30%|███       | 1699/5625 [01:28<03:21, 19.47it/s]
 30%|███       | 1701/5625 [01:28<03:27, 18.93it/s]
 30%|███       | 1703/5625 [01:28<03:27, 18.94it/s]
 30%|███       | 1706/5625 [01:28<03:25, 19.04it/s]
 30%|███       | 1708/5625 [01:28<03:26, 18.93it/s]
 30%|███       | 1711/5625 [01:28<03:24, 19.14it/s]
 30%|███       | 1713/5625 [01:28<03:28, 18.73it/s]
 30%|███       | 1715/5625 [01:28<03:31, 18.45it/s]
 31%|███       | 1718/5625 [01:29<03:19, 19.57it/s]
 31%|███       | 1720/5625 [01:29<03:25, 19.00it/s]
 31%|███       | 1722/5625 [01:29<03:25, 18.98it/s]
 31%|███       | 1724/5625 [01:29<03:24, 19.03it/s]
 31%|███       | 1727/5625 [01:29<03:21, 19.39it/s]
 31%|███       | 1729/5625 [01:29<03:20, 19.46it/s]
 31%|███       | 1732/5625 [01:29<03:13, 20.14it/s]
 31%|███       | 1735/5625 [01:29<03:11, 20.28it/s]
 31%|███       | 1738/5625 [01:30<03:16, 19.82it/s]
 31%|███       | 1740/5625 [01:30<03:23, 19.13it/s]
 31%|███       | 1742/5625 [01:30<03:23, 19.10it/s]
 31%|███       | 1745/5625 [01:30<03:20, 19.34it/s]
 31%|███       | 1748/5625 [01:30<03:11, 20.28it/s]
 31%|███       | 1751/5625 [01:30<03:15, 19.78it/s]
 31%|███       | 1753/5625 [01:30<03:18, 19.54it/s]
 31%|███       | 1755/5625 [01:31<03:18, 19.52it/s]
 31%|███       | 1757/5625 [01:31<03:20, 19.33it/s]
 31%|███▏      | 1759/5625 [01:31<03:22, 19.08it/s]
 31%|███▏      | 1761/5625 [01:31<03:23, 19.00it/s]
 31%|███▏      | 1763/5625 [01:31<03:24, 18.91it/s]
 31%|███▏      | 1765/5625 [01:31<03:27, 18.57it/s]
 31%|███▏      | 1767/5625 [01:31<03:26, 18.69it/s]
 31%|███▏      | 1769/5625 [01:31<03:29, 18.43it/s]
 31%|███▏      | 1771/5625 [01:31<03:27, 18.61it/s]
 32%|███▏      | 1774/5625 [01:32<03:18, 19.36it/s]
 32%|███▏      | 1776/5625 [01:32<03:24, 18.78it/s]
 32%|███▏      | 1778/5625 [01:32<03:22, 19.00it/s]
 32%|███▏      | 1780/5625 [01:32<03:19, 19.23it/s]
 32%|███▏      | 1782/5625 [01:32<03:18, 19.37it/s]
 32%|███▏      | 1784/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1786/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1788/5625 [01:32<03:24, 18.78it/s]
 32%|███▏      | 1791/5625 [01:32<03:16, 19.50it/s]
 32%|███▏      | 1794/5625 [01:33<03:14, 19.66it/s]
 32%|███▏      | 1797/5625 [01:33<03:07, 20.42it/s]
 32%|███▏      | 1800/5625 [01:33<03:08, 20.28it/s]
 32%|███▏      | 1803/5625 [01:33<03:07, 20.41it/s]
 32%|███▏      | 1806/5625 [01:33<03:08, 20.25it/s]
 32%|███▏      | 1809/5625 [01:33<03:05, 20.53it/s]
 32%|███▏      | 1812/5625 [01:33<03:06, 20.46it/s]
 32%|███▏      | 1815/5625 [01:34<03:10, 20.00it/s]
 32%|███▏      | 1818/5625 [01:34<03:15, 19.49it/s]
 32%|███▏      | 1820/5625 [01:34<03:14, 19.57it/s]
 32%|███▏      | 1822/5625 [01:34<03:16, 19.36it/s]
 32%|███▏      | 1824/5625 [01:34<03:19, 19.01it/s]
 32%|███▏      | 1827/5625 [01:34<03:15, 19.44it/s]
 33%|███▎      | 1829/5625 [01:34<03:21, 18.88it/s]
 33%|███▎      | 1831/5625 [01:34<03:25, 18.43it/s]
 33%|███▎      | 1834/5625 [01:35<03:21, 18.78it/s]
 33%|███▎      | 1836/5625 [01:35<03:25, 18.41it/s]
 33%|███▎      | 1838/5625 [01:35<03:23, 18.59it/s]
 33%|███▎      | 1841/5625 [01:35<03:20, 18.84it/s]
 33%|███▎      | 1844/5625 [01:35<03:12, 19.65it/s]
 33%|███▎      | 1846/5625 [01:35<03:19, 18.98it/s]
 33%|███▎      | 1848/5625 [01:35<03:20, 18.83it/s]
 33%|███▎      | 1851/5625 [01:35<03:11, 19.69it/s]
 33%|███▎      | 1854/5625 [01:36<03:07, 20.15it/s]
 33%|███▎      | 1857/5625 [01:36<03:07, 20.07it/s]
 33%|███▎      | 1859/5625 [01:36<03:12, 19.56it/s]
 33%|███▎      | 1861/5625 [01:36<03:17, 19.09it/s]
 33%|███▎      | 1863/5625 [01:36<03:16, 19.17it/s]
 33%|███▎      | 1865/5625 [01:36<03:19, 18.81it/s]
 33%|███▎      | 1867/5625 [01:36<03:18, 18.97it/s]
 33%|███▎      | 1869/5625 [01:36<03:21, 18.65it/s]
 33%|███▎      | 1871/5625 [01:37<03:17, 18.98it/s]
 33%|███▎      | 1873/5625 [01:37<03:16, 19.10it/s]
                                                   

 33%|███▎      | 1875/5625 [01:37<03:16, 19.10it/s]{'loss': 0.7819, 'learning_rate': 3.3513712538395083e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.64it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.41it/s]

 21%|██        | 66/313 [00:00<00:01, 205.91it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.12it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.45it/s]

 40%|████      | 126/313 [00:00<00:01, 185.27it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.00it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.02it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.18it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.50it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.79it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.46it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.91it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.55it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.57it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.57it/s]
 33%|███▎      | 1875/5625 [01:38<03:16, 19.10it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 1876/5625 [01:39<24:41,  2.53it/s]
 33%|███▎      | 1878/5625 [01:40<18:56,  3.30it/s]
 33%|███▎      | 1880/5625 [01:40<14:39,  4.26it/s]
 33%|███▎      | 1882/5625 [01:40<11:28,  5.43it/s]
 34%|███▎      | 1885/5625 [01:40<08:22,  7.45it/s]
 34%|███▎      | 1887/5625 [01:40<07:02,  8.85it/s]
 34%|███▎      | 1889/5625 [01:40<06:03, 10.28it/s]
 34%|███▎      | 1891/5625 [01:40<05:17, 11.77it/s]
 34%|███▎      | 1894/5625 [01:40<04:30, 13.80it/s]
 34%|███▎      | 1896/5625 [01:41<04:13, 14.73it/s]
 34%|███▍      | 1899/5625 [01:41<03:45, 16.52it/s]
 34%|███▍      | 1902/5625 [01:41<03:30, 17.71it/s]
 34%|███▍      | 1904/5625 [01:41<03:29, 17.76it/s]
 34%|███▍      | 1906/5625 [01:41<03:24, 18.17it/s]
 34%|███▍      | 1908/5625 [01:41<03:26, 17.99it/s]
 34%|███▍      | 1910/5625 [01:41<03:27, 17.86it/s]
 34%|███▍      | 1912/5625 [01:41<03:22, 18.36it/s]
 34%|███▍      | 1915/5625 [01:42<03:16, 18.85it/s]
 34%|███▍      | 1918/5625 [01:42<03:06, 19.89it/s]
 34%|███▍      | 1920/5625 [01:42<03:12, 19.23it/s]
 34%|███▍      | 1922/5625 [01:42<03:15, 18.94it/s]
 34%|███▍      | 1925/5625 [01:42<03:12, 19.24it/s]
 34%|███▍      | 1927/5625 [01:42<03:14, 19.03it/s]
 34%|███▍      | 1930/5625 [01:42<03:09, 19.51it/s]
 34%|███▍      | 1932/5625 [01:42<03:08, 19.55it/s]
 34%|███▍      | 1934/5625 [01:42<03:10, 19.40it/s]
 34%|███▍      | 1937/5625 [01:43<03:05, 19.90it/s]
 34%|███▍      | 1939/5625 [01:43<03:10, 19.33it/s]
 35%|███▍      | 1941/5625 [01:43<03:09, 19.43it/s]
 35%|███▍      | 1943/5625 [01:43<03:13, 19.08it/s]
 35%|███▍      | 1945/5625 [01:43<03:16, 18.74it/s]
 35%|███▍      | 1947/5625 [01:43<03:13, 19.01it/s]
 35%|███▍      | 1949/5625 [01:43<03:14, 18.87it/s]
 35%|███▍      | 1951/5625 [01:43<03:14, 18.86it/s]
 35%|███▍      | 1953/5625 [01:43<03:19, 18.43it/s]
 35%|███▍      | 1955/5625 [01:44<03:17, 18.57it/s]
 35%|███▍      | 1958/5625 [01:44<03:11, 19.13it/s]
 35%|███▍      | 1960/5625 [01:44<03:17, 18.58it/s]
 35%|███▍      | 1963/5625 [01:44<03:12, 18.99it/s]
 35%|███▍      | 1965/5625 [01:44<03:14, 18.86it/s]
 35%|███▍      | 1968/5625 [01:44<03:09, 19.32it/s]
 35%|███▌      | 1970/5625 [01:44<03:10, 19.14it/s]
 35%|███▌      | 1972/5625 [01:44<03:11, 19.10it/s]
 35%|███▌      | 1975/5625 [01:45<03:02, 20.01it/s]
 35%|███▌      | 1977/5625 [01:45<03:03, 19.93it/s]
 35%|███▌      | 1980/5625 [01:45<02:57, 20.48it/s]
 35%|███▌      | 1983/5625 [01:45<03:05, 19.62it/s]
 35%|███▌      | 1986/5625 [01:45<03:04, 19.72it/s]
 35%|███▌      | 1988/5625 [01:45<03:06, 19.54it/s]
 35%|███▌      | 1990/5625 [01:45<03:11, 18.98it/s]
 35%|███▌      | 1992/5625 [01:46<03:11, 18.96it/s]
 35%|███▌      | 1994/5625 [01:46<03:13, 18.73it/s]
 35%|███▌      | 1996/5625 [01:46<03:12, 18.89it/s]
 36%|███▌      | 1999/5625 [01:46<03:04, 19.64it/s]
 36%|███▌      | 2001/5625 [01:46<03:05, 19.55it/s]
 36%|███▌      | 2004/5625 [01:46<03:00, 20.05it/s]
 36%|███▌      | 2006/5625 [01:46<03:00, 20.02it/s]
 36%|███▌      | 2008/5625 [01:46<03:06, 19.41it/s]
 36%|███▌      | 2010/5625 [01:46<03:08, 19.13it/s]
 36%|███▌      | 2012/5625 [01:47<03:08, 19.21it/s]
 36%|███▌      | 2015/5625 [01:47<03:00, 19.97it/s]
 36%|███▌      | 2017/5625 [01:47<03:01, 19.89it/s]
 36%|███▌      | 2019/5625 [01:47<03:04, 19.59it/s]
 36%|███▌      | 2021/5625 [01:47<03:07, 19.19it/s]
 36%|███▌      | 2023/5625 [01:47<03:06, 19.34it/s]
 36%|███▌      | 2025/5625 [01:47<03:04, 19.47it/s]
 36%|███▌      | 2027/5625 [01:47<03:08, 19.04it/s]
 36%|███▌      | 2029/5625 [01:47<03:10, 18.92it/s]
 36%|███▌      | 2031/5625 [01:48<03:12, 18.67it/s]
 36%|███▌      | 2033/5625 [01:48<03:11, 18.76it/s]
 36%|███▌      | 2036/5625 [01:48<03:01, 19.81it/s]
 36%|███▌      | 2038/5625 [01:48<03:04, 19.49it/s]
 36%|███▋      | 2041/5625 [01:48<03:05, 19.36it/s]
 36%|███▋      | 2043/5625 [01:48<03:08, 18.99it/s]
 36%|███▋      | 2045/5625 [01:48<03:09, 18.87it/s]
 36%|███▋      | 2047/5625 [01:48<03:15, 18.34it/s]
 36%|███▋      | 2049/5625 [01:48<03:13, 18.52it/s]
 36%|███▋      | 2051/5625 [01:49<03:09, 18.84it/s]
 37%|███▋      | 2054/5625 [01:49<03:06, 19.12it/s]
 37%|███▋      | 2057/5625 [01:49<03:02, 19.59it/s]
 37%|███▋      | 2059/5625 [01:49<03:02, 19.54it/s]
 37%|███▋      | 2061/5625 [01:49<03:04, 19.29it/s]
 37%|███▋      | 2064/5625 [01:49<03:04, 19.35it/s]
 37%|███▋      | 2067/5625 [01:49<02:56, 20.20it/s]
 37%|███▋      | 2070/5625 [01:50<03:03, 19.41it/s]
 37%|███▋      | 2072/5625 [01:50<03:03, 19.37it/s]
 37%|███▋      | 2074/5625 [01:50<03:07, 18.94it/s]
 37%|███▋      | 2077/5625 [01:50<03:00, 19.69it/s]
 37%|███▋      | 2080/5625 [01:50<02:58, 19.81it/s]
 37%|███▋      | 2082/5625 [01:50<03:02, 19.37it/s]
 37%|███▋      | 2084/5625 [01:50<03:04, 19.22it/s]
 37%|███▋      | 2086/5625 [01:50<03:06, 18.93it/s]
 37%|███▋      | 2088/5625 [01:50<03:10, 18.57it/s]
 37%|███▋      | 2090/5625 [01:51<03:13, 18.26it/s]
 37%|███▋      | 2092/5625 [01:51<03:10, 18.52it/s]
 37%|███▋      | 2095/5625 [01:51<03:04, 19.10it/s]
 37%|███▋      | 2097/5625 [01:51<03:02, 19.29it/s]
 37%|███▋      | 2100/5625 [01:51<02:57, 19.86it/s]
 37%|███▋      | 2102/5625 [01:51<02:59, 19.57it/s]
 37%|███▋      | 2104/5625 [01:51<03:02, 19.26it/s]
 37%|███▋      | 2107/5625 [01:51<02:56, 19.91it/s]
 38%|███▊      | 2110/5625 [01:52<02:57, 19.76it/s]
 38%|███▊      | 2112/5625 [01:52<03:01, 19.31it/s]
 38%|███▊      | 2115/5625 [01:52<02:55, 19.95it/s]
 38%|███▊      | 2118/5625 [01:52<02:58, 19.69it/s]
 38%|███▊      | 2120/5625 [01:52<03:03, 19.14it/s]
 38%|███▊      | 2122/5625 [01:52<03:05, 18.92it/s]
 38%|███▊      | 2124/5625 [01:52<03:07, 18.69it/s]
 38%|███▊      | 2126/5625 [01:52<03:10, 18.40it/s]
 38%|███▊      | 2128/5625 [01:53<03:09, 18.47it/s]
 38%|███▊      | 2130/5625 [01:53<03:08, 18.52it/s]
 38%|███▊      | 2132/5625 [01:53<03:07, 18.67it/s]
 38%|███▊      | 2134/5625 [01:53<03:06, 18.67it/s]
 38%|███▊      | 2136/5625 [01:53<03:19, 17.48it/s]
 38%|███▊      | 2138/5625 [01:53<03:20, 17.40it/s]
 38%|███▊      | 2140/5625 [01:53<03:14, 17.96it/s]
 38%|███▊      | 2142/5625 [01:53<03:08, 18.49it/s]
 38%|███▊      | 2145/5625 [01:53<03:04, 18.87it/s]
 38%|███▊      | 2147/5625 [01:54<03:08, 18.43it/s]
 38%|███▊      | 2149/5625 [01:54<03:11, 18.17it/s]
 38%|███▊      | 2151/5625 [01:54<03:06, 18.65it/s]
 38%|███▊      | 2154/5625 [01:54<03:01, 19.08it/s]
 38%|███▊      | 2156/5625 [01:54<03:04, 18.80it/s]
 38%|███▊      | 2159/5625 [01:54<02:57, 19.56it/s]
 38%|███▊      | 2161/5625 [01:54<02:56, 19.63it/s]
 38%|███▊      | 2164/5625 [01:54<02:52, 20.01it/s]
 39%|███▊      | 2167/5625 [01:55<02:49, 20.41it/s]
 39%|███▊      | 2170/5625 [01:55<02:52, 20.08it/s]
 39%|███▊      | 2173/5625 [01:55<02:51, 20.12it/s]
 39%|███▊      | 2176/5625 [01:55<02:56, 19.57it/s]
 39%|███▊      | 2178/5625 [01:55<02:58, 19.28it/s]
 39%|███▉      | 2180/5625 [01:55<02:57, 19.44it/s]
 39%|███▉      | 2182/5625 [01:55<03:02, 18.85it/s]
 39%|███▉      | 2185/5625 [01:56<02:54, 19.66it/s]
 39%|███▉      | 2187/5625 [01:56<02:55, 19.64it/s]
 39%|███▉      | 2190/5625 [01:56<02:52, 19.89it/s]
 39%|███▉      | 2192/5625 [01:56<02:52, 19.87it/s]
 39%|███▉      | 2195/5625 [01:56<02:46, 20.56it/s]
 39%|███▉      | 2198/5625 [01:56<02:50, 20.15it/s]
 39%|███▉      | 2201/5625 [01:56<02:53, 19.69it/s]
 39%|███▉      | 2203/5625 [01:56<02:57, 19.26it/s]
 39%|███▉      | 2205/5625 [01:57<02:56, 19.37it/s]
 39%|███▉      | 2207/5625 [01:57<02:55, 19.48it/s]
 39%|███▉      | 2210/5625 [01:57<02:53, 19.65it/s]
 39%|███▉      | 2212/5625 [01:57<02:57, 19.23it/s]
 39%|███▉      | 2215/5625 [01:57<02:52, 19.72it/s]
 39%|███▉      | 2217/5625 [01:57<02:58, 19.12it/s]
 39%|███▉      | 2219/5625 [01:57<02:57, 19.23it/s]
 39%|███▉      | 2221/5625 [01:57<02:58, 19.12it/s]
 40%|███▉      | 2223/5625 [01:58<03:02, 18.63it/s]
 40%|███▉      | 2225/5625 [01:58<03:00, 18.83it/s]
 40%|███▉      | 2227/5625 [01:58<03:03, 18.56it/s]
 40%|███▉      | 2229/5625 [01:58<03:00, 18.80it/s]
 40%|███▉      | 2231/5625 [01:58<03:01, 18.73it/s]
 40%|███▉      | 2233/5625 [01:58<03:17, 17.15it/s]
 40%|███▉      | 2235/5625 [01:58<03:14, 17.39it/s]
 40%|███▉      | 2237/5625 [01:58<03:07, 18.04it/s]
 40%|███▉      | 2239/5625 [01:58<03:09, 17.84it/s]
 40%|███▉      | 2241/5625 [01:59<03:09, 17.85it/s]
 40%|███▉      | 2243/5625 [01:59<03:04, 18.32it/s]
 40%|███▉      | 2245/5625 [01:59<03:03, 18.39it/s]
 40%|███▉      | 2247/5625 [01:59<03:02, 18.47it/s]
 40%|███▉      | 2249/5625 [01:59<02:59, 18.76it/s]
 40%|████      | 2252/5625 [01:59<02:54, 19.33it/s]
 40%|████      | 2254/5625 [01:59<02:58, 18.92it/s]
 40%|████      | 2256/5625 [01:59<03:00, 18.66it/s]
 40%|████      | 2258/5625 [01:59<03:00, 18.64it/s]
 40%|████      | 2260/5625 [02:00<02:58, 18.82it/s]
 40%|████      | 2263/5625 [02:00<02:50, 19.72it/s]
 40%|████      | 2265/5625 [02:00<02:50, 19.67it/s]
 40%|████      | 2267/5625 [02:00<02:50, 19.66it/s]
 40%|████      | 2269/5625 [02:00<02:53, 19.36it/s]
 40%|████      | 2271/5625 [02:00<02:54, 19.23it/s]
 40%|████      | 2274/5625 [02:00<02:50, 19.66it/s]
 40%|████      | 2277/5625 [02:00<02:49, 19.71it/s]
 41%|████      | 2279/5625 [02:00<02:53, 19.28it/s]
 41%|████      | 2281/5625 [02:01<02:53, 19.31it/s]
 41%|████      | 2283/5625 [02:01<02:52, 19.37it/s]
 41%|████      | 2285/5625 [02:01<02:52, 19.33it/s]
 41%|████      | 2287/5625 [02:01<02:54, 19.16it/s]
 41%|████      | 2289/5625 [02:01<02:58, 18.73it/s]
 41%|████      | 2292/5625 [02:01<02:52, 19.35it/s]
 41%|████      | 2294/5625 [02:01<02:56, 18.89it/s]
 41%|████      | 2296/5625 [02:01<02:56, 18.82it/s]
 41%|████      | 2298/5625 [02:01<02:58, 18.59it/s]
 41%|████      | 2300/5625 [02:02<02:55, 18.91it/s]
 41%|████      | 2302/5625 [02:02<02:58, 18.66it/s]
 41%|████      | 2305/5625 [02:02<02:48, 19.70it/s]
 41%|████      | 2308/5625 [02:02<02:46, 19.90it/s]
 41%|████      | 2310/5625 [02:02<02:47, 19.84it/s]
 41%|████      | 2312/5625 [02:02<02:51, 19.28it/s]
 41%|████      | 2314/5625 [02:02<02:54, 19.00it/s]
 41%|████      | 2317/5625 [02:02<02:45, 19.99it/s]
 41%|████      | 2320/5625 [02:03<02:39, 20.70it/s]
 41%|████▏     | 2323/5625 [02:03<02:45, 19.97it/s]
 41%|████▏     | 2325/5625 [02:03<02:50, 19.36it/s]
 41%|████▏     | 2327/5625 [02:03<02:51, 19.26it/s]
 41%|████▏     | 2329/5625 [02:03<03:52, 14.21it/s]
 41%|████▏     | 2331/5625 [02:03<03:36, 15.22it/s]
 41%|████▏     | 2333/5625 [02:03<03:26, 15.94it/s]
 42%|████▏     | 2335/5625 [02:04<03:15, 16.80it/s]
 42%|████▏     | 2337/5625 [02:04<03:12, 17.07it/s]
 42%|████▏     | 2339/5625 [02:04<03:04, 17.78it/s]
 42%|████▏     | 2341/5625 [02:04<03:06, 17.64it/s]
 42%|████▏     | 2343/5625 [02:04<03:02, 17.94it/s]
 42%|████▏     | 2345/5625 [02:04<03:01, 18.02it/s]
 42%|████▏     | 2347/5625 [02:04<02:57, 18.48it/s]
 42%|████▏     | 2349/5625 [02:04<02:55, 18.68it/s]
 42%|████▏     | 2351/5625 [02:04<02:53, 18.85it/s]
 42%|████▏     | 2353/5625 [02:04<02:54, 18.75it/s]
 42%|████▏     | 2355/5625 [02:05<02:51, 19.08it/s]
 42%|████▏     | 2358/5625 [02:05<02:50, 19.11it/s]
 42%|████▏     | 2361/5625 [02:05<02:48, 19.41it/s]
 42%|████▏     | 2363/5625 [02:05<02:48, 19.37it/s]
 42%|████▏     | 2365/5625 [02:05<02:47, 19.45it/s]
 42%|████▏     | 2367/5625 [02:05<02:48, 19.28it/s]
 42%|████▏     | 2369/5625 [02:05<02:48, 19.34it/s]
 42%|████▏     | 2371/5625 [02:05<02:48, 19.36it/s]
 42%|████▏     | 2374/5625 [02:06<02:44, 19.75it/s]
 42%|████▏     | 2376/5625 [02:06<02:44, 19.70it/s]
 42%|████▏     | 2378/5625 [02:06<02:48, 19.26it/s]
 42%|████▏     | 2380/5625 [02:06<02:53, 18.70it/s]
 42%|████▏     | 2382/5625 [02:06<02:54, 18.55it/s]
 42%|████▏     | 2385/5625 [02:06<02:43, 19.87it/s]
 42%|████▏     | 2387/5625 [02:06<02:42, 19.89it/s]
 42%|████▏     | 2389/5625 [02:06<02:43, 19.81it/s]
 43%|████▎     | 2391/5625 [02:06<02:43, 19.83it/s]
 43%|████▎     | 2393/5625 [02:07<02:46, 19.45it/s]
 43%|████▎     | 2395/5625 [02:07<02:47, 19.34it/s]
 43%|████▎     | 2398/5625 [02:07<02:38, 20.41it/s]
 43%|████▎     | 2401/5625 [02:07<02:42, 19.80it/s]
 43%|████▎     | 2403/5625 [02:07<02:44, 19.55it/s]
 43%|████▎     | 2405/5625 [02:07<02:44, 19.62it/s]
 43%|████▎     | 2407/5625 [02:07<02:44, 19.62it/s]
 43%|████▎     | 2410/5625 [02:07<02:43, 19.72it/s]
 43%|████▎     | 2413/5625 [02:08<02:41, 19.89it/s]
 43%|████▎     | 2415/5625 [02:08<02:47, 19.22it/s]
 43%|████▎     | 2418/5625 [02:08<02:40, 19.93it/s]
 43%|████▎     | 2420/5625 [02:08<02:44, 19.46it/s]
 43%|████▎     | 2422/5625 [02:08<02:44, 19.42it/s]
 43%|████▎     | 2425/5625 [02:08<02:43, 19.58it/s]
 43%|████▎     | 2427/5625 [02:08<02:44, 19.49it/s]
 43%|████▎     | 2429/5625 [02:08<02:43, 19.53it/s]
 43%|████▎     | 2432/5625 [02:09<02:35, 20.48it/s]
 43%|████▎     | 2435/5625 [02:09<02:31, 21.01it/s]
 43%|████▎     | 2438/5625 [02:09<02:33, 20.80it/s]
 43%|████▎     | 2441/5625 [02:09<02:36, 20.41it/s]
 43%|████▎     | 2444/5625 [02:09<02:37, 20.19it/s]
 44%|████▎     | 2447/5625 [02:09<02:42, 19.52it/s]
 44%|████▎     | 2450/5625 [02:09<02:38, 20.00it/s]
 44%|████▎     | 2453/5625 [02:10<02:38, 20.07it/s]
 44%|████▎     | 2456/5625 [02:10<02:36, 20.26it/s]
 44%|████▎     | 2459/5625 [02:10<02:38, 19.93it/s]
 44%|████▍     | 2461/5625 [02:10<02:41, 19.64it/s]
 44%|████▍     | 2464/5625 [02:10<02:40, 19.72it/s]
 44%|████▍     | 2467/5625 [02:10<02:41, 19.53it/s]
 44%|████▍     | 2469/5625 [02:10<02:40, 19.61it/s]
 44%|████▍     | 2471/5625 [02:10<02:41, 19.48it/s]
 44%|████▍     | 2474/5625 [02:11<02:39, 19.77it/s]
 44%|████▍     | 2476/5625 [02:11<02:39, 19.75it/s]
 44%|████▍     | 2478/5625 [02:11<02:44, 19.08it/s]
 44%|████▍     | 2480/5625 [02:11<02:43, 19.27it/s]
 44%|████▍     | 2483/5625 [02:11<02:35, 20.19it/s]
 44%|████▍     | 2486/5625 [02:11<02:36, 20.00it/s]
 44%|████▍     | 2488/5625 [02:11<02:42, 19.34it/s]
 44%|████▍     | 2490/5625 [02:11<02:43, 19.15it/s]
 44%|████▍     | 2492/5625 [02:12<02:47, 18.72it/s]
 44%|████▍     | 2495/5625 [02:12<02:43, 19.10it/s]
 44%|████▍     | 2497/5625 [02:12<02:46, 18.75it/s]
 44%|████▍     | 2499/5625 [02:12<02:46, 18.75it/s]
 44%|████▍     | 2502/5625 [02:12<02:38, 19.66it/s]
 45%|████▍     | 2504/5625 [02:12<02:38, 19.66it/s]
 45%|████▍     | 2507/5625 [02:12<02:31, 20.61it/s]
 45%|████▍     | 2510/5625 [02:12<02:36, 19.86it/s]
 45%|████▍     | 2513/5625 [02:13<02:31, 20.50it/s]
 45%|████▍     | 2516/5625 [02:13<02:30, 20.62it/s]
 45%|████▍     | 2519/5625 [02:13<02:30, 20.65it/s]
 45%|████▍     | 2522/5625 [02:13<02:36, 19.82it/s]
 45%|████▍     | 2525/5625 [02:13<02:33, 20.24it/s]
 45%|████▍     | 2528/5625 [02:13<03:13, 16.01it/s]
 45%|████▍     | 2530/5625 [02:14<03:06, 16.61it/s]
 45%|████▌     | 2532/5625 [02:14<03:02, 16.92it/s]
 45%|████▌     | 2534/5625 [02:14<03:00, 17.11it/s]
 45%|████▌     | 2536/5625 [02:14<02:56, 17.48it/s]
 45%|████▌     | 2538/5625 [02:14<02:55, 17.57it/s]
 45%|████▌     | 2540/5625 [02:14<02:55, 17.54it/s]
 45%|████▌     | 2542/5625 [02:14<02:51, 17.99it/s]
 45%|████▌     | 2545/5625 [02:14<02:42, 18.96it/s]
 45%|████▌     | 2547/5625 [02:14<02:44, 18.66it/s]
 45%|████▌     | 2549/5625 [02:15<02:44, 18.71it/s]
 45%|████▌     | 2551/5625 [02:15<02:42, 18.89it/s]
 45%|████▌     | 2553/5625 [02:15<02:40, 19.19it/s]
 45%|████▌     | 2555/5625 [02:15<02:41, 19.00it/s]
 45%|████▌     | 2557/5625 [02:15<02:39, 19.21it/s]
 45%|████▌     | 2559/5625 [02:15<02:41, 19.02it/s]
 46%|████▌     | 2561/5625 [02:15<02:40, 19.11it/s]
 46%|████▌     | 2563/5625 [02:15<02:39, 19.19it/s]
 46%|████▌     | 2565/5625 [02:15<02:43, 18.68it/s]
 46%|████▌     | 2568/5625 [02:16<02:39, 19.13it/s]
 46%|████▌     | 2571/5625 [02:16<02:33, 19.87it/s]
 46%|████▌     | 2574/5625 [02:16<02:33, 19.82it/s]
 46%|████▌     | 2576/5625 [02:16<02:39, 19.12it/s]
 46%|████▌     | 2578/5625 [02:16<02:37, 19.34it/s]
 46%|████▌     | 2580/5625 [02:16<02:38, 19.16it/s]
 46%|████▌     | 2582/5625 [02:16<02:42, 18.74it/s]
 46%|████▌     | 2584/5625 [02:16<02:46, 18.26it/s]
 46%|████▌     | 2587/5625 [02:17<02:34, 19.62it/s]
 46%|████▌     | 2590/5625 [02:17<02:35, 19.58it/s]
 46%|████▌     | 2592/5625 [02:17<02:36, 19.37it/s]
 46%|████▌     | 2594/5625 [02:17<02:36, 19.34it/s]
 46%|████▌     | 2596/5625 [02:17<02:39, 18.95it/s]
 46%|████▌     | 2598/5625 [02:17<02:43, 18.50it/s]
 46%|████▌     | 2601/5625 [02:17<02:38, 19.02it/s]
 46%|████▋     | 2603/5625 [02:17<02:41, 18.68it/s]
 46%|████▋     | 2605/5625 [02:18<02:45, 18.28it/s]
 46%|████▋     | 2607/5625 [02:18<02:43, 18.47it/s]
 46%|████▋     | 2609/5625 [02:18<02:42, 18.55it/s]
 46%|████▋     | 2611/5625 [02:18<02:45, 18.21it/s]
 46%|████▋     | 2613/5625 [02:18<02:44, 18.26it/s]
 47%|████▋     | 2616/5625 [02:18<02:39, 18.85it/s]
 47%|████▋     | 2618/5625 [02:18<02:39, 18.87it/s]
 47%|████▋     | 2620/5625 [02:18<02:40, 18.71it/s]
 47%|████▋     | 2623/5625 [02:18<02:36, 19.15it/s]
 47%|████▋     | 2625/5625 [02:19<02:37, 19.04it/s]
 47%|████▋     | 2627/5625 [02:19<02:39, 18.80it/s]
 47%|████▋     | 2629/5625 [02:19<02:40, 18.71it/s]
 47%|████▋     | 2632/5625 [02:19<02:34, 19.31it/s]
 47%|████▋     | 2634/5625 [02:19<02:36, 19.07it/s]
 47%|████▋     | 2636/5625 [02:19<02:37, 19.02it/s]
 47%|████▋     | 2638/5625 [02:19<02:35, 19.26it/s]
 47%|████▋     | 2640/5625 [02:19<02:35, 19.17it/s]
 47%|████▋     | 2643/5625 [02:20<02:30, 19.87it/s]
 47%|████▋     | 2645/5625 [02:20<02:31, 19.73it/s]
 47%|████▋     | 2647/5625 [02:20<02:33, 19.37it/s]
 47%|████▋     | 2649/5625 [02:20<02:34, 19.29it/s]
 47%|████▋     | 2651/5625 [02:20<02:37, 18.93it/s]
 47%|████▋     | 2653/5625 [02:20<02:39, 18.61it/s]
 47%|████▋     | 2655/5625 [02:20<02:40, 18.54it/s]
 47%|████▋     | 2658/5625 [02:20<02:32, 19.50it/s]
 47%|████▋     | 2661/5625 [02:20<02:26, 20.23it/s]
 47%|████▋     | 2664/5625 [02:21<02:27, 20.05it/s]
 47%|████▋     | 2666/5625 [02:21<02:30, 19.65it/s]
 47%|████▋     | 2669/5625 [02:21<02:27, 20.01it/s]
 47%|████▋     | 2671/5625 [02:21<02:29, 19.74it/s]
 48%|████▊     | 2673/5625 [02:21<02:29, 19.69it/s]
 48%|████▊     | 2676/5625 [02:21<02:30, 19.66it/s]
 48%|████▊     | 2678/5625 [02:21<02:32, 19.29it/s]
 48%|████▊     | 2680/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2682/5625 [02:22<02:31, 19.41it/s]
 48%|████▊     | 2684/5625 [02:22<02:32, 19.31it/s]
 48%|████▊     | 2686/5625 [02:22<02:31, 19.46it/s]
 48%|████▊     | 2688/5625 [02:22<02:31, 19.39it/s]
 48%|████▊     | 2691/5625 [02:22<02:30, 19.43it/s]
 48%|████▊     | 2693/5625 [02:22<02:34, 18.96it/s]
 48%|████▊     | 2696/5625 [02:22<02:27, 19.80it/s]
 48%|████▊     | 2699/5625 [02:22<02:24, 20.24it/s]
 48%|████▊     | 2702/5625 [02:23<02:27, 19.82it/s]
 48%|████▊     | 2704/5625 [02:23<02:29, 19.48it/s]
 48%|████▊     | 2706/5625 [02:23<02:33, 18.98it/s]
 48%|████▊     | 2709/5625 [02:23<02:30, 19.35it/s]
 48%|████▊     | 2711/5625 [02:23<02:34, 18.89it/s]
 48%|████▊     | 2713/5625 [02:23<02:34, 18.87it/s]
 48%|████▊     | 2715/5625 [02:23<02:37, 18.45it/s]
 48%|████▊     | 2717/5625 [02:23<02:34, 18.76it/s]
 48%|████▊     | 2719/5625 [02:23<02:38, 18.36it/s]
 48%|████▊     | 2721/5625 [02:24<02:35, 18.69it/s]
 48%|████▊     | 2723/5625 [02:24<02:35, 18.69it/s]
 48%|████▊     | 2725/5625 [02:24<02:33, 18.85it/s]
 48%|████▊     | 2727/5625 [02:24<02:31, 19.13it/s]
 49%|████▊     | 2730/5625 [02:24<02:28, 19.54it/s]
 49%|████▊     | 2732/5625 [02:24<02:29, 19.35it/s]
 49%|████▊     | 2734/5625 [02:24<02:32, 18.96it/s]
 49%|████▊     | 2737/5625 [02:24<02:26, 19.77it/s]
 49%|████▊     | 2739/5625 [02:24<02:26, 19.66it/s]
 49%|████▊     | 2741/5625 [02:25<02:29, 19.31it/s]
 49%|████▉     | 2743/5625 [02:25<02:31, 19.04it/s]
 49%|████▉     | 2746/5625 [02:25<02:29, 19.31it/s]
 49%|████▉     | 2748/5625 [02:25<02:28, 19.39it/s]
 49%|████▉     | 2750/5625 [02:25<02:27, 19.47it/s]
 49%|████▉     | 2752/5625 [02:25<02:27, 19.46it/s]
 49%|████▉     | 2754/5625 [02:25<02:28, 19.32it/s]
 49%|████▉     | 2757/5625 [02:25<02:29, 19.22it/s]
 49%|████▉     | 2760/5625 [02:26<02:25, 19.69it/s]
 49%|████▉     | 2762/5625 [02:26<02:27, 19.43it/s]
 49%|████▉     | 2764/5625 [02:26<02:30, 18.97it/s]
 49%|████▉     | 2767/5625 [02:26<02:25, 19.59it/s]
 49%|████▉     | 2770/5625 [02:26<02:24, 19.75it/s]
 49%|████▉     | 2772/5625 [02:26<02:28, 19.26it/s]
 49%|████▉     | 2774/5625 [02:26<02:27, 19.32it/s]
 49%|████▉     | 2776/5625 [02:26<02:26, 19.43it/s]
 49%|████▉     | 2778/5625 [02:27<02:28, 19.21it/s]
 49%|████▉     | 2780/5625 [02:27<02:29, 19.02it/s]
 49%|████▉     | 2783/5625 [02:27<02:27, 19.22it/s]
 50%|████▉     | 2785/5625 [02:27<02:29, 19.00it/s]
 50%|████▉     | 2788/5625 [02:27<02:23, 19.76it/s]
 50%|████▉     | 2790/5625 [02:27<02:26, 19.33it/s]
 50%|████▉     | 2792/5625 [02:27<02:27, 19.17it/s]
 50%|████▉     | 2794/5625 [02:27<02:26, 19.33it/s]
 50%|████▉     | 2796/5625 [02:27<02:31, 18.72it/s]
 50%|████▉     | 2798/5625 [02:28<02:29, 18.87it/s]
 50%|████▉     | 2800/5625 [02:28<02:27, 19.13it/s]
 50%|████▉     | 2802/5625 [02:28<02:32, 18.57it/s]
 50%|████▉     | 2804/5625 [02:28<02:29, 18.87it/s]
 50%|████▉     | 2806/5625 [02:28<02:29, 18.91it/s]
 50%|████▉     | 2809/5625 [02:28<02:27, 19.11it/s]
 50%|████▉     | 2811/5625 [02:28<02:26, 19.25it/s]
 50%|█████     | 2814/5625 [02:28<02:23, 19.52it/s]
 50%|█████     | 2816/5625 [02:29<02:25, 19.30it/s]
 50%|█████     | 2818/5625 [02:29<02:25, 19.31it/s]
 50%|█████     | 2820/5625 [02:29<02:29, 18.73it/s]
 50%|█████     | 2822/5625 [02:29<02:28, 18.90it/s]
 50%|█████     | 2824/5625 [02:29<02:25, 19.19it/s]
 50%|█████     | 2827/5625 [02:29<02:19, 20.03it/s]
 50%|█████     | 2829/5625 [02:29<02:22, 19.68it/s]
 50%|█████     | 2831/5625 [02:29<02:23, 19.42it/s]
 50%|█████     | 2833/5625 [02:29<02:26, 19.06it/s]
 50%|█████     | 2835/5625 [02:29<02:24, 19.25it/s]
 50%|█████     | 2838/5625 [02:30<02:20, 19.80it/s]
 50%|█████     | 2840/5625 [02:30<02:21, 19.71it/s]
 51%|█████     | 2843/5625 [02:30<02:16, 20.40it/s]
 51%|█████     | 2846/5625 [02:30<02:22, 19.50it/s]
 51%|█████     | 2849/5625 [02:30<02:21, 19.57it/s]
 51%|█████     | 2851/5625 [02:30<02:23, 19.35it/s]
 51%|█████     | 2853/5625 [02:30<02:25, 19.08it/s]
 51%|█████     | 2856/5625 [02:31<02:21, 19.60it/s]
 51%|█████     | 2858/5625 [02:31<02:25, 19.03it/s]
 51%|█████     | 2861/5625 [02:31<02:18, 19.94it/s]
 51%|█████     | 2863/5625 [02:31<02:20, 19.68it/s]
 51%|█████     | 2865/5625 [02:31<02:22, 19.40it/s]
 51%|█████     | 2867/5625 [02:31<02:21, 19.48it/s]
 51%|█████     | 2870/5625 [02:31<02:15, 20.30it/s]
 51%|█████     | 2873/5625 [02:31<02:18, 19.86it/s]
 51%|█████     | 2875/5625 [02:32<02:20, 19.56it/s]
 51%|█████     | 2877/5625 [02:32<02:21, 19.45it/s]
 51%|█████     | 2879/5625 [02:32<02:23, 19.13it/s]
 51%|█████     | 2882/5625 [02:32<02:21, 19.38it/s]
 51%|█████▏    | 2884/5625 [02:32<02:23, 19.14it/s]
 51%|█████▏    | 2887/5625 [02:32<02:16, 20.07it/s]
 51%|█████▏    | 2889/5625 [02:32<02:21, 19.29it/s]
 51%|█████▏    | 2891/5625 [02:32<02:20, 19.40it/s]
 51%|█████▏    | 2894/5625 [02:32<02:16, 19.99it/s]
 51%|█████▏    | 2896/5625 [02:33<02:19, 19.50it/s]
 52%|█████▏    | 2898/5625 [02:33<02:21, 19.34it/s]
 52%|█████▏    | 2900/5625 [02:33<02:26, 18.65it/s]
 52%|█████▏    | 2903/5625 [02:33<02:19, 19.55it/s]
 52%|█████▏    | 2906/5625 [02:33<02:15, 20.14it/s]
 52%|█████▏    | 2908/5625 [02:33<02:16, 19.86it/s]
 52%|█████▏    | 2910/5625 [02:33<02:16, 19.84it/s]
 52%|█████▏    | 2913/5625 [02:33<02:14, 20.11it/s]
 52%|█████▏    | 2915/5625 [02:34<02:17, 19.77it/s]
 52%|█████▏    | 2917/5625 [02:34<02:21, 19.21it/s]
 52%|█████▏    | 2919/5625 [02:34<02:23, 18.80it/s]
 52%|█████▏    | 2921/5625 [02:34<02:26, 18.44it/s]
 52%|█████▏    | 2923/5625 [02:34<02:23, 18.81it/s]
 52%|█████▏    | 2925/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2927/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2929/5625 [02:34<02:22, 18.91it/s]
 52%|█████▏    | 2931/5625 [02:34<02:21, 19.10it/s]
 52%|█████▏    | 2934/5625 [02:35<02:20, 19.20it/s]
 52%|█████▏    | 2937/5625 [02:35<02:19, 19.23it/s]
 52%|█████▏    | 2940/5625 [02:35<02:13, 20.07it/s]
 52%|█████▏    | 2943/5625 [02:35<02:11, 20.42it/s]
 52%|█████▏    | 2946/5625 [02:35<02:14, 19.87it/s]
 52%|█████▏    | 2948/5625 [02:35<02:15, 19.75it/s]
 52%|█████▏    | 2950/5625 [02:35<02:18, 19.32it/s]
 52%|█████▏    | 2952/5625 [02:35<02:18, 19.33it/s]
 53%|█████▎    | 2954/5625 [02:36<02:20, 18.97it/s]
 53%|█████▎    | 2957/5625 [02:36<02:17, 19.44it/s]
 53%|█████▎    | 2960/5625 [02:36<02:15, 19.60it/s]
 53%|█████▎    | 2963/5625 [02:36<02:15, 19.64it/s]
 53%|█████▎    | 2965/5625 [02:36<02:19, 19.04it/s]
 53%|█████▎    | 2967/5625 [02:36<02:18, 19.25it/s]
 53%|█████▎    | 2970/5625 [02:36<02:16, 19.40it/s]
 53%|█████▎    | 2973/5625 [02:37<02:15, 19.64it/s]
 53%|█████▎    | 2976/5625 [02:37<02:14, 19.68it/s]
 53%|█████▎    | 2978/5625 [02:37<02:15, 19.50it/s]
 53%|█████▎    | 2980/5625 [02:37<02:17, 19.20it/s]
 53%|█████▎    | 2983/5625 [02:37<02:17, 19.24it/s]
 53%|█████▎    | 2985/5625 [02:37<02:19, 18.90it/s]
 53%|█████▎    | 2988/5625 [02:37<02:16, 19.35it/s]
 53%|█████▎    | 2990/5625 [02:37<02:18, 19.07it/s]
 53%|█████▎    | 2992/5625 [02:38<02:16, 19.29it/s]
 53%|█████▎    | 2995/5625 [02:38<02:11, 19.93it/s]
 53%|█████▎    | 2997/5625 [02:38<02:14, 19.59it/s]
 53%|█████▎    | 2999/5625 [02:38<02:16, 19.29it/s]
 53%|█████▎    | 3002/5625 [02:38<02:12, 19.75it/s]
 53%|█████▎    | 3005/5625 [02:38<02:09, 20.23it/s]
 53%|█████▎    | 3008/5625 [02:38<02:11, 19.92it/s]
 54%|█████▎    | 3010/5625 [02:38<02:14, 19.51it/s]
 54%|█████▎    | 3012/5625 [02:39<02:15, 19.34it/s]
 54%|█████▎    | 3014/5625 [02:39<02:17, 18.95it/s]
 54%|█████▎    | 3017/5625 [02:39<02:13, 19.57it/s]
 54%|█████▎    | 3019/5625 [02:39<02:14, 19.33it/s]
 54%|█████▎    | 3022/5625 [02:39<02:13, 19.56it/s]
 54%|█████▍    | 3024/5625 [02:39<02:12, 19.65it/s]
 54%|█████▍    | 3027/5625 [02:39<02:09, 20.04it/s]
 54%|█████▍    | 3029/5625 [02:39<02:11, 19.77it/s]
 54%|█████▍    | 3032/5625 [02:40<02:08, 20.11it/s]
 54%|█████▍    | 3034/5625 [02:40<02:09, 20.01it/s]
 54%|█████▍    | 3037/5625 [02:40<02:07, 20.26it/s]
 54%|█████▍    | 3040/5625 [02:40<02:13, 19.37it/s]
 54%|█████▍    | 3042/5625 [02:40<02:15, 19.06it/s]
 54%|█████▍    | 3044/5625 [02:40<02:16, 18.93it/s]
 54%|█████▍    | 3047/5625 [02:40<02:15, 19.07it/s]
 54%|█████▍    | 3050/5625 [02:41<02:10, 19.76it/s]
 54%|█████▍    | 3053/5625 [02:41<02:09, 19.80it/s]
 54%|█████▍    | 3056/5625 [02:41<02:06, 20.30it/s]
 54%|█████▍    | 3059/5625 [02:41<02:08, 19.89it/s]
 54%|█████▍    | 3061/5625 [02:41<02:09, 19.77it/s]
 54%|█████▍    | 3063/5625 [02:41<02:09, 19.80it/s]
 54%|█████▍    | 3065/5625 [02:41<02:12, 19.28it/s]
 55%|█████▍    | 3068/5625 [02:41<02:10, 19.59it/s]
 55%|█████▍    | 3070/5625 [02:42<02:12, 19.28it/s]
 55%|█████▍    | 3072/5625 [02:42<02:13, 19.19it/s]
 55%|█████▍    | 3074/5625 [02:42<02:14, 18.98it/s]
 55%|█████▍    | 3077/5625 [02:42<02:08, 19.86it/s]
 55%|█████▍    | 3079/5625 [02:42<02:09, 19.60it/s]
 55%|█████▍    | 3081/5625 [02:42<02:11, 19.38it/s]
 55%|█████▍    | 3084/5625 [02:42<02:10, 19.43it/s]
 55%|█████▍    | 3086/5625 [02:42<02:10, 19.52it/s]
 55%|█████▍    | 3088/5625 [02:42<02:09, 19.62it/s]
 55%|█████▍    | 3090/5625 [02:43<02:10, 19.43it/s]
 55%|█████▍    | 3092/5625 [02:43<02:10, 19.43it/s]
 55%|█████▌    | 3095/5625 [02:43<02:10, 19.34it/s]
 55%|█████▌    | 3097/5625 [02:43<02:12, 19.09it/s]
 55%|█████▌    | 3100/5625 [02:43<02:10, 19.40it/s]
 55%|█████▌    | 3103/5625 [02:43<02:04, 20.19it/s]
 55%|█████▌    | 3106/5625 [02:43<02:07, 19.82it/s]
 55%|█████▌    | 3109/5625 [02:44<02:03, 20.44it/s]
 55%|█████▌    | 3112/5625 [02:44<02:08, 19.63it/s]
 55%|█████▌    | 3114/5625 [02:44<02:09, 19.40it/s]
 55%|█████▌    | 3116/5625 [02:44<02:12, 18.94it/s]
 55%|█████▌    | 3118/5625 [02:44<02:14, 18.60it/s]
 55%|█████▌    | 3120/5625 [02:44<02:12, 18.87it/s]
 56%|█████▌    | 3123/5625 [02:44<02:09, 19.26it/s]
 56%|█████▌    | 3125/5625 [02:44<02:09, 19.24it/s]
 56%|█████▌    | 3127/5625 [02:44<02:11, 19.05it/s]
 56%|█████▌    | 3129/5625 [02:45<02:13, 18.67it/s]
 56%|█████▌    | 3132/5625 [02:45<02:11, 19.03it/s]
 56%|█████▌    | 3134/5625 [02:45<02:11, 18.99it/s]
 56%|█████▌    | 3136/5625 [02:45<02:13, 18.68it/s]
 56%|█████▌    | 3138/5625 [02:45<02:13, 18.59it/s]
 56%|█████▌    | 3140/5625 [02:45<02:15, 18.30it/s]
 56%|█████▌    | 3143/5625 [02:45<02:07, 19.40it/s]
 56%|█████▌    | 3146/5625 [02:45<02:02, 20.32it/s]
 56%|█████▌    | 3149/5625 [02:46<02:06, 19.60it/s]
 56%|█████▌    | 3152/5625 [02:46<02:06, 19.62it/s]
 56%|█████▌    | 3155/5625 [02:46<02:02, 20.11it/s]
 56%|█████▌    | 3158/5625 [02:46<02:03, 19.94it/s]
 56%|█████▌    | 3160/5625 [02:46<02:05, 19.57it/s]
 56%|█████▌    | 3162/5625 [02:46<02:09, 18.95it/s]
 56%|█████▌    | 3164/5625 [02:46<02:10, 18.80it/s]
 56%|█████▋    | 3166/5625 [02:46<02:09, 19.01it/s]
 56%|█████▋    | 3168/5625 [02:47<02:09, 18.91it/s]
 56%|█████▋    | 3170/5625 [02:47<02:12, 18.51it/s]
 56%|█████▋    | 3172/5625 [02:47<02:13, 18.41it/s]
 56%|█████▋    | 3174/5625 [02:47<02:14, 18.19it/s]
 56%|█████▋    | 3176/5625 [02:47<02:14, 18.24it/s]
 56%|█████▋    | 3178/5625 [02:47<02:15, 18.12it/s]
 57%|█████▋    | 3180/5625 [02:47<02:12, 18.46it/s]
 57%|█████▋    | 3183/5625 [02:47<02:09, 18.86it/s]
 57%|█████▋    | 3185/5625 [02:48<02:11, 18.61it/s]
 57%|█████▋    | 3187/5625 [02:48<02:11, 18.53it/s]
 57%|█████▋    | 3189/5625 [02:48<02:09, 18.88it/s]
 57%|█████▋    | 3191/5625 [02:48<02:10, 18.68it/s]
 57%|█████▋    | 3194/5625 [02:48<02:09, 18.79it/s]
 57%|█████▋    | 3196/5625 [02:48<02:07, 19.07it/s]
 57%|█████▋    | 3198/5625 [02:48<02:07, 19.05it/s]
 57%|█████▋    | 3200/5625 [02:48<02:07, 18.99it/s]
 57%|█████▋    | 3203/5625 [02:48<02:04, 19.45it/s]
 57%|█████▋    | 3206/5625 [02:49<02:05, 19.31it/s]
 57%|█████▋    | 3209/5625 [02:49<02:03, 19.60it/s]
 57%|█████▋    | 3211/5625 [02:49<02:03, 19.61it/s]
 57%|█████▋    | 3213/5625 [02:49<02:02, 19.64it/s]
 57%|█████▋    | 3216/5625 [02:49<02:00, 19.92it/s]
 57%|█████▋    | 3218/5625 [02:49<02:02, 19.66it/s]
 57%|█████▋    | 3220/5625 [02:49<02:05, 19.23it/s]
 57%|█████▋    | 3223/5625 [02:49<02:00, 19.86it/s]
 57%|█████▋    | 3226/5625 [02:50<01:58, 20.18it/s]
 57%|█████▋    | 3229/5625 [02:50<02:01, 19.71it/s]
 57%|█████▋    | 3231/5625 [02:50<02:03, 19.42it/s]
 57%|█████▋    | 3234/5625 [02:50<02:02, 19.55it/s]
 58%|█████▊    | 3237/5625 [02:50<02:02, 19.43it/s]
 58%|█████▊    | 3239/5625 [02:50<02:02, 19.53it/s]
 58%|█████▊    | 3241/5625 [02:50<02:06, 18.85it/s]
 58%|█████▊    | 3244/5625 [02:51<02:02, 19.40it/s]
 58%|█████▊    | 3246/5625 [02:51<02:03, 19.28it/s]
 58%|█████▊    | 3249/5625 [02:51<02:00, 19.77it/s]
 58%|█████▊    | 3251/5625 [02:51<02:01, 19.54it/s]
 58%|█████▊    | 3254/5625 [02:51<02:00, 19.71it/s]
 58%|█████▊    | 3257/5625 [02:51<01:58, 19.93it/s]
 58%|█████▊    | 3259/5625 [02:51<02:00, 19.64it/s]
 58%|█████▊    | 3262/5625 [02:51<01:59, 19.77it/s]
 58%|█████▊    | 3264/5625 [02:52<02:00, 19.53it/s]
 58%|█████▊    | 3267/5625 [02:52<02:00, 19.59it/s]
 58%|█████▊    | 3269/5625 [02:52<02:02, 19.30it/s]
 58%|█████▊    | 3272/5625 [02:52<02:00, 19.53it/s]
 58%|█████▊    | 3275/5625 [02:52<01:57, 20.01it/s]
 58%|█████▊    | 3277/5625 [02:52<01:57, 19.93it/s]
 58%|█████▊    | 3279/5625 [02:52<01:58, 19.79it/s]
 58%|█████▊    | 3281/5625 [02:52<02:00, 19.44it/s]
 58%|█████▊    | 3283/5625 [02:53<02:03, 19.04it/s]
 58%|█████▊    | 3285/5625 [02:53<02:01, 19.28it/s]
 58%|█████▊    | 3287/5625 [02:53<02:01, 19.20it/s]
 58%|█████▊    | 3289/5625 [02:53<02:03, 18.94it/s]
 59%|█████▊    | 3292/5625 [02:53<01:59, 19.59it/s]
 59%|█████▊    | 3294/5625 [02:53<02:02, 19.07it/s]
 59%|█████▊    | 3296/5625 [02:53<02:01, 19.21it/s]
 59%|█████▊    | 3299/5625 [02:53<01:56, 20.00it/s]
 59%|█████▊    | 3301/5625 [02:53<02:00, 19.27it/s]
 59%|█████▊    | 3303/5625 [02:54<02:00, 19.27it/s]
 59%|█████▉    | 3306/5625 [02:54<01:58, 19.60it/s]
 59%|█████▉    | 3308/5625 [02:54<01:59, 19.40it/s]
 59%|█████▉    | 3310/5625 [02:54<02:03, 18.76it/s]
 59%|█████▉    | 3312/5625 [02:54<02:03, 18.78it/s]
 59%|█████▉    | 3314/5625 [02:54<02:01, 19.03it/s]
 59%|█████▉    | 3316/5625 [02:54<02:04, 18.61it/s]
 59%|█████▉    | 3319/5625 [02:54<02:00, 19.06it/s]
 59%|█████▉    | 3321/5625 [02:55<02:01, 18.96it/s]
 59%|█████▉    | 3323/5625 [02:55<02:03, 18.67it/s]
 59%|█████▉    | 3325/5625 [02:55<02:00, 19.03it/s]
 59%|█████▉    | 3328/5625 [02:55<01:57, 19.62it/s]
 59%|█████▉    | 3330/5625 [02:55<02:00, 19.08it/s]
 59%|█████▉    | 3333/5625 [02:55<01:56, 19.67it/s]
 59%|█████▉    | 3335/5625 [02:55<01:56, 19.58it/s]
 59%|█████▉    | 3338/5625 [02:55<01:52, 20.26it/s]
 59%|█████▉    | 3341/5625 [02:56<01:54, 19.97it/s]
 59%|█████▉    | 3344/5625 [02:56<01:53, 20.14it/s]
 60%|█████▉    | 3347/5625 [02:56<01:53, 20.10it/s]
 60%|█████▉    | 3350/5625 [02:56<01:52, 20.15it/s]
 60%|█████▉    | 3353/5625 [02:56<01:54, 19.76it/s]
 60%|█████▉    | 3355/5625 [02:56<01:56, 19.47it/s]
 60%|█████▉    | 3357/5625 [02:56<01:56, 19.53it/s]
 60%|█████▉    | 3359/5625 [02:56<01:58, 19.06it/s]
 60%|█████▉    | 3362/5625 [02:57<01:56, 19.42it/s]
 60%|█████▉    | 3364/5625 [02:57<01:55, 19.49it/s]
 60%|█████▉    | 3366/5625 [02:57<01:57, 19.24it/s]
 60%|█████▉    | 3368/5625 [02:57<01:59, 18.96it/s]
 60%|█████▉    | 3370/5625 [02:57<01:57, 19.19it/s]
 60%|█████▉    | 3372/5625 [02:57<02:00, 18.67it/s]
 60%|██████    | 3375/5625 [02:57<01:55, 19.44it/s]
 60%|██████    | 3377/5625 [02:57<01:59, 18.89it/s]
 60%|██████    | 3380/5625 [02:58<01:55, 19.39it/s]
 60%|██████    | 3382/5625 [02:58<01:56, 19.26it/s]
 60%|██████    | 3385/5625 [02:58<01:51, 20.08it/s]
 60%|██████    | 3387/5625 [02:58<01:52, 19.90it/s]
 60%|██████    | 3389/5625 [02:58<01:53, 19.75it/s]
 60%|██████    | 3391/5625 [02:58<01:56, 19.21it/s]
 60%|██████    | 3393/5625 [02:58<01:58, 18.89it/s]
 60%|██████    | 3395/5625 [02:58<01:58, 18.89it/s]
 60%|██████    | 3397/5625 [02:58<01:57, 18.93it/s]
 60%|██████    | 3399/5625 [02:59<01:57, 18.88it/s]
 60%|██████    | 3402/5625 [02:59<01:56, 19.04it/s]
 61%|██████    | 3404/5625 [02:59<01:58, 18.81it/s]
 61%|██████    | 3406/5625 [02:59<02:00, 18.42it/s]
 61%|██████    | 3409/5625 [02:59<01:58, 18.67it/s]
 61%|██████    | 3411/5625 [02:59<01:58, 18.76it/s]
 61%|██████    | 3414/5625 [02:59<01:50, 19.93it/s]
 61%|██████    | 3416/5625 [02:59<01:52, 19.55it/s]
 61%|██████    | 3418/5625 [03:00<01:53, 19.46it/s]
 61%|██████    | 3420/5625 [03:00<01:54, 19.21it/s]
 61%|██████    | 3423/5625 [03:00<01:53, 19.44it/s]
 61%|██████    | 3426/5625 [03:00<01:50, 19.82it/s]
 61%|██████    | 3428/5625 [03:00<01:53, 19.36it/s]
 61%|██████    | 3431/5625 [03:00<01:51, 19.63it/s]
 61%|██████    | 3433/5625 [03:00<01:53, 19.26it/s]
 61%|██████    | 3436/5625 [03:00<01:51, 19.64it/s]
 61%|██████    | 3438/5625 [03:01<01:53, 19.21it/s]
 61%|██████    | 3440/5625 [03:01<01:56, 18.81it/s]
 61%|██████    | 3442/5625 [03:01<01:58, 18.39it/s]
 61%|██████    | 3444/5625 [03:01<01:59, 18.31it/s]
 61%|██████▏   | 3446/5625 [03:01<01:56, 18.71it/s]
 61%|██████▏   | 3449/5625 [03:01<01:50, 19.71it/s]
 61%|██████▏   | 3451/5625 [03:01<01:52, 19.36it/s]
 61%|██████▏   | 3453/5625 [03:01<01:54, 19.05it/s]
 61%|██████▏   | 3456/5625 [03:02<01:51, 19.51it/s]
 61%|██████▏   | 3459/5625 [03:02<01:48, 20.00it/s]
 62%|██████▏   | 3462/5625 [03:02<01:48, 20.01it/s]
 62%|██████▏   | 3464/5625 [03:02<01:50, 19.56it/s]
 62%|██████▏   | 3466/5625 [03:02<01:51, 19.34it/s]
 62%|██████▏   | 3469/5625 [03:02<01:50, 19.58it/s]
 62%|██████▏   | 3471/5625 [03:02<01:50, 19.56it/s]
 62%|██████▏   | 3473/5625 [03:02<01:49, 19.65it/s]
 62%|██████▏   | 3475/5625 [03:02<01:49, 19.69it/s]
 62%|██████▏   | 3477/5625 [03:03<01:51, 19.32it/s]
 62%|██████▏   | 3479/5625 [03:03<01:50, 19.38it/s]
 62%|██████▏   | 3481/5625 [03:03<01:50, 19.45it/s]
 62%|██████▏   | 3484/5625 [03:03<01:45, 20.37it/s]
 62%|██████▏   | 3487/5625 [03:03<01:49, 19.55it/s]
 62%|██████▏   | 3489/5625 [03:03<01:52, 18.99it/s]
 62%|██████▏   | 3492/5625 [03:03<01:49, 19.49it/s]
 62%|██████▏   | 3494/5625 [03:03<01:51, 19.09it/s]
 62%|██████▏   | 3496/5625 [03:04<01:53, 18.76it/s]
 62%|██████▏   | 3498/5625 [03:04<01:51, 19.00it/s]
 62%|██████▏   | 3501/5625 [03:04<01:47, 19.76it/s]
 62%|██████▏   | 3503/5625 [03:04<01:48, 19.64it/s]
 62%|██████▏   | 3506/5625 [03:04<01:44, 20.21it/s]
 62%|██████▏   | 3509/5625 [03:04<01:46, 19.78it/s]
 62%|██████▏   | 3511/5625 [03:04<01:50, 19.09it/s]
 62%|██████▏   | 3514/5625 [03:04<01:49, 19.23it/s]
 63%|██████▎   | 3516/5625 [03:05<01:53, 18.63it/s]
 63%|██████▎   | 3518/5625 [03:05<01:54, 18.47it/s]
 63%|██████▎   | 3521/5625 [03:05<01:49, 19.26it/s]
 63%|██████▎   | 3524/5625 [03:05<01:47, 19.57it/s]
 63%|██████▎   | 3527/5625 [03:05<01:44, 20.15it/s]
 63%|██████▎   | 3530/5625 [03:05<01:46, 19.70it/s]
 63%|██████▎   | 3532/5625 [03:05<01:48, 19.29it/s]
 63%|██████▎   | 3535/5625 [03:06<01:48, 19.29it/s]
 63%|██████▎   | 3537/5625 [03:06<01:50, 18.92it/s]
 63%|██████▎   | 3540/5625 [03:06<01:45, 19.73it/s]
 63%|██████▎   | 3542/5625 [03:06<01:46, 19.59it/s]
 63%|██████▎   | 3545/5625 [03:06<01:43, 20.06it/s]
 63%|██████▎   | 3547/5625 [03:06<01:44, 19.90it/s]
 63%|██████▎   | 3549/5625 [03:06<01:45, 19.67it/s]
 63%|██████▎   | 3551/5625 [03:06<01:48, 19.15it/s]
 63%|██████▎   | 3554/5625 [03:07<01:44, 19.83it/s]
 63%|██████▎   | 3556/5625 [03:07<01:47, 19.33it/s]
 63%|██████▎   | 3559/5625 [03:07<01:42, 20.12it/s]
 63%|██████▎   | 3562/5625 [03:07<01:41, 20.41it/s]
 63%|██████▎   | 3565/5625 [03:07<01:42, 20.08it/s]
 63%|██████▎   | 3568/5625 [03:07<01:45, 19.54it/s]
 63%|██████▎   | 3570/5625 [03:07<01:46, 19.25it/s]
 64%|██████▎   | 3572/5625 [03:07<01:47, 19.16it/s]
 64%|██████▎   | 3574/5625 [03:08<01:47, 19.04it/s]
 64%|██████▎   | 3576/5625 [03:08<01:47, 19.11it/s]
 64%|██████▎   | 3578/5625 [03:08<01:49, 18.72it/s]
 64%|██████▎   | 3580/5625 [03:08<01:47, 18.96it/s]
 64%|██████▎   | 3582/5625 [03:08<01:47, 18.96it/s]
 64%|██████▎   | 3584/5625 [03:08<01:46, 19.15it/s]
 64%|██████▍   | 3586/5625 [03:08<01:46, 19.18it/s]
 64%|██████▍   | 3588/5625 [03:08<01:45, 19.35it/s]
 64%|██████▍   | 3590/5625 [03:08<01:48, 18.73it/s]
 64%|██████▍   | 3592/5625 [03:09<01:50, 18.47it/s]
 64%|██████▍   | 3594/5625 [03:09<01:52, 18.02it/s]
 64%|██████▍   | 3596/5625 [03:09<01:51, 18.17it/s]
 64%|██████▍   | 3598/5625 [03:09<01:49, 18.49it/s]
 64%|██████▍   | 3600/5625 [03:09<01:50, 18.30it/s]
 64%|██████▍   | 3602/5625 [03:09<01:49, 18.50it/s]
 64%|██████▍   | 3604/5625 [03:09<01:48, 18.70it/s]
 64%|██████▍   | 3606/5625 [03:09<01:47, 18.73it/s]
 64%|██████▍   | 3608/5625 [03:09<01:46, 19.02it/s]
 64%|██████▍   | 3610/5625 [03:09<01:44, 19.28it/s]
 64%|██████▍   | 3613/5625 [03:10<01:42, 19.63it/s]
 64%|██████▍   | 3616/5625 [03:10<01:39, 20.15it/s]
 64%|██████▍   | 3619/5625 [03:10<01:41, 19.76it/s]
 64%|██████▍   | 3621/5625 [03:10<01:41, 19.66it/s]
 64%|██████▍   | 3623/5625 [03:10<01:43, 19.25it/s]
 64%|██████▍   | 3625/5625 [03:10<01:46, 18.87it/s]
 64%|██████▍   | 3628/5625 [03:10<01:42, 19.55it/s]
 65%|██████▍   | 3630/5625 [03:11<01:43, 19.34it/s]
 65%|██████▍   | 3632/5625 [03:11<01:46, 18.76it/s]
 65%|██████▍   | 3635/5625 [03:11<01:44, 19.00it/s]
 65%|██████▍   | 3638/5625 [03:11<01:39, 20.01it/s]
 65%|██████▍   | 3641/5625 [03:11<01:38, 20.20it/s]
 65%|██████▍   | 3644/5625 [03:11<01:40, 19.75it/s]
 65%|██████▍   | 3647/5625 [03:11<01:39, 19.89it/s]
 65%|██████▍   | 3649/5625 [03:11<01:40, 19.61it/s]
 65%|██████▍   | 3651/5625 [03:12<01:40, 19.58it/s]
 65%|██████▍   | 3653/5625 [03:12<01:43, 19.00it/s]
 65%|██████▍   | 3656/5625 [03:12<01:41, 19.34it/s]
 65%|██████▌   | 3658/5625 [03:12<01:43, 19.06it/s]
 65%|██████▌   | 3661/5625 [03:12<01:41, 19.29it/s]
 65%|██████▌   | 3663/5625 [03:12<01:40, 19.45it/s]
 65%|██████▌   | 3665/5625 [03:12<01:42, 19.03it/s]
 65%|██████▌   | 3667/5625 [03:12<01:41, 19.27it/s]
 65%|██████▌   | 3669/5625 [03:13<01:42, 19.16it/s]
 65%|██████▌   | 3671/5625 [03:13<01:45, 18.61it/s]
 65%|██████▌   | 3673/5625 [03:13<01:43, 18.94it/s]
 65%|██████▌   | 3675/5625 [03:13<01:42, 19.02it/s]
 65%|██████▌   | 3677/5625 [03:13<01:41, 19.13it/s]
 65%|██████▌   | 3680/5625 [03:13<01:40, 19.28it/s]
 65%|██████▌   | 3682/5625 [03:13<01:41, 19.18it/s]
 65%|██████▌   | 3684/5625 [03:13<01:40, 19.40it/s]
 66%|██████▌   | 3686/5625 [03:13<01:43, 18.82it/s]
 66%|██████▌   | 3688/5625 [03:14<01:42, 18.86it/s]
 66%|██████▌   | 3691/5625 [03:14<01:41, 19.07it/s]
 66%|██████▌   | 3694/5625 [03:14<01:41, 19.11it/s]
 66%|██████▌   | 3696/5625 [03:14<01:43, 18.68it/s]
 66%|██████▌   | 3698/5625 [03:14<01:43, 18.63it/s]
 66%|██████▌   | 3700/5625 [03:14<01:43, 18.54it/s]
 66%|██████▌   | 3702/5625 [03:14<01:43, 18.52it/s]
 66%|██████▌   | 3704/5625 [03:14<01:41, 18.86it/s]
 66%|██████▌   | 3706/5625 [03:14<01:40, 19.05it/s]
 66%|██████▌   | 3708/5625 [03:15<01:41, 18.85it/s]
 66%|██████▌   | 3710/5625 [03:15<01:40, 19.08it/s]
 66%|██████▌   | 3713/5625 [03:15<01:39, 19.22it/s]
 66%|██████▌   | 3715/5625 [03:15<01:41, 18.78it/s]
 66%|██████▌   | 3717/5625 [03:15<01:40, 19.06it/s]
 66%|██████▌   | 3719/5625 [03:15<01:42, 18.61it/s]
 66%|██████▌   | 3721/5625 [03:15<01:43, 18.41it/s]
 66%|██████▌   | 3724/5625 [03:15<01:35, 19.91it/s]
 66%|██████▌   | 3726/5625 [03:16<01:36, 19.76it/s]
 66%|██████▋   | 3728/5625 [03:16<01:37, 19.37it/s]
 66%|██████▋   | 3731/5625 [03:16<01:36, 19.55it/s]
 66%|██████▋   | 3734/5625 [03:16<01:36, 19.68it/s]
 66%|██████▋   | 3736/5625 [03:16<01:36, 19.66it/s]
 66%|██████▋   | 3738/5625 [03:16<01:37, 19.31it/s]
 66%|██████▋   | 3740/5625 [03:16<01:37, 19.28it/s]
 67%|██████▋   | 3743/5625 [03:16<01:36, 19.59it/s]
 67%|██████▋   | 3745/5625 [03:16<01:37, 19.35it/s]
 67%|██████▋   | 3747/5625 [03:17<01:36, 19.38it/s]
 67%|██████▋   | 3749/5625 [03:17<01:39, 18.93it/s]
                                                   

 67%|██████▋   | 3750/5625 [03:17<01:39, 18.93it/s]{'eval_loss': 0.6867945194244385, 'eval_accuracy': 0.6896, 'eval_f1': 0.6892816142769649, 'eval_runtime': 1.7308, 'eval_samples_per_second': 1444.415, 'eval_steps_per_second': 180.841, 'epoch': 1.0}
{'loss': 0.5094, 'learning_rate': 1.2028041552151718e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.57it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.44it/s]

 21%|██        | 66/313 [00:00<00:01, 205.87it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.12it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.53it/s]

 40%|████      | 126/313 [00:00<00:01, 185.25it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.01it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.06it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.15it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.33it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.38it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.99it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.68it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.60it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.44it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.44it/s]
 67%|██████▋   | 3750/5625 [03:18<01:39, 18.93it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 3751/5625 [03:19<13:30,  2.31it/s]
 67%|██████▋   | 3753/5625 [03:20<10:04,  3.10it/s]
 67%|██████▋   | 3755/5625 [03:20<07:36,  4.09it/s]
 67%|██████▋   | 3757/5625 [03:20<05:51,  5.31it/s]
 67%|██████▋   | 3760/5625 [03:20<04:08,  7.50it/s]
 67%|██████▋   | 3762/5625 [03:20<03:28,  8.95it/s]
 67%|██████▋   | 3764/5625 [03:20<02:57, 10.49it/s]
 67%|██████▋   | 3766/5625 [03:20<02:35, 11.99it/s]
 67%|██████▋   | 3769/5625 [03:20<02:10, 14.20it/s]
 67%|██████▋   | 3771/5625 [03:21<02:01, 15.22it/s]
 67%|██████▋   | 3774/5625 [03:21<01:51, 16.57it/s]
 67%|██████▋   | 3776/5625 [03:21<01:47, 17.14it/s]
 67%|██████▋   | 3778/5625 [03:21<01:44, 17.73it/s]
 67%|██████▋   | 3781/5625 [03:21<01:39, 18.55it/s]
 67%|██████▋   | 3784/5625 [03:21<01:36, 19.04it/s]
 67%|██████▋   | 3786/5625 [03:21<01:37, 18.94it/s]
 67%|██████▋   | 3788/5625 [03:21<01:38, 18.60it/s]
 67%|██████▋   | 3790/5625 [03:21<01:38, 18.58it/s]
 67%|██████▋   | 3792/5625 [03:22<01:37, 18.73it/s]
 67%|██████▋   | 3795/5625 [03:22<01:32, 19.72it/s]
 68%|██████▊   | 3797/5625 [03:22<01:35, 19.07it/s]
 68%|██████▊   | 3800/5625 [03:22<01:34, 19.23it/s]
 68%|██████▊   | 3802/5625 [03:22<01:34, 19.29it/s]
 68%|██████▊   | 3804/5625 [03:22<01:35, 19.10it/s]
 68%|██████▊   | 3807/5625 [03:22<01:33, 19.46it/s]
 68%|██████▊   | 3809/5625 [03:22<01:34, 19.20it/s]
 68%|██████▊   | 3811/5625 [03:23<01:36, 18.76it/s]
 68%|██████▊   | 3813/5625 [03:23<01:35, 18.93it/s]
 68%|██████▊   | 3816/5625 [03:23<01:32, 19.47it/s]
 68%|██████▊   | 3818/5625 [03:23<01:33, 19.23it/s]
 68%|██████▊   | 3820/5625 [03:23<01:33, 19.40it/s]
 68%|██████▊   | 3822/5625 [03:23<01:33, 19.36it/s]
 68%|██████▊   | 3824/5625 [03:23<01:35, 18.90it/s]
 68%|██████▊   | 3827/5625 [03:23<01:34, 19.00it/s]
 68%|██████▊   | 3829/5625 [03:24<01:33, 19.25it/s]
 68%|██████▊   | 3831/5625 [03:24<01:33, 19.11it/s]
 68%|██████▊   | 3834/5625 [03:24<01:32, 19.43it/s]
 68%|██████▊   | 3836/5625 [03:24<01:32, 19.24it/s]
 68%|██████▊   | 3839/5625 [03:24<01:31, 19.61it/s]
 68%|██████▊   | 3841/5625 [03:24<01:32, 19.37it/s]
 68%|██████▊   | 3843/5625 [03:24<01:34, 18.83it/s]
 68%|██████▊   | 3845/5625 [03:24<01:33, 19.11it/s]
 68%|██████▊   | 3847/5625 [03:24<01:33, 18.99it/s]
 68%|██████▊   | 3849/5625 [03:25<01:33, 19.04it/s]
 68%|██████▊   | 3852/5625 [03:25<01:29, 19.77it/s]
 69%|██████▊   | 3855/5625 [03:25<01:28, 19.95it/s]
 69%|██████▊   | 3857/5625 [03:25<01:31, 19.35it/s]
 69%|██████▊   | 3859/5625 [03:25<01:33, 18.85it/s]
 69%|██████▊   | 3861/5625 [03:25<01:33, 18.92it/s]
 69%|██████▊   | 3864/5625 [03:25<01:29, 19.64it/s]
 69%|██████▊   | 3867/5625 [03:25<01:27, 20.11it/s]
 69%|██████▉   | 3870/5625 [03:26<01:27, 20.15it/s]
 69%|██████▉   | 3873/5625 [03:26<01:31, 19.22it/s]
 69%|██████▉   | 3876/5625 [03:26<01:30, 19.35it/s]
 69%|██████▉   | 3878/5625 [03:26<01:30, 19.26it/s]
 69%|██████▉   | 3880/5625 [03:26<01:30, 19.32it/s]
 69%|██████▉   | 3882/5625 [03:26<01:29, 19.47it/s]
 69%|██████▉   | 3885/5625 [03:26<01:28, 19.59it/s]
 69%|██████▉   | 3888/5625 [03:27<01:26, 20.05it/s]
 69%|██████▉   | 3891/5625 [03:27<01:26, 20.02it/s]
 69%|██████▉   | 3894/5625 [03:27<01:27, 19.77it/s]
 69%|██████▉   | 3897/5625 [03:27<01:27, 19.67it/s]
 69%|██████▉   | 3899/5625 [03:27<01:29, 19.29it/s]
 69%|██████▉   | 3901/5625 [03:27<01:29, 19.31it/s]
 69%|██████▉   | 3903/5625 [03:27<01:30, 19.10it/s]
 69%|██████▉   | 3905/5625 [03:27<01:29, 19.26it/s]
 69%|██████▉   | 3907/5625 [03:28<01:31, 18.78it/s]
 70%|██████▉   | 3910/5625 [03:28<01:27, 19.65it/s]
 70%|██████▉   | 3912/5625 [03:28<01:29, 19.14it/s]
 70%|██████▉   | 3915/5625 [03:28<01:27, 19.49it/s]
 70%|██████▉   | 3918/5625 [03:28<01:25, 20.07it/s]
 70%|██████▉   | 3921/5625 [03:28<01:25, 19.92it/s]
 70%|██████▉   | 3923/5625 [03:28<01:28, 19.20it/s]
 70%|██████▉   | 3926/5625 [03:28<01:24, 20.04it/s]
 70%|██████▉   | 3928/5625 [03:29<01:26, 19.52it/s]
 70%|██████▉   | 3931/5625 [03:29<01:24, 20.15it/s]
 70%|██████▉   | 3933/5625 [03:29<01:24, 19.98it/s]
 70%|██████▉   | 3936/5625 [03:29<01:25, 19.81it/s]
 70%|███████   | 3938/5625 [03:29<01:28, 19.13it/s]
 70%|███████   | 3941/5625 [03:29<01:26, 19.41it/s]
 70%|███████   | 3943/5625 [03:29<01:26, 19.54it/s]
 70%|███████   | 3946/5625 [03:30<01:25, 19.66it/s]
 70%|███████   | 3948/5625 [03:30<01:26, 19.43it/s]
 70%|███████   | 3950/5625 [03:30<01:26, 19.34it/s]
 70%|███████   | 3952/5625 [03:30<01:28, 18.80it/s]
 70%|███████   | 3955/5625 [03:30<01:22, 20.13it/s]
 70%|███████   | 3957/5625 [03:30<01:23, 19.95it/s]
 70%|███████   | 3960/5625 [03:30<01:18, 21.10it/s]
 70%|███████   | 3963/5625 [03:30<01:21, 20.37it/s]
 71%|███████   | 3966/5625 [03:31<01:24, 19.58it/s]
 71%|███████   | 3968/5625 [03:31<01:26, 19.20it/s]
 71%|███████   | 3970/5625 [03:31<01:26, 19.16it/s]
 71%|███████   | 3973/5625 [03:31<01:23, 19.76it/s]
 71%|███████   | 3976/5625 [03:31<01:22, 19.91it/s]
 71%|███████   | 3978/5625 [03:31<01:24, 19.52it/s]
 71%|███████   | 3980/5625 [03:31<01:24, 19.46it/s]
 71%|███████   | 3982/5625 [03:31<01:24, 19.55it/s]
 71%|███████   | 3985/5625 [03:31<01:22, 19.82it/s]
 71%|███████   | 3987/5625 [03:32<01:22, 19.84it/s]
 71%|███████   | 3989/5625 [03:32<01:23, 19.48it/s]
 71%|███████   | 3991/5625 [03:32<01:25, 19.05it/s]
 71%|███████   | 3994/5625 [03:32<01:24, 19.32it/s]
 71%|███████   | 3997/5625 [03:32<01:23, 19.51it/s]
 71%|███████   | 3999/5625 [03:32<01:24, 19.34it/s]
 71%|███████   | 4001/5625 [03:32<01:23, 19.42it/s]
 71%|███████   | 4004/5625 [03:32<01:19, 20.33it/s]
 71%|███████   | 4007/5625 [03:33<01:20, 19.98it/s]
 71%|███████▏  | 4010/5625 [03:33<01:20, 20.18it/s]
 71%|███████▏  | 4013/5625 [03:33<01:21, 19.79it/s]
 71%|███████▏  | 4015/5625 [03:33<01:23, 19.24it/s]
 71%|███████▏  | 4017/5625 [03:33<01:24, 18.93it/s]
 71%|███████▏  | 4020/5625 [03:33<01:23, 19.34it/s]
 72%|███████▏  | 4022/5625 [03:33<01:24, 19.02it/s]
 72%|███████▏  | 4024/5625 [03:34<01:24, 18.88it/s]
 72%|███████▏  | 4027/5625 [03:34<01:23, 19.23it/s]
 72%|███████▏  | 4030/5625 [03:34<01:23, 19.14it/s]
 72%|███████▏  | 4033/5625 [03:34<01:19, 20.10it/s]
 72%|███████▏  | 4036/5625 [03:34<01:20, 19.73it/s]
 72%|███████▏  | 4038/5625 [03:34<01:20, 19.66it/s]
 72%|███████▏  | 4041/5625 [03:34<01:18, 20.12it/s]
 72%|███████▏  | 4044/5625 [03:35<01:21, 19.43it/s]
 72%|███████▏  | 4047/5625 [03:35<01:21, 19.45it/s]
 72%|███████▏  | 4050/5625 [03:35<01:20, 19.62it/s]
 72%|███████▏  | 4052/5625 [03:35<01:22, 19.12it/s]
 72%|███████▏  | 4054/5625 [03:35<01:22, 19.08it/s]
 72%|███████▏  | 4056/5625 [03:35<01:22, 18.93it/s]
 72%|███████▏  | 4059/5625 [03:35<01:21, 19.20it/s]
 72%|███████▏  | 4061/5625 [03:35<01:21, 19.14it/s]
 72%|███████▏  | 4063/5625 [03:36<01:23, 18.77it/s]
 72%|███████▏  | 4066/5625 [03:36<01:18, 19.80it/s]
 72%|███████▏  | 4068/5625 [03:36<01:19, 19.55it/s]
 72%|███████▏  | 4070/5625 [03:36<01:19, 19.46it/s]
 72%|███████▏  | 4073/5625 [03:36<01:16, 20.40it/s]
 72%|███████▏  | 4076/5625 [03:36<01:14, 20.80it/s]
 73%|███████▎  | 4079/5625 [03:36<01:16, 20.14it/s]
 73%|███████▎  | 4082/5625 [03:36<01:19, 19.34it/s]
 73%|███████▎  | 4085/5625 [03:37<01:16, 20.09it/s]
 73%|███████▎  | 4088/5625 [03:37<01:18, 19.69it/s]
 73%|███████▎  | 4090/5625 [03:37<01:19, 19.28it/s]
 73%|███████▎  | 4092/5625 [03:37<01:21, 18.90it/s]
 73%|███████▎  | 4094/5625 [03:37<01:21, 18.87it/s]
 73%|███████▎  | 4097/5625 [03:37<01:16, 19.94it/s]
 73%|███████▎  | 4099/5625 [03:37<01:18, 19.33it/s]
 73%|███████▎  | 4101/5625 [03:37<01:19, 19.23it/s]
 73%|███████▎  | 4103/5625 [03:38<01:21, 18.76it/s]
 73%|███████▎  | 4106/5625 [03:38<01:15, 20.16it/s]
 73%|███████▎  | 4108/5625 [03:38<01:15, 20.11it/s]
 73%|███████▎  | 4110/5625 [03:38<01:15, 20.08it/s]
 73%|███████▎  | 4113/5625 [03:38<01:16, 19.79it/s]
 73%|███████▎  | 4115/5625 [03:38<01:17, 19.42it/s]
 73%|███████▎  | 4118/5625 [03:38<01:16, 19.72it/s]
 73%|███████▎  | 4120/5625 [03:38<01:18, 19.19it/s]
 73%|███████▎  | 4122/5625 [03:39<01:19, 19.00it/s]
 73%|███████▎  | 4124/5625 [03:39<01:18, 19.21it/s]
 73%|███████▎  | 4126/5625 [03:39<01:18, 19.15it/s]
 73%|███████▎  | 4128/5625 [03:39<01:19, 18.82it/s]
 73%|███████▎  | 4130/5625 [03:39<01:18, 19.10it/s]
 73%|███████▎  | 4132/5625 [03:39<01:19, 18.88it/s]
 73%|███████▎  | 4134/5625 [03:39<01:19, 18.68it/s]
 74%|███████▎  | 4136/5625 [03:39<01:20, 18.41it/s]
 74%|███████▎  | 4138/5625 [03:39<01:21, 18.35it/s]
 74%|███████▎  | 4141/5625 [03:40<01:18, 18.89it/s]
 74%|███████▎  | 4143/5625 [03:40<01:19, 18.75it/s]
 74%|███████▎  | 4145/5625 [03:40<01:19, 18.58it/s]
 74%|███████▎  | 4147/5625 [03:40<01:18, 18.94it/s]
 74%|███████▍  | 4149/5625 [03:40<01:18, 18.89it/s]
 74%|███████▍  | 4151/5625 [03:40<01:17, 18.95it/s]
 74%|███████▍  | 4153/5625 [03:40<01:19, 18.60it/s]
 74%|███████▍  | 4155/5625 [03:40<01:17, 18.91it/s]
 74%|███████▍  | 4158/5625 [03:40<01:15, 19.47it/s]
 74%|███████▍  | 4161/5625 [03:41<01:15, 19.49it/s]
 74%|███████▍  | 4164/5625 [03:41<01:14, 19.60it/s]
 74%|███████▍  | 4167/5625 [03:41<01:11, 20.49it/s]
 74%|███████▍  | 4170/5625 [03:41<01:12, 19.98it/s]
 74%|███████▍  | 4173/5625 [03:41<01:15, 19.29it/s]
 74%|███████▍  | 4176/5625 [03:41<01:14, 19.45it/s]
 74%|███████▍  | 4179/5625 [03:41<01:14, 19.44it/s]
 74%|███████▍  | 4181/5625 [03:42<01:14, 19.41it/s]
 74%|███████▍  | 4184/5625 [03:42<01:14, 19.41it/s]
 74%|███████▍  | 4186/5625 [03:42<01:15, 19.08it/s]
 74%|███████▍  | 4188/5625 [03:42<01:15, 18.97it/s]
 75%|███████▍  | 4191/5625 [03:42<01:13, 19.46it/s]
 75%|███████▍  | 4193/5625 [03:42<01:14, 19.27it/s]
 75%|███████▍  | 4196/5625 [03:42<01:14, 19.15it/s]
 75%|███████▍  | 4199/5625 [03:43<01:12, 19.75it/s]
 75%|███████▍  | 4201/5625 [03:43<01:13, 19.37it/s]
 75%|███████▍  | 4203/5625 [03:43<01:14, 19.02it/s]
 75%|███████▍  | 4205/5625 [03:43<01:14, 18.96it/s]
 75%|███████▍  | 4207/5625 [03:43<01:15, 18.89it/s]
 75%|███████▍  | 4209/5625 [03:43<01:16, 18.57it/s]
 75%|███████▍  | 4211/5625 [03:43<01:15, 18.83it/s]
 75%|███████▍  | 4213/5625 [03:43<01:17, 18.34it/s]
 75%|███████▍  | 4215/5625 [03:43<01:17, 18.22it/s]
 75%|███████▍  | 4217/5625 [03:44<01:17, 18.05it/s]
 75%|███████▌  | 4220/5625 [03:44<01:14, 18.92it/s]
 75%|███████▌  | 4223/5625 [03:44<01:10, 19.88it/s]
 75%|███████▌  | 4226/5625 [03:44<01:08, 20.30it/s]
 75%|███████▌  | 4229/5625 [03:44<01:09, 20.09it/s]
 75%|███████▌  | 4232/5625 [03:44<01:11, 19.53it/s]
 75%|███████▌  | 4235/5625 [03:44<01:09, 20.06it/s]
 75%|███████▌  | 4238/5625 [03:45<01:11, 19.39it/s]
 75%|███████▌  | 4240/5625 [03:45<01:11, 19.49it/s]
 75%|███████▌  | 4243/5625 [03:45<01:08, 20.26it/s]
 75%|███████▌  | 4246/5625 [03:45<01:11, 19.31it/s]
 76%|███████▌  | 4249/5625 [03:45<01:08, 20.12it/s]
 76%|███████▌  | 4252/5625 [03:45<01:10, 19.59it/s]
 76%|███████▌  | 4254/5625 [03:45<01:11, 19.08it/s]
 76%|███████▌  | 4256/5625 [03:45<01:11, 19.21it/s]
 76%|███████▌  | 4258/5625 [03:46<01:12, 18.73it/s]
 76%|███████▌  | 4260/5625 [03:46<01:12, 18.82it/s]
 76%|███████▌  | 4262/5625 [03:46<01:11, 18.93it/s]
 76%|███████▌  | 4264/5625 [03:46<01:12, 18.68it/s]
 76%|███████▌  | 4266/5625 [03:46<01:13, 18.57it/s]
 76%|███████▌  | 4268/5625 [03:46<01:12, 18.63it/s]
 76%|███████▌  | 4271/5625 [03:46<01:11, 19.03it/s]
 76%|███████▌  | 4273/5625 [03:46<01:10, 19.25it/s]
 76%|███████▌  | 4275/5625 [03:46<01:10, 19.28it/s]
 76%|███████▌  | 4277/5625 [03:47<01:11, 18.75it/s]
 76%|███████▌  | 4279/5625 [03:47<01:11, 18.75it/s]
 76%|███████▌  | 4281/5625 [03:47<01:12, 18.46it/s]
 76%|███████▌  | 4283/5625 [03:47<01:12, 18.61it/s]
 76%|███████▌  | 4286/5625 [03:47<01:10, 19.11it/s]
 76%|███████▌  | 4289/5625 [03:47<01:07, 19.69it/s]
 76%|███████▋  | 4291/5625 [03:47<01:09, 19.21it/s]
 76%|███████▋  | 4293/5625 [03:47<01:11, 18.69it/s]
 76%|███████▋  | 4295/5625 [03:48<01:11, 18.65it/s]
 76%|███████▋  | 4297/5625 [03:48<01:11, 18.62it/s]
 76%|███████▋  | 4300/5625 [03:48<01:09, 19.04it/s]
 76%|███████▋  | 4302/5625 [03:48<01:11, 18.60it/s]
 77%|███████▋  | 4305/5625 [03:48<01:08, 19.38it/s]
 77%|███████▋  | 4307/5625 [03:48<01:09, 18.96it/s]
 77%|███████▋  | 4309/5625 [03:48<01:08, 19.19it/s]
 77%|███████▋  | 4311/5625 [03:48<01:09, 18.93it/s]
 77%|███████▋  | 4313/5625 [03:49<01:08, 19.06it/s]
 77%|███████▋  | 4315/5625 [03:49<01:09, 18.88it/s]
 77%|███████▋  | 4317/5625 [03:49<01:09, 18.76it/s]
 77%|███████▋  | 4319/5625 [03:49<01:10, 18.47it/s]
 77%|███████▋  | 4322/5625 [03:49<01:08, 18.89it/s]
 77%|███████▋  | 4325/5625 [03:49<01:05, 19.78it/s]
 77%|███████▋  | 4327/5625 [03:49<01:05, 19.73it/s]
 77%|███████▋  | 4329/5625 [03:49<01:07, 19.15it/s]
 77%|███████▋  | 4332/5625 [03:49<01:07, 19.29it/s]
 77%|███████▋  | 4335/5625 [03:50<01:05, 19.56it/s]
 77%|███████▋  | 4337/5625 [03:50<01:06, 19.30it/s]
 77%|███████▋  | 4339/5625 [03:50<01:07, 18.93it/s]
 77%|███████▋  | 4342/5625 [03:50<01:05, 19.70it/s]
 77%|███████▋  | 4344/5625 [03:50<01:05, 19.63it/s]
 77%|███████▋  | 4347/5625 [03:50<01:04, 19.79it/s]
 77%|███████▋  | 4349/5625 [03:50<01:05, 19.40it/s]
 77%|███████▋  | 4351/5625 [03:50<01:07, 18.85it/s]
 77%|███████▋  | 4353/5625 [03:51<01:08, 18.51it/s]
 77%|███████▋  | 4356/5625 [03:51<01:05, 19.51it/s]
 77%|███████▋  | 4358/5625 [03:51<01:04, 19.58it/s]
 78%|███████▊  | 4360/5625 [03:51<01:04, 19.56it/s]
 78%|███████▊  | 4363/5625 [03:51<01:03, 19.96it/s]
 78%|███████▊  | 4365/5625 [03:51<01:04, 19.42it/s]
 78%|███████▊  | 4368/5625 [03:51<01:04, 19.55it/s]
 78%|███████▊  | 4371/5625 [03:51<01:04, 19.42it/s]
 78%|███████▊  | 4373/5625 [03:52<01:04, 19.28it/s]
 78%|███████▊  | 4375/5625 [03:52<01:06, 18.84it/s]
 78%|███████▊  | 4377/5625 [03:52<01:05, 19.13it/s]
 78%|███████▊  | 4379/5625 [03:52<01:06, 18.84it/s]
 78%|███████▊  | 4381/5625 [03:52<01:05, 19.09it/s]
 78%|███████▊  | 4383/5625 [03:52<01:05, 18.99it/s]
 78%|███████▊  | 4386/5625 [03:52<01:02, 19.92it/s]
 78%|███████▊  | 4389/5625 [03:52<01:02, 19.76it/s]
 78%|███████▊  | 4391/5625 [03:53<01:02, 19.81it/s]
 78%|███████▊  | 4394/5625 [03:53<01:02, 19.64it/s]
 78%|███████▊  | 4397/5625 [03:53<01:02, 19.64it/s]
 78%|███████▊  | 4399/5625 [03:53<01:03, 19.42it/s]
 78%|███████▊  | 4401/5625 [03:53<01:03, 19.16it/s]
 78%|███████▊  | 4403/5625 [03:53<01:03, 19.34it/s]
 78%|███████▊  | 4406/5625 [03:53<01:01, 19.74it/s]
 78%|███████▊  | 4408/5625 [03:53<01:01, 19.66it/s]
 78%|███████▊  | 4410/5625 [03:54<01:03, 19.02it/s]
 78%|███████▊  | 4413/5625 [03:54<01:01, 19.61it/s]
 79%|███████▊  | 4416/5625 [03:54<01:01, 19.66it/s]
 79%|███████▊  | 4419/5625 [03:54<01:01, 19.54it/s]
 79%|███████▊  | 4421/5625 [03:54<01:03, 18.89it/s]
 79%|███████▊  | 4424/5625 [03:54<01:02, 19.08it/s]
 79%|███████▊  | 4426/5625 [03:54<01:04, 18.65it/s]
 79%|███████▊  | 4429/5625 [03:55<01:02, 19.20it/s]
 79%|███████▉  | 4431/5625 [03:55<01:03, 18.93it/s]
 79%|███████▉  | 4433/5625 [03:55<01:02, 18.96it/s]
 79%|███████▉  | 4436/5625 [03:55<01:00, 19.73it/s]
 79%|███████▉  | 4439/5625 [03:55<00:59, 19.80it/s]
 79%|███████▉  | 4441/5625 [03:55<00:59, 19.76it/s]
 79%|███████▉  | 4443/5625 [03:55<00:59, 19.77it/s]
 79%|███████▉  | 4445/5625 [03:55<01:01, 19.26it/s]
 79%|███████▉  | 4447/5625 [03:55<01:02, 18.99it/s]
 79%|███████▉  | 4449/5625 [03:56<01:02, 18.89it/s]
 79%|███████▉  | 4452/5625 [03:56<01:00, 19.25it/s]
 79%|███████▉  | 4454/5625 [03:56<01:01, 19.17it/s]
 79%|███████▉  | 4456/5625 [03:56<01:00, 19.34it/s]
 79%|███████▉  | 4459/5625 [03:56<00:59, 19.65it/s]
 79%|███████▉  | 4462/5625 [03:56<00:58, 19.74it/s]
 79%|███████▉  | 4464/5625 [03:56<00:58, 19.75it/s]
 79%|███████▉  | 4466/5625 [03:56<00:58, 19.78it/s]
 79%|███████▉  | 4468/5625 [03:57<01:23, 13.93it/s]
 79%|███████▉  | 4470/5625 [03:57<01:17, 14.87it/s]
 80%|███████▉  | 4472/5625 [03:57<01:12, 15.98it/s]
 80%|███████▉  | 4474/5625 [03:57<01:09, 16.47it/s]
 80%|███████▉  | 4476/5625 [03:57<01:06, 17.17it/s]
 80%|███████▉  | 4478/5625 [03:57<01:05, 17.44it/s]
 80%|███████▉  | 4481/5625 [03:57<01:02, 18.33it/s]
 80%|███████▉  | 4484/5625 [03:57<00:57, 19.86it/s]
 80%|███████▉  | 4487/5625 [03:58<00:57, 19.69it/s]
 80%|███████▉  | 4489/5625 [03:58<00:59, 19.15it/s]
 80%|███████▉  | 4492/5625 [03:58<00:57, 19.63it/s]
 80%|███████▉  | 4494/5625 [03:58<00:58, 19.43it/s]
 80%|███████▉  | 4497/5625 [03:58<00:55, 20.19it/s]
 80%|████████  | 4500/5625 [03:58<00:55, 20.43it/s]
 80%|████████  | 4503/5625 [03:58<00:53, 21.15it/s]
 80%|████████  | 4506/5625 [03:59<00:53, 20.83it/s]
 80%|████████  | 4509/5625 [03:59<00:54, 20.53it/s]
 80%|████████  | 4512/5625 [03:59<00:55, 20.07it/s]
 80%|████████  | 4515/5625 [03:59<00:57, 19.30it/s]
 80%|████████  | 4518/5625 [03:59<00:57, 19.35it/s]
 80%|████████  | 4521/5625 [03:59<00:54, 20.27it/s]
 80%|████████  | 4524/5625 [03:59<00:55, 19.86it/s]
 80%|████████  | 4527/5625 [04:00<00:53, 20.46it/s]
 81%|████████  | 4530/5625 [04:00<00:55, 19.71it/s]
 81%|████████  | 4533/5625 [04:00<00:55, 19.76it/s]
 81%|████████  | 4535/5625 [04:00<00:55, 19.70it/s]
 81%|████████  | 4537/5625 [04:00<00:55, 19.55it/s]
 81%|████████  | 4539/5625 [04:00<00:56, 19.34it/s]
 81%|████████  | 4542/5625 [04:00<00:54, 19.73it/s]
 81%|████████  | 4544/5625 [04:00<00:54, 19.68it/s]
 81%|████████  | 4546/5625 [04:01<00:55, 19.41it/s]
 81%|████████  | 4548/5625 [04:01<00:55, 19.50it/s]
 81%|████████  | 4551/5625 [04:01<00:52, 20.34it/s]
 81%|████████  | 4554/5625 [04:01<00:50, 21.09it/s]
 81%|████████  | 4557/5625 [04:01<00:50, 21.15it/s]
 81%|████████  | 4560/5625 [04:01<00:52, 20.26it/s]
 81%|████████  | 4563/5625 [04:01<00:53, 19.71it/s]
 81%|████████  | 4566/5625 [04:02<00:53, 19.61it/s]
 81%|████████  | 4568/5625 [04:02<00:58, 18.03it/s]
 81%|████████  | 4570/5625 [04:02<00:57, 18.35it/s]
 81%|████████▏ | 4572/5625 [04:02<00:58, 18.14it/s]
 81%|████████▏ | 4575/5625 [04:02<00:56, 18.66it/s]
 81%|████████▏ | 4577/5625 [04:02<00:55, 18.95it/s]
 81%|████████▏ | 4579/5625 [04:02<00:55, 18.93it/s]
 81%|████████▏ | 4581/5625 [04:02<00:55, 18.94it/s]
 81%|████████▏ | 4583/5625 [04:03<00:55, 18.93it/s]
 82%|████████▏ | 4585/5625 [04:03<00:54, 19.22it/s]
 82%|████████▏ | 4587/5625 [04:03<00:54, 19.01it/s]
 82%|████████▏ | 4589/5625 [04:03<00:55, 18.72it/s]
 82%|████████▏ | 4592/5625 [04:03<00:53, 19.27it/s]
 82%|████████▏ | 4594/5625 [04:03<00:54, 19.02it/s]
 82%|████████▏ | 4597/5625 [04:03<00:52, 19.50it/s]
 82%|████████▏ | 4599/5625 [04:03<00:52, 19.57it/s]
 82%|████████▏ | 4601/5625 [04:03<00:52, 19.62it/s]
 82%|████████▏ | 4603/5625 [04:04<00:52, 19.31it/s]
 82%|████████▏ | 4605/5625 [04:04<00:52, 19.29it/s]
 82%|████████▏ | 4607/5625 [04:04<00:53, 18.85it/s]
 82%|████████▏ | 4609/5625 [04:04<00:54, 18.60it/s]
 82%|████████▏ | 4611/5625 [04:04<00:55, 18.20it/s]
 82%|████████▏ | 4613/5625 [04:04<00:54, 18.63it/s]
 82%|████████▏ | 4615/5625 [04:04<00:53, 18.91it/s]
 82%|████████▏ | 4617/5625 [04:04<00:53, 18.88it/s]
 82%|████████▏ | 4619/5625 [04:04<00:52, 19.17it/s]
 82%|████████▏ | 4621/5625 [04:05<00:52, 19.21it/s]
 82%|████████▏ | 4623/5625 [04:05<00:53, 18.75it/s]
 82%|████████▏ | 4625/5625 [04:05<00:53, 18.65it/s]
 82%|████████▏ | 4627/5625 [04:05<00:53, 18.63it/s]
 82%|████████▏ | 4629/5625 [04:05<00:53, 18.69it/s]
 82%|████████▏ | 4631/5625 [04:05<00:53, 18.41it/s]
 82%|████████▏ | 4634/5625 [04:05<00:50, 19.74it/s]
 82%|████████▏ | 4637/5625 [04:05<00:50, 19.60it/s]
 82%|████████▏ | 4639/5625 [04:05<00:50, 19.55it/s]
 83%|████████▎ | 4641/5625 [04:06<00:50, 19.56it/s]
 83%|████████▎ | 4643/5625 [04:06<00:51, 19.00it/s]
 83%|████████▎ | 4645/5625 [04:06<00:51, 19.06it/s]
 83%|████████▎ | 4647/5625 [04:06<00:51, 19.01it/s]
 83%|████████▎ | 4649/5625 [04:06<00:52, 18.71it/s]
 83%|████████▎ | 4651/5625 [04:06<00:52, 18.64it/s]
 83%|████████▎ | 4653/5625 [04:06<00:51, 19.00it/s]
 83%|████████▎ | 4655/5625 [04:06<00:51, 18.91it/s]
 83%|████████▎ | 4657/5625 [04:06<00:50, 19.18it/s]
 83%|████████▎ | 4659/5625 [04:07<00:51, 18.90it/s]
 83%|████████▎ | 4661/5625 [04:07<00:50, 18.94it/s]
 83%|████████▎ | 4663/5625 [04:07<00:52, 18.46it/s]
 83%|████████▎ | 4665/5625 [04:07<00:52, 18.31it/s]
 83%|████████▎ | 4667/5625 [04:07<00:51, 18.72it/s]
 83%|████████▎ | 4670/5625 [04:07<00:49, 19.32it/s]
 83%|████████▎ | 4672/5625 [04:07<00:50, 18.83it/s]
 83%|████████▎ | 4675/5625 [04:07<00:49, 19.26it/s]
 83%|████████▎ | 4677/5625 [04:07<00:50, 18.84it/s]
 83%|████████▎ | 4680/5625 [04:08<00:48, 19.52it/s]
 83%|████████▎ | 4682/5625 [04:08<00:48, 19.58it/s]
 83%|████████▎ | 4684/5625 [04:08<00:48, 19.50it/s]
 83%|████████▎ | 4686/5625 [04:08<00:48, 19.46it/s]
 83%|████████▎ | 4688/5625 [04:08<00:48, 19.40it/s]
 83%|████████▎ | 4691/5625 [04:08<00:47, 19.74it/s]
 83%|████████▎ | 4693/5625 [04:08<00:47, 19.64it/s]
 83%|████████▎ | 4695/5625 [04:08<00:47, 19.59it/s]
 84%|████████▎ | 4697/5625 [04:08<00:48, 19.22it/s]
 84%|████████▎ | 4699/5625 [04:09<00:47, 19.38it/s]
 84%|████████▎ | 4701/5625 [04:09<00:48, 19.03it/s]
 84%|████████▎ | 4703/5625 [04:09<00:49, 18.47it/s]
 84%|████████▎ | 4706/5625 [04:09<00:48, 19.14it/s]
 84%|████████▎ | 4709/5625 [04:09<00:47, 19.48it/s]
 84%|████████▍ | 4711/5625 [04:09<00:47, 19.14it/s]
 84%|████████▍ | 4713/5625 [04:09<00:47, 19.09it/s]
 84%|████████▍ | 4715/5625 [04:09<00:48, 18.59it/s]
 84%|████████▍ | 4717/5625 [04:10<00:49, 18.48it/s]
 84%|████████▍ | 4719/5625 [04:10<00:49, 18.42it/s]
 84%|████████▍ | 4722/5625 [04:10<00:46, 19.46it/s]
 84%|████████▍ | 4724/5625 [04:10<00:47, 19.01it/s]
 84%|████████▍ | 4727/5625 [04:10<00:45, 19.73it/s]
 84%|████████▍ | 4730/5625 [04:10<00:44, 20.22it/s]
 84%|████████▍ | 4733/5625 [04:10<00:43, 20.31it/s]
 84%|████████▍ | 4736/5625 [04:10<00:45, 19.68it/s]
 84%|████████▍ | 4738/5625 [04:11<00:45, 19.69it/s]
 84%|████████▍ | 4740/5625 [04:11<00:45, 19.41it/s]
 84%|████████▍ | 4742/5625 [04:11<00:45, 19.30it/s]
 84%|████████▍ | 4744/5625 [04:11<00:46, 19.13it/s]
 84%|████████▍ | 4746/5625 [04:11<00:46, 18.78it/s]
 84%|████████▍ | 4748/5625 [04:11<00:45, 19.08it/s]
 84%|████████▍ | 4751/5625 [04:11<00:44, 19.86it/s]
 84%|████████▍ | 4753/5625 [04:11<00:45, 19.20it/s]
 85%|████████▍ | 4755/5625 [04:11<00:45, 19.11it/s]
 85%|████████▍ | 4757/5625 [04:12<00:44, 19.31it/s]
 85%|████████▍ | 4759/5625 [04:12<00:46, 18.81it/s]
 85%|████████▍ | 4761/5625 [04:12<00:56, 15.37it/s]
 85%|████████▍ | 4764/5625 [04:12<00:49, 17.23it/s]
 85%|████████▍ | 4766/5625 [04:12<00:48, 17.88it/s]
 85%|████████▍ | 4769/5625 [04:12<00:44, 19.07it/s]
 85%|████████▍ | 4771/5625 [04:12<00:45, 18.58it/s]
 85%|████████▍ | 4773/5625 [04:12<00:45, 18.58it/s]
 85%|████████▍ | 4776/5625 [04:13<00:43, 19.47it/s]
 85%|████████▍ | 4778/5625 [04:13<00:44, 18.96it/s]
 85%|████████▍ | 4780/5625 [04:13<00:44, 19.18it/s]
 85%|████████▌ | 4782/5625 [04:13<00:43, 19.31it/s]
 85%|████████▌ | 4784/5625 [04:13<00:43, 19.17it/s]
 85%|████████▌ | 4786/5625 [04:13<00:44, 18.67it/s]
 85%|████████▌ | 4788/5625 [04:13<00:44, 18.63it/s]
 85%|████████▌ | 4791/5625 [04:13<00:41, 19.95it/s]
 85%|████████▌ | 4794/5625 [04:14<00:40, 20.35it/s]
 85%|████████▌ | 4797/5625 [04:14<00:40, 20.21it/s]
 85%|████████▌ | 4800/5625 [04:14<00:39, 20.73it/s]
 85%|████████▌ | 4803/5625 [04:14<00:40, 20.22it/s]
 85%|████████▌ | 4806/5625 [04:14<00:41, 19.54it/s]
 85%|████████▌ | 4808/5625 [04:14<00:41, 19.54it/s]
 86%|████████▌ | 4810/5625 [04:14<00:42, 18.98it/s]
 86%|████████▌ | 4813/5625 [04:15<00:40, 19.85it/s]
 86%|████████▌ | 4815/5625 [04:15<00:41, 19.55it/s]
 86%|████████▌ | 4818/5625 [04:15<00:40, 19.96it/s]
 86%|████████▌ | 4820/5625 [04:15<00:41, 19.37it/s]
 86%|████████▌ | 4822/5625 [04:15<00:42, 18.97it/s]
 86%|████████▌ | 4824/5625 [04:15<00:42, 18.95it/s]
 86%|████████▌ | 4827/5625 [04:15<00:40, 19.53it/s]
 86%|████████▌ | 4829/5625 [04:15<00:41, 19.33it/s]
 86%|████████▌ | 4832/5625 [04:15<00:39, 20.06it/s]
 86%|████████▌ | 4834/5625 [04:16<00:39, 19.85it/s]
 86%|████████▌ | 4836/5625 [04:16<00:39, 19.81it/s]
 86%|████████▌ | 4839/5625 [04:16<00:39, 20.11it/s]
 86%|████████▌ | 4842/5625 [04:16<00:38, 20.54it/s]
 86%|████████▌ | 4845/5625 [04:16<00:38, 20.49it/s]
 86%|████████▌ | 4848/5625 [04:16<00:38, 20.10it/s]
 86%|████████▌ | 4851/5625 [04:16<00:38, 20.15it/s]
 86%|████████▋ | 4854/5625 [04:17<00:39, 19.54it/s]
 86%|████████▋ | 4856/5625 [04:17<00:39, 19.56it/s]
 86%|████████▋ | 4858/5625 [04:17<00:39, 19.45it/s]
 86%|████████▋ | 4861/5625 [04:17<00:38, 19.80it/s]
 86%|████████▋ | 4863/5625 [04:17<00:38, 19.60it/s]
 86%|████████▋ | 4865/5625 [04:17<00:39, 19.39it/s]
 87%|████████▋ | 4868/5625 [04:17<00:37, 19.98it/s]
 87%|████████▋ | 4871/5625 [04:17<00:37, 20.13it/s]
 87%|████████▋ | 4874/5625 [04:18<00:36, 20.41it/s]
 87%|████████▋ | 4877/5625 [04:18<00:37, 19.78it/s]
 87%|████████▋ | 4879/5625 [04:18<00:38, 19.56it/s]
 87%|████████▋ | 4881/5625 [04:18<00:38, 19.16it/s]
 87%|████████▋ | 4883/5625 [04:18<00:38, 19.36it/s]
 87%|████████▋ | 4886/5625 [04:18<00:37, 19.81it/s]
 87%|████████▋ | 4888/5625 [04:18<00:37, 19.42it/s]
 87%|████████▋ | 4890/5625 [04:18<00:38, 19.22it/s]
 87%|████████▋ | 4893/5625 [04:19<00:37, 19.32it/s]
 87%|████████▋ | 4896/5625 [04:19<00:37, 19.64it/s]
 87%|████████▋ | 4899/5625 [04:19<00:36, 19.79it/s]
 87%|████████▋ | 4902/5625 [04:19<00:36, 20.00it/s]
 87%|████████▋ | 4904/5625 [04:19<00:36, 19.65it/s]
 87%|████████▋ | 4906/5625 [04:19<00:37, 19.32it/s]
 87%|████████▋ | 4909/5625 [04:19<00:36, 19.55it/s]
 87%|████████▋ | 4911/5625 [04:20<00:37, 19.09it/s]
 87%|████████▋ | 4914/5625 [04:20<00:35, 19.94it/s]
 87%|████████▋ | 4916/5625 [04:20<00:35, 19.72it/s]
 87%|████████▋ | 4918/5625 [04:20<00:36, 19.50it/s]
 87%|████████▋ | 4920/5625 [04:20<00:35, 19.60it/s]
 88%|████████▊ | 4922/5625 [04:20<00:35, 19.62it/s]
 88%|████████▊ | 4925/5625 [04:20<00:35, 19.68it/s]
 88%|████████▊ | 4928/5625 [04:20<00:34, 20.22it/s]
 88%|████████▊ | 4931/5625 [04:21<00:35, 19.62it/s]
 88%|████████▊ | 4933/5625 [04:21<00:36, 19.09it/s]
 88%|████████▊ | 4935/5625 [04:21<00:36, 18.96it/s]
 88%|████████▊ | 4938/5625 [04:21<00:35, 19.25it/s]
 88%|████████▊ | 4941/5625 [04:21<00:34, 19.68it/s]
 88%|████████▊ | 4944/5625 [04:21<00:33, 20.22it/s]
 88%|████████▊ | 4947/5625 [04:21<00:33, 20.11it/s]
 88%|████████▊ | 4950/5625 [04:21<00:34, 19.42it/s]
 88%|████████▊ | 4952/5625 [04:22<00:34, 19.33it/s]
 88%|████████▊ | 4955/5625 [04:22<00:32, 20.32it/s]
 88%|████████▊ | 4958/5625 [04:22<00:33, 19.80it/s]
 88%|████████▊ | 4960/5625 [04:22<00:33, 19.83it/s]
 88%|████████▊ | 4962/5625 [04:22<00:47, 13.90it/s]
 88%|████████▊ | 4964/5625 [04:22<00:44, 14.89it/s]
 88%|████████▊ | 4966/5625 [04:22<00:41, 15.97it/s]
 88%|████████▊ | 4968/5625 [04:23<00:39, 16.45it/s]
 88%|████████▊ | 4970/5625 [04:23<00:37, 17.27it/s]
 88%|████████▊ | 4972/5625 [04:23<00:37, 17.45it/s]
 88%|████████▊ | 4974/5625 [04:23<00:36, 17.70it/s]
 88%|████████▊ | 4976/5625 [04:23<00:36, 17.79it/s]
 89%|████████▊ | 4979/5625 [04:23<00:34, 18.78it/s]
 89%|████████▊ | 4981/5625 [04:23<00:33, 18.96it/s]
 89%|████████▊ | 4984/5625 [04:23<00:32, 19.53it/s]
 89%|████████▊ | 4987/5625 [04:24<00:32, 19.85it/s]
 89%|████████▊ | 4989/5625 [04:24<00:32, 19.29it/s]
 89%|████████▊ | 4992/5625 [04:24<00:30, 20.55it/s]
 89%|████████▉ | 4995/5625 [04:24<00:31, 19.84it/s]
 89%|████████▉ | 4997/5625 [04:24<00:32, 19.60it/s]
 89%|████████▉ | 5000/5625 [04:24<00:30, 20.32it/s]
 89%|████████▉ | 5003/5625 [04:24<00:31, 19.69it/s]
 89%|████████▉ | 5005/5625 [04:24<00:32, 19.16it/s]
 89%|████████▉ | 5007/5625 [04:25<00:32, 19.25it/s]
 89%|████████▉ | 5009/5625 [04:25<00:32, 19.11it/s]
 89%|████████▉ | 5011/5625 [04:25<00:32, 18.68it/s]
 89%|████████▉ | 5013/5625 [04:25<00:32, 18.87it/s]
 89%|████████▉ | 5015/5625 [04:25<00:32, 18.78it/s]
 89%|████████▉ | 5018/5625 [04:25<00:30, 19.68it/s]
 89%|████████▉ | 5021/5625 [04:25<00:31, 19.48it/s]
 89%|████████▉ | 5024/5625 [04:25<00:30, 19.84it/s]
 89%|████████▉ | 5027/5625 [04:26<00:29, 20.19it/s]
 89%|████████▉ | 5030/5625 [04:26<00:29, 19.97it/s]
 89%|████████▉ | 5032/5625 [04:26<00:30, 19.58it/s]
 90%|████████▉ | 5035/5625 [04:26<00:30, 19.63it/s]
 90%|████████▉ | 5037/5625 [04:26<00:30, 19.50it/s]
 90%|████████▉ | 5040/5625 [04:26<00:29, 19.85it/s]
 90%|████████▉ | 5042/5625 [04:26<00:29, 19.84it/s]
 90%|████████▉ | 5044/5625 [04:26<00:29, 19.87it/s]
 90%|████████▉ | 5046/5625 [04:27<00:29, 19.70it/s]
 90%|████████▉ | 5048/5625 [04:27<00:30, 19.18it/s]
 90%|████████▉ | 5050/5625 [04:27<00:29, 19.33it/s]
 90%|████████▉ | 5052/5625 [04:27<00:29, 19.49it/s]
 90%|████████▉ | 5054/5625 [04:27<00:29, 19.55it/s]
 90%|████████▉ | 5056/5625 [04:27<00:29, 19.24it/s]
 90%|████████▉ | 5058/5625 [04:27<00:29, 19.10it/s]
 90%|████████▉ | 5060/5625 [04:27<00:29, 19.05it/s]
 90%|█████████ | 5063/5625 [04:27<00:28, 20.04it/s]
 90%|█████████ | 5065/5625 [04:28<00:28, 19.80it/s]
 90%|█████████ | 5067/5625 [04:28<00:29, 19.19it/s]
 90%|█████████ | 5070/5625 [04:28<00:28, 19.35it/s]
 90%|█████████ | 5072/5625 [04:28<00:28, 19.18it/s]
 90%|█████████ | 5074/5625 [04:28<00:28, 19.32it/s]
 90%|█████████ | 5076/5625 [04:28<00:28, 19.04it/s]
 90%|█████████ | 5078/5625 [04:28<00:28, 19.01it/s]
 90%|█████████ | 5080/5625 [04:28<00:28, 19.00it/s]
 90%|█████████ | 5082/5625 [04:28<00:28, 19.27it/s]
 90%|█████████ | 5084/5625 [04:29<00:28, 19.05it/s]
 90%|█████████ | 5087/5625 [04:29<00:27, 19.34it/s]
 90%|█████████ | 5089/5625 [04:29<00:28, 19.04it/s]
 91%|█████████ | 5091/5625 [04:29<00:27, 19.26it/s]
 91%|█████████ | 5094/5625 [04:29<00:26, 19.68it/s]
 91%|█████████ | 5096/5625 [04:29<00:27, 19.18it/s]
 91%|█████████ | 5098/5625 [04:29<00:27, 18.98it/s]
 91%|█████████ | 5100/5625 [04:29<00:27, 18.90it/s]
 91%|█████████ | 5102/5625 [04:29<00:27, 19.16it/s]
 91%|█████████ | 5105/5625 [04:30<00:25, 20.47it/s]
 91%|█████████ | 5108/5625 [04:30<00:24, 20.94it/s]
 91%|█████████ | 5111/5625 [04:30<00:24, 20.81it/s]
 91%|█████████ | 5114/5625 [04:30<00:25, 19.83it/s]
 91%|█████████ | 5116/5625 [04:30<00:26, 19.31it/s]
 91%|█████████ | 5119/5625 [04:30<00:25, 20.01it/s]
 91%|█████████ | 5122/5625 [04:30<00:25, 19.86it/s]
 91%|█████████ | 5124/5625 [04:31<00:25, 19.66it/s]
 91%|█████████ | 5127/5625 [04:31<00:24, 20.33it/s]
 91%|█████████ | 5130/5625 [04:31<00:25, 19.75it/s]
 91%|█████████ | 5132/5625 [04:31<00:25, 19.52it/s]
 91%|█████████▏| 5134/5625 [04:31<00:25, 19.42it/s]
 91%|█████████▏| 5137/5625 [04:31<00:24, 19.84it/s]
 91%|█████████▏| 5139/5625 [04:31<00:25, 19.20it/s]
 91%|█████████▏| 5141/5625 [04:31<00:25, 18.97it/s]
 91%|█████████▏| 5143/5625 [04:32<00:25, 18.64it/s]
 91%|█████████▏| 5145/5625 [04:32<00:26, 18.24it/s]
 92%|█████████▏| 5147/5625 [04:32<00:26, 18.16it/s]
 92%|█████████▏| 5150/5625 [04:32<00:25, 18.70it/s]
 92%|█████████▏| 5152/5625 [04:32<00:25, 18.53it/s]
 92%|█████████▏| 5155/5625 [04:32<00:24, 19.03it/s]
 92%|█████████▏| 5158/5625 [04:32<00:24, 19.26it/s]
 92%|█████████▏| 5160/5625 [04:32<00:24, 19.01it/s]
 92%|█████████▏| 5162/5625 [04:33<00:24, 19.17it/s]
 92%|█████████▏| 5164/5625 [04:33<00:24, 19.15it/s]
 92%|█████████▏| 5166/5625 [04:33<00:24, 19.08it/s]
 92%|█████████▏| 5168/5625 [04:33<00:24, 18.61it/s]
 92%|█████████▏| 5170/5625 [04:33<00:24, 18.33it/s]
 92%|█████████▏| 5173/5625 [04:33<00:23, 18.91it/s]
 92%|█████████▏| 5176/5625 [04:33<00:23, 19.40it/s]
 92%|█████████▏| 5179/5625 [04:33<00:22, 19.89it/s]
 92%|█████████▏| 5181/5625 [04:34<00:22, 19.58it/s]
 92%|█████████▏| 5183/5625 [04:34<00:22, 19.54it/s]
 92%|█████████▏| 5186/5625 [04:34<00:22, 19.84it/s]
 92%|█████████▏| 5188/5625 [04:34<00:22, 19.30it/s]
 92%|█████████▏| 5190/5625 [04:34<00:23, 18.79it/s]
 92%|█████████▏| 5192/5625 [04:34<00:22, 19.00it/s]
 92%|█████████▏| 5194/5625 [04:34<00:22, 19.13it/s]
 92%|█████████▏| 5197/5625 [04:34<00:22, 19.36it/s]
 92%|█████████▏| 5199/5625 [04:34<00:21, 19.51it/s]
 92%|█████████▏| 5201/5625 [04:35<00:22, 19.27it/s]
 92%|█████████▏| 5203/5625 [04:35<00:22, 18.83it/s]
 93%|█████████▎| 5205/5625 [04:35<00:22, 18.64it/s]
 93%|█████████▎| 5207/5625 [04:35<00:22, 18.98it/s]
 93%|█████████▎| 5209/5625 [04:35<00:21, 19.27it/s]
 93%|█████████▎| 5211/5625 [04:35<00:21, 19.45it/s]
 93%|█████████▎| 5214/5625 [04:35<00:20, 19.75it/s]
 93%|█████████▎| 5216/5625 [04:35<00:21, 19.41it/s]
 93%|█████████▎| 5219/5625 [04:36<00:20, 20.17it/s]
 93%|█████████▎| 5222/5625 [04:36<00:20, 19.32it/s]
 93%|█████████▎| 5224/5625 [04:36<00:20, 19.11it/s]
 93%|█████████▎| 5226/5625 [04:36<00:21, 18.93it/s]
 93%|█████████▎| 5228/5625 [04:36<00:20, 19.01it/s]
 93%|█████████▎| 5231/5625 [04:36<00:20, 19.59it/s]
 93%|█████████▎| 5233/5625 [04:36<00:20, 19.07it/s]
 93%|█████████▎| 5235/5625 [04:36<00:20, 19.20it/s]
 93%|█████████▎| 5238/5625 [04:37<00:19, 19.83it/s]
 93%|█████████▎| 5240/5625 [04:37<00:19, 19.43it/s]
 93%|█████████▎| 5242/5625 [04:37<00:20, 19.09it/s]
 93%|█████████▎| 5245/5625 [04:37<00:19, 19.30it/s]
 93%|█████████▎| 5247/5625 [04:37<00:19, 19.21it/s]
 93%|█████████▎| 5249/5625 [04:37<00:20, 18.75it/s]
 93%|█████████▎| 5251/5625 [04:37<00:20, 18.62it/s]
 93%|█████████▎| 5254/5625 [04:37<00:19, 19.03it/s]
 93%|█████████▎| 5256/5625 [04:37<00:19, 19.05it/s]
 93%|█████████▎| 5258/5625 [04:38<00:19, 18.87it/s]
 94%|█████████▎| 5260/5625 [04:38<00:19, 18.70it/s]
 94%|█████████▎| 5263/5625 [04:38<00:18, 19.27it/s]
 94%|█████████▎| 5265/5625 [04:38<00:18, 19.24it/s]
 94%|█████████▎| 5267/5625 [04:38<00:18, 19.39it/s]
 94%|█████████▎| 5270/5625 [04:38<00:17, 19.80it/s]
 94%|█████████▎| 5272/5625 [04:38<00:18, 19.44it/s]
 94%|█████████▍| 5274/5625 [04:38<00:18, 18.86it/s]
 94%|█████████▍| 5276/5625 [04:39<00:18, 18.91it/s]
 94%|█████████▍| 5278/5625 [04:39<00:18, 18.82it/s]
 94%|█████████▍| 5280/5625 [04:39<00:18, 18.76it/s]
 94%|█████████▍| 5282/5625 [04:39<00:18, 19.03it/s]
 94%|█████████▍| 5284/5625 [04:39<00:18, 18.65it/s]
 94%|█████████▍| 5286/5625 [04:39<00:18, 18.62it/s]
 94%|█████████▍| 5288/5625 [04:39<00:18, 18.54it/s]
 94%|█████████▍| 5291/5625 [04:39<00:17, 18.91it/s]
 94%|█████████▍| 5293/5625 [04:39<00:17, 18.64it/s]
 94%|█████████▍| 5295/5625 [04:40<00:17, 18.38it/s]
 94%|█████████▍| 5297/5625 [04:40<00:17, 18.55it/s]
 94%|█████████▍| 5299/5625 [04:40<00:17, 18.35it/s]
 94%|█████████▍| 5301/5625 [04:40<00:17, 18.58it/s]
 94%|█████████▍| 5304/5625 [04:40<00:16, 19.06it/s]
 94%|█████████▍| 5306/5625 [04:40<00:16, 19.07it/s]
 94%|█████████▍| 5308/5625 [04:40<00:16, 19.30it/s]
 94%|█████████▍| 5310/5625 [04:40<00:16, 19.36it/s]
 94%|█████████▍| 5312/5625 [04:40<00:16, 18.95it/s]
 94%|█████████▍| 5315/5625 [04:41<00:16, 19.18it/s]
 95%|█████████▍| 5318/5625 [04:41<00:15, 19.53it/s]
 95%|█████████▍| 5320/5625 [04:41<00:15, 19.24it/s]
 95%|█████████▍| 5322/5625 [04:41<00:15, 19.29it/s]
 95%|█████████▍| 5324/5625 [04:41<00:15, 19.17it/s]
 95%|█████████▍| 5327/5625 [04:41<00:15, 19.37it/s]
 95%|█████████▍| 5329/5625 [04:41<00:15, 19.14it/s]
 95%|█████████▍| 5331/5625 [04:41<00:15, 19.19it/s]
 95%|█████████▍| 5334/5625 [04:42<00:15, 19.38it/s]
 95%|█████████▍| 5337/5625 [04:42<00:14, 19.48it/s]
 95%|█████████▍| 5339/5625 [04:42<00:15, 19.01it/s]
 95%|█████████▍| 5341/5625 [04:42<00:15, 18.88it/s]
 95%|█████████▍| 5343/5625 [04:42<00:15, 18.49it/s]
 95%|█████████▌| 5345/5625 [04:42<00:14, 18.76it/s]
 95%|█████████▌| 5348/5625 [04:42<00:14, 19.70it/s]
 95%|█████████▌| 5351/5625 [04:42<00:13, 19.67it/s]
 95%|█████████▌| 5353/5625 [04:43<00:13, 19.50it/s]
 95%|█████████▌| 5356/5625 [04:43<00:13, 19.85it/s]
 95%|█████████▌| 5358/5625 [04:43<00:13, 19.30it/s]
 95%|█████████▌| 5360/5625 [04:43<00:13, 19.26it/s]
 95%|█████████▌| 5362/5625 [04:43<00:14, 18.73it/s]
 95%|█████████▌| 5364/5625 [04:43<00:13, 18.68it/s]
 95%|█████████▌| 5366/5625 [04:43<00:13, 18.81it/s]
 95%|█████████▌| 5369/5625 [04:43<00:12, 20.05it/s]
 95%|█████████▌| 5371/5625 [04:43<00:13, 19.44it/s]
 96%|█████████▌| 5373/5625 [04:44<00:13, 19.32it/s]
 96%|█████████▌| 5376/5625 [04:44<00:12, 19.92it/s]
 96%|█████████▌| 5379/5625 [04:44<00:12, 20.45it/s]
 96%|█████████▌| 5382/5625 [04:44<00:11, 20.65it/s]
 96%|█████████▌| 5385/5625 [04:44<00:11, 20.45it/s]
 96%|█████████▌| 5388/5625 [04:44<00:12, 19.69it/s]
 96%|█████████▌| 5390/5625 [04:44<00:12, 19.06it/s]
 96%|█████████▌| 5392/5625 [04:45<00:12, 18.75it/s]
 96%|█████████▌| 5394/5625 [04:45<00:12, 18.81it/s]
 96%|█████████▌| 5396/5625 [04:45<00:12, 18.99it/s]
 96%|█████████▌| 5399/5625 [04:45<00:11, 19.51it/s]
 96%|█████████▌| 5401/5625 [04:45<00:11, 19.01it/s]
 96%|█████████▌| 5403/5625 [04:45<00:11, 18.66it/s]
 96%|█████████▌| 5406/5625 [04:45<00:11, 19.47it/s]
 96%|█████████▌| 5409/5625 [04:45<00:10, 20.05it/s]
 96%|█████████▌| 5411/5625 [04:46<00:10, 19.47it/s]
 96%|█████████▌| 5413/5625 [04:46<00:11, 18.94it/s]
 96%|█████████▋| 5415/5625 [04:46<00:11, 18.52it/s]
 96%|█████████▋| 5418/5625 [04:46<00:10, 19.37it/s]
 96%|█████████▋| 5420/5625 [04:46<00:10, 19.31it/s]
 96%|█████████▋| 5422/5625 [04:46<00:10, 19.36it/s]
 96%|█████████▋| 5424/5625 [04:46<00:10, 18.95it/s]
 96%|█████████▋| 5426/5625 [04:46<00:10, 18.74it/s]
 96%|█████████▋| 5428/5625 [04:46<00:10, 18.97it/s]
 97%|█████████▋| 5430/5625 [04:47<00:10, 19.08it/s]
 97%|█████████▋| 5433/5625 [04:47<00:09, 19.51it/s]
 97%|█████████▋| 5435/5625 [04:47<00:09, 19.56it/s]
 97%|█████████▋| 5437/5625 [04:47<00:09, 19.44it/s]
 97%|█████████▋| 5439/5625 [04:47<00:09, 18.85it/s]
 97%|█████████▋| 5441/5625 [04:47<00:09, 18.79it/s]
 97%|█████████▋| 5443/5625 [04:47<00:09, 18.40it/s]
 97%|█████████▋| 5445/5625 [04:47<00:09, 18.67it/s]
 97%|█████████▋| 5447/5625 [04:47<00:09, 18.70it/s]
 97%|█████████▋| 5449/5625 [04:48<00:09, 18.94it/s]
 97%|█████████▋| 5451/5625 [04:48<00:09, 19.21it/s]
 97%|█████████▋| 5453/5625 [04:48<00:08, 19.14it/s]
 97%|█████████▋| 5455/5625 [04:48<00:08, 19.25it/s]
 97%|█████████▋| 5458/5625 [04:48<00:08, 19.32it/s]
 97%|█████████▋| 5460/5625 [04:48<00:08, 18.96it/s]
 97%|█████████▋| 5462/5625 [04:48<00:08, 18.42it/s]
 97%|█████████▋| 5464/5625 [04:48<00:08, 18.41it/s]
 97%|█████████▋| 5466/5625 [04:48<00:08, 18.48it/s]
 97%|█████████▋| 5468/5625 [04:49<00:08, 18.39it/s]
 97%|█████████▋| 5470/5625 [04:49<00:08, 18.46it/s]
 97%|█████████▋| 5473/5625 [04:49<00:08, 18.73it/s]
 97%|█████████▋| 5475/5625 [04:49<00:08, 18.52it/s]
 97%|█████████▋| 5478/5625 [04:49<00:07, 19.26it/s]
 97%|█████████▋| 5481/5625 [04:49<00:07, 20.29it/s]
 97%|█████████▋| 5484/5625 [04:49<00:07, 19.31it/s]
 98%|█████████▊| 5486/5625 [04:49<00:07, 19.00it/s]
 98%|█████████▊| 5489/5625 [04:50<00:07, 19.35it/s]
 98%|█████████▊| 5491/5625 [04:50<00:07, 19.02it/s]
 98%|█████████▊| 5494/5625 [04:50<00:06, 19.39it/s]
 98%|█████████▊| 5496/5625 [04:50<00:06, 19.08it/s]
 98%|█████████▊| 5498/5625 [04:50<00:06, 18.82it/s]
 98%|█████████▊| 5500/5625 [04:50<00:06, 19.12it/s]
 98%|█████████▊| 5502/5625 [04:50<00:06, 18.59it/s]
 98%|█████████▊| 5505/5625 [04:50<00:06, 18.76it/s]
 98%|█████████▊| 5507/5625 [04:51<00:06, 18.43it/s]
 98%|█████████▊| 5509/5625 [04:51<00:06, 18.24it/s]
 98%|█████████▊| 5511/5625 [04:51<00:06, 18.08it/s]
 98%|█████████▊| 5514/5625 [04:51<00:05, 19.00it/s]
 98%|█████████▊| 5516/5625 [04:51<00:05, 18.81it/s]
 98%|█████████▊| 5518/5625 [04:51<00:05, 19.05it/s]
 98%|█████████▊| 5521/5625 [04:51<00:05, 19.36it/s]
 98%|█████████▊| 5523/5625 [04:51<00:05, 19.25it/s]
 98%|█████████▊| 5526/5625 [04:52<00:05, 19.49it/s]
 98%|█████████▊| 5528/5625 [04:52<00:05, 19.30it/s]
 98%|█████████▊| 5530/5625 [04:52<00:04, 19.26it/s]
 98%|█████████▊| 5533/5625 [04:52<00:04, 19.74it/s]
 98%|█████████▊| 5535/5625 [04:52<00:04, 19.72it/s]
 98%|█████████▊| 5538/5625 [04:52<00:04, 20.27it/s]
 99%|█████████▊| 5541/5625 [04:52<00:04, 20.54it/s]
 99%|█████████▊| 5544/5625 [04:52<00:03, 20.36it/s]
 99%|█████████▊| 5547/5625 [04:53<00:03, 19.72it/s]
 99%|█████████▊| 5549/5625 [04:53<00:03, 19.59it/s]
 99%|█████████▊| 5551/5625 [04:53<00:03, 19.27it/s]
 99%|█████████▊| 5553/5625 [04:53<00:03, 19.11it/s]
 99%|█████████▉| 5556/5625 [04:53<00:03, 19.49it/s]
 99%|█████████▉| 5558/5625 [04:53<00:03, 18.91it/s]
 99%|█████████▉| 5560/5625 [04:53<00:03, 19.11it/s]
 99%|█████████▉| 5562/5625 [04:53<00:03, 18.97it/s]
 99%|█████████▉| 5565/5625 [04:54<00:03, 19.44it/s]
 99%|█████████▉| 5568/5625 [04:54<00:02, 19.66it/s]
 99%|█████████▉| 5570/5625 [04:54<00:02, 19.35it/s]
 99%|█████████▉| 5573/5625 [04:54<00:02, 19.60it/s]
 99%|█████████▉| 5576/5625 [04:54<00:02, 19.69it/s]
 99%|█████████▉| 5578/5625 [04:54<00:02, 19.35it/s]
 99%|█████████▉| 5580/5625 [04:54<00:02, 19.07it/s]
 99%|█████████▉| 5583/5625 [04:54<00:02, 19.85it/s]
 99%|█████████▉| 5586/5625 [04:55<00:01, 20.25it/s]
 99%|█████████▉| 5589/5625 [04:55<00:01, 19.61it/s]
 99%|█████████▉| 5591/5625 [04:55<00:01, 19.08it/s]
 99%|█████████▉| 5593/5625 [04:55<00:01, 19.19it/s]
 99%|█████████▉| 5595/5625 [04:55<00:01, 19.18it/s]
100%|█████████▉| 5597/5625 [04:55<00:01, 19.06it/s]
100%|█████████▉| 5599/5625 [04:55<00:01, 19.16it/s]
100%|█████████▉| 5602/5625 [04:55<00:01, 19.25it/s]
100%|█████████▉| 5604/5625 [04:56<00:01, 18.97it/s]
100%|█████████▉| 5606/5625 [04:56<00:01, 18.96it/s]
100%|█████████▉| 5608/5625 [04:56<00:00, 18.45it/s]
100%|█████████▉| 5610/5625 [04:56<00:00, 18.79it/s]
100%|█████████▉| 5613/5625 [04:56<00:00, 19.42it/s]
100%|█████████▉| 5616/5625 [04:56<00:00, 19.54it/s]
100%|█████████▉| 5618/5625 [04:56<00:00, 19.35it/s]
100%|█████████▉| 5620/5625 [04:56<00:00, 19.25it/s]
100%|█████████▉| 5622/5625 [04:57<00:00, 19.04it/s]
100%|█████████▉| 5624/5625 [04:57<00:00, 18.55it/s]
                                                   

100%|██████████| 5625/5625 [04:57<00:00, 18.55it/s]{'eval_loss': 0.6989438533782959, 'eval_accuracy': 0.7072, 'eval_f1': 0.7056686018062932, 'eval_runtime': 1.7323, 'eval_samples_per_second': 1443.144, 'eval_steps_per_second': 180.682, 'epoch': 2.0}
{'loss': 0.2556, 'learning_rate': 6.11866484974525e-11, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.35it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.44it/s]

 21%|██        | 66/313 [00:00<00:01, 205.96it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.17it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.59it/s]

 40%|████      | 126/313 [00:00<00:01, 185.30it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.27it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.30it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.41it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.56it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.60it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.17it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.75it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.69it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.56it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.56it/s]
100%|██████████| 5625/5625 [04:58<00:00, 18.55it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 5625/5625 [04:59<00:00, 18.55it/s]
100%|██████████| 5625/5625 [04:59<00:00, 18.75it/s]
[I 2023-10-26 22:33:20,274] Trial 9 finished with value: 0.7139125949312289 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 3.97137989895134e-05, 'per_device_train_batch_size': 16, 'weight_decay': 0.00039871506175014456}. Best is trial 6 with value: 0.716991552355688.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.9098975658416748, 'eval_accuracy': 0.7132, 'eval_f1': 0.7139125949312289, 'eval_runtime': 1.7311, 'eval_samples_per_second': 1444.185, 'eval_steps_per_second': 180.812, 'epoch': 3.0}
{'train_runtime': 299.9947, 'train_samples_per_second': 300.005, 'train_steps_per_second': 18.75, 'train_loss': 0.5156346028645833, 'epoch': 3.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<03:58, 11.78it/s]
  0%|          | 4/2814 [00:00<04:00, 11.69it/s]
  0%|          | 6/2814 [00:00<04:00, 11.68it/s]
  0%|          | 8/2814 [00:00<03:57, 11.81it/s]
  0%|          | 10/2814 [00:00<04:00, 11.66it/s]
  0%|          | 12/2814 [00:01<04:02, 11.54it/s]
  0%|          | 14/2814 [00:01<04:01, 11.57it/s]
  1%|          | 16/2814 [00:01<03:54, 11.92it/s]
  1%|          | 18/2814 [00:01<03:55, 11.89it/s]
  1%|          | 20/2814 [00:01<03:49, 12.19it/s]
  1%|          | 22/2814 [00:01<03:51, 12.04it/s]
  1%|          | 24/2814 [00:01<03:36, 12.86it/s]
  1%|          | 26/2814 [00:02<03:39, 12.67it/s]
  1%|          | 28/2814 [00:02<03:46, 12.27it/s]
  1%|          | 30/2814 [00:02<03:48, 12.16it/s]
  1%|          | 32/2814 [00:02<03:39, 12.70it/s]
  1%|          | 34/2814 [00:02<03:36, 12.82it/s]
  1%|▏         | 36/2814 [00:02<03:33, 13.04it/s]
  1%|▏         | 38/2814 [00:03<03:41, 12.51it/s]
  1%|▏         | 40/2814 [00:03<03:49, 12.07it/s]
  1%|▏         | 42/2814 [00:03<03:44, 12.34it/s]
  2%|▏         | 44/2814 [00:03<03:49, 12.08it/s]
  2%|▏         | 46/2814 [00:03<03:52, 11.92it/s]
  2%|▏         | 48/2814 [00:03<03:51, 11.93it/s]
  2%|▏         | 50/2814 [00:04<03:49, 12.04it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.94it/s]
  2%|▏         | 54/2814 [00:04<03:50, 11.97it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.08it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.04it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.80it/s]
  2%|▏         | 62/2814 [00:05<03:29, 13.15it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.62it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.08it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.91it/s]
  2%|▏         | 70/2814 [00:05<03:55, 11.64it/s]
  3%|▎         | 72/2814 [00:05<03:55, 11.62it/s]
  3%|▎         | 74/2814 [00:06<03:50, 11.90it/s]
  3%|▎         | 76/2814 [00:06<03:51, 11.81it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.76it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.29it/s]
  3%|▎         | 82/2814 [00:06<03:47, 12.00it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.12it/s]
  3%|▎         | 86/2814 [00:07<03:43, 12.19it/s]
  3%|▎         | 88/2814 [00:07<03:42, 12.24it/s]
  3%|▎         | 90/2814 [00:07<03:43, 12.18it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.68it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.18it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.32it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.20it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.02it/s]
  4%|▎         | 102/2814 [00:08<03:41, 12.25it/s]
  4%|▎         | 104/2814 [00:08<03:30, 12.86it/s]
  4%|▍         | 106/2814 [00:08<03:38, 12.40it/s]
  4%|▍         | 108/2814 [00:08<03:40, 12.27it/s]
  4%|▍         | 110/2814 [00:09<03:32, 12.73it/s]
  4%|▍         | 112/2814 [00:09<03:40, 12.27it/s]
  4%|▍         | 114/2814 [00:09<03:42, 12.13it/s]
  4%|▍         | 116/2814 [00:09<03:37, 12.43it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.05it/s]
  4%|▍         | 120/2814 [00:09<03:36, 12.42it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.04it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.21it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.94it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.09it/s]
  5%|▍         | 130/2814 [00:10<03:44, 11.94it/s]
  5%|▍         | 132/2814 [00:10<03:34, 12.50it/s]
  5%|▍         | 134/2814 [00:10<03:32, 12.62it/s]
  5%|▍         | 136/2814 [00:11<03:34, 12.51it/s]
  5%|▍         | 138/2814 [00:11<03:35, 12.43it/s]
  5%|▍         | 140/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 142/2814 [00:11<03:34, 12.46it/s]
  5%|▌         | 144/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 146/2814 [00:11<03:39, 12.16it/s]
  5%|▌         | 148/2814 [00:12<03:41, 12.04it/s]
  5%|▌         | 150/2814 [00:12<03:35, 12.37it/s]
  5%|▌         | 152/2814 [00:12<03:40, 12.09it/s]
  5%|▌         | 154/2814 [00:12<03:43, 11.91it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.41it/s]
  6%|▌         | 158/2814 [00:12<03:34, 12.37it/s]
  6%|▌         | 160/2814 [00:13<03:40, 12.02it/s]
  6%|▌         | 162/2814 [00:13<03:38, 12.14it/s]
  6%|▌         | 164/2814 [00:13<03:38, 12.13it/s]
  6%|▌         | 166/2814 [00:13<03:36, 12.22it/s]
  6%|▌         | 168/2814 [00:13<03:32, 12.43it/s]
  6%|▌         | 170/2814 [00:13<03:36, 12.21it/s]
  6%|▌         | 172/2814 [00:14<03:40, 11.98it/s]
  6%|▌         | 174/2814 [00:14<03:34, 12.32it/s]
  6%|▋         | 176/2814 [00:14<03:29, 12.57it/s]
  6%|▋         | 178/2814 [00:14<03:22, 13.00it/s]
  6%|▋         | 180/2814 [00:14<03:31, 12.44it/s]
  6%|▋         | 182/2814 [00:14<03:38, 12.06it/s]
  7%|▋         | 184/2814 [00:15<03:42, 11.82it/s]
  7%|▋         | 186/2814 [00:15<03:44, 11.71it/s]
  7%|▋         | 188/2814 [00:15<03:39, 11.95it/s]
  7%|▋         | 190/2814 [00:15<03:40, 11.90it/s]
  7%|▋         | 192/2814 [00:15<03:38, 12.03it/s]
  7%|▋         | 194/2814 [00:15<03:40, 11.90it/s]
  7%|▋         | 196/2814 [00:16<03:42, 11.78it/s]
  7%|▋         | 198/2814 [00:16<03:40, 11.88it/s]
  7%|▋         | 200/2814 [00:16<03:38, 11.95it/s]
  7%|▋         | 202/2814 [00:16<03:40, 11.84it/s]
  7%|▋         | 204/2814 [00:16<03:42, 11.76it/s]
  7%|▋         | 206/2814 [00:16<03:46, 11.53it/s]
  7%|▋         | 208/2814 [00:17<03:29, 12.46it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.55it/s]
  8%|▊         | 214/2814 [00:17<03:27, 12.50it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.53it/s]
  8%|▊         | 218/2814 [00:17<03:21, 12.86it/s]
  8%|▊         | 220/2814 [00:18<03:24, 12.71it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.90it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.43it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.10it/s]
  8%|▊         | 228/2814 [00:18<03:23, 12.68it/s]
  8%|▊         | 230/2814 [00:18<03:31, 12.25it/s]
  8%|▊         | 232/2814 [00:19<03:36, 11.94it/s]
  8%|▊         | 234/2814 [00:19<03:32, 12.15it/s]
  8%|▊         | 236/2814 [00:19<03:32, 12.12it/s]
  8%|▊         | 238/2814 [00:19<03:32, 12.11it/s]
  9%|▊         | 240/2814 [00:19<03:28, 12.32it/s]
  9%|▊         | 242/2814 [00:19<03:32, 12.09it/s]
  9%|▊         | 244/2814 [00:20<03:31, 12.14it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.33it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.82it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.56it/s]
  9%|▉         | 252/2814 [00:20<03:30, 12.18it/s]
  9%|▉         | 254/2814 [00:20<03:19, 12.83it/s]
  9%|▉         | 256/2814 [00:20<03:26, 12.41it/s]
  9%|▉         | 258/2814 [00:21<03:30, 12.13it/s]
  9%|▉         | 260/2814 [00:21<03:35, 11.88it/s]
  9%|▉         | 262/2814 [00:21<03:39, 11.65it/s]
  9%|▉         | 264/2814 [00:21<03:32, 11.99it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.77it/s]
 10%|▉         | 268/2814 [00:22<03:39, 11.62it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.96it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.24it/s]
 10%|▉         | 274/2814 [00:22<03:30, 12.05it/s]
 10%|▉         | 276/2814 [00:22<03:31, 11.98it/s]
 10%|▉         | 278/2814 [00:22<03:30, 12.07it/s]
 10%|▉         | 280/2814 [00:22<03:27, 12.23it/s]
 10%|█         | 282/2814 [00:23<03:30, 12.04it/s]
 10%|█         | 284/2814 [00:23<03:31, 11.95it/s]
 10%|█         | 286/2814 [00:23<03:25, 12.29it/s]
 10%|█         | 288/2814 [00:23<03:27, 12.17it/s]
 10%|█         | 290/2814 [00:23<03:28, 12.10it/s]
 10%|█         | 292/2814 [00:23<03:32, 11.88it/s]
 10%|█         | 294/2814 [00:24<03:34, 11.73it/s]
 11%|█         | 296/2814 [00:24<03:30, 11.98it/s]
 11%|█         | 298/2814 [00:24<03:33, 11.78it/s]
 11%|█         | 300/2814 [00:24<03:22, 12.39it/s]
 11%|█         | 302/2814 [00:24<03:29, 11.99it/s]
 11%|█         | 304/2814 [00:24<03:27, 12.11it/s]
 11%|█         | 306/2814 [00:25<03:29, 11.99it/s]
 11%|█         | 308/2814 [00:25<03:32, 11.82it/s]
 11%|█         | 310/2814 [00:25<03:26, 12.10it/s]
 11%|█         | 312/2814 [00:25<03:28, 11.99it/s]
 11%|█         | 314/2814 [00:25<03:26, 12.10it/s]
 11%|█         | 316/2814 [00:25<03:23, 12.27it/s]
 11%|█▏        | 318/2814 [00:26<03:27, 12.02it/s]
 11%|█▏        | 320/2814 [00:26<03:24, 12.18it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.58it/s]
 12%|█▏        | 324/2814 [00:26<03:24, 12.16it/s]
 12%|█▏        | 326/2814 [00:26<03:28, 11.94it/s]
 12%|█▏        | 328/2814 [00:26<03:20, 12.39it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 332/2814 [00:27<03:23, 12.18it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.02it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.36it/s]
 12%|█▏        | 338/2814 [00:27<03:25, 12.04it/s]
 12%|█▏        | 340/2814 [00:27<03:29, 11.80it/s]
 12%|█▏        | 342/2814 [00:28<03:32, 11.62it/s]
 12%|█▏        | 344/2814 [00:28<03:27, 11.93it/s]
 12%|█▏        | 346/2814 [00:28<03:24, 12.07it/s]
 12%|█▏        | 348/2814 [00:28<03:26, 11.95it/s]
 12%|█▏        | 350/2814 [00:28<03:23, 12.10it/s]
 13%|█▎        | 352/2814 [00:28<03:26, 11.93it/s]
 13%|█▎        | 354/2814 [00:29<03:28, 11.80it/s]
 13%|█▎        | 356/2814 [00:29<03:25, 11.98it/s]
 13%|█▎        | 358/2814 [00:29<03:42, 11.05it/s]
 13%|█▎        | 360/2814 [00:29<03:41, 11.07it/s]
 13%|█▎        | 362/2814 [00:29<03:32, 11.53it/s]
 13%|█▎        | 364/2814 [00:30<03:32, 11.55it/s]
 13%|█▎        | 366/2814 [00:30<03:32, 11.51it/s]
 13%|█▎        | 368/2814 [00:30<03:30, 11.64it/s]
 13%|█▎        | 370/2814 [00:30<03:31, 11.54it/s]
 13%|█▎        | 372/2814 [00:30<03:21, 12.13it/s]
 13%|█▎        | 374/2814 [00:30<03:25, 11.88it/s]
 13%|█▎        | 376/2814 [00:31<03:27, 11.72it/s]
 13%|█▎        | 378/2814 [00:31<03:28, 11.69it/s]
 14%|█▎        | 380/2814 [00:31<03:24, 11.89it/s]
 14%|█▎        | 382/2814 [00:31<03:26, 11.76it/s]
 14%|█▎        | 384/2814 [00:31<03:23, 11.95it/s]
 14%|█▎        | 386/2814 [00:31<03:26, 11.79it/s]
 14%|█▍        | 388/2814 [00:32<03:24, 11.89it/s]
 14%|█▍        | 390/2814 [00:32<03:26, 11.74it/s]
 14%|█▍        | 392/2814 [00:32<03:10, 12.68it/s]
 14%|█▍        | 394/2814 [00:32<03:18, 12.17it/s]
 14%|█▍        | 396/2814 [00:32<03:21, 11.98it/s]
 14%|█▍        | 398/2814 [00:32<03:19, 12.12it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.85it/s]
 14%|█▍        | 402/2814 [00:33<03:18, 12.14it/s]
 14%|█▍        | 404/2814 [00:33<03:20, 12.03it/s]
 14%|█▍        | 406/2814 [00:33<03:24, 11.79it/s]
 14%|█▍        | 408/2814 [00:33<03:16, 12.23it/s]
 15%|█▍        | 410/2814 [00:33<03:21, 11.94it/s]
 15%|█▍        | 412/2814 [00:34<03:20, 12.01it/s]
 15%|█▍        | 414/2814 [00:34<03:23, 11.81it/s]
 15%|█▍        | 416/2814 [00:34<03:11, 12.49it/s]
 15%|█▍        | 418/2814 [00:34<03:12, 12.44it/s]
 15%|█▍        | 420/2814 [00:34<03:14, 12.28it/s]
 15%|█▍        | 422/2814 [00:34<03:12, 12.45it/s]
 15%|█▌        | 424/2814 [00:35<03:16, 12.18it/s]
 15%|█▌        | 426/2814 [00:35<03:13, 12.37it/s]
 15%|█▌        | 428/2814 [00:35<03:14, 12.28it/s]
 15%|█▌        | 430/2814 [00:35<03:09, 12.60it/s]
 15%|█▌        | 432/2814 [00:35<03:14, 12.22it/s]
 15%|█▌        | 434/2814 [00:35<03:10, 12.50it/s]
 15%|█▌        | 436/2814 [00:35<03:11, 12.44it/s]
 16%|█▌        | 438/2814 [00:36<03:14, 12.24it/s]
 16%|█▌        | 440/2814 [00:36<03:17, 12.05it/s]
 16%|█▌        | 442/2814 [00:36<03:19, 11.88it/s]
 16%|█▌        | 444/2814 [00:36<03:13, 12.23it/s]
 16%|█▌        | 446/2814 [00:36<03:15, 12.09it/s]
 16%|█▌        | 448/2814 [00:36<03:21, 11.75it/s]
 16%|█▌        | 450/2814 [00:37<03:08, 12.54it/s]
 16%|█▌        | 452/2814 [00:37<03:06, 12.64it/s]
 16%|█▌        | 454/2814 [00:37<03:12, 12.26it/s]
 16%|█▌        | 456/2814 [00:37<03:08, 12.50it/s]
 16%|█▋        | 458/2814 [00:37<03:03, 12.84it/s]
 16%|█▋        | 460/2814 [00:37<03:11, 12.27it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.96it/s]
 16%|█▋        | 464/2814 [00:38<03:18, 11.86it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.26it/s]
 17%|█▋        | 468/2814 [00:38<03:11, 12.27it/s]
 17%|█▋        | 470/2814 [00:38<03:14, 12.06it/s]
 17%|█▋        | 472/2814 [00:38<03:10, 12.32it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.52it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 12.00it/s]
 17%|█▋        | 480/2814 [00:39<03:35, 10.82it/s]
 17%|█▋        | 482/2814 [00:39<03:29, 11.14it/s]
 17%|█▋        | 484/2814 [00:39<03:26, 11.28it/s]
 17%|█▋        | 486/2814 [00:40<03:26, 11.28it/s]
 17%|█▋        | 488/2814 [00:40<03:24, 11.36it/s]
 17%|█▋        | 490/2814 [00:40<03:17, 11.77it/s]
 17%|█▋        | 492/2814 [00:40<03:18, 11.72it/s]
 18%|█▊        | 494/2814 [00:40<03:17, 11.72it/s]
 18%|█▊        | 496/2814 [00:40<03:08, 12.29it/s]
 18%|█▊        | 498/2814 [00:41<03:12, 12.05it/s]
 18%|█▊        | 500/2814 [00:41<03:09, 12.20it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.39it/s]
 18%|█▊        | 504/2814 [00:41<03:02, 12.65it/s]
 18%|█▊        | 506/2814 [00:41<03:07, 12.31it/s]
 18%|█▊        | 508/2814 [00:41<03:05, 12.46it/s]
 18%|█▊        | 510/2814 [00:42<02:57, 12.98it/s]
 18%|█▊        | 512/2814 [00:42<03:03, 12.56it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.67it/s]
 18%|█▊        | 516/2814 [00:42<03:06, 12.30it/s]
 18%|█▊        | 518/2814 [00:42<03:03, 12.52it/s]
 18%|█▊        | 520/2814 [00:42<03:08, 12.19it/s]
 19%|█▊        | 522/2814 [00:43<03:12, 11.91it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.31it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.66it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.31it/s]
 19%|█▉        | 530/2814 [00:43<03:08, 12.10it/s]
 19%|█▉        | 532/2814 [00:43<03:07, 12.16it/s]
 19%|█▉        | 534/2814 [00:44<03:01, 12.54it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.15it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.01it/s]
 19%|█▉        | 540/2814 [00:44<03:13, 11.75it/s]
 19%|█▉        | 542/2814 [00:44<03:12, 11.79it/s]
 19%|█▉        | 544/2814 [00:44<03:02, 12.42it/s]
 19%|█▉        | 546/2814 [00:45<03:01, 12.48it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.16it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.51it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.32it/s]
 20%|█▉        | 554/2814 [00:45<03:04, 12.26it/s]
 20%|█▉        | 556/2814 [00:45<02:57, 12.71it/s]
 20%|█▉        | 558/2814 [00:45<03:00, 12.50it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.48it/s]
 20%|█▉        | 562/2814 [00:46<03:06, 12.05it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.96it/s]
 20%|██        | 566/2814 [00:46<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:46<03:02, 12.34it/s]
 20%|██        | 570/2814 [00:46<03:06, 12.01it/s]
 20%|██        | 572/2814 [00:47<03:09, 11.80it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.02it/s]
 20%|██        | 576/2814 [00:47<02:57, 12.63it/s]
 21%|██        | 578/2814 [00:47<02:57, 12.59it/s]
 21%|██        | 580/2814 [00:47<03:04, 12.12it/s]
 21%|██        | 582/2814 [00:47<02:55, 12.71it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.49it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.27it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.62it/s]
 21%|██        | 590/2814 [00:48<02:59, 12.39it/s]
 21%|██        | 592/2814 [00:48<02:57, 12.51it/s]
 21%|██        | 594/2814 [00:48<03:02, 12.18it/s]
 21%|██        | 596/2814 [00:49<03:05, 11.97it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.75it/s]
 21%|██▏       | 600/2814 [00:49<02:51, 12.91it/s]
 21%|██▏       | 602/2814 [00:49<02:47, 13.19it/s]
 21%|██▏       | 604/2814 [00:49<02:50, 12.99it/s]
 22%|██▏       | 606/2814 [00:49<02:54, 12.68it/s]
 22%|██▏       | 608/2814 [00:50<02:53, 12.68it/s]
 22%|██▏       | 610/2814 [00:50<02:48, 13.06it/s]
 22%|██▏       | 612/2814 [00:50<02:56, 12.50it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.04it/s]
 22%|██▏       | 616/2814 [00:50<03:05, 11.83it/s]
 22%|██▏       | 618/2814 [00:50<03:01, 12.13it/s]
 22%|██▏       | 620/2814 [00:51<03:00, 12.19it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.09it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.19it/s]
 22%|██▏       | 626/2814 [00:51<03:00, 12.15it/s]
 22%|██▏       | 628/2814 [00:51<02:51, 12.72it/s]
 22%|██▏       | 630/2814 [00:51<02:53, 12.61it/s]
 22%|██▏       | 632/2814 [00:51<02:52, 12.66it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.20it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.94it/s]
 23%|██▎       | 638/2814 [00:52<03:05, 11.75it/s]
 23%|██▎       | 640/2814 [00:52<03:06, 11.66it/s]
 23%|██▎       | 642/2814 [00:52<03:02, 11.90it/s]
 23%|██▎       | 644/2814 [00:52<02:52, 12.61it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.12it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.97it/s]
 23%|██▎       | 650/2814 [00:53<02:57, 12.22it/s]
 23%|██▎       | 652/2814 [00:53<03:02, 11.88it/s]
 23%|██▎       | 654/2814 [00:53<03:03, 11.80it/s]
 23%|██▎       | 656/2814 [00:53<02:55, 12.32it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.29it/s]
 23%|██▎       | 660/2814 [00:54<02:54, 12.37it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.34it/s]
 24%|██▎       | 664/2814 [00:54<02:57, 12.09it/s]
 24%|██▎       | 666/2814 [00:54<02:55, 12.23it/s]
 24%|██▎       | 668/2814 [00:54<02:58, 12.05it/s]
 24%|██▍       | 670/2814 [00:55<03:02, 11.78it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.04it/s]
 24%|██▍       | 674/2814 [00:55<02:56, 12.16it/s]
 24%|██▍       | 676/2814 [00:55<02:54, 12.28it/s]
 24%|██▍       | 678/2814 [00:55<02:53, 12.31it/s]
 24%|██▍       | 680/2814 [00:55<02:55, 12.14it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.10it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.76it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.91it/s]
 24%|██▍       | 688/2814 [00:56<02:56, 12.03it/s]
 25%|██▍       | 690/2814 [00:56<02:57, 11.98it/s]
 25%|██▍       | 692/2814 [00:56<03:01, 11.72it/s]
 25%|██▍       | 694/2814 [00:57<02:52, 12.27it/s]
 25%|██▍       | 696/2814 [00:57<02:53, 12.24it/s]
 25%|██▍       | 698/2814 [00:57<02:49, 12.47it/s]
 25%|██▍       | 700/2814 [00:57<02:49, 12.50it/s]
 25%|██▍       | 702/2814 [00:57<02:49, 12.48it/s]
 25%|██▌       | 704/2814 [00:57<02:53, 12.16it/s]
 25%|██▌       | 706/2814 [00:58<02:47, 12.57it/s]
 25%|██▌       | 708/2814 [00:58<02:43, 12.85it/s]
 25%|██▌       | 710/2814 [00:58<02:50, 12.37it/s]
 25%|██▌       | 712/2814 [00:58<02:53, 12.15it/s]
 25%|██▌       | 714/2814 [00:58<02:51, 12.23it/s]
 25%|██▌       | 716/2814 [00:58<02:50, 12.30it/s]
 26%|██▌       | 718/2814 [00:59<02:51, 12.19it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 724/2814 [00:59<02:51, 12.21it/s]
 26%|██▌       | 726/2814 [00:59<02:42, 12.81it/s]
 26%|██▌       | 728/2814 [00:59<02:50, 12.24it/s]
 26%|██▌       | 730/2814 [01:00<02:47, 12.47it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.44it/s]
 26%|██▌       | 734/2814 [01:00<02:51, 12.16it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.25it/s]
 26%|██▌       | 738/2814 [01:00<02:51, 12.07it/s]
 26%|██▋       | 740/2814 [01:00<02:47, 12.38it/s]
 26%|██▋       | 742/2814 [01:01<02:47, 12.40it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.63it/s]
 27%|██▋       | 746/2814 [01:01<02:48, 12.29it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.28it/s]
 27%|██▋       | 750/2814 [01:01<02:53, 11.92it/s]
 27%|██▋       | 752/2814 [01:01<02:52, 11.95it/s]
 27%|██▋       | 754/2814 [01:02<02:53, 11.84it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.06it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.93it/s]
 27%|██▋       | 760/2814 [01:02<02:48, 12.16it/s]
 27%|██▋       | 762/2814 [01:02<02:48, 12.16it/s]
 27%|██▋       | 764/2814 [01:02<02:44, 12.45it/s]
 27%|██▋       | 766/2814 [01:02<02:45, 12.35it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.11it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.91it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.79it/s]
 28%|██▊       | 774/2814 [01:03<02:46, 12.24it/s]
 28%|██▊       | 776/2814 [01:03<02:43, 12.44it/s]
 28%|██▊       | 778/2814 [01:03<02:45, 12.31it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.29it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.11it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 11.99it/s]
 28%|██▊       | 786/2814 [01:04<02:47, 12.13it/s]
 28%|██▊       | 788/2814 [01:04<02:47, 12.12it/s]
 28%|██▊       | 790/2814 [01:04<02:45, 12.21it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.28it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.12it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.51it/s]
 28%|██▊       | 798/2814 [01:05<02:44, 12.26it/s]
 28%|██▊       | 800/2814 [01:05<02:46, 12.09it/s]
 29%|██▊       | 802/2814 [01:05<02:48, 11.95it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.01it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.16it/s]
 29%|██▊       | 808/2814 [01:06<02:47, 12.01it/s]
 29%|██▉       | 810/2814 [01:06<02:43, 12.23it/s]
 29%|██▉       | 812/2814 [01:06<02:38, 12.61it/s]
 29%|██▉       | 814/2814 [01:06<02:41, 12.36it/s]
 29%|██▉       | 816/2814 [01:07<02:39, 12.49it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.64it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.49it/s]
 29%|██▉       | 822/2814 [01:07<02:44, 12.11it/s]
 29%|██▉       | 824/2814 [01:07<02:40, 12.39it/s]
 29%|██▉       | 826/2814 [01:07<02:43, 12.18it/s]
 29%|██▉       | 828/2814 [01:08<02:45, 11.97it/s]
 29%|██▉       | 830/2814 [01:08<02:44, 12.08it/s]
 30%|██▉       | 832/2814 [01:08<02:46, 11.92it/s]
 30%|██▉       | 834/2814 [01:08<02:49, 11.71it/s]
 30%|██▉       | 836/2814 [01:08<02:42, 12.17it/s]
 30%|██▉       | 838/2814 [01:08<02:41, 12.22it/s]
 30%|██▉       | 840/2814 [01:09<02:45, 11.93it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.83it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.75it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.11it/s]
 30%|███       | 848/2814 [01:09<02:37, 12.49it/s]
 30%|███       | 850/2814 [01:09<02:41, 12.18it/s]
 30%|███       | 852/2814 [01:10<02:41, 12.15it/s]
 30%|███       | 854/2814 [01:10<02:42, 12.06it/s]
 30%|███       | 856/2814 [01:10<02:45, 11.86it/s]
 30%|███       | 858/2814 [01:10<02:46, 11.75it/s]
 31%|███       | 860/2814 [01:10<02:43, 11.92it/s]
 31%|███       | 862/2814 [01:10<02:43, 11.90it/s]
 31%|███       | 864/2814 [01:11<02:39, 12.20it/s]
 31%|███       | 866/2814 [01:11<02:35, 12.56it/s]
 31%|███       | 868/2814 [01:11<02:34, 12.60it/s]
 31%|███       | 870/2814 [01:11<02:39, 12.21it/s]
 31%|███       | 872/2814 [01:11<02:39, 12.18it/s]
 31%|███       | 874/2814 [01:11<02:38, 12.26it/s]
 31%|███       | 876/2814 [01:12<02:41, 12.00it/s]
 31%|███       | 878/2814 [01:12<02:38, 12.23it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.06it/s]
 31%|███▏      | 882/2814 [01:12<02:42, 11.92it/s]
 31%|███▏      | 884/2814 [01:12<02:41, 11.93it/s]
 31%|███▏      | 886/2814 [01:12<02:42, 11.87it/s]
 32%|███▏      | 888/2814 [01:13<02:44, 11.69it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.88it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.69it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.60it/s]
 32%|███▏      | 896/2814 [01:13<02:42, 11.84it/s]
 32%|███▏      | 898/2814 [01:13<02:35, 12.36it/s]
 32%|███▏      | 900/2814 [01:14<02:34, 12.39it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.79it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.67it/s]
 32%|███▏      | 906/2814 [01:14<02:28, 12.89it/s]
 32%|███▏      | 908/2814 [01:14<02:33, 12.43it/s]
 32%|███▏      | 910/2814 [01:14<02:35, 12.22it/s]
 32%|███▏      | 912/2814 [01:15<02:38, 12.00it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.30it/s]
 33%|███▎      | 916/2814 [01:15<02:36, 12.10it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.04it/s]
 33%|███▎      | 920/2814 [01:15<02:35, 12.15it/s]
 33%|███▎      | 922/2814 [01:15<02:35, 12.19it/s]
 33%|███▎      | 924/2814 [01:16<02:39, 11.82it/s]
 33%|███▎      | 926/2814 [01:16<02:29, 12.66it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.78it/s]
 33%|███▎      | 930/2814 [01:16<02:32, 12.38it/s]
 33%|███▎      | 932/2814 [01:16<02:35, 12.09it/s]
 33%|███▎      | 934/2814 [01:16<02:36, 11.98it/s]
 33%|███▎      | 936/2814 [01:17<02:37, 11.90it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.46it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.46it/s]{'loss': 0.8485, 'learning_rate': 3.7844403673093306e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.27it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.33it/s]

 21%|██        | 66/313 [00:00<00:01, 205.88it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.96it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.25it/s]

 40%|████      | 126/313 [00:00<00:01, 185.08it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.88it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.67it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.69it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.88it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.12it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.84it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.59it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.49it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.36it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.36it/s]
 33%|███▎      | 938/2814 [01:18<02:30, 12.46it/s]

                                                  
 33%|███▎      | 938/2814 [01:18<02:37, 11.89it/s]
[I 2023-10-26 22:34:39,940] Trial 10 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7245466113090515, 'eval_accuracy': 0.676, 'eval_f1': 0.6731244521147167, 'eval_runtime': 1.7341, 'eval_samples_per_second': 1441.686, 'eval_steps_per_second': 180.499, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:10,  3.69it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:08,  3.72it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.84it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:44,  3.82it/s]
 11%|█         | 78/705 [00:20<02:42,  3.86it/s]
 11%|█         | 79/705 [00:20<02:44,  3.81it/s]
 11%|█▏        | 80/705 [00:21<02:44,  3.80it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.74it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.78it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:38<02:22,  3.91it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.75it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8414, 'learning_rate': 1.5359840509543407e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.93it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.66it/s]

 21%|██        | 65/313 [00:00<00:01, 204.72it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.19it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.22it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.78it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.32it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.17it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.97it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.80it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.76it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.93it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.34it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.97it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.94it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.94it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 22:35:43,990] Trial 11 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7145503163337708, 'eval_accuracy': 0.69, 'eval_f1': 0.6880584547140108, 'eval_runtime': 1.7329, 'eval_samples_per_second': 1442.673, 'eval_steps_per_second': 180.623, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.71it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:08,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.74it/s]
  1%|          | 6/705 [00:01<03:02,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.81it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:54,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.84it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.89it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.84it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:42,  3.87it/s]
 11%|█         | 78/705 [00:20<02:40,  3.91it/s]
 11%|█         | 79/705 [00:20<02:43,  3.84it/s]
 11%|█▏        | 80/705 [00:21<02:43,  3.82it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.78it/s]
 12%|█▏        | 82/705 [00:21<02:45,  3.75it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.78it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.80it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:39<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:23,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.79it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.83it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:56<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8337, 'learning_rate': 2.0092643403704745e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.17it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.25it/s]

 21%|██        | 66/313 [00:00<00:01, 205.74it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.99it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.34it/s]

 40%|████      | 126/313 [00:00<00:01, 185.17it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.04it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.91it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.82it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.94it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.14it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.80it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.56it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.51it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.35it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.35it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:05,  1.03s/it]
 34%|███▎      | 237/705 [01:04<06:15,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:59,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:05,  1.90it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.98it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:16<01:50,  3.83it/s]
 40%|████      | 284/705 [01:16<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.84it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.82it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.84it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:46,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:21<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:22<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:25<01:41,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:54,  3.35it/s]
 46%|████▌     | 323/705 [01:27<01:50,  3.45it/s]
 46%|████▌     | 324/705 [01:27<01:48,  3.52it/s]
 46%|████▌     | 325/705 [01:27<01:45,  3.61it/s]
 46%|████▌     | 326/705 [01:28<01:42,  3.68it/s]
 46%|████▋     | 327/705 [01:28<01:42,  3.69it/s]
 47%|████▋     | 328/705 [01:28<01:42,  3.69it/s]
 47%|████▋     | 329/705 [01:28<01:39,  3.77it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.76it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.76it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.74it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.77it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:40,  3.42it/s]
 51%|█████     | 361/705 [01:37<01:38,  3.51it/s]
 51%|█████▏    | 362/705 [01:37<01:35,  3.58it/s]
 51%|█████▏    | 363/705 [01:37<01:34,  3.62it/s]
 52%|█████▏    | 364/705 [01:38<01:33,  3.64it/s]
 52%|█████▏    | 365/705 [01:38<01:32,  3.67it/s]
 52%|█████▏    | 366/705 [01:38<01:31,  3.70it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.76it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.83it/s]
 54%|█████▍    | 379/705 [01:42<01:33,  3.49it/s]
 54%|█████▍    | 380/705 [01:42<01:30,  3.58it/s]
 54%|█████▍    | 381/705 [01:42<01:29,  3.63it/s]
 54%|█████▍    | 382/705 [01:43<01:27,  3.68it/s]
 54%|█████▍    | 383/705 [01:43<01:25,  3.75it/s]
 54%|█████▍    | 384/705 [01:43<01:26,  3.73it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.72it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.77it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.77it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:19,  3.78it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.88it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.80it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.81it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]{'eval_loss': 0.6991425156593323, 'eval_accuracy': 0.6924, 'eval_f1': 0.6923072188984468, 'eval_runtime': 1.734, 'eval_samples_per_second': 1441.759, 'eval_steps_per_second': 180.508, 'epoch': 1.0}
{'loss': 0.6048, 'learning_rate': 1.0088890861605985e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.65it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.75it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.29it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.39it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.95it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.72it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.48it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.76it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.60it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.57it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.76it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.06it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.75it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.80it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.80it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:08<04:03,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:07,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.89it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.21it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.79it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.83it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.83it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:18<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:49,  3.57it/s]
 75%|███████▌  | 531/705 [02:24<00:47,  3.64it/s]
 75%|███████▌  | 532/705 [02:25<00:47,  3.66it/s]
 76%|███████▌  | 533/705 [02:25<00:46,  3.70it/s]
 76%|███████▌  | 534/705 [02:25<00:46,  3.71it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.79it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.76it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.76it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.74it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.72it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.77it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.77it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:44,  3.48it/s]
 78%|███████▊  | 550/705 [02:29<00:43,  3.58it/s]
 78%|███████▊  | 551/705 [02:30<00:42,  3.64it/s]
 78%|███████▊  | 552/705 [02:30<00:41,  3.67it/s]
 78%|███████▊  | 553/705 [02:30<00:41,  3.68it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.68it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.68it/s]
 79%|███████▉  | 556/705 [02:31<00:39,  3.81it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.80it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.82it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.80it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.85it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.02it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.96it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.15it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.17it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:39<00:34,  3.41it/s]
 84%|████████▎ | 589/705 [02:40<00:33,  3.50it/s]
 84%|████████▎ | 590/705 [02:40<00:32,  3.55it/s]
 84%|████████▍ | 591/705 [02:40<00:31,  3.60it/s]
 84%|████████▍ | 592/705 [02:40<00:30,  3.69it/s]
 84%|████████▍ | 593/705 [02:41<00:30,  3.70it/s]
 84%|████████▍ | 594/705 [02:41<00:30,  3.70it/s]
 84%|████████▍ | 595/705 [02:41<00:29,  3.78it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.78it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.78it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.76it/s]
 85%|████████▍ | 599/705 [02:42<00:27,  3.84it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.82it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.04it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.93it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.92it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 616/705 [02:47<00:23,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:47<00:21,  3.96it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:48<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.80it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.85it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.78it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.80it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.76it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.82it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.86it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.78it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.75it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.79it/s]
100%|██████████| 705/705 [03:10<00:00,  4.53it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.53it/s]{'eval_loss': 0.6820339560508728, 'eval_accuracy': 0.706, 'eval_f1': 0.702598566754131, 'eval_runtime': 1.7331, 'eval_samples_per_second': 1442.464, 'eval_steps_per_second': 180.596, 'epoch': 2.0}
{'loss': 0.4941, 'learning_rate': 8.51383195072235e-08, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.80it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.87it/s]

 21%|██        | 65/313 [00:00<00:01, 204.99it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.25it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.41it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.06it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.71it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.59it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.21it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.04it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.90it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.04it/s]

 83%|████████▎ | 259/313 [00:01<00:00, 184.10it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.85it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.15it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.15it/s]
100%|██████████| 705/705 [03:12<00:00,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.53it/s]
100%|██████████| 705/705 [03:13<00:00,  3.65it/s]
[I 2023-10-26 22:38:57,943] Trial 12 finished with value: 0.7137972810664746 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 2.6988847283789848e-05, 'per_device_train_batch_size': 128, 'weight_decay': 1.5635579416386512e-05}. Best is trial 6 with value: 0.716991552355688.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6828380823135376, 'eval_accuracy': 0.7148, 'eval_f1': 0.7137972810664746, 'eval_runtime': 1.7301, 'eval_samples_per_second': 1445.014, 'eval_steps_per_second': 180.916, 'epoch': 3.0}
{'train_runtime': 193.2152, 'train_samples_per_second': 465.802, 'train_steps_per_second': 3.649, 'train_loss': 0.6441856654823249, 'epoch': 3.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<04:00, 11.69it/s]
  0%|          | 4/2814 [00:00<04:00, 11.67it/s]
  0%|          | 6/2814 [00:00<04:01, 11.62it/s]
  0%|          | 8/2814 [00:00<03:58, 11.78it/s]
  0%|          | 10/2814 [00:00<04:00, 11.64it/s]
  0%|          | 12/2814 [00:01<04:03, 11.52it/s]
  0%|          | 14/2814 [00:01<04:02, 11.55it/s]
  1%|          | 16/2814 [00:01<03:54, 11.91it/s]
  1%|          | 18/2814 [00:01<03:55, 11.87it/s]
  1%|          | 20/2814 [00:01<03:49, 12.18it/s]
  1%|          | 22/2814 [00:01<03:51, 12.04it/s]
  1%|          | 24/2814 [00:01<03:36, 12.86it/s]
  1%|          | 26/2814 [00:02<03:39, 12.68it/s]
  1%|          | 28/2814 [00:02<03:46, 12.28it/s]
  1%|          | 30/2814 [00:02<03:48, 12.16it/s]
  1%|          | 32/2814 [00:02<03:38, 12.71it/s]
  1%|          | 34/2814 [00:02<03:36, 12.83it/s]
  1%|▏         | 36/2814 [00:02<03:37, 12.75it/s]
  1%|▏         | 38/2814 [00:03<03:45, 12.29it/s]
  1%|▏         | 40/2814 [00:03<03:52, 11.93it/s]
  1%|▏         | 42/2814 [00:03<03:46, 12.24it/s]
  2%|▏         | 44/2814 [00:03<03:50, 12.00it/s]
  2%|▏         | 46/2814 [00:03<03:53, 11.86it/s]
  2%|▏         | 48/2814 [00:03<03:52, 11.89it/s]
  2%|▏         | 50/2814 [00:04<03:49, 12.03it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.93it/s]
  2%|▏         | 54/2814 [00:04<03:50, 11.96it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.08it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.05it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.80it/s]
  2%|▏         | 62/2814 [00:05<03:29, 13.15it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.63it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.08it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.90it/s]
  2%|▏         | 70/2814 [00:05<03:55, 11.63it/s]
  3%|▎         | 72/2814 [00:05<03:56, 11.61it/s]
  3%|▎         | 74/2814 [00:06<03:50, 11.91it/s]
  3%|▎         | 76/2814 [00:06<03:51, 11.82it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.76it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.29it/s]
  3%|▎         | 82/2814 [00:06<03:47, 11.99it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.09it/s]
  3%|▎         | 86/2814 [00:07<03:44, 12.16it/s]
  3%|▎         | 88/2814 [00:07<03:43, 12.21it/s]
  3%|▎         | 90/2814 [00:07<03:44, 12.14it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.67it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.16it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.32it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.21it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.02it/s]
  4%|▎         | 102/2814 [00:08<03:35, 12.56it/s]
  4%|▎         | 104/2814 [00:08<03:26, 13.09it/s]
  4%|▍         | 106/2814 [00:08<03:35, 12.56it/s]
  4%|▍         | 108/2814 [00:08<03:38, 12.37it/s]
  4%|▍         | 110/2814 [00:09<03:31, 12.80it/s]
  4%|▍         | 112/2814 [00:09<03:39, 12.33it/s]
  4%|▍         | 114/2814 [00:09<03:41, 12.17it/s]
  4%|▍         | 116/2814 [00:09<03:36, 12.47it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.07it/s]
  4%|▍         | 120/2814 [00:09<03:36, 12.42it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.05it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.21it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.93it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.08it/s]
  5%|▍         | 130/2814 [00:10<03:44, 11.93it/s]
  5%|▍         | 132/2814 [00:10<03:34, 12.50it/s]
  5%|▍         | 134/2814 [00:11<03:32, 12.62it/s]
  5%|▍         | 136/2814 [00:11<03:34, 12.51it/s]
  5%|▍         | 138/2814 [00:11<03:35, 12.43it/s]
  5%|▍         | 140/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 142/2814 [00:11<03:34, 12.45it/s]
  5%|▌         | 144/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 146/2814 [00:11<03:39, 12.16it/s]
  5%|▌         | 148/2814 [00:12<03:41, 12.04it/s]
  5%|▌         | 150/2814 [00:12<03:35, 12.37it/s]
  5%|▌         | 152/2814 [00:12<03:40, 12.08it/s]
  5%|▌         | 154/2814 [00:12<03:43, 11.90it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.40it/s]
  6%|▌         | 158/2814 [00:12<03:34, 12.36it/s]
  6%|▌         | 160/2814 [00:13<04:27,  9.91it/s]
  6%|▌         | 162/2814 [00:13<04:11, 10.55it/s]
  6%|▌         | 164/2814 [00:13<04:01, 10.95it/s]
  6%|▌         | 166/2814 [00:13<03:53, 11.36it/s]
  6%|▌         | 168/2814 [00:13<03:44, 11.79it/s]
  6%|▌         | 170/2814 [00:14<03:44, 11.77it/s]
  6%|▌         | 172/2814 [00:14<03:46, 11.69it/s]
  6%|▌         | 174/2814 [00:14<03:38, 12.10it/s]
  6%|▋         | 176/2814 [00:14<03:32, 12.40it/s]
  6%|▋         | 178/2814 [00:14<03:24, 12.87it/s]
  6%|▋         | 180/2814 [00:14<03:33, 12.37it/s]
  6%|▋         | 182/2814 [00:15<03:39, 12.00it/s]
  7%|▋         | 184/2814 [00:15<03:43, 11.78it/s]
  7%|▋         | 186/2814 [00:15<03:44, 11.69it/s]
  7%|▋         | 188/2814 [00:15<03:39, 11.94it/s]
  7%|▋         | 190/2814 [00:15<03:40, 11.89it/s]
  7%|▋         | 192/2814 [00:15<03:38, 12.02it/s]
  7%|▋         | 194/2814 [00:16<03:40, 11.89it/s]
  7%|▋         | 196/2814 [00:16<03:42, 11.77it/s]
  7%|▋         | 198/2814 [00:16<03:40, 11.86it/s]
  7%|▋         | 200/2814 [00:16<03:38, 11.94it/s]
  7%|▋         | 202/2814 [00:16<03:40, 11.82it/s]
  7%|▋         | 204/2814 [00:16<03:42, 11.74it/s]
  7%|▋         | 206/2814 [00:17<03:46, 11.52it/s]
  7%|▋         | 208/2814 [00:17<03:29, 12.45it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.53it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 214/2814 [00:17<03:27, 12.50it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.53it/s]
  8%|▊         | 218/2814 [00:18<03:21, 12.88it/s]
  8%|▊         | 220/2814 [00:18<03:23, 12.72it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.92it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.44it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.11it/s]
  8%|▊         | 228/2814 [00:18<03:23, 12.69it/s]
  8%|▊         | 230/2814 [00:18<03:30, 12.25it/s]
  8%|▊         | 232/2814 [00:19<03:36, 11.94it/s]
  8%|▊         | 234/2814 [00:19<03:32, 12.15it/s]
  8%|▊         | 236/2814 [00:19<03:32, 12.12it/s]
  8%|▊         | 238/2814 [00:19<03:32, 12.11it/s]
  9%|▊         | 240/2814 [00:19<03:28, 12.32it/s]
  9%|▊         | 242/2814 [00:19<03:32, 12.09it/s]
  9%|▊         | 244/2814 [00:20<03:31, 12.14it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.33it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.81it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.56it/s]
  9%|▉         | 252/2814 [00:20<03:30, 12.17it/s]
  9%|▉         | 254/2814 [00:20<03:19, 12.82it/s]
  9%|▉         | 256/2814 [00:21<03:26, 12.41it/s]
  9%|▉         | 258/2814 [00:21<03:30, 12.11it/s]
  9%|▉         | 260/2814 [00:21<03:35, 11.87it/s]
  9%|▉         | 262/2814 [00:21<03:39, 11.65it/s]
  9%|▉         | 264/2814 [00:21<03:32, 11.99it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.78it/s]
 10%|▉         | 268/2814 [00:22<03:39, 11.62it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.97it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.24it/s]
 10%|▉         | 274/2814 [00:22<03:30, 12.05it/s]
 10%|▉         | 276/2814 [00:22<03:31, 11.98it/s]
 10%|▉         | 278/2814 [00:22<03:30, 12.08it/s]
 10%|▉         | 280/2814 [00:23<03:26, 12.24it/s]
 10%|█         | 282/2814 [00:23<04:11, 10.06it/s]
 10%|█         | 284/2814 [00:23<04:00, 10.52it/s]
 10%|█         | 286/2814 [00:23<03:45, 11.19it/s]
 10%|█         | 288/2814 [00:23<03:41, 11.38it/s]
 10%|█         | 290/2814 [00:24<03:38, 11.55it/s]
 10%|█         | 292/2814 [00:24<03:39, 11.50it/s]
 10%|█         | 294/2814 [00:24<03:39, 11.47it/s]
 11%|█         | 296/2814 [00:24<03:33, 11.78it/s]
 11%|█         | 298/2814 [00:24<03:36, 11.64it/s]
 11%|█         | 300/2814 [00:24<03:24, 12.27it/s]
 11%|█         | 302/2814 [00:25<03:30, 11.91it/s]
 11%|█         | 304/2814 [00:25<03:32, 11.80it/s]
 11%|█         | 306/2814 [00:25<03:33, 11.74it/s]
 11%|█         | 308/2814 [00:25<03:35, 11.65it/s]
 11%|█         | 310/2814 [00:25<03:29, 11.98it/s]
 11%|█         | 312/2814 [00:25<03:30, 11.91it/s]
 11%|█         | 314/2814 [00:26<03:27, 12.04it/s]
 11%|█         | 316/2814 [00:26<03:24, 12.23it/s]
 11%|█▏        | 318/2814 [00:26<03:28, 11.99it/s]
 11%|█▏        | 320/2814 [00:26<03:25, 12.15it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.55it/s]
 12%|█▏        | 324/2814 [00:26<03:25, 12.15it/s]
 12%|█▏        | 326/2814 [00:27<03:28, 11.93it/s]
 12%|█▏        | 328/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 332/2814 [00:27<03:24, 12.17it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.01it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.35it/s]
 12%|█▏        | 338/2814 [00:28<03:25, 12.02it/s]
 12%|█▏        | 340/2814 [00:28<03:29, 11.78it/s]
 12%|█▏        | 342/2814 [00:28<04:27,  9.25it/s]
 12%|█▏        | 344/2814 [00:28<04:05, 10.07it/s]
 12%|█▏        | 346/2814 [00:28<03:51, 10.68it/s]
 12%|█▏        | 348/2814 [00:29<03:44, 10.96it/s]
 12%|█▏        | 350/2814 [00:29<03:36, 11.36it/s]
 13%|█▎        | 352/2814 [00:29<03:35, 11.42it/s]
 13%|█▎        | 354/2814 [00:29<03:34, 11.45it/s]
 13%|█▎        | 356/2814 [00:29<03:29, 11.72it/s]
 13%|█▎        | 358/2814 [00:29<03:30, 11.65it/s]
 13%|█▎        | 360/2814 [00:30<03:33, 11.49it/s]
 13%|█▎        | 362/2814 [00:30<03:27, 11.84it/s]
 13%|█▎        | 364/2814 [00:30<03:28, 11.76it/s]
 13%|█▎        | 366/2814 [00:30<03:29, 11.66it/s]
 13%|█▎        | 368/2814 [00:30<03:28, 11.74it/s]
 13%|█▎        | 370/2814 [00:30<03:30, 11.61it/s]
 13%|█▎        | 372/2814 [00:31<03:20, 12.17it/s]
 13%|█▎        | 374/2814 [00:31<03:24, 11.92it/s]
 13%|█▎        | 376/2814 [00:31<03:27, 11.76it/s]
 13%|█▎        | 378/2814 [00:31<03:27, 11.72it/s]
 14%|█▎        | 380/2814 [00:31<03:24, 11.91it/s]
 14%|█▎        | 382/2814 [00:31<03:26, 11.78it/s]
 14%|█▎        | 384/2814 [00:32<03:23, 11.97it/s]
 14%|█▎        | 386/2814 [00:32<03:25, 11.80it/s]
 14%|█▍        | 388/2814 [00:32<03:24, 11.88it/s]
 14%|█▍        | 390/2814 [00:32<03:26, 11.73it/s]
 14%|█▍        | 392/2814 [00:32<03:11, 12.68it/s]
 14%|█▍        | 394/2814 [00:32<03:18, 12.18it/s]
 14%|█▍        | 396/2814 [00:33<03:21, 11.99it/s]
 14%|█▍        | 398/2814 [00:33<03:19, 12.12it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.87it/s]
 14%|█▍        | 402/2814 [00:33<03:23, 11.84it/s]
 14%|█▍        | 404/2814 [00:33<03:23, 11.82it/s]
 14%|█▍        | 406/2814 [00:33<03:26, 11.65it/s]
 14%|█▍        | 408/2814 [00:34<03:18, 12.13it/s]
 15%|█▍        | 410/2814 [00:34<03:22, 11.88it/s]
 15%|█▍        | 412/2814 [00:34<03:20, 11.97it/s]
 15%|█▍        | 414/2814 [00:34<03:23, 11.78it/s]
 15%|█▍        | 416/2814 [00:34<03:12, 12.47it/s]
 15%|█▍        | 418/2814 [00:34<03:12, 12.44it/s]
 15%|█▍        | 420/2814 [00:35<03:14, 12.28it/s]
 15%|█▍        | 422/2814 [00:35<03:12, 12.45it/s]
 15%|█▌        | 424/2814 [00:35<03:16, 12.18it/s]
 15%|█▌        | 426/2814 [00:35<03:13, 12.36it/s]
 15%|█▌        | 428/2814 [00:35<03:14, 12.28it/s]
 15%|█▌        | 430/2814 [00:35<03:09, 12.61it/s]
 15%|█▌        | 432/2814 [00:36<03:14, 12.22it/s]
 15%|█▌        | 434/2814 [00:36<03:10, 12.52it/s]
 15%|█▌        | 436/2814 [00:36<03:10, 12.45it/s]
 16%|█▌        | 438/2814 [00:36<03:13, 12.25it/s]
 16%|█▌        | 440/2814 [00:36<03:16, 12.06it/s]
 16%|█▌        | 442/2814 [00:36<03:19, 11.89it/s]
 16%|█▌        | 444/2814 [00:37<03:13, 12.23it/s]
 16%|█▌        | 446/2814 [00:37<03:16, 12.08it/s]
 16%|█▌        | 448/2814 [00:37<03:21, 11.74it/s]
 16%|█▌        | 450/2814 [00:37<03:08, 12.52it/s]
 16%|█▌        | 452/2814 [00:37<03:07, 12.63it/s]
 16%|█▌        | 454/2814 [00:37<03:12, 12.25it/s]
 16%|█▌        | 456/2814 [00:37<03:08, 12.50it/s]
 16%|█▋        | 458/2814 [00:38<03:03, 12.85it/s]
 16%|█▋        | 460/2814 [00:38<03:11, 12.30it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.98it/s]
 16%|█▋        | 464/2814 [00:38<03:18, 11.87it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.26it/s]
 17%|█▋        | 468/2814 [00:38<03:10, 12.28it/s]
 17%|█▋        | 470/2814 [00:39<03:14, 12.07it/s]
 17%|█▋        | 472/2814 [00:39<03:10, 12.32it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.52it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 12.00it/s]
 17%|█▋        | 480/2814 [00:39<03:15, 11.94it/s]
 17%|█▋        | 482/2814 [00:40<03:14, 11.96it/s]
 17%|█▋        | 484/2814 [00:40<03:16, 11.86it/s]
 17%|█▋        | 486/2814 [00:40<03:19, 11.67it/s]
 17%|█▋        | 488/2814 [00:40<03:19, 11.64it/s]
 17%|█▋        | 490/2814 [00:40<03:13, 11.98it/s]
 17%|█▋        | 492/2814 [00:40<03:15, 11.86it/s]
 18%|█▊        | 494/2814 [00:41<03:16, 11.83it/s]
 18%|█▊        | 496/2814 [00:41<03:07, 12.37it/s]
 18%|█▊        | 498/2814 [00:41<03:11, 12.10it/s]
 18%|█▊        | 500/2814 [00:41<03:09, 12.23it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.41it/s]
 18%|█▊        | 504/2814 [00:41<03:02, 12.66it/s]
 18%|█▊        | 506/2814 [00:42<03:07, 12.31it/s]
 18%|█▊        | 508/2814 [00:42<03:05, 12.46it/s]
 18%|█▊        | 510/2814 [00:42<02:57, 12.98it/s]
 18%|█▊        | 512/2814 [00:42<03:03, 12.57it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.68it/s]
 18%|█▊        | 516/2814 [00:42<03:06, 12.30it/s]
 18%|█▊        | 518/2814 [00:43<03:03, 12.52it/s]
 18%|█▊        | 520/2814 [00:43<03:08, 12.20it/s]
 19%|█▊        | 522/2814 [00:43<03:12, 11.91it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.33it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.68it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.33it/s]
 19%|█▉        | 530/2814 [00:44<03:08, 12.11it/s]
 19%|█▉        | 532/2814 [00:44<03:07, 12.16it/s]
 19%|█▉        | 534/2814 [00:44<03:01, 12.54it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.15it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.01it/s]
 19%|█▉        | 540/2814 [00:44<03:13, 11.76it/s]
 19%|█▉        | 542/2814 [00:45<03:12, 11.80it/s]
 19%|█▉        | 544/2814 [00:45<03:02, 12.42it/s]
 19%|█▉        | 546/2814 [00:45<03:01, 12.48it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.16it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.52it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.32it/s]
 20%|█▉        | 554/2814 [00:45<03:04, 12.26it/s]
 20%|█▉        | 556/2814 [00:46<02:57, 12.70it/s]
 20%|█▉        | 558/2814 [00:46<03:00, 12.50it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.47it/s]
 20%|█▉        | 562/2814 [00:46<03:07, 12.03it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.95it/s]
 20%|██        | 566/2814 [00:46<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:47<03:02, 12.34it/s]
 20%|██        | 570/2814 [00:47<03:06, 12.02it/s]
 20%|██        | 572/2814 [00:47<03:09, 11.80it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.03it/s]
 20%|██        | 576/2814 [00:47<02:57, 12.63it/s]
 21%|██        | 578/2814 [00:47<02:57, 12.59it/s]
 21%|██        | 580/2814 [00:48<03:04, 12.13it/s]
 21%|██        | 582/2814 [00:48<02:55, 12.72it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.50it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.28it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.64it/s]
 21%|██        | 590/2814 [00:48<02:59, 12.39it/s]
 21%|██        | 592/2814 [00:49<02:57, 12.51it/s]
 21%|██        | 594/2814 [00:49<03:01, 12.21it/s]
 21%|██        | 596/2814 [00:49<03:04, 11.99it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.77it/s]
 21%|██▏       | 600/2814 [00:49<02:51, 12.92it/s]
 21%|██▏       | 602/2814 [00:49<02:47, 13.20it/s]
 21%|██▏       | 604/2814 [00:50<02:49, 13.01it/s]
 22%|██▏       | 606/2814 [00:50<02:53, 12.70it/s]
 22%|██▏       | 608/2814 [00:50<02:53, 12.70it/s]
 22%|██▏       | 610/2814 [00:50<02:48, 13.08it/s]
 22%|██▏       | 612/2814 [00:50<02:55, 12.52it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.05it/s]
 22%|██▏       | 616/2814 [00:51<03:05, 11.84it/s]
 22%|██▏       | 618/2814 [00:51<03:00, 12.13it/s]
 22%|██▏       | 620/2814 [00:51<03:00, 12.19it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.10it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.20it/s]
 22%|██▏       | 626/2814 [00:51<02:59, 12.16it/s]
 22%|██▏       | 628/2814 [00:51<02:51, 12.74it/s]
 22%|██▏       | 630/2814 [00:52<02:53, 12.62it/s]
 22%|██▏       | 632/2814 [00:52<02:52, 12.68it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.22it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.95it/s]
 23%|██▎       | 638/2814 [00:52<03:04, 11.76it/s]
 23%|██▎       | 640/2814 [00:52<03:06, 11.68it/s]
 23%|██▎       | 642/2814 [00:53<03:02, 11.92it/s]
 23%|██▎       | 644/2814 [00:53<02:51, 12.62it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.13it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.98it/s]
 23%|██▎       | 650/2814 [00:53<02:56, 12.24it/s]
 23%|██▎       | 652/2814 [00:53<03:01, 11.90it/s]
 23%|██▎       | 654/2814 [00:54<03:02, 11.83it/s]
 23%|██▎       | 656/2814 [00:54<02:54, 12.35it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.30it/s]
 23%|██▎       | 660/2814 [00:54<02:53, 12.38it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.36it/s]
 24%|██▎       | 664/2814 [00:54<02:57, 12.11it/s]
 24%|██▎       | 666/2814 [00:55<02:55, 12.24it/s]
 24%|██▎       | 668/2814 [00:55<02:58, 12.05it/s]
 24%|██▍       | 670/2814 [00:55<03:02, 11.78it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.04it/s]
 24%|██▍       | 674/2814 [00:55<02:55, 12.16it/s]
 24%|██▍       | 676/2814 [00:55<02:54, 12.29it/s]
 24%|██▍       | 678/2814 [00:56<02:53, 12.31it/s]
 24%|██▍       | 680/2814 [00:56<02:55, 12.15it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.10it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.77it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.91it/s]
 24%|██▍       | 688/2814 [00:56<02:56, 12.03it/s]
 25%|██▍       | 690/2814 [00:57<02:57, 11.98it/s]
 25%|██▍       | 692/2814 [00:57<03:01, 11.72it/s]
 25%|██▍       | 694/2814 [00:57<02:52, 12.26it/s]
 25%|██▍       | 696/2814 [00:57<02:53, 12.23it/s]
 25%|██▍       | 698/2814 [00:57<02:49, 12.46it/s]
 25%|██▍       | 700/2814 [00:57<02:49, 12.48it/s]
 25%|██▍       | 702/2814 [00:58<02:49, 12.47it/s]
 25%|██▌       | 704/2814 [00:58<02:53, 12.16it/s]
 25%|██▌       | 706/2814 [00:58<02:47, 12.57it/s]
 25%|██▌       | 708/2814 [00:58<02:43, 12.86it/s]
 25%|██▌       | 710/2814 [00:58<02:49, 12.38it/s]
 25%|██▌       | 712/2814 [00:58<02:52, 12.17it/s]
 25%|██▌       | 714/2814 [00:59<02:51, 12.23it/s]
 25%|██▌       | 716/2814 [00:59<02:50, 12.29it/s]
 26%|██▌       | 718/2814 [00:59<02:52, 12.18it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 724/2814 [00:59<02:51, 12.22it/s]
 26%|██▌       | 726/2814 [01:00<02:42, 12.82it/s]
 26%|██▌       | 728/2814 [01:00<02:50, 12.24it/s]
 26%|██▌       | 730/2814 [01:00<02:47, 12.47it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.44it/s]
 26%|██▌       | 734/2814 [01:00<02:50, 12.17it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.25it/s]
 26%|██▌       | 738/2814 [01:01<02:52, 12.07it/s]
 26%|██▋       | 740/2814 [01:01<02:47, 12.38it/s]
 26%|██▋       | 742/2814 [01:01<02:47, 12.41it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.64it/s]
 27%|██▋       | 746/2814 [01:01<02:47, 12.32it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.29it/s]
 27%|██▋       | 750/2814 [01:01<02:52, 11.94it/s]
 27%|██▋       | 752/2814 [01:02<02:52, 11.95it/s]
 27%|██▋       | 754/2814 [01:02<02:53, 11.84it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.05it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.92it/s]
 27%|██▋       | 760/2814 [01:02<02:49, 12.15it/s]
 27%|██▋       | 762/2814 [01:02<02:48, 12.17it/s]
 27%|██▋       | 764/2814 [01:03<02:44, 12.46it/s]
 27%|██▋       | 766/2814 [01:03<02:45, 12.37it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.12it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.93it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.80it/s]
 28%|██▊       | 774/2814 [01:03<02:46, 12.26it/s]
 28%|██▊       | 776/2814 [01:04<02:43, 12.45it/s]
 28%|██▊       | 778/2814 [01:04<02:45, 12.31it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.30it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.13it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 12.00it/s]
 28%|██▊       | 786/2814 [01:04<02:46, 12.15it/s]
 28%|██▊       | 788/2814 [01:05<02:46, 12.14it/s]
 28%|██▊       | 790/2814 [01:05<02:45, 12.22it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.29it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.12it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.51it/s]
 28%|██▊       | 798/2814 [01:05<02:44, 12.26it/s]
 28%|██▊       | 800/2814 [01:06<02:46, 12.08it/s]
 29%|██▊       | 802/2814 [01:06<02:48, 11.94it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.01it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.16it/s]
 29%|██▊       | 808/2814 [01:06<02:47, 12.01it/s]
 29%|██▉       | 810/2814 [01:06<02:43, 12.22it/s]
 29%|██▉       | 812/2814 [01:07<02:38, 12.60it/s]
 29%|██▉       | 814/2814 [01:07<02:41, 12.35it/s]
 29%|██▉       | 816/2814 [01:07<02:40, 12.47it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.65it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.51it/s]
 29%|██▉       | 822/2814 [01:07<02:44, 12.13it/s]
 29%|██▉       | 824/2814 [01:08<02:40, 12.42it/s]
 29%|██▉       | 826/2814 [01:08<02:43, 12.19it/s]
 29%|██▉       | 828/2814 [01:08<02:45, 11.99it/s]
 29%|██▉       | 830/2814 [01:08<02:44, 12.10it/s]
 30%|██▉       | 832/2814 [01:08<02:46, 11.94it/s]
 30%|██▉       | 834/2814 [01:08<02:48, 11.72it/s]
 30%|██▉       | 836/2814 [01:09<02:42, 12.17it/s]
 30%|██▉       | 838/2814 [01:09<02:41, 12.24it/s]
 30%|██▉       | 840/2814 [01:09<02:45, 11.94it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.84it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.75it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.13it/s]
 30%|███       | 848/2814 [01:10<02:37, 12.51it/s]
 30%|███       | 850/2814 [01:10<02:41, 12.20it/s]
 30%|███       | 852/2814 [01:10<02:41, 12.17it/s]
 30%|███       | 854/2814 [01:10<02:42, 12.08it/s]
 30%|███       | 856/2814 [01:10<02:44, 11.87it/s]
 30%|███       | 858/2814 [01:10<02:46, 11.75it/s]
 31%|███       | 860/2814 [01:11<02:43, 11.92it/s]
 31%|███       | 862/2814 [01:11<02:43, 11.90it/s]
 31%|███       | 864/2814 [01:11<02:39, 12.19it/s]
 31%|███       | 866/2814 [01:11<02:35, 12.56it/s]
 31%|███       | 868/2814 [01:11<02:34, 12.61it/s]
 31%|███       | 870/2814 [01:11<02:39, 12.22it/s]
 31%|███       | 872/2814 [01:12<02:39, 12.17it/s]
 31%|███       | 874/2814 [01:12<02:38, 12.25it/s]
 31%|███       | 876/2814 [01:12<02:41, 12.00it/s]
 31%|███       | 878/2814 [01:12<02:38, 12.24it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.06it/s]
 31%|███▏      | 882/2814 [01:12<02:41, 11.93it/s]
 31%|███▏      | 884/2814 [01:13<02:41, 11.93it/s]
 31%|███▏      | 886/2814 [01:13<02:42, 11.87it/s]
 32%|███▏      | 888/2814 [01:13<02:44, 11.69it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.89it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.60it/s]
 32%|███▏      | 896/2814 [01:14<02:41, 11.85it/s]
 32%|███▏      | 898/2814 [01:14<02:34, 12.37it/s]
 32%|███▏      | 900/2814 [01:14<02:34, 12.40it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.80it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.68it/s]
 32%|███▏      | 906/2814 [01:14<02:28, 12.89it/s]
 32%|███▏      | 908/2814 [01:14<02:33, 12.44it/s]
 32%|███▏      | 910/2814 [01:15<02:35, 12.22it/s]
 32%|███▏      | 912/2814 [01:15<02:38, 12.00it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.30it/s]
 33%|███▎      | 916/2814 [01:15<02:36, 12.09it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.04it/s]
 33%|███▎      | 920/2814 [01:15<02:36, 12.14it/s]
 33%|███▎      | 922/2814 [01:16<02:35, 12.19it/s]
 33%|███▎      | 924/2814 [01:16<02:39, 11.83it/s]
 33%|███▎      | 926/2814 [01:16<02:28, 12.67it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.78it/s]
 33%|███▎      | 930/2814 [01:16<02:31, 12.40it/s]
 33%|███▎      | 932/2814 [01:16<02:35, 12.10it/s]
 33%|███▎      | 934/2814 [01:17<02:36, 11.98it/s]
 33%|███▎      | 936/2814 [01:17<02:37, 11.92it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]{'loss': 0.7822, 'learning_rate': 3.168649461984037e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.60it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.69it/s]

 21%|██        | 66/313 [00:00<00:01, 206.16it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.19it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.58it/s]

 40%|████      | 126/313 [00:00<00:01, 185.35it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.21it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.24it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.44it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.40it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.54it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.15it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.82it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.53it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.62it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.62it/s]
 33%|███▎      | 938/2814 [01:19<02:30, 12.48it/s]

                                                  
 33%|███▎      | 938/2814 [01:19<02:38, 11.85it/s]
[I 2023-10-26 22:40:17,875] Trial 13 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6994996666908264, 'eval_accuracy': 0.6852, 'eval_f1': 0.6804156384666895, 'eval_runtime': 1.7303, 'eval_samples_per_second': 1444.83, 'eval_steps_per_second': 180.893, 'epoch': 1.0}

  0%|          | 0/1407 [00:00<?, ?it/s]
  0%|          | 1/1407 [00:00<03:32,  6.61it/s]
  0%|          | 2/1407 [00:00<03:25,  6.83it/s]
  0%|          | 3/1407 [00:00<03:25,  6.82it/s]
  0%|          | 4/1407 [00:00<03:31,  6.64it/s]
  0%|          | 5/1407 [00:00<03:33,  6.56it/s]
  0%|          | 6/1407 [00:00<03:34,  6.52it/s]
  0%|          | 7/1407 [00:01<03:36,  6.48it/s]
  1%|          | 8/1407 [00:01<03:29,  6.68it/s]
  1%|          | 9/1407 [00:01<03:25,  6.80it/s]
  1%|          | 10/1407 [00:01<03:26,  6.78it/s]
  1%|          | 11/1407 [00:01<03:23,  6.84it/s]
  1%|          | 12/1407 [00:01<03:06,  7.48it/s]
  1%|          | 13/1407 [00:01<03:12,  7.23it/s]
  1%|          | 14/1407 [00:02<03:16,  7.10it/s]
  1%|          | 15/1407 [00:02<03:17,  7.05it/s]
  1%|          | 16/1407 [00:02<03:16,  7.08it/s]
  1%|          | 17/1407 [00:02<03:18,  7.00it/s]
  1%|▏         | 18/1407 [00:02<03:23,  6.81it/s]
  1%|▏         | 19/1407 [00:02<03:26,  6.71it/s]
  1%|▏         | 20/1407 [00:02<03:29,  6.61it/s]
  1%|▏         | 21/1407 [00:03<03:27,  6.67it/s]
  2%|▏         | 22/1407 [00:03<03:27,  6.69it/s]
  2%|▏         | 23/1407 [00:03<03:24,  6.76it/s]
  2%|▏         | 24/1407 [00:03<03:24,  6.78it/s]
  2%|▏         | 25/1407 [00:03<03:21,  6.86it/s]
  2%|▏         | 26/1407 [00:03<03:20,  6.90it/s]
  2%|▏         | 27/1407 [00:03<03:19,  6.92it/s]
  2%|▏         | 28/1407 [00:04<03:19,  6.91it/s]
  2%|▏         | 29/1407 [00:04<03:23,  6.78it/s]
  2%|▏         | 30/1407 [00:04<03:26,  6.68it/s]
  2%|▏         | 32/1407 [00:04<03:03,  7.47it/s]
  2%|▏         | 33/1407 [00:04<03:11,  7.17it/s]
  2%|▏         | 34/1407 [00:04<03:14,  7.08it/s]
  2%|▏         | 35/1407 [00:05<03:19,  6.87it/s]
  3%|▎         | 36/1407 [00:05<03:19,  6.89it/s]
  3%|▎         | 37/1407 [00:05<03:11,  7.16it/s]
  3%|▎         | 38/1407 [00:05<03:12,  7.10it/s]
  3%|▎         | 39/1407 [00:05<03:13,  7.06it/s]
  3%|▎         | 40/1407 [00:05<03:16,  6.96it/s]
  3%|▎         | 41/1407 [00:05<03:20,  6.82it/s]
  3%|▎         | 42/1407 [00:06<03:19,  6.86it/s]
  3%|▎         | 43/1407 [00:06<03:18,  6.89it/s]
  3%|▎         | 44/1407 [00:06<03:16,  6.94it/s]
  3%|▎         | 45/1407 [00:06<03:21,  6.77it/s]
  3%|▎         | 46/1407 [00:06<03:10,  7.13it/s]
  3%|▎         | 47/1407 [00:06<03:16,  6.90it/s]
  3%|▎         | 48/1407 [00:06<03:09,  7.19it/s]
  3%|▎         | 49/1407 [00:07<03:11,  7.07it/s]
  4%|▎         | 50/1407 [00:07<03:13,  7.01it/s]
  4%|▎         | 51/1407 [00:07<03:18,  6.82it/s]
  4%|▎         | 52/1407 [00:07<03:14,  6.96it/s]
  4%|▍         | 53/1407 [00:07<03:16,  6.89it/s]
  4%|▍         | 54/1407 [00:07<03:21,  6.73it/s]
  4%|▍         | 55/1407 [00:07<03:06,  7.23it/s]
  4%|▍         | 56/1407 [00:08<03:14,  6.96it/s]
  4%|▍         | 57/1407 [00:08<03:12,  7.02it/s]
  4%|▍         | 58/1407 [00:08<03:04,  7.30it/s]
  4%|▍         | 59/1407 [00:08<03:12,  7.01it/s]
  4%|▍         | 60/1407 [00:08<03:03,  7.35it/s]
  4%|▍         | 61/1407 [00:08<03:10,  7.07it/s]
  4%|▍         | 62/1407 [00:08<03:09,  7.09it/s]
  4%|▍         | 63/1407 [00:09<03:14,  6.91it/s]
  5%|▍         | 64/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 65/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 66/1407 [00:09<03:12,  6.98it/s]
  5%|▍         | 67/1407 [00:09<03:17,  6.79it/s]
  5%|▍         | 68/1407 [00:09<03:20,  6.67it/s]
  5%|▍         | 69/1407 [00:09<03:18,  6.74it/s]
  5%|▍         | 70/1407 [00:10<03:16,  6.80it/s]
  5%|▌         | 71/1407 [00:10<03:16,  6.81it/s]
  5%|▌         | 72/1407 [00:10<03:14,  6.86it/s]
  5%|▌         | 73/1407 [00:10<03:11,  6.98it/s]
  5%|▌         | 74/1407 [00:10<03:09,  7.02it/s]
  5%|▌         | 75/1407 [00:10<03:09,  7.04it/s]
  5%|▌         | 76/1407 [00:10<03:13,  6.88it/s]
  5%|▌         | 77/1407 [00:11<03:16,  6.77it/s]
  6%|▌         | 78/1407 [00:11<03:07,  7.09it/s]
  6%|▌         | 79/1407 [00:11<03:08,  7.05it/s]
  6%|▌         | 80/1407 [00:11<03:13,  6.86it/s]
  6%|▌         | 81/1407 [00:11<03:13,  6.85it/s]
  6%|▌         | 82/1407 [00:11<03:16,  6.75it/s]
  6%|▌         | 83/1407 [00:12<03:14,  6.80it/s]
  6%|▌         | 84/1407 [00:12<03:14,  6.79it/s]
  6%|▌         | 85/1407 [00:12<03:18,  6.66it/s]
  6%|▌         | 86/1407 [00:12<03:17,  6.69it/s]
  6%|▌         | 87/1407 [00:12<03:15,  6.75it/s]
  6%|▋         | 88/1407 [00:12<03:04,  7.13it/s]
  6%|▋         | 89/1407 [00:12<03:06,  7.08it/s]
  6%|▋         | 90/1407 [00:13<03:12,  6.85it/s]
  6%|▋         | 91/1407 [00:13<03:16,  6.70it/s]
  7%|▋         | 92/1407 [00:13<03:19,  6.60it/s]
  7%|▋         | 93/1407 [00:13<03:18,  6.64it/s]
  7%|▋         | 94/1407 [00:13<03:15,  6.73it/s]
  7%|▋         | 95/1407 [00:13<03:16,  6.66it/s]
  7%|▋         | 96/1407 [00:13<03:17,  6.63it/s]
  7%|▋         | 97/1407 [00:14<03:16,  6.66it/s]
  7%|▋         | 98/1407 [00:14<03:15,  6.69it/s]
  7%|▋         | 99/1407 [00:14<03:18,  6.59it/s]
  7%|▋         | 100/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 101/1407 [00:14<03:14,  6.71it/s]
  7%|▋         | 102/1407 [00:14<03:13,  6.75it/s]
  7%|▋         | 103/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 104/1407 [00:15<03:03,  7.08it/s]
  7%|▋         | 105/1407 [00:15<03:03,  7.10it/s]
  8%|▊         | 106/1407 [00:15<03:02,  7.13it/s]
  8%|▊         | 107/1407 [00:15<03:02,  7.13it/s]
  8%|▊         | 108/1407 [00:15<03:04,  7.05it/s]
  8%|▊         | 109/1407 [00:15<02:54,  7.43it/s]
  8%|▊         | 110/1407 [00:15<03:01,  7.14it/s]
  8%|▊         | 111/1407 [00:16<03:02,  7.08it/s]
  8%|▊         | 112/1407 [00:16<03:05,  6.98it/s]
  8%|▊         | 113/1407 [00:16<03:07,  6.91it/s]
  8%|▊         | 114/1407 [00:16<03:04,  6.99it/s]
  8%|▊         | 115/1407 [00:16<03:09,  6.83it/s]
  8%|▊         | 116/1407 [00:16<03:12,  6.69it/s]
  8%|▊         | 117/1407 [00:16<03:09,  6.81it/s]
  8%|▊         | 118/1407 [00:17<03:13,  6.67it/s]
  8%|▊         | 119/1407 [00:17<03:14,  6.63it/s]
  9%|▊         | 120/1407 [00:17<03:12,  6.70it/s]
  9%|▊         | 121/1407 [00:17<03:10,  6.75it/s]
  9%|▊         | 122/1407 [00:17<03:09,  6.80it/s]
  9%|▊         | 123/1407 [00:17<03:00,  7.11it/s]
  9%|▉         | 124/1407 [00:17<02:59,  7.14it/s]
  9%|▉         | 125/1407 [00:18<03:05,  6.91it/s]
  9%|▉         | 126/1407 [00:18<03:08,  6.79it/s]
  9%|▉         | 127/1407 [00:18<02:57,  7.22it/s]
  9%|▉         | 128/1407 [00:18<02:59,  7.11it/s]
  9%|▉         | 129/1407 [00:18<03:02,  6.99it/s]
  9%|▉         | 130/1407 [00:18<03:07,  6.80it/s]
  9%|▉         | 131/1407 [00:19<03:11,  6.68it/s]
  9%|▉         | 132/1407 [00:19<03:09,  6.72it/s]
  9%|▉         | 133/1407 [00:19<03:12,  6.61it/s]
 10%|▉         | 134/1407 [00:19<03:14,  6.54it/s]
 10%|▉         | 135/1407 [00:19<03:04,  6.89it/s]
 10%|▉         | 136/1407 [00:19<03:03,  6.93it/s]
 10%|▉         | 137/1407 [00:19<03:03,  6.94it/s]
 10%|▉         | 138/1407 [00:20<03:01,  6.98it/s]
 10%|▉         | 139/1407 [00:20<03:02,  6.94it/s]
 10%|▉         | 140/1407 [00:20<03:00,  7.00it/s]
 10%|█         | 141/1407 [00:20<03:02,  6.92it/s]
 10%|█         | 142/1407 [00:20<03:02,  6.93it/s]
 10%|█         | 143/1407 [00:20<02:55,  7.22it/s]
 10%|█         | 144/1407 [00:20<02:55,  7.21it/s]
 10%|█         | 145/1407 [00:21<02:56,  7.13it/s]
 10%|█         | 146/1407 [00:21<02:59,  7.01it/s]
 10%|█         | 147/1407 [00:21<03:01,  6.93it/s]
 11%|█         | 148/1407 [00:21<03:01,  6.93it/s]
 11%|█         | 149/1407 [00:21<03:05,  6.79it/s]
 11%|█         | 150/1407 [00:21<03:02,  6.87it/s]
 11%|█         | 151/1407 [00:21<03:06,  6.73it/s]
 11%|█         | 152/1407 [00:22<03:05,  6.75it/s]
 11%|█         | 153/1407 [00:22<03:05,  6.75it/s]
 11%|█         | 154/1407 [00:22<03:07,  6.67it/s]
 11%|█         | 155/1407 [00:22<03:05,  6.75it/s]
 11%|█         | 156/1407 [00:22<03:02,  6.86it/s]
 11%|█         | 157/1407 [00:22<03:00,  6.93it/s]
 11%|█         | 158/1407 [00:22<03:04,  6.76it/s]
 11%|█▏        | 159/1407 [00:23<03:06,  6.68it/s]
 11%|█▏        | 160/1407 [00:23<03:02,  6.85it/s]
 11%|█▏        | 161/1407 [00:23<02:54,  7.15it/s]
 12%|█▏        | 162/1407 [00:23<03:00,  6.89it/s]
 12%|█▏        | 163/1407 [00:23<03:04,  6.73it/s]
 12%|█▏        | 164/1407 [00:23<02:54,  7.11it/s]
 12%|█▏        | 165/1407 [00:23<02:56,  7.03it/s]
 12%|█▏        | 166/1407 [00:24<02:57,  6.97it/s]
 12%|█▏        | 167/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 168/1407 [00:24<02:55,  7.07it/s]
 12%|█▏        | 169/1407 [00:24<02:59,  6.90it/s]
 12%|█▏        | 170/1407 [00:24<03:00,  6.84it/s]
 12%|█▏        | 171/1407 [00:24<03:04,  6.71it/s]
 12%|█▏        | 172/1407 [00:24<02:59,  6.87it/s]
 12%|█▏        | 173/1407 [00:25<02:59,  6.87it/s]
 12%|█▏        | 174/1407 [00:25<03:02,  6.76it/s]
 12%|█▏        | 175/1407 [00:25<03:04,  6.68it/s]
 13%|█▎        | 176/1407 [00:25<03:02,  6.73it/s]
 13%|█▎        | 177/1407 [00:25<03:02,  6.73it/s]
 13%|█▎        | 178/1407 [00:25<02:53,  7.08it/s]
 13%|█▎        | 179/1407 [00:25<02:56,  6.97it/s]
 13%|█▎        | 180/1407 [00:26<03:00,  6.79it/s]
 13%|█▎        | 181/1407 [00:26<02:57,  6.89it/s]
 13%|█▎        | 182/1407 [00:26<02:57,  6.91it/s]
 13%|█▎        | 183/1407 [00:26<03:00,  6.78it/s]
 13%|█▎        | 184/1407 [00:26<02:59,  6.82it/s]
 13%|█▎        | 185/1407 [00:26<03:02,  6.69it/s]
 13%|█▎        | 186/1407 [00:26<02:50,  7.14it/s]
 13%|█▎        | 187/1407 [00:27<02:55,  6.94it/s]
 13%|█▎        | 188/1407 [00:27<02:59,  6.80it/s]
 13%|█▎        | 189/1407 [00:27<02:58,  6.84it/s]
 14%|█▎        | 190/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 191/1407 [00:27<03:02,  6.68it/s]
 14%|█▎        | 192/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 193/1407 [00:28<03:02,  6.64it/s]
 14%|█▍        | 194/1407 [00:28<03:04,  6.56it/s]
 14%|█▍        | 195/1407 [00:28<03:03,  6.62it/s]
 14%|█▍        | 196/1407 [00:28<02:49,  7.13it/s]
 14%|█▍        | 197/1407 [00:28<02:55,  6.89it/s]
 14%|█▍        | 198/1407 [00:28<02:55,  6.87it/s]
 14%|█▍        | 199/1407 [00:28<02:54,  6.90it/s]
 14%|█▍        | 200/1407 [00:29<02:58,  6.78it/s]
 14%|█▍        | 201/1407 [00:29<03:00,  6.66it/s]
 14%|█▍        | 202/1407 [00:29<03:00,  6.68it/s]
 14%|█▍        | 203/1407 [00:29<03:02,  6.59it/s]
 14%|█▍        | 204/1407 [00:29<02:57,  6.78it/s]
 15%|█▍        | 205/1407 [00:29<02:57,  6.77it/s]
 15%|█▍        | 206/1407 [00:29<02:56,  6.79it/s]
 15%|█▍        | 207/1407 [00:30<02:58,  6.72it/s]
 15%|█▍        | 208/1407 [00:30<02:47,  7.17it/s]
 15%|█▍        | 209/1407 [00:30<02:48,  7.10it/s]
 15%|█▍        | 210/1407 [00:30<02:49,  7.06it/s]
 15%|█▍        | 211/1407 [00:30<02:43,  7.33it/s]
 15%|█▌        | 212/1407 [00:30<02:45,  7.21it/s]
 15%|█▌        | 213/1407 [00:30<02:45,  7.22it/s]
 15%|█▌        | 214/1407 [00:31<02:51,  6.95it/s]
 15%|█▌        | 215/1407 [00:31<02:49,  7.02it/s]
 15%|█▌        | 216/1407 [00:31<02:51,  6.93it/s]
 15%|█▌        | 217/1407 [00:31<02:44,  7.25it/s]
 15%|█▌        | 218/1407 [00:31<02:47,  7.08it/s]
 16%|█▌        | 219/1407 [00:31<02:47,  7.08it/s]
 16%|█▌        | 220/1407 [00:31<02:51,  6.90it/s]
 16%|█▌        | 221/1407 [00:32<02:51,  6.90it/s]
 16%|█▌        | 222/1407 [00:32<02:44,  7.20it/s]
 16%|█▌        | 223/1407 [00:32<02:45,  7.17it/s]
 16%|█▌        | 224/1407 [00:32<02:50,  6.93it/s]
 16%|█▌        | 225/1407 [00:32<02:36,  7.54it/s]
 16%|█▌        | 226/1407 [00:32<02:40,  7.35it/s]
 16%|█▌        | 227/1407 [00:32<02:44,  7.15it/s]
 16%|█▌        | 228/1407 [00:33<02:39,  7.41it/s]
 16%|█▋        | 229/1407 [00:33<02:39,  7.36it/s]
 16%|█▋        | 230/1407 [00:33<02:47,  7.04it/s]
 16%|█▋        | 231/1407 [00:33<02:50,  6.88it/s]
 16%|█▋        | 232/1407 [00:33<02:50,  6.87it/s]
 17%|█▋        | 233/1407 [00:33<02:48,  6.97it/s]
 17%|█▋        | 234/1407 [00:33<02:49,  6.93it/s]
 17%|█▋        | 235/1407 [00:34<02:49,  6.90it/s]
 17%|█▋        | 236/1407 [00:34<02:45,  7.08it/s]
 17%|█▋        | 237/1407 [00:34<02:47,  6.97it/s]
 17%|█▋        | 238/1407 [00:34<02:52,  6.78it/s]
 17%|█▋        | 239/1407 [00:34<02:51,  6.80it/s]
 17%|█▋        | 240/1407 [00:34<02:49,  6.89it/s]
 17%|█▋        | 241/1407 [00:34<02:47,  6.98it/s]
 17%|█▋        | 242/1407 [00:35<02:47,  6.97it/s]
 17%|█▋        | 243/1407 [00:35<02:50,  6.83it/s]
 17%|█▋        | 244/1407 [00:35<02:49,  6.86it/s]
 17%|█▋        | 245/1407 [00:35<02:46,  6.96it/s]
 17%|█▋        | 246/1407 [00:35<02:47,  6.93it/s]
 18%|█▊        | 247/1407 [00:35<02:46,  6.98it/s]
 18%|█▊        | 248/1407 [00:35<02:37,  7.34it/s]
 18%|█▊        | 249/1407 [00:36<02:41,  7.19it/s]
 18%|█▊        | 250/1407 [00:36<02:43,  7.08it/s]
 18%|█▊        | 251/1407 [00:36<02:37,  7.33it/s]
 18%|█▊        | 252/1407 [00:36<02:41,  7.17it/s]
 18%|█▊        | 253/1407 [00:36<02:42,  7.10it/s]
 18%|█▊        | 254/1407 [00:36<02:44,  7.02it/s]
 18%|█▊        | 255/1407 [00:36<02:36,  7.35it/s]
 18%|█▊        | 256/1407 [00:37<02:39,  7.20it/s]
 18%|█▊        | 257/1407 [00:37<02:37,  7.31it/s]
 18%|█▊        | 258/1407 [00:37<02:40,  7.17it/s]
 18%|█▊        | 259/1407 [00:37<02:44,  6.97it/s]
 18%|█▊        | 260/1407 [00:37<02:45,  6.93it/s]
 19%|█▊        | 261/1407 [00:37<02:46,  6.87it/s]
 19%|█▊        | 262/1407 [00:37<02:45,  6.90it/s]
 19%|█▊        | 263/1407 [00:38<02:37,  7.25it/s]
 19%|█▉        | 264/1407 [00:38<02:40,  7.12it/s]
 19%|█▉        | 265/1407 [00:38<02:41,  7.05it/s]
 19%|█▉        | 266/1407 [00:38<02:45,  6.88it/s]
 19%|█▉        | 267/1407 [00:38<02:45,  6.89it/s]
 19%|█▉        | 268/1407 [00:38<02:48,  6.78it/s]
 19%|█▉        | 269/1407 [00:38<02:46,  6.82it/s]
 19%|█▉        | 270/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 271/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 272/1407 [00:39<02:45,  6.86it/s]
 19%|█▉        | 273/1407 [00:39<02:44,  6.88it/s]
 19%|█▉        | 274/1407 [00:39<02:44,  6.87it/s]
 20%|█▉        | 275/1407 [00:39<02:42,  6.96it/s]
 20%|█▉        | 276/1407 [00:39<02:43,  6.93it/s]
 20%|█▉        | 277/1407 [00:40<02:47,  6.76it/s]
 20%|█▉        | 278/1407 [00:40<02:36,  7.20it/s]
 20%|█▉        | 279/1407 [00:40<02:42,  6.95it/s]
 20%|█▉        | 280/1407 [00:40<02:43,  6.89it/s]
 20%|█▉        | 281/1407 [00:40<02:47,  6.73it/s]
 20%|██        | 282/1407 [00:40<02:45,  6.80it/s]
 20%|██        | 283/1407 [00:40<02:37,  7.12it/s]
 20%|██        | 284/1407 [00:41<02:34,  7.25it/s]
 20%|██        | 285/1407 [00:41<02:41,  6.96it/s]
 20%|██        | 286/1407 [00:41<02:44,  6.83it/s]
 20%|██        | 287/1407 [00:41<02:43,  6.85it/s]
 20%|██        | 288/1407 [00:41<02:34,  7.25it/s]
 21%|██        | 289/1407 [00:41<02:37,  7.09it/s]
 21%|██        | 290/1407 [00:41<02:42,  6.86it/s]
 21%|██        | 291/1407 [00:42<02:43,  6.82it/s]
 21%|██        | 292/1407 [00:42<02:46,  6.69it/s]
 21%|██        | 293/1407 [00:42<02:43,  6.83it/s]
 21%|██        | 294/1407 [00:42<02:38,  7.04it/s]
 21%|██        | 295/1407 [00:42<02:38,  7.02it/s]
 21%|██        | 296/1407 [00:42<02:32,  7.29it/s]
 21%|██        | 297/1407 [00:42<02:37,  7.05it/s]
 21%|██        | 298/1407 [00:43<02:38,  6.99it/s]
 21%|██▏       | 299/1407 [00:43<02:42,  6.80it/s]
 21%|██▏       | 300/1407 [00:43<02:27,  7.51it/s]
 21%|██▏       | 301/1407 [00:43<02:23,  7.71it/s]
 21%|██▏       | 302/1407 [00:43<02:28,  7.43it/s]
 22%|██▏       | 303/1407 [00:43<02:31,  7.28it/s]
 22%|██▏       | 304/1407 [00:43<02:33,  7.19it/s]
 22%|██▏       | 305/1407 [00:44<02:26,  7.52it/s]
 22%|██▏       | 306/1407 [00:44<02:34,  7.14it/s]
 22%|██▏       | 307/1407 [00:44<02:38,  6.93it/s]
 22%|██▏       | 308/1407 [00:44<02:39,  6.87it/s]
 22%|██▏       | 309/1407 [00:44<02:32,  7.19it/s]
 22%|██▏       | 310/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 311/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 312/1407 [00:45<02:35,  7.05it/s]
 22%|██▏       | 313/1407 [00:45<02:33,  7.12it/s]
 22%|██▏       | 314/1407 [00:45<02:28,  7.38it/s]
 22%|██▏       | 315/1407 [00:45<02:29,  7.29it/s]
 22%|██▏       | 316/1407 [00:45<02:35,  7.04it/s]
 23%|██▎       | 317/1407 [00:45<02:39,  6.83it/s]
 23%|██▎       | 318/1407 [00:45<02:41,  6.73it/s]
 23%|██▎       | 319/1407 [00:46<02:44,  6.63it/s]
 23%|██▎       | 320/1407 [00:46<02:42,  6.70it/s]
 23%|██▎       | 321/1407 [00:46<02:41,  6.71it/s]
 23%|██▎       | 322/1407 [00:46<02:32,  7.13it/s]
 23%|██▎       | 323/1407 [00:46<02:37,  6.90it/s]
 23%|██▎       | 324/1407 [00:46<02:36,  6.91it/s]
 23%|██▎       | 325/1407 [00:46<02:39,  6.79it/s]
 23%|██▎       | 326/1407 [00:47<02:41,  6.70it/s]
 23%|██▎       | 327/1407 [00:47<02:39,  6.78it/s]
 23%|██▎       | 328/1407 [00:47<02:31,  7.11it/s]
 23%|██▎       | 329/1407 [00:47<02:33,  7.04it/s]
 23%|██▎       | 330/1407 [00:47<02:33,  7.01it/s]
 24%|██▎       | 331/1407 [00:47<02:35,  6.93it/s]
 24%|██▎       | 332/1407 [00:47<02:35,  6.93it/s]
 24%|██▎       | 333/1407 [00:48<02:30,  7.11it/s]
 24%|██▎       | 334/1407 [00:48<02:31,  7.07it/s]
 24%|██▍       | 335/1407 [00:48<02:35,  6.90it/s]
 24%|██▍       | 336/1407 [00:48<02:34,  6.92it/s]
 24%|██▍       | 337/1407 [00:48<02:34,  6.94it/s]
 24%|██▍       | 338/1407 [00:48<02:32,  7.01it/s]
 24%|██▍       | 339/1407 [00:48<02:33,  6.95it/s]
 24%|██▍       | 340/1407 [00:49<02:34,  6.89it/s]
 24%|██▍       | 341/1407 [00:49<02:33,  6.94it/s]
 24%|██▍       | 342/1407 [00:49<02:37,  6.77it/s]
 24%|██▍       | 343/1407 [00:49<02:37,  6.76it/s]
 24%|██▍       | 344/1407 [00:49<02:39,  6.65it/s]
 25%|██▍       | 345/1407 [00:49<02:37,  6.74it/s]
 25%|██▍       | 346/1407 [00:49<02:40,  6.63it/s]
 25%|██▍       | 347/1407 [00:50<02:29,  7.07it/s]
 25%|██▍       | 348/1407 [00:50<02:32,  6.96it/s]
 25%|██▍       | 349/1407 [00:50<02:30,  7.03it/s]
 25%|██▍       | 350/1407 [00:50<02:28,  7.12it/s]
 25%|██▍       | 351/1407 [00:50<02:28,  7.12it/s]
 25%|██▌       | 352/1407 [00:50<02:32,  6.94it/s]
 25%|██▌       | 353/1407 [00:50<02:35,  6.76it/s]
 25%|██▌       | 354/1407 [00:51<02:32,  6.90it/s]
 25%|██▌       | 355/1407 [00:51<02:36,  6.73it/s]
 25%|██▌       | 356/1407 [00:51<02:35,  6.77it/s]
 25%|██▌       | 357/1407 [00:51<02:33,  6.86it/s]
 25%|██▌       | 358/1407 [00:51<02:31,  6.94it/s]
 26%|██▌       | 359/1407 [00:51<02:30,  6.98it/s]
 26%|██▌       | 360/1407 [00:51<02:34,  6.79it/s]
 26%|██▌       | 361/1407 [00:52<02:33,  6.83it/s]
 26%|██▌       | 362/1407 [00:52<02:35,  6.73it/s]
 26%|██▌       | 363/1407 [00:52<02:27,  7.06it/s]
 26%|██▌       | 364/1407 [00:52<02:32,  6.84it/s]
 26%|██▌       | 365/1407 [00:52<02:30,  6.91it/s]
 26%|██▌       | 366/1407 [00:52<02:34,  6.76it/s]
 26%|██▌       | 367/1407 [00:53<02:34,  6.75it/s]
 26%|██▌       | 368/1407 [00:53<02:31,  6.87it/s]
 26%|██▌       | 369/1407 [00:53<02:30,  6.88it/s]
 26%|██▋       | 370/1407 [00:53<02:31,  6.86it/s]
 26%|██▋       | 371/1407 [00:53<02:30,  6.90it/s]
 26%|██▋       | 372/1407 [00:53<02:29,  6.92it/s]
 27%|██▋       | 373/1407 [00:53<02:33,  6.74it/s]
 27%|██▋       | 374/1407 [00:54<02:31,  6.80it/s]
 27%|██▋       | 375/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 376/1407 [00:54<02:36,  6.60it/s]
 27%|██▋       | 377/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 378/1407 [00:54<02:31,  6.78it/s]
 27%|██▋       | 379/1407 [00:54<02:30,  6.83it/s]
 27%|██▋       | 380/1407 [00:54<02:29,  6.86it/s]
 27%|██▋       | 381/1407 [00:55<02:30,  6.83it/s]
 27%|██▋       | 382/1407 [00:55<02:22,  7.20it/s]
 27%|██▋       | 383/1407 [00:55<02:22,  7.18it/s]
 27%|██▋       | 384/1407 [00:55<02:25,  7.04it/s]
 27%|██▋       | 385/1407 [00:55<02:26,  6.98it/s]
 27%|██▋       | 386/1407 [00:55<02:29,  6.83it/s]
 28%|██▊       | 387/1407 [00:55<02:21,  7.21it/s]
 28%|██▊       | 388/1407 [00:56<02:24,  7.07it/s]
 28%|██▊       | 389/1407 [00:56<02:23,  7.08it/s]
 28%|██▊       | 390/1407 [00:56<02:20,  7.23it/s]
 28%|██▊       | 391/1407 [00:56<02:21,  7.19it/s]
 28%|██▊       | 392/1407 [00:56<02:23,  7.09it/s]
 28%|██▊       | 393/1407 [00:56<02:23,  7.06it/s]
 28%|██▊       | 394/1407 [00:56<02:25,  6.97it/s]
 28%|██▊       | 395/1407 [00:57<02:25,  6.97it/s]
 28%|██▊       | 396/1407 [00:57<02:25,  6.94it/s]
 28%|██▊       | 397/1407 [00:57<02:25,  6.95it/s]
 28%|██▊       | 398/1407 [00:57<02:19,  7.24it/s]
 28%|██▊       | 399/1407 [00:57<02:20,  7.19it/s]
 28%|██▊       | 400/1407 [00:57<02:20,  7.16it/s]
 29%|██▊       | 401/1407 [00:57<02:21,  7.09it/s]
 29%|██▊       | 402/1407 [00:58<02:23,  7.01it/s]
 29%|██▊       | 403/1407 [00:58<02:24,  6.96it/s]
 29%|██▊       | 404/1407 [00:58<02:25,  6.89it/s]
 29%|██▉       | 405/1407 [00:58<02:19,  7.19it/s]
 29%|██▉       | 406/1407 [00:58<02:15,  7.41it/s]
 29%|██▉       | 407/1407 [00:58<02:20,  7.12it/s]
 29%|██▉       | 408/1407 [00:58<02:15,  7.38it/s]
 29%|██▉       | 409/1407 [00:58<02:12,  7.56it/s]
 29%|██▉       | 410/1407 [00:59<02:18,  7.21it/s]
 29%|██▉       | 411/1407 [00:59<02:21,  7.06it/s]
 29%|██▉       | 412/1407 [00:59<02:22,  6.96it/s]
 29%|██▉       | 413/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 414/1407 [00:59<02:23,  6.91it/s]
 29%|██▉       | 415/1407 [00:59<02:26,  6.76it/s]
 30%|██▉       | 416/1407 [01:00<02:29,  6.64it/s]
 30%|██▉       | 417/1407 [01:00<02:30,  6.57it/s]
 30%|██▉       | 418/1407 [01:00<02:20,  7.02it/s]
 30%|██▉       | 419/1407 [01:00<02:20,  7.01it/s]
 30%|██▉       | 420/1407 [01:00<02:23,  6.86it/s]
 30%|██▉       | 421/1407 [01:00<02:26,  6.71it/s]
 30%|██▉       | 422/1407 [01:00<02:25,  6.75it/s]
 30%|███       | 423/1407 [01:01<02:18,  7.11it/s]
 30%|███       | 424/1407 [01:01<02:17,  7.14it/s]
 30%|███       | 425/1407 [01:01<02:19,  7.04it/s]
 30%|███       | 426/1407 [01:01<02:22,  6.88it/s]
 30%|███       | 427/1407 [01:01<02:22,  6.87it/s]
 30%|███       | 428/1407 [01:01<02:23,  6.83it/s]
 30%|███       | 429/1407 [01:01<02:23,  6.80it/s]
 31%|███       | 430/1407 [01:02<02:26,  6.68it/s]
 31%|███       | 431/1407 [01:02<02:24,  6.77it/s]
 31%|███       | 432/1407 [01:02<02:22,  6.84it/s]
 31%|███       | 433/1407 [01:02<02:15,  7.20it/s]
 31%|███       | 434/1407 [01:02<02:20,  6.93it/s]
 31%|███       | 435/1407 [01:02<02:23,  6.76it/s]
 31%|███       | 436/1407 [01:02<02:26,  6.64it/s]
 31%|███       | 437/1407 [01:03<02:25,  6.67it/s]
 31%|███       | 438/1407 [01:03<02:24,  6.69it/s]
 31%|███       | 439/1407 [01:03<02:21,  6.85it/s]
 31%|███▏      | 440/1407 [01:03<02:20,  6.88it/s]
 31%|███▏      | 441/1407 [01:03<02:20,  6.89it/s]
 31%|███▏      | 442/1407 [01:03<02:19,  6.91it/s]
 31%|███▏      | 443/1407 [01:03<02:19,  6.92it/s]
 32%|███▏      | 444/1407 [01:04<02:21,  6.80it/s]
 32%|███▏      | 445/1407 [01:04<02:19,  6.88it/s]
 32%|███▏      | 446/1407 [01:04<02:22,  6.72it/s]
 32%|███▏      | 447/1407 [01:04<02:22,  6.72it/s]
 32%|███▏      | 448/1407 [01:04<02:21,  6.78it/s]
 32%|███▏      | 449/1407 [01:04<02:12,  7.23it/s]
 32%|███▏      | 450/1407 [01:04<02:14,  7.13it/s]
 32%|███▏      | 451/1407 [01:05<02:18,  6.89it/s]
 32%|███▏      | 452/1407 [01:05<02:20,  6.78it/s]
 32%|███▏      | 453/1407 [01:05<02:13,  7.17it/s]
 32%|███▏      | 454/1407 [01:05<02:14,  7.06it/s]
 32%|███▏      | 455/1407 [01:05<02:15,  7.04it/s]
 32%|███▏      | 456/1407 [01:05<02:16,  6.99it/s]
 32%|███▏      | 457/1407 [01:05<02:17,  6.91it/s]
 33%|███▎      | 458/1407 [01:06<02:20,  6.75it/s]
 33%|███▎      | 459/1407 [01:06<02:19,  6.80it/s]
 33%|███▎      | 460/1407 [01:06<02:17,  6.88it/s]
 33%|███▎      | 461/1407 [01:06<02:16,  6.95it/s]
 33%|███▎      | 462/1407 [01:06<02:19,  6.77it/s]
 33%|███▎      | 463/1407 [01:06<02:07,  7.41it/s]
 33%|███▎      | 464/1407 [01:06<02:08,  7.35it/s]
 33%|███▎      | 465/1407 [01:07<02:11,  7.19it/s]
 33%|███▎      | 466/1407 [01:07<02:12,  7.08it/s]
 33%|███▎      | 467/1407 [01:07<02:13,  7.04it/s]
 33%|███▎      | 468/1407 [01:07<02:15,  6.95it/s]
 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]
                                                  

 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]{'loss': 0.8348, 'learning_rate': 9.89588234643563e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.13it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.67it/s]

 21%|██        | 66/313 [00:00<00:01, 206.14it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.24it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.69it/s]

 40%|████      | 126/313 [00:00<00:01, 185.40it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.17it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.21it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.32it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.55it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.84it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.69it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.39it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 185.14it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 179.13it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 179.13it/s]
 33%|███▎      | 469/1407 [01:09<02:07,  7.35it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 470/1407 [01:10<14:12,  1.10it/s]
 33%|███▎      | 471/1407 [01:10<10:36,  1.47it/s]
 34%|███▎      | 472/1407 [01:10<08:05,  1.93it/s]
 34%|███▎      | 473/1407 [01:10<06:20,  2.46it/s]
 34%|███▎      | 474/1407 [01:10<05:05,  3.05it/s]
 34%|███▍      | 475/1407 [01:11<04:17,  3.62it/s]
 34%|███▍      | 476/1407 [01:11<03:40,  4.22it/s]
 34%|███▍      | 477/1407 [01:11<03:15,  4.76it/s]
 34%|███▍      | 478/1407 [01:11<03:00,  5.16it/s]
 34%|███▍      | 479/1407 [01:11<02:48,  5.51it/s]
 34%|███▍      | 480/1407 [01:11<02:38,  5.85it/s]
 34%|███▍      | 481/1407 [01:11<02:30,  6.15it/s]
 34%|███▍      | 482/1407 [01:12<02:28,  6.22it/s]
 34%|███▍      | 483/1407 [01:12<02:23,  6.42it/s]
 34%|███▍      | 484/1407 [01:12<02:21,  6.52it/s]
 34%|███▍      | 485/1407 [01:12<02:18,  6.64it/s]
 35%|███▍      | 486/1407 [01:12<02:16,  6.76it/s]
 35%|███▍      | 487/1407 [01:12<02:14,  6.82it/s]
 35%|███▍      | 488/1407 [01:13<02:12,  6.96it/s]
 35%|███▍      | 489/1407 [01:13<02:14,  6.81it/s]
 35%|███▍      | 490/1407 [01:13<02:17,  6.68it/s]
 35%|███▍      | 491/1407 [01:13<02:16,  6.70it/s]
 35%|███▍      | 492/1407 [01:13<02:15,  6.76it/s]
 35%|███▌      | 493/1407 [01:13<02:17,  6.65it/s]
 35%|███▌      | 494/1407 [01:13<02:06,  7.21it/s]
 35%|███▌      | 495/1407 [01:14<02:06,  7.18it/s]
 35%|███▌      | 496/1407 [01:14<02:09,  7.04it/s]
 35%|███▌      | 497/1407 [01:14<02:09,  7.02it/s]
 35%|███▌      | 498/1407 [01:14<02:11,  6.93it/s]
 35%|███▌      | 499/1407 [01:14<02:14,  6.76it/s]
 36%|███▌      | 500/1407 [01:14<02:07,  7.09it/s]
 36%|███▌      | 501/1407 [01:14<02:03,  7.33it/s]
 36%|███▌      | 502/1407 [01:15<02:04,  7.25it/s]
 36%|███▌      | 503/1407 [01:15<02:06,  7.13it/s]
 36%|███▌      | 504/1407 [01:15<02:02,  7.37it/s]
 36%|███▌      | 505/1407 [01:15<01:59,  7.55it/s]
 36%|███▌      | 506/1407 [01:15<02:02,  7.35it/s]
 36%|███▌      | 507/1407 [01:15<02:07,  7.03it/s]
 36%|███▌      | 508/1407 [01:15<02:08,  6.99it/s]
 36%|███▌      | 509/1407 [01:15<02:08,  6.98it/s]
 36%|███▌      | 510/1407 [01:16<02:07,  7.02it/s]
 36%|███▋      | 511/1407 [01:16<02:11,  6.81it/s]
 36%|███▋      | 512/1407 [01:16<02:13,  6.68it/s]
 36%|███▋      | 513/1407 [01:16<02:11,  6.80it/s]
 37%|███▋      | 514/1407 [01:16<02:10,  6.86it/s]
 37%|███▋      | 515/1407 [01:16<02:04,  7.17it/s]
 37%|███▋      | 516/1407 [01:16<02:00,  7.40it/s]
 37%|███▋      | 517/1407 [01:17<02:05,  7.11it/s]
 37%|███▋      | 518/1407 [01:17<02:09,  6.89it/s]
 37%|███▋      | 519/1407 [01:17<02:08,  6.91it/s]
 37%|███▋      | 520/1407 [01:17<02:08,  6.92it/s]
 37%|███▋      | 521/1407 [01:17<02:07,  6.98it/s]
 37%|███▋      | 522/1407 [01:17<02:10,  6.78it/s]
 37%|███▋      | 523/1407 [01:18<02:11,  6.70it/s]
 37%|███▋      | 524/1407 [01:18<02:08,  6.88it/s]
 37%|███▋      | 525/1407 [01:18<01:58,  7.42it/s]
 37%|███▋      | 526/1407 [01:18<02:03,  7.13it/s]
 37%|███▋      | 527/1407 [01:18<01:57,  7.50it/s]
 38%|███▊      | 528/1407 [01:18<01:59,  7.33it/s]
 38%|███▊      | 529/1407 [01:18<02:00,  7.29it/s]
 38%|███▊      | 530/1407 [01:18<02:04,  7.04it/s]
 38%|███▊      | 531/1407 [01:19<02:06,  6.94it/s]
 38%|███▊      | 532/1407 [01:19<02:06,  6.92it/s]
 38%|███▊      | 533/1407 [01:19<02:09,  6.76it/s]
 38%|███▊      | 534/1407 [01:19<02:08,  6.80it/s]
 38%|███▊      | 535/1407 [01:19<02:10,  6.67it/s]
 38%|███▊      | 536/1407 [01:19<02:09,  6.72it/s]
 38%|███▊      | 537/1407 [01:20<02:11,  6.60it/s]
 38%|███▊      | 538/1407 [01:20<02:10,  6.65it/s]
 38%|███▊      | 539/1407 [01:20<02:08,  6.74it/s]
 38%|███▊      | 540/1407 [01:20<02:07,  6.79it/s]
 38%|███▊      | 541/1407 [01:20<02:05,  6.88it/s]
 39%|███▊      | 542/1407 [01:20<02:04,  6.94it/s]
 39%|███▊      | 543/1407 [01:20<02:04,  6.94it/s]
 39%|███▊      | 544/1407 [01:21<02:03,  7.00it/s]
 39%|███▊      | 545/1407 [01:21<02:04,  6.94it/s]
 39%|███▉      | 546/1407 [01:21<02:07,  6.78it/s]
 39%|███▉      | 547/1407 [01:21<02:05,  6.83it/s]
 39%|███▉      | 548/1407 [01:21<01:59,  7.20it/s]
 39%|███▉      | 549/1407 [01:21<01:52,  7.61it/s]
 39%|███▉      | 550/1407 [01:21<01:54,  7.46it/s]
 39%|███▉      | 551/1407 [01:22<01:57,  7.30it/s]
 39%|███▉      | 552/1407 [01:22<01:58,  7.20it/s]
 39%|███▉      | 553/1407 [01:22<01:59,  7.13it/s]
 39%|███▉      | 554/1407 [01:22<01:57,  7.26it/s]
 39%|███▉      | 555/1407 [01:22<02:02,  6.98it/s]
 40%|███▉      | 556/1407 [01:22<02:02,  6.93it/s]
 40%|███▉      | 557/1407 [01:22<02:05,  6.76it/s]
 40%|███▉      | 558/1407 [01:23<02:05,  6.75it/s]
 40%|███▉      | 559/1407 [01:23<02:05,  6.78it/s]
 40%|███▉      | 560/1407 [01:23<02:06,  6.70it/s]
 40%|███▉      | 561/1407 [01:23<02:22,  5.95it/s]
 40%|███▉      | 562/1407 [01:23<02:15,  6.22it/s]
 40%|████      | 563/1407 [01:23<02:08,  6.58it/s]
 40%|████      | 564/1407 [01:23<02:06,  6.66it/s]
 40%|████      | 565/1407 [01:24<02:07,  6.61it/s]
 40%|████      | 566/1407 [01:24<02:03,  6.81it/s]
 40%|████      | 567/1407 [01:24<02:02,  6.86it/s]
 40%|████      | 568/1407 [01:24<02:04,  6.74it/s]
 40%|████      | 569/1407 [01:24<02:02,  6.86it/s]
 41%|████      | 570/1407 [01:24<02:01,  6.86it/s]
 41%|████      | 571/1407 [01:24<02:04,  6.72it/s]
 41%|████      | 572/1407 [01:25<02:02,  6.83it/s]
 41%|████      | 573/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 574/1407 [01:25<02:01,  6.83it/s]
 41%|████      | 575/1407 [01:25<02:04,  6.69it/s]
 41%|████      | 576/1407 [01:25<02:02,  6.78it/s]
 41%|████      | 577/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 578/1407 [01:26<02:01,  6.84it/s]
 41%|████      | 579/1407 [01:26<01:59,  6.92it/s]
 41%|████      | 580/1407 [01:26<01:53,  7.27it/s]
 41%|████▏     | 581/1407 [01:26<01:57,  7.03it/s]
 41%|████▏     | 582/1407 [01:26<01:57,  7.05it/s]
 41%|████▏     | 583/1407 [01:26<01:54,  7.20it/s]
 42%|████▏     | 584/1407 [01:26<01:54,  7.17it/s]
 42%|████▏     | 585/1407 [01:26<01:56,  7.04it/s]
 42%|████▏     | 586/1407 [01:27<01:59,  6.87it/s]
 42%|████▏     | 587/1407 [01:27<02:01,  6.77it/s]
 42%|████▏     | 588/1407 [01:27<02:03,  6.66it/s]
 42%|████▏     | 589/1407 [01:27<02:03,  6.62it/s]
 42%|████▏     | 590/1407 [01:27<02:01,  6.70it/s]
 42%|████▏     | 591/1407 [01:27<01:55,  7.05it/s]
 42%|████▏     | 592/1407 [01:28<01:54,  7.09it/s]
 42%|████▏     | 593/1407 [01:28<01:50,  7.35it/s]
 42%|████▏     | 594/1407 [01:28<01:51,  7.32it/s]
 42%|████▏     | 595/1407 [01:28<01:55,  7.05it/s]
 42%|████▏     | 596/1407 [01:28<01:56,  6.96it/s]
 42%|████▏     | 597/1407 [01:28<01:50,  7.31it/s]
 43%|████▎     | 598/1407 [01:28<01:47,  7.55it/s]
 43%|████▎     | 599/1407 [01:28<01:50,  7.32it/s]
 43%|████▎     | 600/1407 [01:29<01:50,  7.31it/s]
 43%|████▎     | 601/1407 [01:29<01:52,  7.16it/s]
 43%|████▎     | 602/1407 [01:29<01:54,  7.03it/s]
 43%|████▎     | 603/1407 [01:29<01:54,  7.05it/s]
 43%|████▎     | 604/1407 [01:29<01:56,  6.88it/s]
 43%|████▎     | 605/1407 [01:29<01:56,  6.89it/s]
 43%|████▎     | 606/1407 [01:29<01:51,  7.19it/s]
 43%|████▎     | 607/1407 [01:30<01:51,  7.19it/s]
 43%|████▎     | 608/1407 [01:30<01:51,  7.16it/s]
 43%|████▎     | 609/1407 [01:30<01:45,  7.58it/s]
 43%|████▎     | 610/1407 [01:30<01:48,  7.34it/s]
 43%|████▎     | 611/1407 [01:30<01:51,  7.14it/s]
 43%|████▎     | 612/1407 [01:30<01:55,  6.90it/s]
 44%|████▎     | 613/1407 [01:30<01:48,  7.29it/s]
 44%|████▎     | 614/1407 [01:31<01:53,  6.99it/s]
 44%|████▎     | 615/1407 [01:31<01:53,  6.95it/s]
 44%|████▍     | 616/1407 [01:31<01:54,  6.93it/s]
 44%|████▍     | 617/1407 [01:31<01:54,  6.90it/s]
 44%|████▍     | 618/1407 [01:31<01:57,  6.74it/s]
 44%|████▍     | 619/1407 [01:31<01:55,  6.79it/s]
 44%|████▍     | 620/1407 [01:31<01:56,  6.78it/s]
 44%|████▍     | 621/1407 [01:32<01:49,  7.18it/s]
 44%|████▍     | 622/1407 [01:32<01:52,  6.97it/s]
 44%|████▍     | 623/1407 [01:32<01:52,  6.96it/s]
 44%|████▍     | 624/1407 [01:32<01:54,  6.81it/s]
 44%|████▍     | 625/1407 [01:32<01:55,  6.79it/s]
 44%|████▍     | 626/1407 [01:32<01:49,  7.15it/s]
 45%|████▍     | 627/1407 [01:32<01:42,  7.62it/s]
 45%|████▍     | 628/1407 [01:33<01:44,  7.45it/s]
 45%|████▍     | 629/1407 [01:33<01:49,  7.11it/s]
 45%|████▍     | 630/1407 [01:33<01:48,  7.17it/s]
 45%|████▍     | 631/1407 [01:33<01:51,  6.97it/s]
 45%|████▍     | 632/1407 [01:33<01:49,  7.06it/s]
 45%|████▍     | 633/1407 [01:33<01:50,  7.03it/s]
 45%|████▌     | 634/1407 [01:33<01:53,  6.83it/s]
 45%|████▌     | 635/1407 [01:34<01:53,  6.83it/s]
 45%|████▌     | 636/1407 [01:34<01:55,  6.69it/s]
 45%|████▌     | 637/1407 [01:34<01:54,  6.70it/s]
 45%|████▌     | 638/1407 [01:34<01:56,  6.60it/s]
 45%|████▌     | 639/1407 [01:34<01:54,  6.70it/s]
 45%|████▌     | 640/1407 [01:34<01:53,  6.76it/s]
 46%|████▌     | 641/1407 [01:34<01:52,  6.79it/s]
 46%|████▌     | 642/1407 [01:35<01:53,  6.77it/s]
 46%|████▌     | 643/1407 [01:35<01:50,  6.91it/s]
 46%|████▌     | 644/1407 [01:35<01:53,  6.75it/s]
 46%|████▌     | 645/1407 [01:35<01:54,  6.67it/s]
 46%|████▌     | 646/1407 [01:35<01:55,  6.60it/s]
 46%|████▌     | 647/1407 [01:35<01:55,  6.58it/s]
 46%|████▌     | 648/1407 [01:36<01:54,  6.66it/s]
 46%|████▌     | 649/1407 [01:36<01:50,  6.83it/s]
 46%|████▌     | 650/1407 [01:36<01:50,  6.84it/s]
 46%|████▋     | 651/1407 [01:36<01:50,  6.87it/s]
 46%|████▋     | 652/1407 [01:36<01:52,  6.71it/s]
 46%|████▋     | 653/1407 [01:36<01:53,  6.66it/s]
 46%|████▋     | 654/1407 [01:36<01:52,  6.68it/s]
 47%|████▋     | 655/1407 [01:37<01:54,  6.59it/s]
 47%|████▋     | 656/1407 [01:37<01:51,  6.72it/s]
 47%|████▋     | 657/1407 [01:37<01:50,  6.79it/s]
 47%|████▋     | 658/1407 [01:37<01:50,  6.80it/s]
 47%|████▋     | 659/1407 [01:37<01:51,  6.68it/s]
 47%|████▋     | 660/1407 [01:37<01:52,  6.64it/s]
 47%|████▋     | 661/1407 [01:37<01:43,  7.24it/s]
 47%|████▋     | 662/1407 [01:38<01:47,  6.96it/s]
 47%|████▋     | 663/1407 [01:38<01:47,  6.95it/s]
 47%|████▋     | 664/1407 [01:38<01:49,  6.81it/s]
 47%|████▋     | 665/1407 [01:38<01:43,  7.18it/s]
 47%|████▋     | 666/1407 [01:38<01:42,  7.21it/s]
 47%|████▋     | 667/1407 [01:38<01:46,  6.96it/s]
 47%|████▋     | 668/1407 [01:38<01:45,  6.99it/s]
 48%|████▊     | 669/1407 [01:39<01:46,  6.95it/s]
 48%|████▊     | 670/1407 [01:39<01:47,  6.88it/s]
 48%|████▊     | 671/1407 [01:39<01:46,  6.91it/s]
 48%|████▊     | 672/1407 [01:39<01:48,  6.76it/s]
 48%|████▊     | 673/1407 [01:39<01:48,  6.78it/s]
 48%|████▊     | 674/1407 [01:39<01:47,  6.79it/s]
 48%|████▊     | 675/1407 [01:39<01:41,  7.18it/s]
 48%|████▊     | 676/1407 [01:40<01:41,  7.21it/s]
 48%|████▊     | 677/1407 [01:40<01:45,  6.94it/s]
 48%|████▊     | 678/1407 [01:40<01:46,  6.87it/s]
 48%|████▊     | 679/1407 [01:40<01:48,  6.73it/s]
 48%|████▊     | 680/1407 [01:40<01:48,  6.73it/s]
 48%|████▊     | 681/1407 [01:40<01:49,  6.62it/s]
 48%|████▊     | 682/1407 [01:40<01:45,  6.89it/s]
 49%|████▊     | 683/1407 [01:41<01:42,  7.08it/s]
 49%|████▊     | 684/1407 [01:41<01:43,  7.00it/s]
 49%|████▊     | 685/1407 [01:41<01:44,  6.92it/s]
 49%|████▉     | 686/1407 [01:41<01:46,  6.75it/s]
 49%|████▉     | 687/1407 [01:41<01:48,  6.63it/s]
 49%|████▉     | 688/1407 [01:41<01:46,  6.77it/s]
 49%|████▉     | 689/1407 [01:42<01:45,  6.83it/s]
 49%|████▉     | 690/1407 [01:42<01:45,  6.83it/s]
 49%|████▉     | 691/1407 [01:42<01:44,  6.85it/s]
 49%|████▉     | 692/1407 [01:42<01:43,  6.89it/s]
 49%|████▉     | 693/1407 [01:42<01:43,  6.87it/s]
 49%|████▉     | 694/1407 [01:42<01:45,  6.75it/s]
 49%|████▉     | 695/1407 [01:42<01:45,  6.75it/s]
 49%|████▉     | 696/1407 [01:43<01:44,  6.82it/s]
 50%|████▉     | 697/1407 [01:43<01:42,  6.90it/s]
 50%|████▉     | 698/1407 [01:43<01:45,  6.73it/s]
 50%|████▉     | 699/1407 [01:43<01:44,  6.80it/s]
 50%|████▉     | 700/1407 [01:43<01:45,  6.72it/s]
 50%|████▉     | 701/1407 [01:43<01:46,  6.61it/s]
 50%|████▉     | 702/1407 [01:43<01:45,  6.70it/s]
 50%|████▉     | 703/1407 [01:44<01:43,  6.83it/s]
 50%|█████     | 704/1407 [01:44<01:52,  6.26it/s]
 50%|█████     | 705/1407 [01:44<01:48,  6.45it/s]
 50%|█████     | 706/1407 [01:44<01:49,  6.43it/s]
 50%|█████     | 707/1407 [01:44<01:45,  6.61it/s]
 50%|█████     | 708/1407 [01:44<01:44,  6.71it/s]
 50%|█████     | 709/1407 [01:45<01:45,  6.61it/s]
 50%|█████     | 710/1407 [01:45<01:43,  6.75it/s]
 51%|█████     | 711/1407 [01:45<01:43,  6.74it/s]
 51%|█████     | 712/1407 [01:45<01:44,  6.67it/s]
 51%|█████     | 713/1407 [01:45<01:45,  6.58it/s]
 51%|█████     | 714/1407 [01:45<01:41,  6.85it/s]
 51%|█████     | 715/1407 [01:45<01:43,  6.70it/s]
 51%|█████     | 716/1407 [01:46<01:42,  6.71it/s]
 51%|█████     | 717/1407 [01:46<01:37,  7.04it/s]
 51%|█████     | 718/1407 [01:46<01:32,  7.41it/s]
 51%|█████     | 719/1407 [01:46<01:35,  7.19it/s]
 51%|█████     | 720/1407 [01:46<01:39,  6.94it/s]
 51%|█████     | 721/1407 [01:46<01:39,  6.88it/s]
 51%|█████▏    | 722/1407 [01:46<01:34,  7.24it/s]
 51%|█████▏    | 723/1407 [01:47<01:37,  7.00it/s]
 51%|█████▏    | 724/1407 [01:47<01:40,  6.82it/s]
 52%|█████▏    | 725/1407 [01:47<01:41,  6.69it/s]
 52%|█████▏    | 726/1407 [01:47<01:43,  6.60it/s]
 52%|█████▏    | 727/1407 [01:47<01:42,  6.64it/s]
 52%|█████▏    | 728/1407 [01:47<01:43,  6.58it/s]
 52%|█████▏    | 729/1407 [01:47<01:40,  6.74it/s]
 52%|█████▏    | 730/1407 [01:48<01:39,  6.79it/s]
 52%|█████▏    | 731/1407 [01:48<01:39,  6.78it/s]
 52%|█████▏    | 732/1407 [01:48<01:38,  6.87it/s]
 52%|█████▏    | 733/1407 [01:48<01:37,  6.89it/s]
 52%|█████▏    | 734/1407 [01:48<01:36,  6.94it/s]
 52%|█████▏    | 735/1407 [01:48<01:37,  6.88it/s]
 52%|█████▏    | 736/1407 [01:48<01:32,  7.22it/s]
 52%|█████▏    | 737/1407 [01:49<01:34,  7.06it/s]
 52%|█████▏    | 738/1407 [01:49<01:34,  7.07it/s]
 53%|█████▎    | 739/1407 [01:49<01:35,  7.00it/s]
 53%|█████▎    | 740/1407 [01:49<01:31,  7.29it/s]
 53%|█████▎    | 741/1407 [01:49<01:32,  7.19it/s]
 53%|█████▎    | 742/1407 [01:49<01:35,  6.93it/s]
 53%|█████▎    | 743/1407 [01:49<01:35,  6.98it/s]
 53%|█████▎    | 744/1407 [01:50<01:36,  6.90it/s]
 53%|█████▎    | 745/1407 [01:50<01:35,  6.92it/s]
 53%|█████▎    | 746/1407 [01:50<01:37,  6.75it/s]
 53%|█████▎    | 747/1407 [01:50<01:37,  6.78it/s]
 53%|█████▎    | 748/1407 [01:50<01:32,  7.11it/s]
 53%|█████▎    | 749/1407 [01:50<01:34,  6.99it/s]
 53%|█████▎    | 750/1407 [01:50<01:36,  6.79it/s]
 53%|█████▎    | 751/1407 [01:51<01:35,  6.83it/s]
 53%|█████▎    | 752/1407 [01:51<01:31,  7.14it/s]
 54%|█████▎    | 753/1407 [01:51<01:31,  7.13it/s]
 54%|█████▎    | 754/1407 [01:51<01:33,  7.00it/s]
 54%|█████▎    | 755/1407 [01:51<01:32,  7.04it/s]
 54%|█████▎    | 756/1407 [01:51<01:33,  6.98it/s]
 54%|█████▍    | 757/1407 [01:51<01:29,  7.26it/s]
 54%|█████▍    | 758/1407 [01:52<01:29,  7.27it/s]
 54%|█████▍    | 759/1407 [01:52<01:30,  7.13it/s]
 54%|█████▍    | 760/1407 [01:52<01:32,  7.03it/s]
 54%|█████▍    | 761/1407 [01:52<01:33,  6.93it/s]
 54%|█████▍    | 762/1407 [01:52<01:33,  6.88it/s]
 54%|█████▍    | 763/1407 [01:52<01:28,  7.30it/s]
 54%|█████▍    | 764/1407 [01:52<01:25,  7.50it/s]
 54%|█████▍    | 765/1407 [01:53<01:27,  7.31it/s]
 54%|█████▍    | 766/1407 [01:53<01:31,  7.00it/s]
 55%|█████▍    | 767/1407 [01:53<01:32,  6.94it/s]
 55%|█████▍    | 768/1407 [01:53<01:33,  6.81it/s]
 55%|█████▍    | 769/1407 [01:53<01:35,  6.67it/s]
 55%|█████▍    | 770/1407 [01:53<01:33,  6.81it/s]
 55%|█████▍    | 771/1407 [01:53<01:32,  6.84it/s]
 55%|█████▍    | 772/1407 [01:54<01:34,  6.73it/s]
 55%|█████▍    | 773/1407 [01:54<01:32,  6.83it/s]
 55%|█████▌    | 774/1407 [01:54<02:09,  4.89it/s]
 55%|█████▌    | 775/1407 [01:54<01:56,  5.42it/s]
 55%|█████▌    | 776/1407 [01:54<01:48,  5.80it/s]
 55%|█████▌    | 777/1407 [01:54<01:42,  6.15it/s]
 55%|█████▌    | 778/1407 [01:55<01:37,  6.46it/s]
 55%|█████▌    | 779/1407 [01:55<01:36,  6.54it/s]
 55%|█████▌    | 780/1407 [01:55<01:33,  6.70it/s]
 56%|█████▌    | 781/1407 [01:55<01:34,  6.60it/s]
 56%|█████▌    | 782/1407 [01:55<01:32,  6.79it/s]
 56%|█████▌    | 783/1407 [01:55<01:31,  6.83it/s]
 56%|█████▌    | 784/1407 [01:55<01:30,  6.86it/s]
 56%|█████▌    | 785/1407 [01:56<01:32,  6.75it/s]
 56%|█████▌    | 786/1407 [01:56<01:31,  6.80it/s]
 56%|█████▌    | 787/1407 [01:56<01:30,  6.88it/s]
 56%|█████▌    | 788/1407 [01:56<01:30,  6.84it/s]
 56%|█████▌    | 789/1407 [01:56<01:31,  6.74it/s]
 56%|█████▌    | 790/1407 [01:56<01:30,  6.79it/s]
 56%|█████▌    | 791/1407 [01:57<01:32,  6.66it/s]
 56%|█████▋    | 792/1407 [01:57<01:32,  6.68it/s]
 56%|█████▋    | 793/1407 [01:57<01:33,  6.59it/s]
 56%|█████▋    | 794/1407 [01:57<01:33,  6.57it/s]
 57%|█████▋    | 795/1407 [01:57<01:31,  6.67it/s]
 57%|█████▋    | 796/1407 [01:57<01:29,  6.81it/s]
 57%|█████▋    | 797/1407 [01:57<01:29,  6.79it/s]
 57%|█████▋    | 798/1407 [01:58<01:29,  6.77it/s]
 57%|█████▋    | 799/1407 [01:58<01:30,  6.69it/s]
 57%|█████▋    | 800/1407 [01:58<01:26,  7.05it/s]
 57%|█████▋    | 801/1407 [01:58<01:25,  7.06it/s]
 57%|█████▋    | 802/1407 [01:58<01:28,  6.84it/s]
 57%|█████▋    | 803/1407 [01:58<01:28,  6.85it/s]
 57%|█████▋    | 804/1407 [01:58<01:23,  7.21it/s]
 57%|█████▋    | 805/1407 [01:59<01:26,  6.94it/s]
 57%|█████▋    | 806/1407 [01:59<01:24,  7.12it/s]
 57%|█████▋    | 807/1407 [01:59<01:20,  7.42it/s]
 57%|█████▋    | 808/1407 [01:59<01:22,  7.27it/s]
 57%|█████▋    | 809/1407 [01:59<01:24,  7.10it/s]
 58%|█████▊    | 810/1407 [01:59<01:22,  7.24it/s]
 58%|█████▊    | 811/1407 [01:59<01:25,  6.96it/s]
 58%|█████▊    | 812/1407 [02:00<01:23,  7.14it/s]
 58%|█████▊    | 813/1407 [02:00<01:23,  7.14it/s]
 58%|█████▊    | 814/1407 [02:00<01:23,  7.07it/s]
 58%|█████▊    | 815/1407 [02:00<01:24,  7.00it/s]
 58%|█████▊    | 816/1407 [02:00<01:25,  6.92it/s]
 58%|█████▊    | 817/1407 [02:00<01:25,  6.89it/s]
 58%|█████▊    | 818/1407 [02:00<01:27,  6.74it/s]
 58%|█████▊    | 819/1407 [02:01<01:26,  6.78it/s]
 58%|█████▊    | 820/1407 [02:01<01:27,  6.70it/s]
 58%|█████▊    | 821/1407 [02:01<01:27,  6.73it/s]
 58%|█████▊    | 822/1407 [02:01<01:24,  6.89it/s]
 58%|█████▊    | 823/1407 [02:01<01:24,  6.88it/s]
 59%|█████▊    | 824/1407 [02:01<01:24,  6.90it/s]
 59%|█████▊    | 825/1407 [02:01<01:20,  7.19it/s]
 59%|█████▊    | 826/1407 [02:02<01:22,  7.04it/s]
 59%|█████▉    | 827/1407 [02:02<01:22,  7.01it/s]
 59%|█████▉    | 828/1407 [02:02<01:24,  6.85it/s]
 59%|█████▉    | 829/1407 [02:02<01:24,  6.82it/s]
 59%|█████▉    | 830/1407 [02:02<01:24,  6.83it/s]
 59%|█████▉    | 831/1407 [02:02<01:23,  6.87it/s]
 59%|█████▉    | 832/1407 [02:02<01:19,  7.20it/s]
 59%|█████▉    | 833/1407 [02:03<01:20,  7.10it/s]
 59%|█████▉    | 834/1407 [02:03<01:19,  7.24it/s]
 59%|█████▉    | 835/1407 [02:03<01:19,  7.21it/s]
 59%|█████▉    | 836/1407 [02:03<01:17,  7.32it/s]
 59%|█████▉    | 837/1407 [02:03<01:19,  7.18it/s]
 60%|█████▉    | 838/1407 [02:03<01:19,  7.15it/s]
 60%|█████▉    | 839/1407 [02:03<01:20,  7.06it/s]
 60%|█████▉    | 840/1407 [02:04<01:20,  7.02it/s]
 60%|█████▉    | 841/1407 [02:04<01:22,  6.86it/s]
 60%|█████▉    | 842/1407 [02:04<01:21,  6.93it/s]
 60%|█████▉    | 843/1407 [02:04<01:22,  6.88it/s]
 60%|█████▉    | 844/1407 [02:04<01:22,  6.83it/s]
 60%|██████    | 845/1407 [02:04<01:23,  6.69it/s]
 60%|██████    | 846/1407 [02:04<01:19,  7.04it/s]
 60%|██████    | 847/1407 [02:05<01:21,  6.88it/s]
 60%|██████    | 848/1407 [02:05<01:21,  6.86it/s]
 60%|██████    | 849/1407 [02:05<01:21,  6.88it/s]
 60%|██████    | 850/1407 [02:05<01:21,  6.86it/s]
 60%|██████    | 851/1407 [02:05<01:20,  6.92it/s]
 61%|██████    | 852/1407 [02:05<01:21,  6.79it/s]
 61%|██████    | 853/1407 [02:05<01:20,  6.90it/s]
 61%|██████    | 854/1407 [02:06<01:13,  7.53it/s]
 61%|██████    | 855/1407 [02:06<01:17,  7.14it/s]
 61%|██████    | 856/1407 [02:06<01:17,  7.08it/s]
 61%|██████    | 857/1407 [02:06<01:17,  7.10it/s]
 61%|██████    | 858/1407 [02:06<01:17,  7.05it/s]
 61%|██████    | 859/1407 [02:06<01:18,  6.95it/s]
 61%|██████    | 860/1407 [02:06<01:19,  6.88it/s]
 61%|██████    | 861/1407 [02:07<01:21,  6.72it/s]
 61%|██████▏   | 862/1407 [02:07<01:19,  6.83it/s]
 61%|██████▏   | 863/1407 [02:07<01:19,  6.84it/s]
 61%|██████▏   | 864/1407 [02:07<01:18,  6.91it/s]
 61%|██████▏   | 865/1407 [02:07<01:19,  6.78it/s]
 62%|██████▏   | 866/1407 [02:07<01:20,  6.71it/s]
 62%|██████▏   | 867/1407 [02:07<01:19,  6.77it/s]
 62%|██████▏   | 868/1407 [02:08<01:16,  7.09it/s]
 62%|██████▏   | 869/1407 [02:08<01:15,  7.09it/s]
 62%|██████▏   | 870/1407 [02:08<01:16,  7.01it/s]
 62%|██████▏   | 871/1407 [02:08<01:16,  6.99it/s]
 62%|██████▏   | 872/1407 [02:08<01:18,  6.84it/s]
 62%|██████▏   | 873/1407 [02:08<01:17,  6.85it/s]
 62%|██████▏   | 874/1407 [02:08<01:18,  6.81it/s]
 62%|██████▏   | 875/1407 [02:09<01:16,  6.95it/s]
 62%|██████▏   | 876/1407 [02:09<01:17,  6.82it/s]
 62%|██████▏   | 877/1407 [02:09<01:13,  7.25it/s]
 62%|██████▏   | 878/1407 [02:09<01:15,  6.98it/s]
 62%|██████▏   | 879/1407 [02:09<01:17,  6.79it/s]
 63%|██████▎   | 880/1407 [02:09<01:19,  6.66it/s]
 63%|██████▎   | 881/1407 [02:10<01:18,  6.71it/s]
 63%|██████▎   | 882/1407 [02:10<01:18,  6.72it/s]
 63%|██████▎   | 883/1407 [02:10<01:16,  6.83it/s]
 63%|██████▎   | 884/1407 [02:10<01:15,  6.90it/s]
 63%|██████▎   | 885/1407 [02:10<01:15,  6.92it/s]
 63%|██████▎   | 886/1407 [02:10<01:17,  6.74it/s]
 63%|██████▎   | 887/1407 [02:10<01:18,  6.67it/s]
 63%|██████▎   | 888/1407 [02:11<01:16,  6.74it/s]
 63%|██████▎   | 889/1407 [02:11<01:16,  6.75it/s]
 63%|██████▎   | 890/1407 [02:11<01:13,  7.08it/s]
 63%|██████▎   | 891/1407 [02:11<01:12,  7.11it/s]
 63%|██████▎   | 892/1407 [02:11<01:13,  7.02it/s]
 63%|██████▎   | 893/1407 [02:11<01:12,  7.06it/s]
 64%|██████▎   | 894/1407 [02:11<01:13,  6.96it/s]
 64%|██████▎   | 895/1407 [02:12<01:13,  6.95it/s]
 64%|██████▎   | 896/1407 [02:12<01:12,  7.06it/s]
 64%|██████▍   | 897/1407 [02:12<01:12,  7.02it/s]
 64%|██████▍   | 898/1407 [02:12<01:14,  6.85it/s]
 64%|██████▍   | 899/1407 [02:12<01:15,  6.70it/s]
 64%|██████▍   | 900/1407 [02:12<01:15,  6.71it/s]
 64%|██████▍   | 901/1407 [02:12<01:15,  6.72it/s]
 64%|██████▍   | 902/1407 [02:13<01:14,  6.78it/s]
 64%|██████▍   | 903/1407 [02:13<01:12,  6.92it/s]
 64%|██████▍   | 904/1407 [02:13<01:10,  7.11it/s]
 64%|██████▍   | 905/1407 [02:13<01:11,  7.06it/s]
 64%|██████▍   | 906/1407 [02:13<01:11,  7.01it/s]
 64%|██████▍   | 907/1407 [02:13<01:11,  6.99it/s]
 65%|██████▍   | 908/1407 [02:13<01:11,  7.01it/s]
 65%|██████▍   | 909/1407 [02:14<01:12,  6.87it/s]
 65%|██████▍   | 910/1407 [02:14<01:06,  7.51it/s]
 65%|██████▍   | 911/1407 [02:14<01:08,  7.29it/s]
 65%|██████▍   | 912/1407 [02:14<01:09,  7.12it/s]
 65%|██████▍   | 913/1407 [02:14<01:10,  7.00it/s]
 65%|██████▍   | 914/1407 [02:14<01:11,  6.85it/s]
 65%|██████▌   | 915/1407 [02:14<01:12,  6.81it/s]
 65%|██████▌   | 916/1407 [02:15<01:12,  6.79it/s]
 65%|██████▌   | 917/1407 [02:15<01:12,  6.80it/s]
 65%|██████▌   | 918/1407 [02:15<01:12,  6.71it/s]
 65%|██████▌   | 919/1407 [02:15<01:13,  6.65it/s]
 65%|██████▌   | 920/1407 [02:15<01:13,  6.61it/s]
 65%|██████▌   | 921/1407 [02:15<01:12,  6.74it/s]
 66%|██████▌   | 922/1407 [02:15<01:12,  6.67it/s]
 66%|██████▌   | 923/1407 [02:16<01:11,  6.75it/s]
 66%|██████▌   | 924/1407 [02:16<01:10,  6.85it/s]
 66%|██████▌   | 925/1407 [02:16<01:11,  6.70it/s]
 66%|██████▌   | 926/1407 [02:16<01:12,  6.60it/s]
 66%|██████▌   | 927/1407 [02:16<01:12,  6.67it/s]
 66%|██████▌   | 928/1407 [02:16<01:10,  6.78it/s]
 66%|██████▌   | 929/1407 [02:16<01:10,  6.79it/s]
 66%|██████▌   | 930/1407 [02:17<01:11,  6.66it/s]
 66%|██████▌   | 931/1407 [02:17<01:12,  6.58it/s]
 66%|██████▌   | 932/1407 [02:17<01:11,  6.66it/s]
 66%|██████▋   | 933/1407 [02:17<01:09,  6.83it/s]
 66%|██████▋   | 934/1407 [02:17<01:10,  6.69it/s]
 66%|██████▋   | 935/1407 [02:17<01:11,  6.61it/s]
 67%|██████▋   | 936/1407 [02:18<01:10,  6.67it/s]
 67%|██████▋   | 937/1407 [02:18<01:09,  6.80it/s]
 67%|██████▋   | 938/1407 [02:18<01:05,  7.19it/s]
                                                  

 67%|██████▋   | 938/1407 [02:18<01:05,  7.19it/s]{'eval_loss': 0.6964702606201172, 'eval_accuracy': 0.6976, 'eval_f1': 0.6972550306615615, 'eval_runtime': 1.7287, 'eval_samples_per_second': 1446.215, 'eval_steps_per_second': 181.066, 'epoch': 1.0}
{'loss': 0.6307, 'learning_rate': 4.953210546139239e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.85it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.98it/s]

 21%|██        | 65/313 [00:00<00:01, 205.14it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.46it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.66it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.28it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.89it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.75it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.35it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.20it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.99it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.09it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.44it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.07it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.29it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 179.29it/s]
 67%|██████▋   | 938/1407 [02:20<01:05,  7.19it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 939/1407 [02:21<07:07,  1.09it/s]
 67%|██████▋   | 940/1407 [02:21<05:20,  1.46it/s]
 67%|██████▋   | 941/1407 [02:21<04:04,  1.91it/s]
 67%|██████▋   | 942/1407 [02:21<03:10,  2.44it/s]
 67%|██████▋   | 943/1407 [02:21<02:34,  3.01it/s]
 67%|██████▋   | 944/1407 [02:21<02:07,  3.62it/s]
 67%|██████▋   | 945/1407 [02:21<01:49,  4.21it/s]
 67%|██████▋   | 946/1407 [02:22<01:36,  4.79it/s]
 67%|██████▋   | 947/1407 [02:22<01:27,  5.25it/s]
 67%|██████▋   | 948/1407 [02:22<01:22,  5.58it/s]
 67%|██████▋   | 949/1407 [02:22<01:16,  5.97it/s]
 68%|██████▊   | 950/1407 [02:22<01:15,  6.09it/s]
 68%|██████▊   | 951/1407 [02:22<01:13,  6.19it/s]
 68%|██████▊   | 952/1407 [02:22<01:11,  6.36it/s]
 68%|██████▊   | 953/1407 [02:23<01:11,  6.37it/s]
 68%|██████▊   | 954/1407 [02:23<01:09,  6.47it/s]
 68%|██████▊   | 955/1407 [02:23<01:08,  6.61it/s]
 68%|██████▊   | 956/1407 [02:23<01:07,  6.65it/s]
 68%|██████▊   | 957/1407 [02:23<01:08,  6.61it/s]
 68%|██████▊   | 958/1407 [02:23<01:08,  6.59it/s]
 68%|██████▊   | 959/1407 [02:24<01:06,  6.71it/s]
 68%|██████▊   | 960/1407 [02:24<01:06,  6.77it/s]
 68%|██████▊   | 961/1407 [02:24<01:05,  6.83it/s]
 68%|██████▊   | 962/1407 [02:24<01:06,  6.69it/s]
 68%|██████▊   | 963/1407 [02:24<01:06,  6.64it/s]
 69%|██████▊   | 964/1407 [02:24<01:05,  6.73it/s]
 69%|██████▊   | 965/1407 [02:24<01:06,  6.63it/s]
 69%|██████▊   | 966/1407 [02:25<01:07,  6.57it/s]
 69%|██████▊   | 967/1407 [02:25<01:03,  6.95it/s]
 69%|██████▉   | 968/1407 [02:25<01:02,  7.00it/s]
 69%|██████▉   | 969/1407 [02:25<01:03,  6.85it/s]
 69%|██████▉   | 970/1407 [02:25<01:04,  6.76it/s]
 69%|██████▉   | 971/1407 [02:25<01:05,  6.68it/s]
 69%|██████▉   | 972/1407 [02:25<01:04,  6.77it/s]
 69%|██████▉   | 973/1407 [02:26<01:03,  6.84it/s]
 69%|██████▉   | 974/1407 [02:26<01:01,  7.04it/s]
 69%|██████▉   | 975/1407 [02:26<01:03,  6.83it/s]
 69%|██████▉   | 976/1407 [02:26<01:04,  6.69it/s]
 69%|██████▉   | 977/1407 [02:26<01:04,  6.65it/s]
 70%|██████▉   | 978/1407 [02:26<01:03,  6.78it/s]
 70%|██████▉   | 979/1407 [02:26<01:02,  6.83it/s]
 70%|██████▉   | 980/1407 [02:27<00:59,  7.22it/s]
 70%|██████▉   | 981/1407 [02:27<01:00,  7.07it/s]
 70%|██████▉   | 982/1407 [02:27<01:02,  6.84it/s]
 70%|██████▉   | 983/1407 [02:27<01:01,  6.87it/s]
 70%|██████▉   | 984/1407 [02:27<01:02,  6.76it/s]
 70%|███████   | 985/1407 [02:27<01:03,  6.65it/s]
 70%|███████   | 986/1407 [02:27<01:02,  6.74it/s]
 70%|███████   | 987/1407 [02:28<00:59,  7.08it/s]
 70%|███████   | 988/1407 [02:28<00:59,  7.09it/s]
 70%|███████   | 989/1407 [02:28<00:59,  7.01it/s]
 70%|███████   | 990/1407 [02:28<00:59,  6.96it/s]
 70%|███████   | 991/1407 [02:28<00:59,  7.00it/s]
 71%|███████   | 992/1407 [02:28<01:01,  6.80it/s]
 71%|███████   | 993/1407 [02:28<01:00,  6.89it/s]
 71%|███████   | 994/1407 [02:29<00:57,  7.18it/s]
 71%|███████   | 995/1407 [02:29<00:58,  7.04it/s]
 71%|███████   | 996/1407 [02:29<00:58,  7.03it/s]
 71%|███████   | 997/1407 [02:29<00:58,  7.00it/s]
 71%|███████   | 998/1407 [02:29<00:58,  7.03it/s]
 71%|███████   | 999/1407 [02:29<00:57,  7.05it/s]
 71%|███████   | 1000/1407 [02:29<00:58,  6.96it/s]
 71%|███████   | 1001/1407 [02:30<00:58,  6.89it/s]
 71%|███████   | 1002/1407 [02:30<00:57,  7.01it/s]
 71%|███████▏  | 1003/1407 [02:30<00:57,  7.08it/s]
 71%|███████▏  | 1004/1407 [02:30<00:57,  6.98it/s]
 71%|███████▏  | 1005/1407 [02:30<00:57,  6.97it/s]
 71%|███████▏  | 1006/1407 [02:30<00:59,  6.78it/s]
 72%|███████▏  | 1007/1407 [02:30<00:58,  6.80it/s]
 72%|███████▏  | 1008/1407 [02:31<00:59,  6.70it/s]
 72%|███████▏  | 1009/1407 [02:31<00:56,  7.09it/s]
 72%|███████▏  | 1010/1407 [02:31<00:56,  6.98it/s]
 72%|███████▏  | 1011/1407 [02:31<00:57,  6.95it/s]
 72%|███████▏  | 1012/1407 [02:31<00:57,  6.92it/s]
 72%|███████▏  | 1013/1407 [02:31<00:58,  6.79it/s]
 72%|███████▏  | 1014/1407 [02:32<00:59,  6.66it/s]
 72%|███████▏  | 1015/1407 [02:32<00:58,  6.73it/s]
 72%|███████▏  | 1016/1407 [02:32<00:57,  6.86it/s]
 72%|███████▏  | 1017/1407 [02:32<00:57,  6.82it/s]
 72%|███████▏  | 1018/1407 [02:32<00:58,  6.68it/s]
 72%|███████▏  | 1019/1407 [02:32<00:54,  7.10it/s]
 72%|███████▏  | 1020/1407 [02:32<00:55,  7.03it/s]
 73%|███████▎  | 1021/1407 [02:33<00:55,  6.94it/s]
 73%|███████▎  | 1022/1407 [02:33<00:53,  7.24it/s]
 73%|███████▎  | 1023/1407 [02:33<00:54,  7.08it/s]
 73%|███████▎  | 1024/1407 [02:33<00:54,  7.00it/s]
 73%|███████▎  | 1025/1407 [02:33<00:53,  7.08it/s]
 73%|███████▎  | 1026/1407 [02:33<00:55,  6.86it/s]
 73%|███████▎  | 1027/1407 [02:33<00:54,  6.99it/s]
 73%|███████▎  | 1028/1407 [02:34<00:54,  6.91it/s]
 73%|███████▎  | 1029/1407 [02:34<00:55,  6.86it/s]
 73%|███████▎  | 1030/1407 [02:34<00:55,  6.74it/s]
 73%|███████▎  | 1031/1407 [02:34<00:56,  6.67it/s]
 73%|███████▎  | 1032/1407 [02:34<00:55,  6.82it/s]
 73%|███████▎  | 1033/1407 [02:34<00:54,  6.87it/s]
 73%|███████▎  | 1034/1407 [02:34<00:55,  6.76it/s]
 74%|███████▎  | 1035/1407 [02:35<00:54,  6.79it/s]
 74%|███████▎  | 1036/1407 [02:35<00:52,  7.01it/s]
 74%|███████▎  | 1037/1407 [02:35<00:52,  7.00it/s]
 74%|███████▍  | 1038/1407 [02:35<00:52,  7.03it/s]
 74%|███████▍  | 1039/1407 [02:35<00:52,  6.98it/s]
 74%|███████▍  | 1040/1407 [02:35<00:52,  6.94it/s]
 74%|███████▍  | 1041/1407 [02:35<00:52,  6.92it/s]
 74%|███████▍  | 1042/1407 [02:36<00:49,  7.33it/s]
 74%|███████▍  | 1043/1407 [02:36<00:51,  7.14it/s]
 74%|███████▍  | 1044/1407 [02:36<00:51,  7.06it/s]
 74%|███████▍  | 1045/1407 [02:36<00:51,  7.03it/s]
 74%|███████▍  | 1046/1407 [02:36<00:51,  7.00it/s]
 74%|███████▍  | 1047/1407 [02:36<00:52,  6.92it/s]
 74%|███████▍  | 1048/1407 [02:36<00:51,  6.93it/s]
 75%|███████▍  | 1049/1407 [02:37<00:52,  6.88it/s]
 75%|███████▍  | 1050/1407 [02:37<00:53,  6.72it/s]
 75%|███████▍  | 1051/1407 [02:37<00:53,  6.63it/s]
 75%|███████▍  | 1052/1407 [02:37<00:54,  6.56it/s]
 75%|███████▍  | 1053/1407 [02:37<00:53,  6.64it/s]
 75%|███████▍  | 1054/1407 [02:37<00:53,  6.57it/s]
 75%|███████▍  | 1055/1407 [02:37<00:53,  6.62it/s]
 75%|███████▌  | 1056/1407 [02:38<00:49,  7.03it/s]
 75%|███████▌  | 1057/1407 [02:38<00:47,  7.33it/s]
 75%|███████▌  | 1058/1407 [02:38<00:48,  7.22it/s]
 75%|███████▌  | 1059/1407 [02:38<00:48,  7.13it/s]
 75%|███████▌  | 1060/1407 [02:38<00:49,  7.04it/s]
 75%|███████▌  | 1061/1407 [02:38<00:47,  7.34it/s]
 75%|███████▌  | 1062/1407 [02:38<00:49,  7.03it/s]
 76%|███████▌  | 1063/1407 [02:39<00:49,  6.96it/s]
 76%|███████▌  | 1064/1407 [02:39<00:49,  6.95it/s]
 76%|███████▌  | 1065/1407 [02:39<00:50,  6.78it/s]
 76%|███████▌  | 1066/1407 [02:39<00:49,  6.82it/s]
 76%|███████▌  | 1067/1407 [02:39<00:49,  6.87it/s]
 76%|███████▌  | 1068/1407 [02:39<00:48,  6.97it/s]
 76%|███████▌  | 1069/1407 [02:39<00:48,  6.90it/s]
 76%|███████▌  | 1070/1407 [02:40<00:50,  6.73it/s]
 76%|███████▌  | 1071/1407 [02:40<00:50,  6.66it/s]
 76%|███████▌  | 1072/1407 [02:40<00:49,  6.71it/s]
 76%|███████▋  | 1073/1407 [02:40<00:48,  6.84it/s]
 76%|███████▋  | 1074/1407 [02:40<00:49,  6.70it/s]
 76%|███████▋  | 1075/1407 [02:40<00:49,  6.71it/s]
 76%|███████▋  | 1076/1407 [02:40<00:50,  6.61it/s]
 77%|███████▋  | 1077/1407 [02:41<00:49,  6.70it/s]
 77%|███████▋  | 1078/1407 [02:41<00:48,  6.77it/s]
 77%|███████▋  | 1079/1407 [02:41<00:48,  6.70it/s]
 77%|███████▋  | 1080/1407 [02:41<00:49,  6.65it/s]
 77%|███████▋  | 1081/1407 [02:41<00:48,  6.75it/s]
 77%|███████▋  | 1082/1407 [02:41<00:44,  7.31it/s]
 77%|███████▋  | 1083/1407 [02:41<00:46,  7.02it/s]
 77%|███████▋  | 1084/1407 [02:42<00:46,  7.01it/s]
 77%|███████▋  | 1085/1407 [02:42<00:46,  6.97it/s]
 77%|███████▋  | 1086/1407 [02:42<00:46,  6.83it/s]
 77%|███████▋  | 1087/1407 [02:42<00:44,  7.15it/s]
 77%|███████▋  | 1088/1407 [02:42<00:46,  6.90it/s]
 77%|███████▋  | 1089/1407 [02:42<00:45,  6.91it/s]
 77%|███████▋  | 1090/1407 [02:42<00:43,  7.26it/s]
 78%|███████▊  | 1091/1407 [02:43<00:44,  7.13it/s]
 78%|███████▊  | 1092/1407 [02:43<00:44,  7.08it/s]
 78%|███████▊  | 1093/1407 [02:43<00:44,  7.01it/s]
 78%|███████▊  | 1094/1407 [02:43<00:45,  6.96it/s]
 78%|███████▊  | 1095/1407 [02:43<00:44,  6.95it/s]
 78%|███████▊  | 1096/1407 [02:43<00:44,  7.00it/s]
 78%|███████▊  | 1097/1407 [02:43<00:42,  7.26it/s]
 78%|███████▊  | 1098/1407 [02:44<00:43,  7.14it/s]
 78%|███████▊  | 1099/1407 [02:44<00:43,  7.02it/s]
 78%|███████▊  | 1100/1407 [02:44<00:43,  7.04it/s]
 78%|███████▊  | 1101/1407 [02:44<00:44,  6.86it/s]
 78%|███████▊  | 1102/1407 [02:44<00:44,  6.82it/s]
 78%|███████▊  | 1103/1407 [02:44<00:45,  6.69it/s]
 78%|███████▊  | 1104/1407 [02:44<00:42,  7.10it/s]
 79%|███████▊  | 1105/1407 [02:45<00:43,  7.01it/s]
 79%|███████▊  | 1106/1407 [02:45<00:44,  6.81it/s]
 79%|███████▊  | 1107/1407 [02:45<00:44,  6.68it/s]
 79%|███████▊  | 1108/1407 [02:45<00:44,  6.69it/s]
 79%|███████▉  | 1109/1407 [02:45<00:43,  6.82it/s]
 79%|███████▉  | 1110/1407 [02:45<00:40,  7.31it/s]
 79%|███████▉  | 1111/1407 [02:45<00:40,  7.31it/s]
 79%|███████▉  | 1112/1407 [02:46<00:43,  6.78it/s]
 79%|███████▉  | 1113/1407 [02:46<00:43,  6.80it/s]
 79%|███████▉  | 1114/1407 [02:46<00:42,  6.84it/s]
 79%|███████▉  | 1115/1407 [02:46<00:43,  6.74it/s]
 79%|███████▉  | 1116/1407 [02:46<00:42,  6.86it/s]
 79%|███████▉  | 1117/1407 [02:46<00:42,  6.87it/s]
 79%|███████▉  | 1118/1407 [02:47<00:41,  6.89it/s]
 80%|███████▉  | 1119/1407 [02:47<00:41,  6.90it/s]
 80%|███████▉  | 1120/1407 [02:47<00:41,  6.96it/s]
 80%|███████▉  | 1121/1407 [02:47<00:39,  7.24it/s]
 80%|███████▉  | 1122/1407 [02:47<00:38,  7.46it/s]
 80%|███████▉  | 1123/1407 [02:47<00:39,  7.25it/s]
 80%|███████▉  | 1124/1407 [02:47<00:39,  7.23it/s]
 80%|███████▉  | 1125/1407 [02:47<00:36,  7.64it/s]
 80%|████████  | 1126/1407 [02:48<00:36,  7.79it/s]
 80%|████████  | 1127/1407 [02:48<00:36,  7.73it/s]
 80%|████████  | 1128/1407 [02:48<00:36,  7.59it/s]
 80%|████████  | 1129/1407 [02:48<00:38,  7.18it/s]
 80%|████████  | 1130/1407 [02:48<00:38,  7.12it/s]
 80%|████████  | 1131/1407 [02:48<00:39,  7.07it/s]
 80%|████████  | 1132/1407 [02:48<00:39,  6.89it/s]
 81%|████████  | 1133/1407 [02:49<00:39,  6.87it/s]
 81%|████████  | 1134/1407 [02:49<00:39,  6.88it/s]
 81%|████████  | 1135/1407 [02:49<00:39,  6.94it/s]
 81%|████████  | 1136/1407 [02:49<00:38,  6.99it/s]
 81%|████████  | 1137/1407 [02:49<00:38,  6.98it/s]
 81%|████████  | 1138/1407 [02:49<00:38,  6.97it/s]
 81%|████████  | 1139/1407 [02:49<00:36,  7.32it/s]
 81%|████████  | 1140/1407 [02:50<00:37,  7.19it/s]
 81%|████████  | 1141/1407 [02:50<00:38,  6.93it/s]
 81%|████████  | 1142/1407 [02:50<00:36,  7.21it/s]
 81%|████████  | 1143/1407 [02:50<00:38,  6.94it/s]
 81%|████████▏ | 1144/1407 [02:50<00:38,  6.90it/s]
 81%|████████▏ | 1145/1407 [02:50<00:38,  6.78it/s]
 81%|████████▏ | 1146/1407 [02:50<00:36,  7.11it/s]
 82%|████████▏ | 1147/1407 [02:51<00:37,  6.98it/s]
 82%|████████▏ | 1148/1407 [02:51<00:53,  4.81it/s]
 82%|████████▏ | 1149/1407 [02:51<00:48,  5.30it/s]
 82%|████████▏ | 1150/1407 [02:51<00:44,  5.71it/s]
 82%|████████▏ | 1151/1407 [02:51<00:42,  5.99it/s]
 82%|████████▏ | 1152/1407 [02:52<00:41,  6.14it/s]
 82%|████████▏ | 1153/1407 [02:52<00:40,  6.24it/s]
 82%|████████▏ | 1154/1407 [02:52<00:39,  6.38it/s]
 82%|████████▏ | 1155/1407 [02:52<00:39,  6.38it/s]
 82%|████████▏ | 1156/1407 [02:52<00:36,  6.79it/s]
 82%|████████▏ | 1157/1407 [02:52<00:36,  6.83it/s]
 82%|████████▏ | 1158/1407 [02:52<00:37,  6.70it/s]
 82%|████████▏ | 1159/1407 [02:53<00:36,  6.77it/s]
 82%|████████▏ | 1160/1407 [02:53<00:35,  6.87it/s]
 83%|████████▎ | 1161/1407 [02:53<00:36,  6.76it/s]
 83%|████████▎ | 1162/1407 [02:53<00:36,  6.64it/s]
 83%|████████▎ | 1163/1407 [02:53<00:37,  6.56it/s]
 83%|████████▎ | 1164/1407 [02:53<00:34,  6.96it/s]
 83%|████████▎ | 1165/1407 [02:53<00:34,  7.00it/s]
 83%|████████▎ | 1166/1407 [02:54<00:34,  6.98it/s]
 83%|████████▎ | 1167/1407 [02:54<00:34,  6.91it/s]
 83%|████████▎ | 1168/1407 [02:54<00:34,  6.89it/s]
 83%|████████▎ | 1169/1407 [02:54<00:34,  6.84it/s]
 83%|████████▎ | 1170/1407 [02:54<00:34,  6.82it/s]
 83%|████████▎ | 1171/1407 [02:54<00:34,  6.86it/s]
 83%|████████▎ | 1172/1407 [02:54<00:34,  6.82it/s]
 83%|████████▎ | 1173/1407 [02:55<00:34,  6.72it/s]
 83%|████████▎ | 1174/1407 [02:55<00:33,  6.88it/s]
 84%|████████▎ | 1175/1407 [02:55<00:32,  7.17it/s]
 84%|████████▎ | 1176/1407 [02:55<00:33,  6.93it/s]
 84%|████████▎ | 1177/1407 [02:55<00:34,  6.76it/s]
 84%|████████▎ | 1178/1407 [02:55<00:33,  6.85it/s]
 84%|████████▍ | 1179/1407 [02:55<00:33,  6.89it/s]
 84%|████████▍ | 1180/1407 [02:56<00:33,  6.73it/s]
 84%|████████▍ | 1181/1407 [02:56<00:32,  6.85it/s]
 84%|████████▍ | 1182/1407 [02:56<00:32,  6.89it/s]
 84%|████████▍ | 1183/1407 [02:56<00:30,  7.26it/s]
 84%|████████▍ | 1184/1407 [02:56<00:31,  6.98it/s]
 84%|████████▍ | 1185/1407 [02:56<00:32,  6.79it/s]
 84%|████████▍ | 1186/1407 [02:57<00:32,  6.81it/s]
 84%|████████▍ | 1187/1407 [02:57<00:32,  6.85it/s]
 84%|████████▍ | 1188/1407 [02:57<00:30,  7.15it/s]
 85%|████████▍ | 1189/1407 [02:57<00:31,  6.96it/s]
 85%|████████▍ | 1190/1407 [02:57<00:31,  6.95it/s]
 85%|████████▍ | 1191/1407 [02:57<00:31,  6.89it/s]
 85%|████████▍ | 1192/1407 [02:57<00:30,  6.95it/s]
 85%|████████▍ | 1193/1407 [02:58<00:30,  6.91it/s]
 85%|████████▍ | 1194/1407 [02:58<00:31,  6.75it/s]
 85%|████████▍ | 1195/1407 [02:58<00:30,  6.84it/s]
 85%|████████▌ | 1196/1407 [02:58<00:30,  6.97it/s]
 85%|████████▌ | 1197/1407 [02:58<00:30,  6.95it/s]
 85%|████████▌ | 1198/1407 [02:58<00:30,  6.82it/s]
 85%|████████▌ | 1199/1407 [02:58<00:28,  7.18it/s]
 85%|████████▌ | 1200/1407 [02:58<00:27,  7.51it/s]
 85%|████████▌ | 1201/1407 [02:59<00:27,  7.38it/s]
 85%|████████▌ | 1202/1407 [02:59<00:29,  7.04it/s]
 86%|████████▌ | 1203/1407 [02:59<00:29,  6.95it/s]
 86%|████████▌ | 1204/1407 [02:59<00:29,  6.99it/s]
 86%|████████▌ | 1205/1407 [02:59<00:28,  7.03it/s]
 86%|████████▌ | 1206/1407 [02:59<00:28,  6.94it/s]
 86%|████████▌ | 1207/1407 [03:00<00:28,  6.94it/s]
 86%|████████▌ | 1208/1407 [03:00<00:28,  6.91it/s]
 86%|████████▌ | 1209/1407 [03:00<00:29,  6.76it/s]
 86%|████████▌ | 1210/1407 [03:00<00:28,  6.82it/s]
 86%|████████▌ | 1211/1407 [03:00<00:26,  7.36it/s]
 86%|████████▌ | 1212/1407 [03:00<00:25,  7.55it/s]
 86%|████████▌ | 1213/1407 [03:00<00:26,  7.35it/s]
 86%|████████▋ | 1214/1407 [03:00<00:26,  7.15it/s]
 86%|████████▋ | 1215/1407 [03:01<00:27,  6.94it/s]
 86%|████████▋ | 1216/1407 [03:01<00:28,  6.77it/s]
 86%|████████▋ | 1217/1407 [03:01<00:27,  6.86it/s]
 87%|████████▋ | 1218/1407 [03:01<00:35,  5.33it/s]
 87%|████████▋ | 1219/1407 [03:01<00:31,  5.98it/s]
 87%|████████▋ | 1220/1407 [03:01<00:29,  6.29it/s]
 87%|████████▋ | 1221/1407 [03:02<00:28,  6.45it/s]
 87%|████████▋ | 1222/1407 [03:02<00:27,  6.63it/s]
 87%|████████▋ | 1223/1407 [03:02<00:28,  6.55it/s]
 87%|████████▋ | 1224/1407 [03:02<00:27,  6.61it/s]
 87%|████████▋ | 1225/1407 [03:02<00:26,  6.99it/s]
 87%|████████▋ | 1226/1407 [03:02<00:25,  6.97it/s]
 87%|████████▋ | 1227/1407 [03:02<00:25,  6.92it/s]
 87%|████████▋ | 1228/1407 [03:03<00:25,  6.90it/s]
 87%|████████▋ | 1229/1407 [03:03<00:25,  6.95it/s]
 87%|████████▋ | 1230/1407 [03:03<00:25,  6.94it/s]
 87%|████████▋ | 1231/1407 [03:03<00:24,  7.25it/s]
 88%|████████▊ | 1232/1407 [03:03<00:24,  7.20it/s]
 88%|████████▊ | 1233/1407 [03:03<00:24,  7.10it/s]
 88%|████████▊ | 1234/1407 [03:03<00:24,  6.92it/s]
 88%|████████▊ | 1235/1407 [03:04<00:24,  7.00it/s]
 88%|████████▊ | 1236/1407 [03:04<00:22,  7.45it/s]
 88%|████████▊ | 1237/1407 [03:04<00:22,  7.63it/s]
 88%|████████▊ | 1238/1407 [03:04<00:23,  7.34it/s]
 88%|████████▊ | 1239/1407 [03:04<00:22,  7.32it/s]
 88%|████████▊ | 1240/1407 [03:04<00:23,  7.21it/s]
 88%|████████▊ | 1241/1407 [03:04<00:23,  6.94it/s]
 88%|████████▊ | 1242/1407 [03:05<00:23,  6.94it/s]
 88%|████████▊ | 1243/1407 [03:05<00:23,  7.05it/s]
 88%|████████▊ | 1244/1407 [03:05<00:23,  6.95it/s]
 88%|████████▊ | 1245/1407 [03:05<00:23,  6.92it/s]
 89%|████████▊ | 1246/1407 [03:05<00:22,  7.21it/s]
 89%|████████▊ | 1247/1407 [03:05<00:22,  7.06it/s]
 89%|████████▊ | 1248/1407 [03:05<00:22,  6.99it/s]
 89%|████████▉ | 1249/1407 [03:06<00:22,  6.92it/s]
 89%|████████▉ | 1250/1407 [03:06<00:22,  6.93it/s]
 89%|████████▉ | 1251/1407 [03:06<00:22,  6.93it/s]
 89%|████████▉ | 1252/1407 [03:06<00:22,  6.77it/s]
 89%|████████▉ | 1253/1407 [03:06<00:22,  6.87it/s]
 89%|████████▉ | 1254/1407 [03:06<00:22,  6.89it/s]
 89%|████████▉ | 1255/1407 [03:06<00:20,  7.28it/s]
 89%|████████▉ | 1256/1407 [03:07<00:21,  7.12it/s]
 89%|████████▉ | 1257/1407 [03:07<00:21,  7.04it/s]
 89%|████████▉ | 1258/1407 [03:07<00:21,  6.87it/s]
 89%|████████▉ | 1259/1407 [03:07<00:21,  6.86it/s]
 90%|████████▉ | 1260/1407 [03:07<00:21,  6.71it/s]
 90%|████████▉ | 1261/1407 [03:07<00:22,  6.62it/s]
 90%|████████▉ | 1262/1407 [03:07<00:21,  6.65it/s]
 90%|████████▉ | 1263/1407 [03:08<00:21,  6.73it/s]
 90%|████████▉ | 1264/1407 [03:08<00:21,  6.79it/s]
 90%|████████▉ | 1265/1407 [03:08<00:20,  6.84it/s]
 90%|████████▉ | 1266/1407 [03:08<00:20,  6.94it/s]
 90%|█████████ | 1267/1407 [03:08<00:19,  7.05it/s]
 90%|█████████ | 1268/1407 [03:08<00:20,  6.84it/s]
 90%|█████████ | 1269/1407 [03:08<00:20,  6.87it/s]
 90%|█████████ | 1270/1407 [03:09<00:20,  6.83it/s]
 90%|█████████ | 1271/1407 [03:09<00:20,  6.74it/s]
 90%|█████████ | 1272/1407 [03:09<00:19,  6.78it/s]
 90%|█████████ | 1273/1407 [03:09<00:19,  6.87it/s]
 91%|█████████ | 1274/1407 [03:09<00:19,  6.76it/s]
 91%|█████████ | 1275/1407 [03:09<00:19,  6.78it/s]
 91%|█████████ | 1276/1407 [03:10<00:19,  6.87it/s]
 91%|█████████ | 1278/1407 [03:10<00:16,  7.75it/s]
 91%|█████████ | 1279/1407 [03:10<00:17,  7.47it/s]
 91%|█████████ | 1280/1407 [03:10<00:17,  7.40it/s]
 91%|█████████ | 1281/1407 [03:10<00:17,  7.32it/s]
 91%|█████████ | 1282/1407 [03:10<00:17,  7.26it/s]
 91%|█████████ | 1283/1407 [03:10<00:17,  7.00it/s]
 91%|█████████▏| 1284/1407 [03:11<00:17,  6.98it/s]
 91%|█████████▏| 1285/1407 [03:11<00:17,  6.80it/s]
 91%|█████████▏| 1286/1407 [03:11<00:18,  6.72it/s]
 91%|█████████▏| 1287/1407 [03:11<00:18,  6.65it/s]
 92%|█████████▏| 1288/1407 [03:11<00:17,  6.78it/s]
 92%|█████████▏| 1289/1407 [03:11<00:17,  6.77it/s]
 92%|█████████▏| 1290/1407 [03:11<00:16,  6.92it/s]
 92%|█████████▏| 1291/1407 [03:12<00:16,  7.10it/s]
 92%|█████████▏| 1292/1407 [03:12<00:16,  6.87it/s]
 92%|█████████▏| 1293/1407 [03:12<00:16,  6.87it/s]
 92%|█████████▏| 1294/1407 [03:12<00:16,  6.99it/s]
 92%|█████████▏| 1295/1407 [03:12<00:16,  6.92it/s]
 92%|█████████▏| 1296/1407 [03:12<00:15,  7.20it/s]
 92%|█████████▏| 1297/1407 [03:12<00:15,  7.08it/s]
 92%|█████████▏| 1298/1407 [03:13<00:15,  7.02it/s]
 92%|█████████▏| 1299/1407 [03:13<00:15,  6.96it/s]
 92%|█████████▏| 1300/1407 [03:13<00:15,  6.89it/s]
 92%|█████████▏| 1301/1407 [03:13<00:15,  6.92it/s]
 93%|█████████▎| 1302/1407 [03:13<00:15,  6.75it/s]
 93%|█████████▎| 1303/1407 [03:13<00:15,  6.87it/s]
 93%|█████████▎| 1304/1407 [03:13<00:14,  7.19it/s]
 93%|█████████▎| 1305/1407 [03:14<00:14,  7.13it/s]
 93%|█████████▎| 1306/1407 [03:14<00:14,  7.01it/s]
 93%|█████████▎| 1307/1407 [03:14<00:14,  6.80it/s]
 93%|█████████▎| 1308/1407 [03:14<00:13,  7.20it/s]
 93%|█████████▎| 1309/1407 [03:14<00:13,  7.09it/s]
 93%|█████████▎| 1310/1407 [03:14<00:13,  6.99it/s]
 93%|█████████▎| 1311/1407 [03:14<00:13,  7.02it/s]
 93%|█████████▎| 1312/1407 [03:15<00:13,  6.97it/s]
 93%|█████████▎| 1313/1407 [03:15<00:13,  6.95it/s]
 93%|█████████▎| 1314/1407 [03:15<00:13,  7.00it/s]
 93%|█████████▎| 1315/1407 [03:15<00:13,  6.86it/s]
 94%|█████████▎| 1316/1407 [03:15<00:13,  6.95it/s]
 94%|█████████▎| 1317/1407 [03:15<00:12,  6.94it/s]
 94%|█████████▎| 1318/1407 [03:15<00:12,  7.30it/s]
 94%|█████████▎| 1319/1407 [03:16<00:12,  7.12it/s]
 94%|█████████▍| 1320/1407 [03:16<00:12,  7.11it/s]
 94%|█████████▍| 1321/1407 [03:16<00:11,  7.34it/s]
 94%|█████████▍| 1322/1407 [03:16<00:12,  7.03it/s]
 94%|█████████▍| 1323/1407 [03:16<00:11,  7.07it/s]
 94%|█████████▍| 1324/1407 [03:16<00:11,  6.97it/s]
 94%|█████████▍| 1325/1407 [03:16<00:11,  6.96it/s]
 94%|█████████▍| 1326/1407 [03:17<00:11,  6.79it/s]
 94%|█████████▍| 1327/1407 [03:17<00:11,  6.94it/s]
 94%|█████████▍| 1328/1407 [03:17<00:10,  7.25it/s]
 94%|█████████▍| 1329/1407 [03:17<00:10,  7.15it/s]
 95%|█████████▍| 1330/1407 [03:17<00:10,  7.02it/s]
 95%|█████████▍| 1331/1407 [03:17<00:11,  6.86it/s]
 95%|█████████▍| 1332/1407 [03:18<00:11,  6.76it/s]
 95%|█████████▍| 1333/1407 [03:18<00:10,  6.78it/s]
 95%|█████████▍| 1334/1407 [03:18<00:10,  6.90it/s]
 95%|█████████▍| 1335/1407 [03:18<00:10,  6.75it/s]
 95%|█████████▍| 1336/1407 [03:18<00:10,  6.79it/s]
 95%|█████████▌| 1337/1407 [03:18<00:10,  6.78it/s]
 95%|█████████▌| 1338/1407 [03:18<00:09,  6.92it/s]
 95%|█████████▌| 1339/1407 [03:19<00:09,  6.87it/s]
 95%|█████████▌| 1340/1407 [03:19<00:09,  6.86it/s]
 95%|█████████▌| 1341/1407 [03:19<00:09,  6.81it/s]
 95%|█████████▌| 1342/1407 [03:19<00:09,  6.71it/s]
 95%|█████████▌| 1343/1407 [03:19<00:09,  6.79it/s]
 96%|█████████▌| 1344/1407 [03:19<00:09,  6.84it/s]
 96%|█████████▌| 1345/1407 [03:19<00:08,  6.92it/s]
 96%|█████████▌| 1346/1407 [03:20<00:08,  7.26it/s]
 96%|█████████▌| 1347/1407 [03:20<00:08,  7.35it/s]
 96%|█████████▌| 1348/1407 [03:20<00:08,  7.03it/s]
 96%|█████████▌| 1349/1407 [03:20<00:08,  7.00it/s]
 96%|█████████▌| 1350/1407 [03:20<00:07,  7.43it/s]
 96%|█████████▌| 1351/1407 [03:20<00:07,  7.10it/s]
 96%|█████████▌| 1352/1407 [03:20<00:07,  7.05it/s]
 96%|█████████▌| 1353/1407 [03:21<00:07,  7.20it/s]
 96%|█████████▌| 1354/1407 [03:21<00:07,  6.94it/s]
 96%|█████████▋| 1355/1407 [03:21<00:07,  6.98it/s]
 96%|█████████▋| 1356/1407 [03:21<00:07,  6.83it/s]
 96%|█████████▋| 1357/1407 [03:21<00:07,  6.73it/s]
 97%|█████████▋| 1358/1407 [03:21<00:07,  6.74it/s]
 97%|█████████▋| 1359/1407 [03:21<00:07,  6.80it/s]
 97%|█████████▋| 1360/1407 [03:22<00:07,  6.68it/s]
 97%|█████████▋| 1361/1407 [03:22<00:06,  6.62it/s]
 97%|█████████▋| 1362/1407 [03:22<00:06,  6.59it/s]
 97%|█████████▋| 1363/1407 [03:22<00:06,  6.70it/s]
 97%|█████████▋| 1364/1407 [03:22<00:06,  6.72it/s]
 97%|█████████▋| 1365/1407 [03:22<00:06,  6.78it/s]
 97%|█████████▋| 1366/1407 [03:22<00:06,  6.65it/s]
 97%|█████████▋| 1367/1407 [03:23<00:06,  6.57it/s]
 97%|█████████▋| 1368/1407 [03:23<00:05,  6.55it/s]
 97%|█████████▋| 1369/1407 [03:23<00:05,  6.55it/s]
 97%|█████████▋| 1370/1407 [03:23<00:05,  6.63it/s]
 97%|█████████▋| 1371/1407 [03:23<00:05,  6.73it/s]
 98%|█████████▊| 1372/1407 [03:23<00:05,  6.75it/s]
 98%|█████████▊| 1373/1407 [03:23<00:04,  6.82it/s]
 98%|█████████▊| 1374/1407 [03:24<00:04,  6.86it/s]
 98%|█████████▊| 1375/1407 [03:24<00:04,  6.71it/s]
 98%|█████████▊| 1376/1407 [03:24<00:04,  6.62it/s]
 98%|█████████▊| 1377/1407 [03:24<00:04,  6.59it/s]
 98%|█████████▊| 1378/1407 [03:24<00:04,  6.57it/s]
 98%|█████████▊| 1379/1407 [03:24<00:04,  6.75it/s]
 98%|█████████▊| 1380/1407 [03:25<00:03,  6.81it/s]
 98%|█████████▊| 1381/1407 [03:25<00:03,  7.03it/s]
 98%|█████████▊| 1382/1407 [03:25<00:03,  6.96it/s]
 98%|█████████▊| 1383/1407 [03:25<00:03,  6.78it/s]
 98%|█████████▊| 1384/1407 [03:25<00:03,  6.71it/s]
 98%|█████████▊| 1385/1407 [03:25<00:03,  6.77it/s]
 99%|█████████▊| 1386/1407 [03:25<00:03,  6.86it/s]
 99%|█████████▊| 1387/1407 [03:26<00:02,  6.75it/s]
 99%|█████████▊| 1388/1407 [03:26<00:02,  6.63it/s]
 99%|█████████▊| 1389/1407 [03:26<00:02,  6.56it/s]
 99%|█████████▉| 1390/1407 [03:26<00:02,  6.55it/s]
 99%|█████████▉| 1391/1407 [03:26<00:02,  6.70it/s]
 99%|█████████▉| 1392/1407 [03:26<00:02,  7.05it/s]
 99%|█████████▉| 1393/1407 [03:26<00:01,  7.02it/s]
 99%|█████████▉| 1394/1407 [03:27<00:01,  7.01it/s]
 99%|█████████▉| 1395/1407 [03:27<00:01,  6.86it/s]
 99%|█████████▉| 1396/1407 [03:27<00:01,  6.83it/s]
 99%|█████████▉| 1397/1407 [03:27<00:01,  7.37it/s]
 99%|█████████▉| 1398/1407 [03:27<00:01,  7.20it/s]
 99%|█████████▉| 1399/1407 [03:27<00:01,  6.94it/s]
100%|█████████▉| 1400/1407 [03:27<00:00,  7.01it/s]
100%|█████████▉| 1401/1407 [03:28<00:00,  7.00it/s]
100%|█████████▉| 1402/1407 [03:28<00:00,  6.81it/s]
100%|█████████▉| 1403/1407 [03:28<00:00,  6.70it/s]
100%|█████████▉| 1404/1407 [03:28<00:00,  7.14it/s]
100%|█████████▉| 1405/1407 [03:28<00:00,  7.09it/s]
100%|█████████▉| 1406/1407 [03:28<00:00,  7.02it/s]
100%|██████████| 1407/1407 [03:28<00:00,  7.38it/s]
                                                   

100%|██████████| 1407/1407 [03:28<00:00,  7.38it/s]{'eval_loss': 0.6806452870368958, 'eval_accuracy': 0.7116, 'eval_f1': 0.7092190261111732, 'eval_runtime': 1.7293, 'eval_samples_per_second': 1445.695, 'eval_steps_per_second': 181.001, 'epoch': 2.0}
{'loss': 0.5453, 'learning_rate': 1.0538745842849446e-08, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.35it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.73it/s]

 21%|██        | 66/313 [00:00<00:01, 206.28it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.37it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.82it/s]

 40%|████      | 126/313 [00:00<00:01, 185.55it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.29it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.37it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.53it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.57it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.56it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.26it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.06it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 185.06it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 179.13it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 179.13it/s]
100%|██████████| 1407/1407 [03:30<00:00,  7.38it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 1407/1407 [03:31<00:00,  7.38it/s]
100%|██████████| 1407/1407 [03:31<00:00,  6.65it/s]
[I 2023-10-26 22:43:50,164] Trial 14 finished with value: 0.7148284939983418 and parameters: {'lr_scheduler_type': 'linear', 'learning_rate': 1.3342052237047397e-05, 'per_device_train_batch_size': 64, 'weight_decay': 0.0001294026845779533}. Best is trial 6 with value: 0.716991552355688.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6737045645713806, 'eval_accuracy': 0.7156, 'eval_f1': 0.7148284939983418, 'eval_runtime': 1.7283, 'eval_samples_per_second': 1446.541, 'eval_steps_per_second': 181.107, 'epoch': 3.0}
{'train_runtime': 211.5899, 'train_samples_per_second': 425.351, 'train_steps_per_second': 6.65, 'train_loss': 0.6702649103637782, 'epoch': 3.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<03:58, 11.79it/s]
  0%|          | 4/2814 [00:00<04:00, 11.70it/s]
  0%|          | 6/2814 [00:00<04:00, 11.68it/s]
  0%|          | 8/2814 [00:00<03:57, 11.81it/s]
  0%|          | 10/2814 [00:00<04:00, 11.67it/s]
  0%|          | 12/2814 [00:01<04:02, 11.54it/s]
  0%|          | 14/2814 [00:01<04:02, 11.57it/s]
  1%|          | 16/2814 [00:01<03:54, 11.92it/s]
  1%|          | 18/2814 [00:01<03:55, 11.88it/s]
  1%|          | 20/2814 [00:01<03:49, 12.19it/s]
  1%|          | 22/2814 [00:01<03:51, 12.04it/s]
  1%|          | 24/2814 [00:01<03:36, 12.88it/s]
  1%|          | 26/2814 [00:02<03:39, 12.69it/s]
  1%|          | 28/2814 [00:02<03:46, 12.29it/s]
  1%|          | 30/2814 [00:02<03:48, 12.18it/s]
  1%|          | 32/2814 [00:02<03:38, 12.72it/s]
  1%|          | 34/2814 [00:02<03:36, 12.83it/s]
  1%|▏         | 36/2814 [00:02<03:37, 12.75it/s]
  1%|▏         | 38/2814 [00:03<03:45, 12.28it/s]
  1%|▏         | 40/2814 [00:03<03:52, 11.92it/s]
  1%|▏         | 42/2814 [00:03<03:46, 12.23it/s]
  2%|▏         | 44/2814 [00:03<03:50, 12.00it/s]
  2%|▏         | 46/2814 [00:03<03:53, 11.86it/s]
  2%|▏         | 48/2814 [00:03<03:52, 11.89it/s]
  2%|▏         | 50/2814 [00:04<03:50, 12.01it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.91it/s]
  2%|▏         | 54/2814 [00:04<03:50, 11.95it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.08it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.04it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.80it/s]
  2%|▏         | 62/2814 [00:05<03:29, 13.16it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.63it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.09it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.91it/s]
  2%|▏         | 70/2814 [00:05<03:55, 11.64it/s]
  3%|▎         | 72/2814 [00:05<03:55, 11.63it/s]
  3%|▎         | 74/2814 [00:06<03:49, 11.91it/s]
  3%|▎         | 76/2814 [00:06<03:51, 11.80it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.76it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.29it/s]
  3%|▎         | 82/2814 [00:06<03:47, 12.01it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.11it/s]
  3%|▎         | 86/2814 [00:07<03:44, 12.18it/s]
  3%|▎         | 88/2814 [00:07<03:42, 12.24it/s]
  3%|▎         | 90/2814 [00:07<03:44, 12.16it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.68it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.18it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.33it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.22it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.04it/s]
  4%|▎         | 102/2814 [00:08<03:41, 12.26it/s]
  4%|▎         | 104/2814 [00:08<03:30, 12.85it/s]
  4%|▍         | 106/2814 [00:08<03:38, 12.40it/s]
  4%|▍         | 108/2814 [00:08<03:40, 12.26it/s]
  4%|▍         | 110/2814 [00:09<03:32, 12.73it/s]
  4%|▍         | 112/2814 [00:09<03:40, 12.28it/s]
  4%|▍         | 114/2814 [00:09<03:42, 12.13it/s]
  4%|▍         | 116/2814 [00:09<03:36, 12.44it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.05it/s]
  4%|▍         | 120/2814 [00:09<03:37, 12.41it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.04it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.21it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.94it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.09it/s]
  5%|▍         | 130/2814 [00:10<04:22, 10.24it/s]
  5%|▍         | 132/2814 [00:10<04:00, 11.15it/s]
  5%|▍         | 134/2814 [00:11<03:50, 11.61it/s]
  5%|▍         | 136/2814 [00:11<03:46, 11.80it/s]
  5%|▍         | 138/2814 [00:11<03:44, 11.93it/s]
  5%|▍         | 140/2814 [00:11<03:46, 11.83it/s]
  5%|▌         | 142/2814 [00:11<03:38, 12.20it/s]
  5%|▌         | 144/2814 [00:11<03:42, 12.00it/s]
  5%|▌         | 146/2814 [00:12<03:41, 12.03it/s]
  5%|▌         | 148/2814 [00:12<03:43, 11.95it/s]
  5%|▌         | 150/2814 [00:12<03:36, 12.31it/s]
  5%|▌         | 152/2814 [00:12<03:41, 12.04it/s]
  5%|▌         | 154/2814 [00:12<03:44, 11.87it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.38it/s]
  6%|▌         | 158/2814 [00:13<03:35, 12.34it/s]
  6%|▌         | 160/2814 [00:13<03:41, 11.99it/s]
  6%|▌         | 162/2814 [00:13<03:38, 12.12it/s]
  6%|▌         | 164/2814 [00:13<03:38, 12.11it/s]
  6%|▌         | 166/2814 [00:13<03:36, 12.20it/s]
  6%|▌         | 168/2814 [00:13<03:32, 12.43it/s]
  6%|▌         | 170/2814 [00:14<03:36, 12.19it/s]
  6%|▌         | 172/2814 [00:14<03:40, 11.97it/s]
  6%|▌         | 174/2814 [00:14<03:34, 12.31it/s]
  6%|▋         | 176/2814 [00:14<03:29, 12.57it/s]
  6%|▋         | 178/2814 [00:14<03:22, 13.01it/s]
  6%|▋         | 180/2814 [00:14<03:31, 12.46it/s]
  6%|▋         | 182/2814 [00:15<03:37, 12.08it/s]
  7%|▋         | 184/2814 [00:15<03:41, 11.85it/s]
  7%|▋         | 186/2814 [00:15<03:43, 11.74it/s]
  7%|▋         | 188/2814 [00:15<03:39, 11.98it/s]
  7%|▋         | 190/2814 [00:15<03:40, 11.92it/s]
  7%|▋         | 192/2814 [00:15<03:37, 12.04it/s]
  7%|▋         | 194/2814 [00:16<03:39, 11.92it/s]
  7%|▋         | 196/2814 [00:16<03:42, 11.79it/s]
  7%|▋         | 198/2814 [00:16<03:39, 11.89it/s]
  7%|▋         | 200/2814 [00:16<03:38, 11.95it/s]
  7%|▋         | 202/2814 [00:16<03:40, 11.84it/s]
  7%|▋         | 204/2814 [00:16<03:42, 11.75it/s]
  7%|▋         | 206/2814 [00:17<03:46, 11.53it/s]
  7%|▋         | 208/2814 [00:17<03:29, 12.46it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.55it/s]
  8%|▊         | 214/2814 [00:17<03:28, 12.50it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.53it/s]
  8%|▊         | 218/2814 [00:17<03:21, 12.88it/s]
  8%|▊         | 220/2814 [00:18<03:23, 12.72it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.90it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.43it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.10it/s]
  8%|▊         | 228/2814 [00:18<03:24, 12.67it/s]
  8%|▊         | 230/2814 [00:18<03:31, 12.23it/s]
  8%|▊         | 232/2814 [00:19<03:36, 11.92it/s]
  8%|▊         | 234/2814 [00:19<03:32, 12.13it/s]
  8%|▊         | 236/2814 [00:19<03:33, 12.10it/s]
  8%|▊         | 238/2814 [00:19<03:33, 12.08it/s]
  9%|▊         | 240/2814 [00:19<03:29, 12.29it/s]
  9%|▊         | 242/2814 [00:19<03:32, 12.08it/s]
  9%|▊         | 244/2814 [00:20<03:32, 12.12it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.30it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.80it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.54it/s]
  9%|▉         | 252/2814 [00:20<03:35, 11.90it/s]
  9%|▉         | 254/2814 [00:20<03:23, 12.61it/s]
  9%|▉         | 256/2814 [00:21<03:28, 12.26it/s]
  9%|▉         | 258/2814 [00:21<03:32, 12.04it/s]
  9%|▉         | 260/2814 [00:21<03:36, 11.82it/s]
  9%|▉         | 262/2814 [00:21<03:39, 11.62it/s]
  9%|▉         | 264/2814 [00:21<03:33, 11.97it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.76it/s]
 10%|▉         | 268/2814 [00:22<03:39, 11.62it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.97it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.24it/s]
 10%|▉         | 274/2814 [00:22<03:30, 12.06it/s]
 10%|▉         | 276/2814 [00:22<03:31, 11.99it/s]
 10%|▉         | 278/2814 [00:22<03:30, 12.07it/s]
 10%|▉         | 280/2814 [00:23<03:27, 12.23it/s]
 10%|█         | 282/2814 [00:23<03:30, 12.03it/s]
 10%|█         | 284/2814 [00:23<03:31, 11.95it/s]
 10%|█         | 286/2814 [00:23<03:25, 12.29it/s]
 10%|█         | 288/2814 [00:23<03:27, 12.16it/s]
 10%|█         | 290/2814 [00:23<03:28, 12.09it/s]
 10%|█         | 292/2814 [00:24<03:32, 11.88it/s]
 10%|█         | 294/2814 [00:24<03:34, 11.72it/s]
 11%|█         | 296/2814 [00:24<03:30, 11.98it/s]
 11%|█         | 298/2814 [00:24<03:33, 11.78it/s]
 11%|█         | 300/2814 [00:24<03:23, 12.38it/s]
 11%|█         | 302/2814 [00:24<03:24, 12.28it/s]
 11%|█         | 304/2814 [00:25<03:28, 12.06it/s]
 11%|█         | 306/2814 [00:25<03:30, 11.92it/s]
 11%|█         | 308/2814 [00:25<03:32, 11.78it/s]
 11%|█         | 310/2814 [00:25<03:27, 12.08it/s]
 11%|█         | 312/2814 [00:25<03:28, 11.98it/s]
 11%|█         | 314/2814 [00:25<03:26, 12.09it/s]
 11%|█         | 316/2814 [00:26<03:23, 12.27it/s]
 11%|█▏        | 318/2814 [00:26<03:27, 12.03it/s]
 11%|█▏        | 320/2814 [00:26<03:24, 12.18it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.57it/s]
 12%|█▏        | 324/2814 [00:26<03:24, 12.16it/s]
 12%|█▏        | 326/2814 [00:26<03:28, 11.95it/s]
 12%|█▏        | 328/2814 [00:27<03:20, 12.40it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.39it/s]
 12%|█▏        | 332/2814 [00:27<03:23, 12.18it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.03it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.36it/s]
 12%|█▏        | 338/2814 [00:27<03:25, 12.04it/s]
 12%|█▏        | 340/2814 [00:28<03:29, 11.80it/s]
 12%|█▏        | 342/2814 [00:28<03:32, 11.61it/s]
 12%|█▏        | 344/2814 [00:28<03:27, 11.92it/s]
 12%|█▏        | 346/2814 [00:28<03:24, 12.06it/s]
 12%|█▏        | 348/2814 [00:28<03:26, 11.95it/s]
 12%|█▏        | 350/2814 [00:28<03:23, 12.08it/s]
 13%|█▎        | 352/2814 [00:29<03:26, 11.92it/s]
 13%|█▎        | 354/2814 [00:29<03:28, 11.78it/s]
 13%|█▎        | 356/2814 [00:29<03:25, 11.97it/s]
 13%|█▎        | 358/2814 [00:29<03:27, 11.82it/s]
 13%|█▎        | 360/2814 [00:29<03:31, 11.61it/s]
 13%|█▎        | 362/2814 [00:29<03:25, 11.95it/s]
 13%|█▎        | 364/2814 [00:30<03:27, 11.82it/s]
 13%|█▎        | 366/2814 [00:30<03:29, 11.71it/s]
 13%|█▎        | 368/2814 [00:30<03:27, 11.78it/s]
 13%|█▎        | 370/2814 [00:30<03:30, 11.64it/s]
 13%|█▎        | 372/2814 [00:30<03:20, 12.20it/s]
 13%|█▎        | 374/2814 [00:31<04:16,  9.50it/s]
 13%|█▎        | 376/2814 [00:31<04:03, 10.00it/s]
 13%|█▎        | 378/2814 [00:31<03:53, 10.44it/s]
 14%|█▎        | 380/2814 [00:31<03:42, 10.96it/s]
 14%|█▎        | 382/2814 [00:31<03:38, 11.11it/s]
 14%|█▎        | 384/2814 [00:31<03:31, 11.47it/s]
 14%|█▎        | 386/2814 [00:32<03:32, 11.45it/s]
 14%|█▍        | 388/2814 [00:32<03:28, 11.64it/s]
 14%|█▍        | 390/2814 [00:32<03:29, 11.57it/s]
 14%|█▍        | 392/2814 [00:32<03:13, 12.55it/s]
 14%|█▍        | 394/2814 [00:32<03:20, 12.10it/s]
 14%|█▍        | 396/2814 [00:32<03:22, 11.94it/s]
 14%|█▍        | 398/2814 [00:33<03:19, 12.09it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.85it/s]
 14%|█▍        | 402/2814 [00:33<03:18, 12.14it/s]
 14%|█▍        | 404/2814 [00:33<03:20, 12.04it/s]
 14%|█▍        | 406/2814 [00:33<03:24, 11.79it/s]
 14%|█▍        | 408/2814 [00:33<03:16, 12.24it/s]
 15%|█▍        | 410/2814 [00:34<03:21, 11.95it/s]
 15%|█▍        | 412/2814 [00:34<03:19, 12.02it/s]
 15%|█▍        | 414/2814 [00:34<03:23, 11.81it/s]
 15%|█▍        | 416/2814 [00:34<03:11, 12.49it/s]
 15%|█▍        | 418/2814 [00:34<03:12, 12.45it/s]
 15%|█▍        | 420/2814 [00:34<03:14, 12.29it/s]
 15%|█▍        | 422/2814 [00:35<03:11, 12.46it/s]
 15%|█▌        | 424/2814 [00:35<03:16, 12.19it/s]
 15%|█▌        | 426/2814 [00:35<03:13, 12.37it/s]
 15%|█▌        | 428/2814 [00:35<03:09, 12.59it/s]
 15%|█▌        | 430/2814 [00:35<03:05, 12.84it/s]
 15%|█▌        | 432/2814 [00:35<03:12, 12.37it/s]
 15%|█▌        | 434/2814 [00:36<03:08, 12.63it/s]
 15%|█▌        | 436/2814 [00:36<03:57, 10.01it/s]
 16%|█▌        | 438/2814 [00:36<03:46, 10.49it/s]
 16%|█▌        | 440/2814 [00:36<03:39, 10.81it/s]
 16%|█▌        | 442/2814 [00:36<03:35, 11.01it/s]
 16%|█▌        | 444/2814 [00:36<03:24, 11.57it/s]
 16%|█▌        | 446/2814 [00:37<03:23, 11.63it/s]
 16%|█▌        | 448/2814 [00:37<03:26, 11.45it/s]
 16%|█▌        | 450/2814 [00:37<03:12, 12.30it/s]
 16%|█▌        | 452/2814 [00:37<03:09, 12.48it/s]
 16%|█▌        | 454/2814 [00:37<03:14, 12.16it/s]
 16%|█▌        | 456/2814 [00:37<03:09, 12.42it/s]
 16%|█▋        | 458/2814 [00:38<03:04, 12.80it/s]
 16%|█▋        | 460/2814 [00:38<03:12, 12.25it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.95it/s]
 16%|█▋        | 464/2814 [00:38<03:18, 11.86it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.25it/s]
 17%|█▋        | 468/2814 [00:38<03:11, 12.28it/s]
 17%|█▋        | 470/2814 [00:39<03:14, 12.06it/s]
 17%|█▋        | 472/2814 [00:39<03:10, 12.32it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.53it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 11.99it/s]
 17%|█▋        | 480/2814 [00:39<03:15, 11.94it/s]
 17%|█▋        | 482/2814 [00:40<03:15, 11.95it/s]
 17%|█▋        | 484/2814 [00:40<03:16, 11.85it/s]
 17%|█▋        | 486/2814 [00:40<03:19, 11.67it/s]
 17%|█▋        | 488/2814 [00:40<03:19, 11.64it/s]
 17%|█▋        | 490/2814 [00:40<03:13, 11.98it/s]
 17%|█▋        | 492/2814 [00:40<03:15, 11.86it/s]
 18%|█▊        | 494/2814 [00:41<03:16, 11.82it/s]
 18%|█▊        | 496/2814 [00:41<03:07, 12.36it/s]
 18%|█▊        | 498/2814 [00:41<03:11, 12.10it/s]
 18%|█▊        | 500/2814 [00:41<03:09, 12.24it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.41it/s]
 18%|█▊        | 504/2814 [00:41<03:02, 12.66it/s]
 18%|█▊        | 506/2814 [00:42<03:07, 12.32it/s]
 18%|█▊        | 508/2814 [00:42<03:04, 12.47it/s]
 18%|█▊        | 510/2814 [00:42<02:57, 12.98it/s]
 18%|█▊        | 512/2814 [00:42<03:03, 12.57it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.67it/s]
 18%|█▊        | 516/2814 [00:42<03:06, 12.30it/s]
 18%|█▊        | 518/2814 [00:43<03:03, 12.53it/s]
 18%|█▊        | 520/2814 [00:43<03:07, 12.21it/s]
 19%|█▊        | 522/2814 [00:43<03:12, 11.92it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.32it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.67it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.32it/s]
 19%|█▉        | 530/2814 [00:44<03:08, 12.10it/s]
 19%|█▉        | 532/2814 [00:44<03:07, 12.17it/s]
 19%|█▉        | 534/2814 [00:44<03:01, 12.54it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.15it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.02it/s]
 19%|█▉        | 540/2814 [00:44<03:13, 11.76it/s]
 19%|█▉        | 542/2814 [00:45<03:12, 11.80it/s]
 19%|█▉        | 544/2814 [00:45<03:02, 12.43it/s]
 19%|█▉        | 546/2814 [00:45<03:01, 12.48it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.16it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.52it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.33it/s]
 20%|█▉        | 554/2814 [00:45<03:04, 12.27it/s]
 20%|█▉        | 556/2814 [00:46<02:57, 12.73it/s]
 20%|█▉        | 558/2814 [00:46<03:00, 12.51it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.49it/s]
 20%|█▉        | 562/2814 [00:46<03:06, 12.05it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.96it/s]
 20%|██        | 566/2814 [00:46<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:47<03:02, 12.33it/s]
 20%|██        | 570/2814 [00:47<03:06, 12.02it/s]
 20%|██        | 572/2814 [00:47<03:09, 11.81it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.04it/s]
 20%|██        | 576/2814 [00:47<02:56, 12.65it/s]
 21%|██        | 578/2814 [00:47<02:57, 12.59it/s]
 21%|██        | 580/2814 [00:48<03:04, 12.12it/s]
 21%|██        | 582/2814 [00:48<02:55, 12.70it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.47it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.25it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.61it/s]
 21%|██        | 590/2814 [00:48<02:59, 12.38it/s]
 21%|██        | 592/2814 [00:49<02:57, 12.50it/s]
 21%|██        | 594/2814 [00:49<03:02, 12.19it/s]
 21%|██        | 596/2814 [00:49<03:05, 11.98it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.76it/s]
 21%|██▏       | 600/2814 [00:49<02:51, 12.92it/s]
 21%|██▏       | 602/2814 [00:49<02:47, 13.18it/s]
 21%|██▏       | 604/2814 [00:49<02:50, 13.00it/s]
 22%|██▏       | 606/2814 [00:50<02:53, 12.69it/s]
 22%|██▏       | 608/2814 [00:50<02:53, 12.70it/s]
 22%|██▏       | 610/2814 [00:50<02:48, 13.08it/s]
 22%|██▏       | 612/2814 [00:50<02:55, 12.53it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.06it/s]
 22%|██▏       | 616/2814 [00:50<03:05, 11.86it/s]
 22%|██▏       | 618/2814 [00:51<03:00, 12.15it/s]
 22%|██▏       | 620/2814 [00:51<02:59, 12.20it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.10it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.20it/s]
 22%|██▏       | 626/2814 [00:51<02:59, 12.16it/s]
 22%|██▏       | 628/2814 [00:51<02:51, 12.73it/s]
 22%|██▏       | 630/2814 [00:52<02:53, 12.62it/s]
 22%|██▏       | 632/2814 [00:52<02:52, 12.67it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.21it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.95it/s]
 23%|██▎       | 638/2814 [00:52<03:04, 11.77it/s]
 23%|██▎       | 640/2814 [00:52<03:06, 11.68it/s]
 23%|██▎       | 642/2814 [00:53<03:02, 11.92it/s]
 23%|██▎       | 644/2814 [00:53<02:52, 12.61it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.13it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.98it/s]
 23%|██▎       | 650/2814 [00:53<02:56, 12.24it/s]
 23%|██▎       | 652/2814 [00:53<03:01, 11.90it/s]
 23%|██▎       | 654/2814 [00:54<03:02, 11.82it/s]
 23%|██▎       | 656/2814 [00:54<02:54, 12.34it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.29it/s]
 23%|██▎       | 660/2814 [00:54<02:54, 12.38it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.34it/s]
 24%|██▎       | 664/2814 [00:54<02:57, 12.11it/s]
 24%|██▎       | 666/2814 [00:55<02:55, 12.24it/s]
 24%|██▎       | 668/2814 [00:55<02:58, 12.05it/s]
 24%|██▍       | 670/2814 [00:55<03:01, 11.79it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.05it/s]
 24%|██▍       | 674/2814 [00:55<02:55, 12.16it/s]
 24%|██▍       | 676/2814 [00:55<02:54, 12.28it/s]
 24%|██▍       | 678/2814 [00:56<02:53, 12.30it/s]
 24%|██▍       | 680/2814 [00:56<02:55, 12.13it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.09it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.75it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.90it/s]
 24%|██▍       | 688/2814 [00:56<02:56, 12.02it/s]
 25%|██▍       | 690/2814 [00:57<02:57, 11.97it/s]
 25%|██▍       | 692/2814 [00:57<03:01, 11.71it/s]
 25%|██▍       | 694/2814 [00:57<02:52, 12.26it/s]
 25%|██▍       | 696/2814 [00:57<02:53, 12.22it/s]
 25%|██▍       | 698/2814 [00:57<02:50, 12.44it/s]
 25%|██▍       | 700/2814 [00:57<02:49, 12.47it/s]
 25%|██▍       | 702/2814 [00:58<02:49, 12.45it/s]
 25%|██▌       | 704/2814 [00:58<02:53, 12.14it/s]
 25%|██▌       | 706/2814 [00:58<02:48, 12.55it/s]
 25%|██▌       | 708/2814 [00:58<02:44, 12.83it/s]
 25%|██▌       | 710/2814 [00:58<02:50, 12.36it/s]
 25%|██▌       | 712/2814 [00:58<02:53, 12.15it/s]
 25%|██▌       | 714/2814 [00:59<02:51, 12.22it/s]
 25%|██▌       | 716/2814 [00:59<02:50, 12.29it/s]
 26%|██▌       | 718/2814 [00:59<02:52, 12.18it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.87it/s]
 26%|██▌       | 724/2814 [00:59<02:51, 12.22it/s]
 26%|██▌       | 726/2814 [00:59<02:42, 12.81it/s]
 26%|██▌       | 728/2814 [01:00<02:50, 12.24it/s]
 26%|██▌       | 730/2814 [01:00<02:47, 12.47it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.45it/s]
 26%|██▌       | 734/2814 [01:00<02:50, 12.17it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.25it/s]
 26%|██▌       | 738/2814 [01:00<02:52, 12.07it/s]
 26%|██▋       | 740/2814 [01:01<02:47, 12.38it/s]
 26%|██▋       | 742/2814 [01:01<02:47, 12.40it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.63it/s]
 27%|██▋       | 746/2814 [01:01<02:47, 12.31it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.29it/s]
 27%|██▋       | 750/2814 [01:01<02:52, 11.94it/s]
 27%|██▋       | 752/2814 [01:02<02:52, 11.95it/s]
 27%|██▋       | 754/2814 [01:02<02:53, 11.85it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.06it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.93it/s]
 27%|██▋       | 760/2814 [01:02<02:48, 12.16it/s]
 27%|██▋       | 762/2814 [01:02<02:48, 12.17it/s]
 27%|██▋       | 764/2814 [01:03<02:44, 12.47it/s]
 27%|██▋       | 766/2814 [01:03<02:45, 12.37it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.12it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.92it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.79it/s]
 28%|██▊       | 774/2814 [01:03<02:46, 12.26it/s]
 28%|██▊       | 776/2814 [01:04<02:43, 12.46it/s]
 28%|██▊       | 778/2814 [01:04<02:45, 12.32it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.30it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.12it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 12.00it/s]
 28%|██▊       | 786/2814 [01:04<02:47, 12.14it/s]
 28%|██▊       | 788/2814 [01:05<02:46, 12.14it/s]
 28%|██▊       | 790/2814 [01:05<02:45, 12.23it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.29it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.12it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.51it/s]
 28%|██▊       | 798/2814 [01:05<02:44, 12.25it/s]
 28%|██▊       | 800/2814 [01:06<02:46, 12.08it/s]
 29%|██▊       | 802/2814 [01:06<02:48, 11.94it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.01it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.15it/s]
 29%|██▊       | 808/2814 [01:06<02:46, 12.02it/s]
 29%|██▉       | 810/2814 [01:06<02:43, 12.23it/s]
 29%|██▉       | 812/2814 [01:07<02:38, 12.61it/s]
 29%|██▉       | 814/2814 [01:07<02:41, 12.36it/s]
 29%|██▉       | 816/2814 [01:07<02:40, 12.48it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.66it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.51it/s]
 29%|██▉       | 822/2814 [01:07<02:44, 12.13it/s]
 29%|██▉       | 824/2814 [01:08<02:40, 12.43it/s]
 29%|██▉       | 826/2814 [01:08<02:42, 12.20it/s]
 29%|██▉       | 828/2814 [01:08<02:45, 12.00it/s]
 29%|██▉       | 830/2814 [01:08<02:43, 12.10it/s]
 30%|██▉       | 832/2814 [01:08<02:45, 11.94it/s]
 30%|██▉       | 834/2814 [01:08<02:49, 11.71it/s]
 30%|██▉       | 836/2814 [01:09<02:42, 12.17it/s]
 30%|██▉       | 838/2814 [01:09<02:41, 12.24it/s]
 30%|██▉       | 840/2814 [01:09<02:45, 11.94it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.84it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.76it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.14it/s]
 30%|███       | 848/2814 [01:10<02:37, 12.51it/s]
 30%|███       | 850/2814 [01:10<02:41, 12.20it/s]
 30%|███       | 852/2814 [01:10<02:41, 12.17it/s]
 30%|███       | 854/2814 [01:10<02:42, 12.08it/s]
 30%|███       | 856/2814 [01:10<02:45, 11.87it/s]
 30%|███       | 858/2814 [01:10<02:46, 11.75it/s]
 31%|███       | 860/2814 [01:11<02:43, 11.92it/s]
 31%|███       | 862/2814 [01:11<02:43, 11.90it/s]
 31%|███       | 864/2814 [01:11<02:39, 12.20it/s]
 31%|███       | 866/2814 [01:11<02:35, 12.56it/s]
 31%|███       | 868/2814 [01:11<02:34, 12.61it/s]
 31%|███       | 870/2814 [01:11<02:39, 12.22it/s]
 31%|███       | 872/2814 [01:11<02:39, 12.17it/s]
 31%|███       | 874/2814 [01:12<02:38, 12.26it/s]
 31%|███       | 876/2814 [01:12<02:41, 12.01it/s]
 31%|███       | 878/2814 [01:12<02:37, 12.26it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.08it/s]
 31%|███▏      | 882/2814 [01:12<02:41, 11.94it/s]
 31%|███▏      | 884/2814 [01:12<02:41, 11.93it/s]
 31%|███▏      | 886/2814 [01:13<02:42, 11.87it/s]
 32%|███▏      | 888/2814 [01:13<02:44, 11.69it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.90it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.61it/s]
 32%|███▏      | 896/2814 [01:14<02:41, 11.85it/s]
 32%|███▏      | 898/2814 [01:14<02:34, 12.36it/s]
 32%|███▏      | 900/2814 [01:14<02:34, 12.40it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.79it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.68it/s]
 32%|███▏      | 906/2814 [01:14<02:27, 12.89it/s]
 32%|███▏      | 908/2814 [01:14<02:33, 12.45it/s]
 32%|███▏      | 910/2814 [01:15<02:35, 12.23it/s]
 32%|███▏      | 912/2814 [01:15<02:38, 12.01it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.31it/s]
 33%|███▎      | 916/2814 [01:15<02:36, 12.11it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.05it/s]
 33%|███▎      | 920/2814 [01:15<02:35, 12.16it/s]
 33%|███▎      | 922/2814 [01:16<02:35, 12.19it/s]
 33%|███▎      | 924/2814 [01:16<02:39, 11.83it/s]
 33%|███▎      | 926/2814 [01:16<02:29, 12.67it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.78it/s]
 33%|███▎      | 930/2814 [01:16<02:31, 12.40it/s]
 33%|███▎      | 932/2814 [01:16<02:35, 12.11it/s]
 33%|███▎      | 934/2814 [01:17<02:36, 12.00it/s]
 33%|███▎      | 936/2814 [01:17<02:37, 11.91it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]{'loss': 0.8887, 'learning_rate': 3.4774460438975904e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.37it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.35it/s]

 21%|██        | 66/313 [00:00<00:01, 205.75it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.12it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.47it/s]

 40%|████      | 126/313 [00:00<00:01, 185.24it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.10it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.95it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.86it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.96it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.22it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.92it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.72it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.67it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.52it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.52it/s]
 33%|███▎      | 938/2814 [01:19<02:30, 12.48it/s]

                                                  
 33%|███▎      | 938/2814 [01:19<02:38, 11.85it/s]
[I 2023-10-26 22:45:10,020] Trial 15 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7308015823364258, 'eval_accuracy': 0.6732, 'eval_f1': 0.6699749828406618, 'eval_runtime': 1.7329, 'eval_samples_per_second': 1442.708, 'eval_steps_per_second': 180.627, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.71it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.84it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.74it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:33,  3.89it/s]
 15%|█▌        | 107/705 [00:28<02:35,  3.84it/s]
 15%|█▌        | 108/705 [00:28<02:36,  3.82it/s]
 15%|█▌        | 109/705 [00:28<02:36,  3.80it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:36,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.84it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:32,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:33,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.77it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:27,  3.82it/s]
 20%|██        | 144/705 [00:37<02:25,  3.84it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:25,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8757, 'learning_rate': 8.925610107565378e-06, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.87it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.82it/s]

 21%|██        | 65/313 [00:00<00:01, 204.76it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.08it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.27it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.95it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.62it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.47it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.14it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.03it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.97it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.13it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.46it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.06it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.27it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.27it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 22:46:14,045] Trial 16 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7244936227798462, 'eval_accuracy': 0.6772, 'eval_f1': 0.6766693643188509, 'eval_runtime': 1.7306, 'eval_samples_per_second': 1444.559, 'eval_steps_per_second': 180.859, 'epoch': 1.0}

  0%|          | 0/2814 [00:00<?, ?it/s]
  0%|          | 2/2814 [00:00<04:00, 11.69it/s]
  0%|          | 4/2814 [00:00<04:00, 11.66it/s]
  0%|          | 6/2814 [00:00<04:00, 11.68it/s]
  0%|          | 8/2814 [00:00<03:57, 11.81it/s]
  0%|          | 10/2814 [00:00<04:00, 11.66it/s]
  0%|          | 12/2814 [00:01<04:02, 11.54it/s]
  0%|          | 14/2814 [00:01<04:02, 11.56it/s]
  1%|          | 16/2814 [00:01<03:54, 11.91it/s]
  1%|          | 18/2814 [00:01<03:55, 11.87it/s]
  1%|          | 20/2814 [00:01<03:49, 12.18it/s]
  1%|          | 22/2814 [00:01<03:51, 12.04it/s]
  1%|          | 24/2814 [00:01<03:36, 12.86it/s]
  1%|          | 26/2814 [00:02<03:39, 12.67it/s]
  1%|          | 28/2814 [00:02<03:46, 12.28it/s]
  1%|          | 30/2814 [00:02<03:48, 12.16it/s]
  1%|          | 32/2814 [00:02<03:38, 12.70it/s]
  1%|          | 34/2814 [00:02<03:36, 12.82it/s]
  1%|▏         | 36/2814 [00:02<03:38, 12.74it/s]
  1%|▏         | 38/2814 [00:03<03:46, 12.28it/s]
  1%|▏         | 40/2814 [00:03<03:52, 11.92it/s]
  1%|▏         | 42/2814 [00:03<03:46, 12.23it/s]
  2%|▏         | 44/2814 [00:03<03:50, 12.00it/s]
  2%|▏         | 46/2814 [00:03<03:53, 11.87it/s]
  2%|▏         | 48/2814 [00:03<03:52, 11.90it/s]
  2%|▏         | 50/2814 [00:04<03:49, 12.02it/s]
  2%|▏         | 52/2814 [00:04<03:51, 11.93it/s]
  2%|▏         | 54/2814 [00:04<03:50, 11.96it/s]
  2%|▏         | 56/2814 [00:04<03:48, 12.09it/s]
  2%|▏         | 58/2814 [00:04<03:48, 12.05it/s]
  2%|▏         | 60/2814 [00:04<03:53, 11.80it/s]
  2%|▏         | 62/2814 [00:05<03:29, 13.15it/s]
  2%|▏         | 64/2814 [00:05<03:37, 12.63it/s]
  2%|▏         | 66/2814 [00:05<03:47, 12.08it/s]
  2%|▏         | 68/2814 [00:05<03:50, 11.91it/s]
  2%|▏         | 70/2814 [00:05<03:55, 11.64it/s]
  3%|▎         | 72/2814 [00:05<03:56, 11.62it/s]
  3%|▎         | 74/2814 [00:06<03:50, 11.91it/s]
  3%|▎         | 76/2814 [00:06<03:51, 11.81it/s]
  3%|▎         | 78/2814 [00:06<03:52, 11.76it/s]
  3%|▎         | 80/2814 [00:06<03:42, 12.29it/s]
  3%|▎         | 82/2814 [00:06<03:47, 11.99it/s]
  3%|▎         | 84/2814 [00:06<03:45, 12.09it/s]
  3%|▎         | 86/2814 [00:07<03:44, 12.17it/s]
  3%|▎         | 88/2814 [00:07<03:43, 12.21it/s]
  3%|▎         | 90/2814 [00:07<03:44, 12.15it/s]
  3%|▎         | 92/2814 [00:07<03:34, 12.67it/s]
  3%|▎         | 94/2814 [00:07<03:43, 12.17it/s]
  3%|▎         | 96/2814 [00:07<03:40, 12.33it/s]
  3%|▎         | 98/2814 [00:08<03:42, 12.22it/s]
  4%|▎         | 100/2814 [00:08<03:45, 12.02it/s]
  4%|▎         | 102/2814 [00:08<03:41, 12.26it/s]
  4%|▎         | 104/2814 [00:08<03:30, 12.85it/s]
  4%|▍         | 106/2814 [00:08<03:38, 12.40it/s]
  4%|▍         | 108/2814 [00:08<03:40, 12.26it/s]
  4%|▍         | 110/2814 [00:09<03:32, 12.72it/s]
  4%|▍         | 112/2814 [00:09<03:40, 12.27it/s]
  4%|▍         | 114/2814 [00:09<03:42, 12.13it/s]
  4%|▍         | 116/2814 [00:09<03:36, 12.44it/s]
  4%|▍         | 118/2814 [00:09<03:43, 12.05it/s]
  4%|▍         | 120/2814 [00:09<03:37, 12.40it/s]
  4%|▍         | 122/2814 [00:10<03:43, 12.03it/s]
  4%|▍         | 124/2814 [00:10<03:40, 12.20it/s]
  4%|▍         | 126/2814 [00:10<03:45, 11.93it/s]
  5%|▍         | 128/2814 [00:10<03:42, 12.07it/s]
  5%|▍         | 130/2814 [00:10<03:40, 12.18it/s]
  5%|▍         | 132/2814 [00:10<03:30, 12.74it/s]
  5%|▍         | 134/2814 [00:10<03:29, 12.79it/s]
  5%|▍         | 136/2814 [00:11<03:32, 12.63it/s]
  5%|▍         | 138/2814 [00:11<03:33, 12.52it/s]
  5%|▍         | 140/2814 [00:11<03:38, 12.23it/s]
  5%|▌         | 142/2814 [00:11<03:33, 12.49it/s]
  5%|▌         | 144/2814 [00:11<03:39, 12.19it/s]
  5%|▌         | 146/2814 [00:11<03:39, 12.17it/s]
  5%|▌         | 148/2814 [00:12<03:41, 12.05it/s]
  5%|▌         | 150/2814 [00:12<03:35, 12.37it/s]
  5%|▌         | 152/2814 [00:12<03:40, 12.09it/s]
  5%|▌         | 154/2814 [00:12<03:43, 11.91it/s]
  6%|▌         | 156/2814 [00:12<03:34, 12.41it/s]
  6%|▌         | 158/2814 [00:12<03:34, 12.38it/s]
  6%|▌         | 160/2814 [00:13<03:40, 12.02it/s]
  6%|▌         | 162/2814 [00:13<03:38, 12.14it/s]
  6%|▌         | 164/2814 [00:13<03:38, 12.13it/s]
  6%|▌         | 166/2814 [00:13<03:36, 12.23it/s]
  6%|▌         | 168/2814 [00:13<03:32, 12.44it/s]
  6%|▌         | 170/2814 [00:13<03:36, 12.21it/s]
  6%|▌         | 172/2814 [00:14<03:40, 11.99it/s]
  6%|▌         | 174/2814 [00:14<03:34, 12.32it/s]
  6%|▋         | 176/2814 [00:14<03:29, 12.58it/s]
  6%|▋         | 178/2814 [00:14<03:22, 13.01it/s]
  6%|▋         | 180/2814 [00:14<03:31, 12.46it/s]
  6%|▋         | 182/2814 [00:14<03:37, 12.08it/s]
  7%|▋         | 184/2814 [00:15<03:42, 11.84it/s]
  7%|▋         | 186/2814 [00:15<03:44, 11.73it/s]
  7%|▋         | 188/2814 [00:15<03:39, 11.97it/s]
  7%|▋         | 190/2814 [00:15<03:40, 11.91it/s]
  7%|▋         | 192/2814 [00:15<03:37, 12.04it/s]
  7%|▋         | 194/2814 [00:15<03:34, 12.21it/s]
  7%|▋         | 196/2814 [00:16<03:38, 11.99it/s]
  7%|▋         | 198/2814 [00:16<03:37, 12.04it/s]
  7%|▋         | 200/2814 [00:16<03:36, 12.06it/s]
  7%|▋         | 202/2814 [00:16<03:39, 11.90it/s]
  7%|▋         | 204/2814 [00:16<03:41, 11.80it/s]
  7%|▋         | 206/2814 [00:16<03:45, 11.56it/s]
  7%|▋         | 208/2814 [00:17<03:28, 12.48it/s]
  7%|▋         | 210/2814 [00:17<03:27, 12.55it/s]
  8%|▊         | 212/2814 [00:17<03:27, 12.56it/s]
  8%|▊         | 214/2814 [00:17<03:27, 12.51it/s]
  8%|▊         | 216/2814 [00:17<03:27, 12.54it/s]
  8%|▊         | 218/2814 [00:17<03:21, 12.89it/s]
  8%|▊         | 220/2814 [00:18<03:23, 12.73it/s]
  8%|▊         | 222/2814 [00:18<03:20, 12.91it/s]
  8%|▊         | 224/2814 [00:18<03:28, 12.44it/s]
  8%|▊         | 226/2814 [00:18<03:33, 12.10it/s]
  8%|▊         | 228/2814 [00:18<03:24, 12.68it/s]
  8%|▊         | 230/2814 [00:18<03:31, 12.23it/s]
  8%|▊         | 232/2814 [00:19<03:36, 11.92it/s]
  8%|▊         | 234/2814 [00:19<03:32, 12.13it/s]
  8%|▊         | 236/2814 [00:19<03:33, 12.10it/s]
  8%|▊         | 238/2814 [00:19<03:33, 12.08it/s]
  9%|▊         | 240/2814 [00:19<03:29, 12.29it/s]
  9%|▊         | 242/2814 [00:19<03:33, 12.07it/s]
  9%|▊         | 244/2814 [00:20<03:32, 12.12it/s]
  9%|▊         | 246/2814 [00:20<03:28, 12.30it/s]
  9%|▉         | 248/2814 [00:20<03:20, 12.80it/s]
  9%|▉         | 250/2814 [00:20<03:24, 12.56it/s]
  9%|▉         | 252/2814 [00:20<03:30, 12.16it/s]
  9%|▉         | 254/2814 [00:20<03:19, 12.81it/s]
  9%|▉         | 256/2814 [00:20<03:26, 12.39it/s]
  9%|▉         | 258/2814 [00:21<03:30, 12.12it/s]
  9%|▉         | 260/2814 [00:21<03:35, 11.87it/s]
  9%|▉         | 262/2814 [00:21<03:38, 11.65it/s]
  9%|▉         | 264/2814 [00:21<03:32, 11.98it/s]
  9%|▉         | 266/2814 [00:21<03:36, 11.75it/s]
 10%|▉         | 268/2814 [00:22<03:39, 11.61it/s]
 10%|▉         | 270/2814 [00:22<03:32, 11.96it/s]
 10%|▉         | 272/2814 [00:22<03:27, 12.22it/s]
 10%|▉         | 274/2814 [00:22<03:31, 12.04it/s]
 10%|▉         | 276/2814 [00:22<03:32, 11.97it/s]
 10%|▉         | 278/2814 [00:22<03:30, 12.05it/s]
 10%|▉         | 280/2814 [00:22<03:27, 12.21it/s]
 10%|█         | 282/2814 [00:23<03:30, 12.03it/s]
 10%|█         | 284/2814 [00:23<03:32, 11.93it/s]
 10%|█         | 286/2814 [00:23<03:25, 12.27it/s]
 10%|█         | 288/2814 [00:23<03:27, 12.15it/s]
 10%|█         | 290/2814 [00:23<03:28, 12.10it/s]
 10%|█         | 292/2814 [00:23<03:32, 11.87it/s]
 10%|█         | 294/2814 [00:24<03:34, 11.72it/s]
 11%|█         | 296/2814 [00:24<03:30, 11.98it/s]
 11%|█         | 298/2814 [00:24<03:33, 11.78it/s]
 11%|█         | 300/2814 [00:24<03:23, 12.38it/s]
 11%|█         | 302/2814 [00:24<03:29, 11.98it/s]
 11%|█         | 304/2814 [00:24<03:31, 11.85it/s]
 11%|█         | 306/2814 [00:25<03:32, 11.78it/s]
 11%|█         | 308/2814 [00:25<03:34, 11.68it/s]
 11%|█         | 310/2814 [00:25<03:28, 12.00it/s]
 11%|█         | 312/2814 [00:25<03:29, 11.93it/s]
 11%|█         | 314/2814 [00:25<03:27, 12.05it/s]
 11%|█         | 316/2814 [00:25<03:24, 12.23it/s]
 11%|█▏        | 318/2814 [00:26<03:28, 12.00it/s]
 11%|█▏        | 320/2814 [00:26<03:25, 12.15it/s]
 11%|█▏        | 322/2814 [00:26<03:18, 12.56it/s]
 12%|█▏        | 324/2814 [00:26<03:25, 12.15it/s]
 12%|█▏        | 326/2814 [00:26<03:28, 11.94it/s]
 12%|█▏        | 328/2814 [00:26<03:20, 12.38it/s]
 12%|█▏        | 330/2814 [00:27<03:20, 12.38it/s]
 12%|█▏        | 332/2814 [00:27<03:23, 12.17it/s]
 12%|█▏        | 334/2814 [00:27<03:26, 12.02it/s]
 12%|█▏        | 336/2814 [00:27<03:20, 12.35it/s]
 12%|█▏        | 338/2814 [00:27<03:25, 12.03it/s]
 12%|█▏        | 340/2814 [00:27<03:29, 11.79it/s]
 12%|█▏        | 342/2814 [00:28<03:33, 11.60it/s]
 12%|█▏        | 344/2814 [00:28<03:27, 11.90it/s]
 12%|█▏        | 346/2814 [00:28<03:24, 12.05it/s]
 12%|█▏        | 348/2814 [00:28<03:26, 11.94it/s]
 12%|█▏        | 350/2814 [00:28<03:24, 12.08it/s]
 13%|█▎        | 352/2814 [00:28<03:26, 11.92it/s]
 13%|█▎        | 354/2814 [00:29<03:28, 11.78it/s]
 13%|█▎        | 356/2814 [00:29<03:25, 11.97it/s]
 13%|█▎        | 358/2814 [00:29<03:27, 11.81it/s]
 13%|█▎        | 360/2814 [00:29<03:31, 11.59it/s]
 13%|█▎        | 362/2814 [00:29<03:25, 11.92it/s]
 13%|█▎        | 364/2814 [00:29<03:27, 11.82it/s]
 13%|█▎        | 366/2814 [00:30<03:29, 11.69it/s]
 13%|█▎        | 368/2814 [00:30<03:27, 11.76it/s]
 13%|█▎        | 370/2814 [00:30<03:30, 11.63it/s]
 13%|█▎        | 372/2814 [00:30<03:20, 12.19it/s]
 13%|█▎        | 374/2814 [00:30<03:24, 11.92it/s]
 13%|█▎        | 376/2814 [00:31<03:27, 11.76it/s]
 13%|█▎        | 378/2814 [00:31<03:27, 11.72it/s]
 14%|█▎        | 380/2814 [00:31<03:24, 11.91it/s]
 14%|█▎        | 382/2814 [00:31<03:26, 11.78it/s]
 14%|█▎        | 384/2814 [00:31<03:23, 11.97it/s]
 14%|█▎        | 386/2814 [00:31<03:25, 11.81it/s]
 14%|█▍        | 388/2814 [00:32<03:24, 11.89it/s]
 14%|█▍        | 390/2814 [00:32<03:26, 11.74it/s]
 14%|█▍        | 392/2814 [00:32<03:10, 12.69it/s]
 14%|█▍        | 394/2814 [00:32<03:18, 12.18it/s]
 14%|█▍        | 396/2814 [00:32<03:21, 11.99it/s]
 14%|█▍        | 398/2814 [00:32<03:19, 12.12it/s]
 14%|█▍        | 400/2814 [00:33<03:23, 11.87it/s]
 14%|█▍        | 402/2814 [00:33<03:18, 12.16it/s]
 14%|█▍        | 404/2814 [00:33<03:20, 12.04it/s]
 14%|█▍        | 406/2814 [00:33<03:24, 11.79it/s]
 14%|█▍        | 408/2814 [00:33<03:16, 12.24it/s]
 15%|█▍        | 410/2814 [00:33<03:21, 11.94it/s]
 15%|█▍        | 412/2814 [00:34<03:19, 12.01it/s]
 15%|█▍        | 414/2814 [00:34<03:23, 11.81it/s]
 15%|█▍        | 416/2814 [00:34<03:11, 12.49it/s]
 15%|█▍        | 418/2814 [00:34<03:12, 12.46it/s]
 15%|█▍        | 420/2814 [00:34<03:14, 12.29it/s]
 15%|█▍        | 422/2814 [00:34<03:12, 12.45it/s]
 15%|█▌        | 424/2814 [00:34<03:16, 12.17it/s]
 15%|█▌        | 426/2814 [00:35<03:13, 12.36it/s]
 15%|█▌        | 428/2814 [00:35<03:14, 12.28it/s]
 15%|█▌        | 430/2814 [00:35<03:09, 12.61it/s]
 15%|█▌        | 432/2814 [00:35<03:14, 12.22it/s]
 15%|█▌        | 434/2814 [00:35<03:10, 12.51it/s]
 15%|█▌        | 436/2814 [00:35<03:10, 12.45it/s]
 16%|█▌        | 438/2814 [00:36<03:13, 12.26it/s]
 16%|█▌        | 440/2814 [00:36<03:16, 12.06it/s]
 16%|█▌        | 442/2814 [00:36<03:19, 11.89it/s]
 16%|█▌        | 444/2814 [00:36<03:13, 12.24it/s]
 16%|█▌        | 446/2814 [00:36<03:16, 12.08it/s]
 16%|█▌        | 448/2814 [00:36<03:21, 11.75it/s]
 16%|█▌        | 450/2814 [00:37<03:08, 12.54it/s]
 16%|█▌        | 452/2814 [00:37<03:06, 12.64it/s]
 16%|█▌        | 454/2814 [00:37<03:12, 12.26it/s]
 16%|█▌        | 456/2814 [00:37<03:08, 12.51it/s]
 16%|█▋        | 458/2814 [00:37<03:03, 12.86it/s]
 16%|█▋        | 460/2814 [00:37<03:11, 12.30it/s]
 16%|█▋        | 462/2814 [00:38<03:16, 11.99it/s]
 16%|█▋        | 464/2814 [00:38<03:17, 11.88it/s]
 17%|█▋        | 466/2814 [00:38<03:11, 12.26it/s]
 17%|█▋        | 468/2814 [00:38<03:10, 12.29it/s]
 17%|█▋        | 470/2814 [00:38<03:14, 12.07it/s]
 17%|█▋        | 472/2814 [00:38<03:10, 12.32it/s]
 17%|█▋        | 474/2814 [00:39<03:06, 12.52it/s]
 17%|█▋        | 476/2814 [00:39<03:11, 12.22it/s]
 17%|█▋        | 478/2814 [00:39<03:14, 11.99it/s]
 17%|█▋        | 480/2814 [00:39<03:15, 11.93it/s]
 17%|█▋        | 482/2814 [00:39<03:15, 11.95it/s]
 17%|█▋        | 484/2814 [00:39<03:16, 11.85it/s]
 17%|█▋        | 486/2814 [00:40<03:19, 11.67it/s]
 17%|█▋        | 488/2814 [00:40<03:19, 11.64it/s]
 17%|█▋        | 490/2814 [00:40<03:13, 11.98it/s]
 17%|█▋        | 492/2814 [00:40<03:15, 11.86it/s]
 18%|█▊        | 494/2814 [00:40<03:16, 11.82it/s]
 18%|█▊        | 496/2814 [00:40<03:07, 12.36it/s]
 18%|█▊        | 498/2814 [00:41<03:11, 12.09it/s]
 18%|█▊        | 500/2814 [00:41<03:09, 12.23it/s]
 18%|█▊        | 502/2814 [00:41<03:06, 12.42it/s]
 18%|█▊        | 504/2814 [00:41<03:02, 12.67it/s]
 18%|█▊        | 506/2814 [00:41<03:07, 12.33it/s]
 18%|█▊        | 508/2814 [00:41<03:04, 12.47it/s]
 18%|█▊        | 510/2814 [00:41<02:57, 12.99it/s]
 18%|█▊        | 512/2814 [00:42<03:02, 12.59it/s]
 18%|█▊        | 514/2814 [00:42<03:01, 12.69it/s]
 18%|█▊        | 516/2814 [00:42<03:06, 12.31it/s]
 18%|█▊        | 518/2814 [00:42<03:03, 12.53it/s]
 18%|█▊        | 520/2814 [00:42<03:07, 12.21it/s]
 19%|█▊        | 522/2814 [00:42<03:12, 11.92it/s]
 19%|█▊        | 524/2814 [00:43<03:05, 12.33it/s]
 19%|█▊        | 526/2814 [00:43<03:00, 12.67it/s]
 19%|█▉        | 528/2814 [00:43<03:05, 12.34it/s]
 19%|█▉        | 530/2814 [00:43<03:08, 12.12it/s]
 19%|█▉        | 532/2814 [00:43<03:07, 12.17it/s]
 19%|█▉        | 534/2814 [00:43<03:01, 12.54it/s]
 19%|█▉        | 536/2814 [00:44<03:07, 12.15it/s]
 19%|█▉        | 538/2814 [00:44<03:09, 12.01it/s]
 19%|█▉        | 540/2814 [00:44<03:13, 11.76it/s]
 19%|█▉        | 542/2814 [00:44<03:12, 11.80it/s]
 19%|█▉        | 544/2814 [00:44<03:02, 12.42it/s]
 19%|█▉        | 546/2814 [00:44<03:01, 12.48it/s]
 19%|█▉        | 548/2814 [00:45<03:06, 12.15it/s]
 20%|█▉        | 550/2814 [00:45<03:00, 12.51it/s]
 20%|█▉        | 552/2814 [00:45<03:03, 12.31it/s]
 20%|█▉        | 554/2814 [00:45<03:04, 12.25it/s]
 20%|█▉        | 556/2814 [00:45<02:57, 12.70it/s]
 20%|█▉        | 558/2814 [00:45<03:00, 12.49it/s]
 20%|█▉        | 560/2814 [00:46<03:00, 12.47it/s]
 20%|█▉        | 562/2814 [00:46<03:07, 12.04it/s]
 20%|██        | 564/2814 [00:46<03:08, 11.95it/s]
 20%|██        | 566/2814 [00:46<03:04, 12.19it/s]
 20%|██        | 568/2814 [00:46<03:02, 12.34it/s]
 20%|██        | 570/2814 [00:46<03:06, 12.03it/s]
 20%|██        | 572/2814 [00:47<03:09, 11.81it/s]
 20%|██        | 574/2814 [00:47<03:06, 12.03it/s]
 20%|██        | 576/2814 [00:47<02:57, 12.63it/s]
 21%|██        | 578/2814 [00:47<02:57, 12.58it/s]
 21%|██        | 580/2814 [00:47<03:04, 12.11it/s]
 21%|██        | 582/2814 [00:47<02:55, 12.71it/s]
 21%|██        | 584/2814 [00:48<02:58, 12.49it/s]
 21%|██        | 586/2814 [00:48<03:01, 12.28it/s]
 21%|██        | 588/2814 [00:48<02:56, 12.63it/s]
 21%|██        | 590/2814 [00:48<02:59, 12.39it/s]
 21%|██        | 592/2814 [00:48<02:57, 12.51it/s]
 21%|██        | 594/2814 [00:48<03:01, 12.20it/s]
 21%|██        | 596/2814 [00:49<03:05, 11.98it/s]
 21%|██▏       | 598/2814 [00:49<03:08, 11.75it/s]
 21%|██▏       | 600/2814 [00:49<02:51, 12.91it/s]
 21%|██▏       | 602/2814 [00:49<02:47, 13.19it/s]
 21%|██▏       | 604/2814 [00:49<02:49, 13.00it/s]
 22%|██▏       | 606/2814 [00:49<02:53, 12.69it/s]
 22%|██▏       | 608/2814 [00:49<02:53, 12.68it/s]
 22%|██▏       | 610/2814 [00:50<02:48, 13.07it/s]
 22%|██▏       | 612/2814 [00:50<02:56, 12.50it/s]
 22%|██▏       | 614/2814 [00:50<03:02, 12.05it/s]
 22%|██▏       | 616/2814 [00:50<03:05, 11.85it/s]
 22%|██▏       | 618/2814 [00:50<03:00, 12.14it/s]
 22%|██▏       | 620/2814 [00:50<02:59, 12.19it/s]
 22%|██▏       | 622/2814 [00:51<03:01, 12.10it/s]
 22%|██▏       | 624/2814 [00:51<02:59, 12.19it/s]
 22%|██▏       | 626/2814 [00:51<03:00, 12.15it/s]
 22%|██▏       | 628/2814 [00:51<02:51, 12.73it/s]
 22%|██▏       | 630/2814 [00:51<02:52, 12.63it/s]
 22%|██▏       | 632/2814 [00:51<02:52, 12.68it/s]
 23%|██▎       | 634/2814 [00:52<02:58, 12.22it/s]
 23%|██▎       | 636/2814 [00:52<03:02, 11.96it/s]
 23%|██▎       | 638/2814 [00:52<03:04, 11.77it/s]
 23%|██▎       | 640/2814 [00:52<03:06, 11.67it/s]
 23%|██▎       | 642/2814 [00:52<03:02, 11.91it/s]
 23%|██▎       | 644/2814 [00:52<02:52, 12.61it/s]
 23%|██▎       | 646/2814 [00:53<02:58, 12.13it/s]
 23%|██▎       | 648/2814 [00:53<03:00, 11.98it/s]
 23%|██▎       | 650/2814 [00:53<02:56, 12.23it/s]
 23%|██▎       | 652/2814 [00:53<03:01, 11.89it/s]
 23%|██▎       | 654/2814 [00:53<03:02, 11.81it/s]
 23%|██▎       | 656/2814 [00:53<02:54, 12.33it/s]
 23%|██▎       | 658/2814 [00:54<02:55, 12.29it/s]
 23%|██▎       | 660/2814 [00:54<02:54, 12.38it/s]
 24%|██▎       | 662/2814 [00:54<02:54, 12.35it/s]
 24%|██▎       | 664/2814 [00:54<02:57, 12.10it/s]
 24%|██▎       | 666/2814 [00:54<02:55, 12.25it/s]
 24%|██▎       | 668/2814 [00:54<02:57, 12.06it/s]
 24%|██▍       | 670/2814 [00:55<03:01, 11.79it/s]
 24%|██▍       | 672/2814 [00:55<02:57, 12.05it/s]
 24%|██▍       | 674/2814 [00:55<02:55, 12.16it/s]
 24%|██▍       | 676/2814 [00:55<02:54, 12.28it/s]
 24%|██▍       | 678/2814 [00:55<02:53, 12.31it/s]
 24%|██▍       | 680/2814 [00:55<02:55, 12.14it/s]
 24%|██▍       | 682/2814 [00:56<02:56, 12.10it/s]
 24%|██▍       | 684/2814 [00:56<03:01, 11.76it/s]
 24%|██▍       | 686/2814 [00:56<02:58, 11.91it/s]
 24%|██▍       | 688/2814 [00:56<02:56, 12.03it/s]
 25%|██▍       | 690/2814 [00:56<02:57, 11.98it/s]
 25%|██▍       | 692/2814 [00:56<03:01, 11.72it/s]
 25%|██▍       | 694/2814 [00:57<02:52, 12.26it/s]
 25%|██▍       | 696/2814 [00:57<02:53, 12.24it/s]
 25%|██▍       | 698/2814 [00:57<02:49, 12.47it/s]
 25%|██▍       | 700/2814 [00:57<02:49, 12.50it/s]
 25%|██▍       | 702/2814 [00:57<02:49, 12.49it/s]
 25%|██▌       | 704/2814 [00:57<02:53, 12.17it/s]
 25%|██▌       | 706/2814 [00:57<02:47, 12.58it/s]
 25%|██▌       | 708/2814 [00:58<02:43, 12.86it/s]
 25%|██▌       | 710/2814 [00:58<02:50, 12.37it/s]
 25%|██▌       | 712/2814 [00:58<02:52, 12.16it/s]
 25%|██▌       | 714/2814 [00:58<02:51, 12.24it/s]
 25%|██▌       | 716/2814 [00:58<02:50, 12.31it/s]
 26%|██▌       | 718/2814 [00:58<02:51, 12.20it/s]
 26%|██▌       | 720/2814 [00:59<02:56, 11.89it/s]
 26%|██▌       | 722/2814 [00:59<02:56, 11.88it/s]
 26%|██▌       | 724/2814 [00:59<02:51, 12.21it/s]
 26%|██▌       | 726/2814 [00:59<02:42, 12.81it/s]
 26%|██▌       | 728/2814 [00:59<02:50, 12.23it/s]
 26%|██▌       | 730/2814 [00:59<02:47, 12.46it/s]
 26%|██▌       | 732/2814 [01:00<02:47, 12.44it/s]
 26%|██▌       | 734/2814 [01:00<02:51, 12.16it/s]
 26%|██▌       | 736/2814 [01:00<02:49, 12.25it/s]
 26%|██▌       | 738/2814 [01:00<02:52, 12.06it/s]
 26%|██▋       | 740/2814 [01:00<02:47, 12.37it/s]
 26%|██▋       | 742/2814 [01:00<02:47, 12.40it/s]
 26%|██▋       | 744/2814 [01:01<02:43, 12.63it/s]
 27%|██▋       | 746/2814 [01:01<02:48, 12.30it/s]
 27%|██▋       | 748/2814 [01:01<02:48, 12.29it/s]
 27%|██▋       | 750/2814 [01:01<02:52, 11.93it/s]
 27%|██▋       | 752/2814 [01:01<02:52, 11.95it/s]
 27%|██▋       | 754/2814 [01:01<02:53, 11.85it/s]
 27%|██▋       | 756/2814 [01:02<02:50, 12.06it/s]
 27%|██▋       | 758/2814 [01:02<02:52, 11.93it/s]
 27%|██▋       | 760/2814 [01:02<02:48, 12.16it/s]
 27%|██▋       | 762/2814 [01:02<02:48, 12.16it/s]
 27%|██▋       | 764/2814 [01:02<02:44, 12.45it/s]
 27%|██▋       | 766/2814 [01:02<02:45, 12.36it/s]
 27%|██▋       | 768/2814 [01:03<02:48, 12.11it/s]
 27%|██▋       | 770/2814 [01:03<02:51, 11.92it/s]
 27%|██▋       | 772/2814 [01:03<02:53, 11.79it/s]
 28%|██▊       | 774/2814 [01:03<02:46, 12.24it/s]
 28%|██▊       | 776/2814 [01:03<02:43, 12.44it/s]
 28%|██▊       | 778/2814 [01:03<02:45, 12.31it/s]
 28%|██▊       | 780/2814 [01:04<02:45, 12.29it/s]
 28%|██▊       | 782/2814 [01:04<02:47, 12.11it/s]
 28%|██▊       | 784/2814 [01:04<02:49, 11.99it/s]
 28%|██▊       | 786/2814 [01:04<02:47, 12.13it/s]
 28%|██▊       | 788/2814 [01:04<02:47, 12.12it/s]
 28%|██▊       | 790/2814 [01:04<02:45, 12.22it/s]
 28%|██▊       | 792/2814 [01:05<02:44, 12.27it/s]
 28%|██▊       | 794/2814 [01:05<02:46, 12.12it/s]
 28%|██▊       | 796/2814 [01:05<02:41, 12.50it/s]
 28%|██▊       | 798/2814 [01:05<02:44, 12.25it/s]
 28%|██▊       | 800/2814 [01:05<02:46, 12.08it/s]
 29%|██▊       | 802/2814 [01:05<02:48, 11.94it/s]
 29%|██▊       | 804/2814 [01:06<02:47, 12.00it/s]
 29%|██▊       | 806/2814 [01:06<02:45, 12.14it/s]
 29%|██▊       | 808/2814 [01:06<02:47, 12.01it/s]
 29%|██▉       | 810/2814 [01:06<02:43, 12.23it/s]
 29%|██▉       | 812/2814 [01:06<02:38, 12.62it/s]
 29%|██▉       | 814/2814 [01:06<02:41, 12.36it/s]
 29%|██▉       | 816/2814 [01:06<02:40, 12.48it/s]
 29%|██▉       | 818/2814 [01:07<02:37, 12.64it/s]
 29%|██▉       | 820/2814 [01:07<02:39, 12.50it/s]
 29%|██▉       | 822/2814 [01:07<02:44, 12.12it/s]
 29%|██▉       | 824/2814 [01:07<02:40, 12.40it/s]
 29%|██▉       | 826/2814 [01:07<02:43, 12.19it/s]
 29%|██▉       | 828/2814 [01:07<02:45, 11.99it/s]
 29%|██▉       | 830/2814 [01:08<02:44, 12.09it/s]
 30%|██▉       | 832/2814 [01:08<02:46, 11.93it/s]
 30%|██▉       | 834/2814 [01:08<02:49, 11.71it/s]
 30%|██▉       | 836/2814 [01:08<02:42, 12.16it/s]
 30%|██▉       | 838/2814 [01:08<02:41, 12.21it/s]
 30%|██▉       | 840/2814 [01:08<02:45, 11.92it/s]
 30%|██▉       | 842/2814 [01:09<02:46, 11.83it/s]
 30%|██▉       | 844/2814 [01:09<02:47, 11.76it/s]
 30%|███       | 846/2814 [01:09<02:42, 12.12it/s]
 30%|███       | 848/2814 [01:09<02:37, 12.50it/s]
 30%|███       | 850/2814 [01:09<02:41, 12.18it/s]
 30%|███       | 852/2814 [01:09<02:41, 12.16it/s]
 30%|███       | 854/2814 [01:10<02:42, 12.07it/s]
 30%|███       | 856/2814 [01:10<02:44, 11.87it/s]
 30%|███       | 858/2814 [01:10<02:46, 11.75it/s]
 31%|███       | 860/2814 [01:10<02:43, 11.93it/s]
 31%|███       | 862/2814 [01:10<02:43, 11.92it/s]
 31%|███       | 864/2814 [01:10<02:39, 12.21it/s]
 31%|███       | 866/2814 [01:11<02:35, 12.56it/s]
 31%|███       | 868/2814 [01:11<02:34, 12.61it/s]
 31%|███       | 870/2814 [01:11<02:39, 12.22it/s]
 31%|███       | 872/2814 [01:11<02:39, 12.18it/s]
 31%|███       | 874/2814 [01:11<02:38, 12.27it/s]
 31%|███       | 876/2814 [01:11<02:41, 12.03it/s]
 31%|███       | 878/2814 [01:12<02:37, 12.26it/s]
 31%|███▏      | 880/2814 [01:12<02:40, 12.08it/s]
 31%|███▏      | 882/2814 [01:12<02:41, 11.94it/s]
 31%|███▏      | 884/2814 [01:12<02:41, 11.94it/s]
 31%|███▏      | 886/2814 [01:12<02:42, 11.88it/s]
 32%|███▏      | 888/2814 [01:12<02:44, 11.69it/s]
 32%|███▏      | 890/2814 [01:13<02:41, 11.89it/s]
 32%|███▏      | 892/2814 [01:13<02:44, 11.70it/s]
 32%|███▏      | 894/2814 [01:13<02:45, 11.60it/s]
 32%|███▏      | 896/2814 [01:13<02:41, 11.84it/s]
 32%|███▏      | 898/2814 [01:13<02:34, 12.36it/s]
 32%|███▏      | 900/2814 [01:13<02:34, 12.39it/s]
 32%|███▏      | 902/2814 [01:14<02:29, 12.78it/s]
 32%|███▏      | 904/2814 [01:14<02:30, 12.67it/s]
 32%|███▏      | 906/2814 [01:14<02:28, 12.87it/s]
 32%|███▏      | 908/2814 [01:14<02:33, 12.41it/s]
 32%|███▏      | 910/2814 [01:14<02:36, 12.20it/s]
 32%|███▏      | 912/2814 [01:14<02:38, 11.99it/s]
 32%|███▏      | 914/2814 [01:15<02:34, 12.29it/s]
 33%|███▎      | 916/2814 [01:15<02:36, 12.09it/s]
 33%|███▎      | 918/2814 [01:15<02:37, 12.04it/s]
 33%|███▎      | 920/2814 [01:15<02:35, 12.16it/s]
 33%|███▎      | 922/2814 [01:15<02:35, 12.20it/s]
 33%|███▎      | 924/2814 [01:15<02:39, 11.83it/s]
 33%|███▎      | 926/2814 [01:16<02:29, 12.67it/s]
 33%|███▎      | 928/2814 [01:16<02:27, 12.78it/s]
 33%|███▎      | 930/2814 [01:16<02:32, 12.39it/s]
 33%|███▎      | 932/2814 [01:16<02:35, 12.10it/s]
 33%|███▎      | 934/2814 [01:16<02:36, 11.99it/s]
 33%|███▎      | 936/2814 [01:16<02:37, 11.92it/s]
 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]
                                                  

 33%|███▎      | 938/2814 [01:17<02:30, 12.48it/s]{'loss': 0.7897, 'learning_rate': 1.8211894169189838e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.87it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.89it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.18it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.30it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.91it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.63it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.46it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.07it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.93it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.84it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.92it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.25it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.85it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.85it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.85it/s]
 33%|███▎      | 938/2814 [01:18<02:30, 12.48it/s]

                                                  
 33%|███▎      | 938/2814 [01:18<02:37, 11.91it/s]
[I 2023-10-26 22:47:33,545] Trial 17 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6882477402687073, 'eval_accuracy': 0.692, 'eval_f1': 0.6852221321862735, 'eval_runtime': 1.7323, 'eval_samples_per_second': 1443.157, 'eval_steps_per_second': 180.683, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:48,  3.86it/s]
  8%|▊         | 58/705 [00:15<02:49,  3.81it/s]
  8%|▊         | 59/705 [00:15<02:51,  3.77it/s]
  9%|▊         | 60/705 [00:15<02:50,  3.77it/s]
  9%|▊         | 61/705 [00:16<02:49,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.91it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.86it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.86it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.93it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:43,  3.85it/s]
 11%|█         | 75/705 [00:19<02:44,  3.82it/s]
 11%|█         | 76/705 [00:19<02:45,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:43,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.79it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.79it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:39<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:21,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:19,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.75it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.80it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:56<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8037, 'learning_rate': 5.0162051828639564e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.38it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.59it/s]

 21%|██        | 66/313 [00:00<00:01, 206.00it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.07it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.47it/s]

 40%|████      | 126/313 [00:00<00:01, 185.29it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.13it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.16it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.25it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.49it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.53it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.16it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.82it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.65it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.54it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.54it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:03,  1.03s/it]
 34%|███▎      | 237/705 [01:04<06:14,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:58,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:05,  1.90it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.55it/s]
 34%|███▍      | 242/705 [01:06<02:44,  2.81it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.73it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:16<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:59,  3.49it/s]
 41%|████      | 289/705 [01:18<01:54,  3.62it/s]
 41%|████      | 290/705 [01:18<01:52,  3.69it/s]
 41%|████▏     | 291/705 [01:18<01:51,  3.71it/s]
 41%|████▏     | 292/705 [01:19<01:48,  3.81it/s]
 42%|████▏     | 293/705 [01:19<01:48,  3.80it/s]
 42%|████▏     | 294/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.77it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.80it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.91it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:50,  3.60it/s]
 44%|████▍     | 309/705 [01:23<01:47,  3.67it/s]
 44%|████▍     | 310/705 [01:23<01:47,  3.68it/s]
 44%|████▍     | 311/705 [01:24<01:46,  3.71it/s]
 44%|████▍     | 312/705 [01:24<01:45,  3.73it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.74it/s]
 45%|████▍     | 314/705 [01:24<01:38,  3.98it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.90it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.86it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:25<01:41,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.80it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:44,  3.44it/s]
 49%|████▉     | 348/705 [01:33<01:41,  3.53it/s]
 50%|████▉     | 349/705 [01:34<01:37,  3.65it/s]
 50%|████▉     | 350/705 [01:34<01:36,  3.66it/s]
 50%|████▉     | 351/705 [01:34<01:36,  3.67it/s]
 50%|████▉     | 352/705 [01:35<01:34,  3.74it/s]
 50%|█████     | 353/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 354/705 [01:35<01:34,  3.73it/s]
 50%|█████     | 355/705 [01:35<01:34,  3.72it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.73it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.75it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.74it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.73it/s]
 52%|█████▏    | 366/705 [01:38<01:36,  3.51it/s]
 52%|█████▏    | 367/705 [01:39<01:33,  3.62it/s]
 52%|█████▏    | 368/705 [01:39<01:31,  3.67it/s]
 52%|█████▏    | 369/705 [01:39<01:30,  3.70it/s]
 52%|█████▏    | 370/705 [01:39<01:29,  3.75it/s]
 53%|█████▎    | 371/705 [01:40<01:27,  3.81it/s]
 53%|█████▎    | 372/705 [01:40<01:28,  3.78it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.78it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.75it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.83it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:27,  3.66it/s]
 55%|█████▍    | 386/705 [01:44<01:25,  3.73it/s]
 55%|█████▍    | 387/705 [01:44<01:25,  3.73it/s]
 55%|█████▌    | 388/705 [01:44<01:25,  3.72it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.78it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.78it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.75it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.80it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.86it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.86it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:15,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.82it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.75it/s]
 66%|██████▌   | 466/705 [02:05<01:04,  3.73it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6726274490356445, 'eval_accuracy': 0.6984, 'eval_f1': 0.6955769670196205, 'eval_runtime': 1.7316, 'eval_samples_per_second': 1443.75, 'eval_steps_per_second': 180.757, 'epoch': 1.0}
{'loss': 0.5392, 'learning_rate': 1.807317410323941e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.64it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.91it/s]

 21%|██        | 65/313 [00:00<00:01, 204.85it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.21it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.55it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.22it/s]

 46%|████▌     | 144/313 [00:00<00:00, 184.01it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.77it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.08it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.92it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.10it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.36it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.66it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.21it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.42it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.42it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:08<04:02,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:07,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.56it/s]
 67%|██████▋   | 474/705 [02:09<02:01,  1.89it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.53it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.21it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:13<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:18<00:51,  3.81it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.80it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:23<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:45,  3.69it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.69it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.75it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.76it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.83it/s]
 77%|███████▋  | 543/705 [02:27<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.79it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.86it/s]
 78%|███████▊  | 550/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:30<00:40,  3.75it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 558/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.85it/s]
 80%|███████▉  | 562/705 [02:32<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.96it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:33<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:34<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:35<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:38<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:39<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:39<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:40<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.80it/s]
 85%|████████▍ | 596/705 [02:41<00:31,  3.43it/s]
 85%|████████▍ | 597/705 [02:42<00:30,  3.53it/s]
 85%|████████▍ | 598/705 [02:42<00:29,  3.59it/s]
 85%|████████▍ | 599/705 [02:42<00:28,  3.71it/s]
 85%|████████▌ | 600/705 [02:42<00:28,  3.73it/s]
 85%|████████▌ | 601/705 [02:43<00:26,  3.97it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.88it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.85it/s]
 86%|████████▌ | 604/705 [02:43<00:26,  3.83it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.83it/s]
 86%|████████▌ | 606/705 [02:44<00:26,  3.80it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  3.98it/s]
 86%|████████▌ | 608/705 [02:44<00:24,  3.92it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:45<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:25,  3.46it/s]
 88%|████████▊ | 617/705 [02:47<00:24,  3.62it/s]
 88%|████████▊ | 618/705 [02:47<00:23,  3.66it/s]
 88%|████████▊ | 619/705 [02:47<00:22,  3.81it/s]
 88%|████████▊ | 620/705 [02:48<00:22,  3.80it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.85it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.80it/s]
 88%|████████▊ | 623/705 [02:48<00:21,  3.79it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.81it/s]
 89%|████████▊ | 625/705 [02:49<00:21,  3.80it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.79it/s]
 89%|████████▉ | 627/705 [02:49<00:20,  3.77it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.77it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.85it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.80it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.85it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [02:59<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.78it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:04<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.76it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.86it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:09<00:00,  3.75it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.79it/s]
100%|██████████| 705/705 [03:10<00:00,  4.53it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.53it/s]{'eval_loss': 0.6842123866081238, 'eval_accuracy': 0.7164, 'eval_f1': 0.7140845687805438, 'eval_runtime': 1.7292, 'eval_samples_per_second': 1445.789, 'eval_steps_per_second': 181.013, 'epoch': 2.0}
{'loss': 0.3426, 'learning_rate': 3.641494537311916e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.82it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.38it/s]

 20%|██        | 63/313 [00:00<00:01, 202.92it/s]

 27%|██▋       | 84/313 [00:00<00:01, 195.26it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.59it/s]

 40%|███▉      | 124/313 [00:00<00:01, 185.29it/s]

 46%|████▌     | 143/313 [00:00<00:00, 184.66it/s]

 52%|█████▏    | 162/313 [00:00<00:00, 184.69it/s]

 58%|█████▊    | 181/313 [00:00<00:00, 179.60it/s]

 64%|██████▎   | 199/313 [00:01<00:00, 172.81it/s]

 69%|██████▉   | 217/313 [00:01<00:00, 168.39it/s]

 75%|███████▍  | 234/313 [00:01<00:00, 165.55it/s]

 82%|████████▏ | 257/313 [00:01<00:00, 182.36it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 185.31it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 178.65it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.65it/s]
100%|██████████| 705/705 [03:12<00:00,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.53it/s]
100%|██████████| 705/705 [03:13<00:00,  3.65it/s]
[I 2023-10-26 22:50:47,380] Trial 18 finished with value: 0.7197401896178178 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 5.932248198706452e-05, 'per_device_train_batch_size': 128, 'weight_decay': 2.7549584773477678e-05}. Best is trial 18 with value: 0.7197401896178178.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7302001714706421, 'eval_accuracy': 0.72, 'eval_f1': 0.7197401896178178, 'eval_runtime': 1.7308, 'eval_samples_per_second': 1444.448, 'eval_steps_per_second': 180.845, 'epoch': 3.0}
{'train_runtime': 193.138, 'train_samples_per_second': 465.988, 'train_steps_per_second': 3.65, 'train_loss': 0.5618183433586824, 'epoch': 3.0}

  0%|          | 0/1407 [00:00<?, ?it/s]
  0%|          | 1/1407 [00:00<03:31,  6.63it/s]
  0%|          | 2/1407 [00:00<03:25,  6.83it/s]
  0%|          | 3/1407 [00:00<03:25,  6.83it/s]
  0%|          | 4/1407 [00:00<03:31,  6.64it/s]
  0%|          | 5/1407 [00:00<03:33,  6.56it/s]
  0%|          | 6/1407 [00:00<03:35,  6.51it/s]
  0%|          | 7/1407 [00:01<03:36,  6.47it/s]
  1%|          | 8/1407 [00:01<03:29,  6.68it/s]
  1%|          | 9/1407 [00:01<03:25,  6.81it/s]
  1%|          | 10/1407 [00:01<03:25,  6.80it/s]
  1%|          | 11/1407 [00:01<03:23,  6.86it/s]
  1%|          | 12/1407 [00:01<03:06,  7.48it/s]
  1%|          | 13/1407 [00:01<03:12,  7.24it/s]
  1%|          | 14/1407 [00:02<03:15,  7.11it/s]
  1%|          | 15/1407 [00:02<03:17,  7.06it/s]
  1%|          | 16/1407 [00:02<03:16,  7.09it/s]
  1%|          | 17/1407 [00:02<03:18,  7.00it/s]
  1%|▏         | 18/1407 [00:02<03:24,  6.81it/s]
  1%|▏         | 19/1407 [00:02<03:26,  6.72it/s]
  1%|▏         | 20/1407 [00:02<03:29,  6.61it/s]
  1%|▏         | 21/1407 [00:03<03:27,  6.68it/s]
  2%|▏         | 22/1407 [00:03<03:27,  6.69it/s]
  2%|▏         | 23/1407 [00:03<03:24,  6.76it/s]
  2%|▏         | 24/1407 [00:03<03:23,  6.78it/s]
  2%|▏         | 25/1407 [00:03<03:21,  6.87it/s]
  2%|▏         | 26/1407 [00:03<03:20,  6.90it/s]
  2%|▏         | 27/1407 [00:03<03:19,  6.92it/s]
  2%|▏         | 28/1407 [00:04<03:19,  6.90it/s]
  2%|▏         | 29/1407 [00:04<03:23,  6.78it/s]
  2%|▏         | 30/1407 [00:04<03:26,  6.68it/s]
  2%|▏         | 32/1407 [00:04<03:03,  7.47it/s]
  2%|▏         | 33/1407 [00:04<03:11,  7.17it/s]
  2%|▏         | 34/1407 [00:04<03:13,  7.08it/s]
  2%|▏         | 35/1407 [00:05<03:19,  6.88it/s]
  3%|▎         | 36/1407 [00:05<03:18,  6.89it/s]
  3%|▎         | 37/1407 [00:05<03:11,  7.17it/s]
  3%|▎         | 38/1407 [00:05<03:12,  7.10it/s]
  3%|▎         | 39/1407 [00:05<03:13,  7.07it/s]
  3%|▎         | 40/1407 [00:05<03:16,  6.96it/s]
  3%|▎         | 41/1407 [00:05<03:19,  6.83it/s]
  3%|▎         | 42/1407 [00:06<03:18,  6.87it/s]
  3%|▎         | 43/1407 [00:06<03:17,  6.89it/s]
  3%|▎         | 44/1407 [00:06<03:16,  6.95it/s]
  3%|▎         | 45/1407 [00:06<03:21,  6.77it/s]
  3%|▎         | 46/1407 [00:06<03:10,  7.14it/s]
  3%|▎         | 47/1407 [00:06<03:16,  6.91it/s]
  3%|▎         | 48/1407 [00:06<03:04,  7.38it/s]
  3%|▎         | 49/1407 [00:07<03:07,  7.24it/s]
  4%|▎         | 50/1407 [00:07<03:10,  7.12it/s]
  4%|▎         | 51/1407 [00:07<03:16,  6.89it/s]
  4%|▎         | 52/1407 [00:07<03:13,  7.01it/s]
  4%|▍         | 53/1407 [00:07<03:15,  6.92it/s]
  4%|▍         | 54/1407 [00:07<03:20,  6.75it/s]
  4%|▍         | 55/1407 [00:07<03:06,  7.24it/s]
  4%|▍         | 56/1407 [00:08<03:14,  6.96it/s]
  4%|▍         | 57/1407 [00:08<03:12,  7.02it/s]
  4%|▍         | 58/1407 [00:08<03:04,  7.31it/s]
  4%|▍         | 59/1407 [00:08<03:12,  7.01it/s]
  4%|▍         | 60/1407 [00:08<03:02,  7.37it/s]
  4%|▍         | 61/1407 [00:08<03:10,  7.08it/s]
  4%|▍         | 62/1407 [00:08<03:09,  7.11it/s]
  4%|▍         | 63/1407 [00:09<03:13,  6.93it/s]
  5%|▍         | 64/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 65/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 66/1407 [00:09<03:11,  6.99it/s]
  5%|▍         | 67/1407 [00:09<03:17,  6.80it/s]
  5%|▍         | 68/1407 [00:09<03:20,  6.68it/s]
  5%|▍         | 69/1407 [00:09<03:18,  6.74it/s]
  5%|▍         | 70/1407 [00:10<03:16,  6.80it/s]
  5%|▌         | 71/1407 [00:10<03:16,  6.81it/s]
  5%|▌         | 72/1407 [00:10<03:14,  6.86it/s]
  5%|▌         | 73/1407 [00:10<03:10,  6.99it/s]
  5%|▌         | 74/1407 [00:10<03:09,  7.02it/s]
  5%|▌         | 75/1407 [00:10<03:09,  7.05it/s]
  5%|▌         | 76/1407 [00:10<03:13,  6.89it/s]
  5%|▌         | 77/1407 [00:11<03:16,  6.78it/s]
  6%|▌         | 78/1407 [00:11<03:07,  7.10it/s]
  6%|▌         | 79/1407 [00:11<03:08,  7.06it/s]
  6%|▌         | 80/1407 [00:11<03:13,  6.86it/s]
  6%|▌         | 81/1407 [00:11<03:13,  6.86it/s]
  6%|▌         | 82/1407 [00:11<03:16,  6.75it/s]
  6%|▌         | 83/1407 [00:11<03:14,  6.81it/s]
  6%|▌         | 84/1407 [00:12<03:14,  6.80it/s]
  6%|▌         | 85/1407 [00:12<03:18,  6.66it/s]
  6%|▌         | 86/1407 [00:12<03:17,  6.69it/s]
  6%|▌         | 87/1407 [00:12<03:15,  6.75it/s]
  6%|▋         | 88/1407 [00:12<03:04,  7.15it/s]
  6%|▋         | 89/1407 [00:12<03:05,  7.09it/s]
  6%|▋         | 90/1407 [00:13<03:11,  6.86it/s]
  6%|▋         | 91/1407 [00:13<03:16,  6.71it/s]
  7%|▋         | 92/1407 [00:13<03:19,  6.61it/s]
  7%|▋         | 93/1407 [00:13<03:17,  6.64it/s]
  7%|▋         | 94/1407 [00:13<03:15,  6.73it/s]
  7%|▋         | 95/1407 [00:13<03:16,  6.66it/s]
  7%|▋         | 96/1407 [00:13<03:17,  6.62it/s]
  7%|▋         | 97/1407 [00:14<03:16,  6.66it/s]
  7%|▋         | 98/1407 [00:14<03:15,  6.69it/s]
  7%|▋         | 99/1407 [00:14<03:18,  6.59it/s]
  7%|▋         | 100/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 101/1407 [00:14<03:14,  6.71it/s]
  7%|▋         | 102/1407 [00:14<03:13,  6.75it/s]
  7%|▋         | 103/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 104/1407 [00:15<03:04,  7.08it/s]
  7%|▋         | 105/1407 [00:15<03:03,  7.08it/s]
  8%|▊         | 106/1407 [00:15<03:02,  7.11it/s]
  8%|▊         | 107/1407 [00:15<03:02,  7.11it/s]
  8%|▊         | 108/1407 [00:15<03:04,  7.03it/s]
  8%|▊         | 109/1407 [00:15<02:55,  7.40it/s]
  8%|▊         | 110/1407 [00:15<03:02,  7.12it/s]
  8%|▊         | 111/1407 [00:16<03:03,  7.07it/s]
  8%|▊         | 112/1407 [00:16<03:05,  6.97it/s]
  8%|▊         | 113/1407 [00:16<03:07,  6.90it/s]
  8%|▊         | 114/1407 [00:16<03:05,  6.99it/s]
  8%|▊         | 115/1407 [00:16<03:08,  6.84it/s]
  8%|▊         | 116/1407 [00:16<03:12,  6.69it/s]
  8%|▊         | 117/1407 [00:16<03:09,  6.81it/s]
  8%|▊         | 118/1407 [00:17<03:13,  6.67it/s]
  8%|▊         | 119/1407 [00:17<03:14,  6.63it/s]
  9%|▊         | 120/1407 [00:17<03:12,  6.70it/s]
  9%|▊         | 121/1407 [00:17<03:10,  6.75it/s]
  9%|▊         | 122/1407 [00:17<03:09,  6.79it/s]
  9%|▊         | 123/1407 [00:17<03:00,  7.11it/s]
  9%|▉         | 124/1407 [00:17<02:59,  7.14it/s]
  9%|▉         | 125/1407 [00:18<03:05,  6.91it/s]
  9%|▉         | 126/1407 [00:18<03:08,  6.80it/s]
  9%|▉         | 127/1407 [00:18<02:57,  7.23it/s]
  9%|▉         | 128/1407 [00:18<02:59,  7.11it/s]
  9%|▉         | 129/1407 [00:18<03:02,  6.99it/s]
  9%|▉         | 130/1407 [00:18<03:07,  6.80it/s]
  9%|▉         | 131/1407 [00:18<03:10,  6.68it/s]
  9%|▉         | 132/1407 [00:19<03:09,  6.72it/s]
  9%|▉         | 133/1407 [00:19<03:12,  6.62it/s]
 10%|▉         | 134/1407 [00:19<03:14,  6.55it/s]
 10%|▉         | 135/1407 [00:19<03:09,  6.73it/s]
 10%|▉         | 136/1407 [00:19<03:07,  6.79it/s]
 10%|▉         | 137/1407 [00:19<03:05,  6.84it/s]
 10%|▉         | 138/1407 [00:20<03:03,  6.92it/s]
 10%|▉         | 139/1407 [00:20<03:03,  6.90it/s]
 10%|▉         | 140/1407 [00:20<03:01,  6.98it/s]
 10%|█         | 141/1407 [00:20<03:03,  6.91it/s]
 10%|█         | 142/1407 [00:20<03:02,  6.92it/s]
 10%|█         | 143/1407 [00:20<02:55,  7.22it/s]
 10%|█         | 144/1407 [00:20<02:55,  7.20it/s]
 10%|█         | 145/1407 [00:21<02:57,  7.12it/s]
 10%|█         | 146/1407 [00:21<03:00,  7.00it/s]
 10%|█         | 147/1407 [00:21<03:02,  6.92it/s]
 11%|█         | 148/1407 [00:21<03:01,  6.92it/s]
 11%|█         | 149/1407 [00:21<03:05,  6.79it/s]
 11%|█         | 150/1407 [00:21<03:02,  6.87it/s]
 11%|█         | 151/1407 [00:21<03:06,  6.73it/s]
 11%|█         | 152/1407 [00:22<03:05,  6.76it/s]
 11%|█         | 153/1407 [00:22<03:05,  6.75it/s]
 11%|█         | 154/1407 [00:22<03:07,  6.67it/s]
 11%|█         | 155/1407 [00:22<03:05,  6.76it/s]
 11%|█         | 156/1407 [00:22<03:02,  6.85it/s]
 11%|█         | 157/1407 [00:22<03:00,  6.92it/s]
 11%|█         | 158/1407 [00:22<03:05,  6.75it/s]
 11%|█▏        | 159/1407 [00:23<03:06,  6.69it/s]
 11%|█▏        | 160/1407 [00:23<03:01,  6.85it/s]
 11%|█▏        | 161/1407 [00:23<02:54,  7.16it/s]
 12%|█▏        | 162/1407 [00:23<03:00,  6.90it/s]
 12%|█▏        | 163/1407 [00:23<03:04,  6.75it/s]
 12%|█▏        | 164/1407 [00:23<02:54,  7.13it/s]
 12%|█▏        | 165/1407 [00:23<02:56,  7.05it/s]
 12%|█▏        | 166/1407 [00:24<02:57,  6.99it/s]
 12%|█▏        | 167/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 168/1407 [00:24<02:54,  7.08it/s]
 12%|█▏        | 169/1407 [00:24<02:59,  6.90it/s]
 12%|█▏        | 170/1407 [00:24<03:00,  6.84it/s]
 12%|█▏        | 171/1407 [00:24<03:04,  6.70it/s]
 12%|█▏        | 172/1407 [00:24<02:59,  6.87it/s]
 12%|█▏        | 173/1407 [00:25<02:59,  6.86it/s]
 12%|█▏        | 174/1407 [00:25<03:02,  6.75it/s]
 12%|█▏        | 175/1407 [00:25<03:04,  6.68it/s]
 13%|█▎        | 176/1407 [00:25<03:03,  6.72it/s]
 13%|█▎        | 177/1407 [00:25<03:02,  6.73it/s]
 13%|█▎        | 178/1407 [00:25<03:21,  6.10it/s]
 13%|█▎        | 179/1407 [00:26<03:15,  6.27it/s]
 13%|█▎        | 180/1407 [00:26<03:14,  6.30it/s]
 13%|█▎        | 181/1407 [00:26<03:07,  6.54it/s]
 13%|█▎        | 182/1407 [00:26<03:04,  6.65it/s]
 13%|█▎        | 183/1407 [00:26<03:05,  6.61it/s]
 13%|█▎        | 184/1407 [00:26<03:02,  6.70it/s]
 13%|█▎        | 185/1407 [00:26<03:04,  6.62it/s]
 13%|█▎        | 186/1407 [00:27<02:52,  7.09it/s]
 13%|█▎        | 187/1407 [00:27<02:56,  6.90it/s]
 13%|█▎        | 188/1407 [00:27<03:00,  6.77it/s]
 13%|█▎        | 189/1407 [00:27<02:58,  6.81it/s]
 14%|█▎        | 190/1407 [00:27<03:01,  6.72it/s]
 14%|█▎        | 191/1407 [00:27<03:02,  6.66it/s]
 14%|█▎        | 192/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 193/1407 [00:28<03:02,  6.64it/s]
 14%|█▍        | 194/1407 [00:28<03:04,  6.56it/s]
 14%|█▍        | 195/1407 [00:28<03:03,  6.62it/s]
 14%|█▍        | 196/1407 [00:28<02:49,  7.13it/s]
 14%|█▍        | 197/1407 [00:28<02:55,  6.89it/s]
 14%|█▍        | 198/1407 [00:28<02:55,  6.87it/s]
 14%|█▍        | 199/1407 [00:28<02:55,  6.90it/s]
 14%|█▍        | 200/1407 [00:29<02:58,  6.78it/s]
 14%|█▍        | 201/1407 [00:29<03:00,  6.67it/s]
 14%|█▍        | 202/1407 [00:29<03:00,  6.69it/s]
 14%|█▍        | 203/1407 [00:29<03:02,  6.59it/s]
 14%|█▍        | 204/1407 [00:29<02:57,  6.78it/s]
 15%|█▍        | 205/1407 [00:29<02:57,  6.77it/s]
 15%|█▍        | 206/1407 [00:30<02:56,  6.79it/s]
 15%|█▍        | 207/1407 [00:30<02:58,  6.71it/s]
 15%|█▍        | 208/1407 [00:30<02:47,  7.17it/s]
 15%|█▍        | 209/1407 [00:30<02:48,  7.10it/s]
 15%|█▍        | 210/1407 [00:30<02:49,  7.06it/s]
 15%|█▍        | 211/1407 [00:30<02:43,  7.32it/s]
 15%|█▌        | 212/1407 [00:30<02:45,  7.20it/s]
 15%|█▌        | 213/1407 [00:30<02:45,  7.22it/s]
 15%|█▌        | 214/1407 [00:31<02:51,  6.95it/s]
 15%|█▌        | 215/1407 [00:31<02:49,  7.02it/s]
 15%|█▌        | 216/1407 [00:31<02:51,  6.93it/s]
 15%|█▌        | 217/1407 [00:31<02:44,  7.25it/s]
 15%|█▌        | 218/1407 [00:31<02:47,  7.08it/s]
 16%|█▌        | 219/1407 [00:31<02:47,  7.08it/s]
 16%|█▌        | 220/1407 [00:32<02:52,  6.90it/s]
 16%|█▌        | 221/1407 [00:32<02:52,  6.88it/s]
 16%|█▌        | 222/1407 [00:32<02:44,  7.19it/s]
 16%|█▌        | 223/1407 [00:32<02:45,  7.16it/s]
 16%|█▌        | 224/1407 [00:32<02:50,  6.93it/s]
 16%|█▌        | 225/1407 [00:32<02:36,  7.53it/s]
 16%|█▌        | 226/1407 [00:32<02:40,  7.34it/s]
 16%|█▌        | 227/1407 [00:32<02:45,  7.15it/s]
 16%|█▌        | 228/1407 [00:33<02:39,  7.39it/s]
 16%|█▋        | 229/1407 [00:33<02:40,  7.36it/s]
 16%|█▋        | 230/1407 [00:33<02:47,  7.04it/s]
 16%|█▋        | 231/1407 [00:33<02:50,  6.88it/s]
 16%|█▋        | 232/1407 [00:33<02:50,  6.87it/s]
 17%|█▋        | 233/1407 [00:33<02:48,  6.96it/s]
 17%|█▋        | 234/1407 [00:33<02:49,  6.92it/s]
 17%|█▋        | 235/1407 [00:34<02:49,  6.89it/s]
 17%|█▋        | 236/1407 [00:34<02:45,  7.08it/s]
 17%|█▋        | 237/1407 [00:34<02:47,  6.98it/s]
 17%|█▋        | 238/1407 [00:34<02:52,  6.79it/s]
 17%|█▋        | 239/1407 [00:34<02:51,  6.81it/s]
 17%|█▋        | 240/1407 [00:34<02:49,  6.89it/s]
 17%|█▋        | 241/1407 [00:34<02:47,  6.97it/s]
 17%|█▋        | 242/1407 [00:35<02:47,  6.96it/s]
 17%|█▋        | 243/1407 [00:35<02:50,  6.82it/s]
 17%|█▋        | 244/1407 [00:35<02:49,  6.86it/s]
 17%|█▋        | 245/1407 [00:35<02:47,  6.95it/s]
 17%|█▋        | 246/1407 [00:35<02:47,  6.92it/s]
 18%|█▊        | 247/1407 [00:35<02:46,  6.97it/s]
 18%|█▊        | 248/1407 [00:35<02:38,  7.33it/s]
 18%|█▊        | 249/1407 [00:36<02:41,  7.19it/s]
 18%|█▊        | 250/1407 [00:36<02:43,  7.07it/s]
 18%|█▊        | 251/1407 [00:36<02:37,  7.33it/s]
 18%|█▊        | 252/1407 [00:36<02:41,  7.17it/s]
 18%|█▊        | 253/1407 [00:36<02:42,  7.10it/s]
 18%|█▊        | 254/1407 [00:36<02:44,  7.01it/s]
 18%|█▊        | 255/1407 [00:36<02:37,  7.33it/s]
 18%|█▊        | 256/1407 [00:37<02:40,  7.18it/s]
 18%|█▊        | 257/1407 [00:37<02:37,  7.30it/s]
 18%|█▊        | 258/1407 [00:37<02:40,  7.16it/s]
 18%|█▊        | 259/1407 [00:37<02:44,  6.96it/s]
 18%|█▊        | 260/1407 [00:37<02:45,  6.93it/s]
 19%|█▊        | 261/1407 [00:37<02:46,  6.87it/s]
 19%|█▊        | 262/1407 [00:37<02:45,  6.90it/s]
 19%|█▊        | 263/1407 [00:38<02:37,  7.25it/s]
 19%|█▉        | 264/1407 [00:38<02:40,  7.12it/s]
 19%|█▉        | 265/1407 [00:38<02:41,  7.06it/s]
 19%|█▉        | 266/1407 [00:38<02:45,  6.88it/s]
 19%|█▉        | 267/1407 [00:38<02:45,  6.89it/s]
 19%|█▉        | 268/1407 [00:38<02:48,  6.78it/s]
 19%|█▉        | 269/1407 [00:38<02:46,  6.82it/s]
 19%|█▉        | 270/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 271/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 272/1407 [00:39<02:45,  6.87it/s]
 19%|█▉        | 273/1407 [00:39<02:44,  6.89it/s]
 19%|█▉        | 274/1407 [00:39<02:44,  6.87it/s]
 20%|█▉        | 275/1407 [00:39<02:42,  6.97it/s]
 20%|█▉        | 276/1407 [00:39<02:43,  6.93it/s]
 20%|█▉        | 277/1407 [00:40<02:47,  6.76it/s]
 20%|█▉        | 278/1407 [00:40<02:36,  7.20it/s]
 20%|█▉        | 279/1407 [00:40<02:42,  6.95it/s]
 20%|█▉        | 280/1407 [00:40<02:43,  6.89it/s]
 20%|█▉        | 281/1407 [00:40<02:47,  6.72it/s]
 20%|██        | 282/1407 [00:40<02:45,  6.80it/s]
 20%|██        | 283/1407 [00:40<02:38,  7.11it/s]
 20%|██        | 284/1407 [00:41<03:18,  5.65it/s]
 20%|██        | 285/1407 [00:41<03:11,  5.85it/s]
 20%|██        | 286/1407 [00:41<03:05,  6.04it/s]
 20%|██        | 287/1407 [00:41<02:58,  6.28it/s]
 20%|██        | 288/1407 [00:41<02:44,  6.79it/s]
 21%|██        | 289/1407 [00:41<02:45,  6.77it/s]
 21%|██        | 290/1407 [00:42<02:47,  6.65it/s]
 21%|██        | 291/1407 [00:42<02:47,  6.68it/s]
 21%|██        | 292/1407 [00:42<02:49,  6.59it/s]
 21%|██        | 293/1407 [00:42<02:45,  6.75it/s]
 21%|██        | 294/1407 [00:42<02:39,  6.98it/s]
 21%|██        | 295/1407 [00:42<02:39,  6.98it/s]
 21%|██        | 296/1407 [00:42<02:32,  7.27it/s]
 21%|██        | 297/1407 [00:43<02:37,  7.04it/s]
 21%|██        | 298/1407 [00:43<02:38,  6.98it/s]
 21%|██▏       | 299/1407 [00:43<02:43,  6.80it/s]
 21%|██▏       | 300/1407 [00:43<02:27,  7.52it/s]
 21%|██▏       | 301/1407 [00:43<02:23,  7.73it/s]
 21%|██▏       | 302/1407 [00:43<02:28,  7.45it/s]
 22%|██▏       | 303/1407 [00:43<02:31,  7.30it/s]
 22%|██▏       | 304/1407 [00:44<02:33,  7.20it/s]
 22%|██▏       | 305/1407 [00:44<02:26,  7.54it/s]
 22%|██▏       | 306/1407 [00:44<02:33,  7.15it/s]
 22%|██▏       | 307/1407 [00:44<02:38,  6.94it/s]
 22%|██▏       | 308/1407 [00:44<02:39,  6.88it/s]
 22%|██▏       | 309/1407 [00:44<02:32,  7.18it/s]
 22%|██▏       | 310/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 311/1407 [00:45<02:37,  6.95it/s]
 22%|██▏       | 312/1407 [00:45<02:35,  7.04it/s]
 22%|██▏       | 313/1407 [00:45<02:33,  7.11it/s]
 22%|██▏       | 314/1407 [00:45<02:28,  7.37it/s]
 22%|██▏       | 315/1407 [00:45<02:29,  7.28it/s]
 22%|██▏       | 316/1407 [00:45<02:35,  7.03it/s]
 23%|██▎       | 317/1407 [00:45<02:39,  6.82it/s]
 23%|██▎       | 318/1407 [00:46<02:42,  6.72it/s]
 23%|██▎       | 319/1407 [00:46<02:44,  6.63it/s]
 23%|██▎       | 320/1407 [00:46<02:42,  6.69it/s]
 23%|██▎       | 321/1407 [00:46<02:41,  6.72it/s]
 23%|██▎       | 322/1407 [00:46<02:32,  7.13it/s]
 23%|██▎       | 323/1407 [00:46<02:37,  6.90it/s]
 23%|██▎       | 324/1407 [00:46<02:36,  6.91it/s]
 23%|██▎       | 325/1407 [00:47<02:39,  6.79it/s]
 23%|██▎       | 326/1407 [00:47<02:41,  6.70it/s]
 23%|██▎       | 327/1407 [00:47<02:39,  6.79it/s]
 23%|██▎       | 328/1407 [00:47<02:31,  7.13it/s]
 23%|██▎       | 329/1407 [00:47<02:32,  7.05it/s]
 23%|██▎       | 330/1407 [00:47<02:33,  7.02it/s]
 24%|██▎       | 331/1407 [00:47<02:35,  6.93it/s]
 24%|██▎       | 332/1407 [00:48<02:35,  6.93it/s]
 24%|██▎       | 333/1407 [00:48<02:30,  7.12it/s]
 24%|██▎       | 334/1407 [00:48<02:31,  7.07it/s]
 24%|██▍       | 335/1407 [00:48<02:35,  6.91it/s]
 24%|██▍       | 336/1407 [00:48<02:34,  6.93it/s]
 24%|██▍       | 337/1407 [00:48<02:34,  6.94it/s]
 24%|██▍       | 338/1407 [00:48<02:32,  7.01it/s]
 24%|██▍       | 339/1407 [00:49<02:33,  6.96it/s]
 24%|██▍       | 340/1407 [00:49<02:34,  6.89it/s]
 24%|██▍       | 341/1407 [00:49<02:33,  6.94it/s]
 24%|██▍       | 342/1407 [00:49<02:37,  6.77it/s]
 24%|██▍       | 343/1407 [00:49<02:37,  6.76it/s]
 24%|██▍       | 344/1407 [00:49<02:39,  6.66it/s]
 25%|██▍       | 345/1407 [00:50<02:37,  6.74it/s]
 25%|██▍       | 346/1407 [00:50<02:39,  6.63it/s]
 25%|██▍       | 347/1407 [00:50<02:29,  7.08it/s]
 25%|██▍       | 348/1407 [00:50<02:31,  6.97it/s]
 25%|██▍       | 349/1407 [00:50<02:30,  7.04it/s]
 25%|██▍       | 350/1407 [00:50<02:28,  7.11it/s]
 25%|██▍       | 351/1407 [00:50<02:28,  7.11it/s]
 25%|██▌       | 352/1407 [00:51<02:32,  6.93it/s]
 25%|██▌       | 353/1407 [00:51<02:35,  6.76it/s]
 25%|██▌       | 354/1407 [00:51<02:32,  6.90it/s]
 25%|██▌       | 355/1407 [00:51<02:36,  6.74it/s]
 25%|██▌       | 356/1407 [00:51<02:35,  6.77it/s]
 25%|██▌       | 357/1407 [00:51<02:32,  6.86it/s]
 25%|██▌       | 358/1407 [00:51<02:31,  6.95it/s]
 26%|██▌       | 359/1407 [00:52<02:30,  6.99it/s]
 26%|██▌       | 360/1407 [00:52<02:34,  6.79it/s]
 26%|██▌       | 361/1407 [00:52<02:32,  6.84it/s]
 26%|██▌       | 362/1407 [00:52<02:35,  6.73it/s]
 26%|██▌       | 363/1407 [00:52<02:27,  7.06it/s]
 26%|██▌       | 364/1407 [00:52<02:32,  6.84it/s]
 26%|██▌       | 365/1407 [00:52<02:30,  6.92it/s]
 26%|██▌       | 366/1407 [00:53<02:34,  6.76it/s]
 26%|██▌       | 367/1407 [00:53<02:33,  6.75it/s]
 26%|██▌       | 368/1407 [00:53<02:31,  6.87it/s]
 26%|██▌       | 369/1407 [00:53<02:30,  6.88it/s]
 26%|██▋       | 370/1407 [00:53<02:31,  6.86it/s]
 26%|██▋       | 371/1407 [00:53<02:30,  6.89it/s]
 26%|██▋       | 372/1407 [00:53<02:29,  6.91it/s]
 27%|██▋       | 373/1407 [00:54<02:33,  6.75it/s]
 27%|██▋       | 374/1407 [00:54<02:31,  6.80it/s]
 27%|██▋       | 375/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 376/1407 [00:54<02:36,  6.60it/s]
 27%|██▋       | 377/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 378/1407 [00:54<02:31,  6.77it/s]
 27%|██▋       | 379/1407 [00:54<02:30,  6.83it/s]
 27%|██▋       | 380/1407 [00:55<02:29,  6.86it/s]
 27%|██▋       | 381/1407 [00:55<02:30,  6.83it/s]
 27%|██▋       | 382/1407 [00:55<02:22,  7.19it/s]
 27%|██▋       | 383/1407 [00:55<02:22,  7.18it/s]
 27%|██▋       | 384/1407 [00:55<02:25,  7.04it/s]
 27%|██▋       | 385/1407 [00:55<02:26,  6.97it/s]
 27%|██▋       | 386/1407 [00:55<02:29,  6.82it/s]
 28%|██▊       | 387/1407 [00:56<02:21,  7.20it/s]
 28%|██▊       | 388/1407 [00:56<02:24,  7.06it/s]
 28%|██▊       | 389/1407 [00:56<02:23,  7.07it/s]
 28%|██▊       | 390/1407 [00:56<02:20,  7.22it/s]
 28%|██▊       | 391/1407 [00:56<02:21,  7.18it/s]
 28%|██▊       | 392/1407 [00:56<02:23,  7.08it/s]
 28%|██▊       | 393/1407 [00:56<02:23,  7.06it/s]
 28%|██▊       | 394/1407 [00:57<02:25,  6.96it/s]
 28%|██▊       | 395/1407 [00:57<02:25,  6.97it/s]
 28%|██▊       | 396/1407 [00:57<02:25,  6.93it/s]
 28%|██▊       | 397/1407 [00:57<02:25,  6.93it/s]
 28%|██▊       | 398/1407 [00:57<02:19,  7.22it/s]
 28%|██▊       | 399/1407 [00:57<02:20,  7.19it/s]
 28%|██▊       | 400/1407 [00:57<02:20,  7.16it/s]
 29%|██▊       | 401/1407 [00:58<02:21,  7.09it/s]
 29%|██▊       | 402/1407 [00:58<02:23,  7.00it/s]
 29%|██▊       | 403/1407 [00:58<02:24,  6.95it/s]
 29%|██▊       | 404/1407 [00:58<02:25,  6.89it/s]
 29%|██▉       | 405/1407 [00:58<02:19,  7.18it/s]
 29%|██▉       | 406/1407 [00:58<02:15,  7.40it/s]
 29%|██▉       | 407/1407 [00:58<02:20,  7.12it/s]
 29%|██▉       | 408/1407 [00:59<02:15,  7.37it/s]
 29%|██▉       | 409/1407 [00:59<02:12,  7.55it/s]
 29%|██▉       | 410/1407 [00:59<02:18,  7.21it/s]
 29%|██▉       | 411/1407 [00:59<02:20,  7.06it/s]
 29%|██▉       | 412/1407 [00:59<02:22,  6.96it/s]
 29%|██▉       | 413/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 414/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 415/1407 [01:00<02:26,  6.76it/s]
 30%|██▉       | 416/1407 [01:00<02:29,  6.64it/s]
 30%|██▉       | 417/1407 [01:00<02:30,  6.57it/s]
 30%|██▉       | 418/1407 [01:00<02:20,  7.02it/s]
 30%|██▉       | 419/1407 [01:00<02:21,  7.01it/s]
 30%|██▉       | 420/1407 [01:00<02:24,  6.85it/s]
 30%|██▉       | 421/1407 [01:00<02:27,  6.70it/s]
 30%|██▉       | 422/1407 [01:01<02:26,  6.74it/s]
 30%|███       | 423/1407 [01:01<02:18,  7.09it/s]
 30%|███       | 424/1407 [01:01<02:18,  7.12it/s]
 30%|███       | 425/1407 [01:01<02:19,  7.03it/s]
 30%|███       | 426/1407 [01:01<02:22,  6.88it/s]
 30%|███       | 427/1407 [01:01<02:22,  6.87it/s]
 30%|███       | 428/1407 [01:01<02:23,  6.83it/s]
 30%|███       | 429/1407 [01:02<02:23,  6.80it/s]
 31%|███       | 430/1407 [01:02<02:26,  6.68it/s]
 31%|███       | 431/1407 [01:02<02:24,  6.76it/s]
 31%|███       | 432/1407 [01:02<02:22,  6.83it/s]
 31%|███       | 433/1407 [01:02<02:15,  7.19it/s]
 31%|███       | 434/1407 [01:02<02:20,  6.93it/s]
 31%|███       | 435/1407 [01:02<02:23,  6.76it/s]
 31%|███       | 436/1407 [01:03<02:26,  6.64it/s]
 31%|███       | 437/1407 [01:03<02:25,  6.66it/s]
 31%|███       | 438/1407 [01:03<02:24,  6.69it/s]
 31%|███       | 439/1407 [01:03<02:21,  6.85it/s]
 31%|███▏      | 440/1407 [01:03<02:20,  6.87it/s]
 31%|███▏      | 441/1407 [01:03<02:20,  6.88it/s]
 31%|███▏      | 442/1407 [01:04<02:19,  6.90it/s]
 31%|███▏      | 443/1407 [01:04<02:19,  6.92it/s]
 32%|███▏      | 444/1407 [01:04<02:21,  6.80it/s]
 32%|███▏      | 445/1407 [01:04<02:19,  6.88it/s]
 32%|███▏      | 446/1407 [01:04<02:23,  6.72it/s]
 32%|███▏      | 447/1407 [01:04<02:22,  6.71it/s]
 32%|███▏      | 448/1407 [01:04<02:21,  6.78it/s]
 32%|███▏      | 449/1407 [01:05<02:12,  7.22it/s]
 32%|███▏      | 450/1407 [01:05<02:14,  7.12it/s]
 32%|███▏      | 451/1407 [01:05<02:18,  6.89it/s]
 32%|███▏      | 452/1407 [01:05<02:21,  6.77it/s]
 32%|███▏      | 453/1407 [01:05<02:12,  7.18it/s]
 32%|███▏      | 454/1407 [01:05<02:14,  7.07it/s]
 32%|███▏      | 455/1407 [01:05<02:15,  7.04it/s]
 32%|███▏      | 456/1407 [01:06<02:16,  6.98it/s]
 32%|███▏      | 457/1407 [01:06<02:17,  6.91it/s]
 33%|███▎      | 458/1407 [01:06<02:20,  6.76it/s]
 33%|███▎      | 459/1407 [01:06<02:19,  6.81it/s]
 33%|███▎      | 460/1407 [01:06<02:17,  6.89it/s]
 33%|███▎      | 461/1407 [01:06<02:16,  6.95it/s]
 33%|███▎      | 462/1407 [01:06<02:19,  6.77it/s]
 33%|███▎      | 463/1407 [01:07<02:07,  7.42it/s]
 33%|███▎      | 464/1407 [01:07<02:08,  7.35it/s]
 33%|███▎      | 465/1407 [01:07<02:11,  7.19it/s]
 33%|███▎      | 466/1407 [01:07<02:13,  7.07it/s]
 33%|███▎      | 467/1407 [01:07<02:13,  7.04it/s]
 33%|███▎      | 468/1407 [01:07<02:15,  6.95it/s]
 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]
                                                  

 33%|███▎      | 469/1407 [01:07<02:07,  7.35it/s]{'loss': 0.7909, 'learning_rate': 7.334593635940186e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.98it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.84it/s]

 21%|██        | 65/313 [00:00<00:01, 204.82it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.23it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.39it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.02it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.63it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.19it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.74it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.75it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.03it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.35it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.54it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.09it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.03it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 179.03it/s]
 33%|███▎      | 469/1407 [01:09<02:07,  7.35it/s]

                                                  
 33%|███▎      | 469/1407 [01:09<02:19,  6.74it/s]
[I 2023-10-26 22:51:57,727] Trial 19 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.695231556892395, 'eval_accuracy': 0.6872, 'eval_f1': 0.6877764542550795, 'eval_runtime': 1.7318, 'eval_samples_per_second': 1443.599, 'eval_steps_per_second': 180.739, 'epoch': 1.0}

  0%|          | 0/5625 [00:00<?, ?it/s]
  0%|          | 2/5625 [00:00<04:51, 19.30it/s]
  0%|          | 4/5625 [00:00<04:56, 18.93it/s]
  0%|          | 6/5625 [00:00<04:52, 19.22it/s]
  0%|          | 8/5625 [00:00<04:55, 18.99it/s]
  0%|          | 10/5625 [00:00<04:58, 18.82it/s]
  0%|          | 12/5625 [00:00<04:53, 19.13it/s]
  0%|          | 14/5625 [00:00<05:03, 18.51it/s]
  0%|          | 17/5625 [00:00<04:48, 19.45it/s]
  0%|          | 20/5625 [00:01<04:47, 19.52it/s]
  0%|          | 22/5625 [00:01<04:52, 19.13it/s]
  0%|          | 24/5625 [00:01<04:57, 18.86it/s]
  0%|          | 26/5625 [00:01<05:04, 18.36it/s]
  0%|          | 28/5625 [00:01<05:05, 18.32it/s]
  1%|          | 30/5625 [00:01<04:59, 18.70it/s]
  1%|          | 33/5625 [00:01<04:50, 19.22it/s]
  1%|          | 36/5625 [00:01<04:46, 19.50it/s]
  1%|          | 39/5625 [00:02<04:35, 20.29it/s]
  1%|          | 42/5625 [00:02<04:43, 19.66it/s]
  1%|          | 45/5625 [00:02<04:35, 20.25it/s]
  1%|          | 48/5625 [00:02<04:32, 20.47it/s]
  1%|          | 51/5625 [00:02<04:35, 20.24it/s]
  1%|          | 54/5625 [00:02<04:39, 19.96it/s]
  1%|          | 56/5625 [00:02<04:45, 19.52it/s]
  1%|          | 58/5625 [00:02<04:47, 19.37it/s]
  1%|          | 60/5625 [00:03<04:46, 19.42it/s]
  1%|          | 63/5625 [00:03<04:38, 19.97it/s]
  1%|          | 65/5625 [00:03<04:41, 19.74it/s]
  1%|          | 68/5625 [00:03<04:28, 20.73it/s]
  1%|▏         | 71/5625 [00:03<04:37, 20.05it/s]
  1%|▏         | 74/5625 [00:03<04:42, 19.63it/s]
  1%|▏         | 76/5625 [00:03<04:46, 19.36it/s]
  1%|▏         | 78/5625 [00:04<04:55, 18.74it/s]
  1%|▏         | 80/5625 [00:04<04:57, 18.64it/s]
  1%|▏         | 83/5625 [00:04<04:50, 19.05it/s]
  2%|▏         | 86/5625 [00:04<04:43, 19.52it/s]
  2%|▏         | 88/5625 [00:04<04:44, 19.47it/s]
  2%|▏         | 90/5625 [00:04<04:47, 19.29it/s]
  2%|▏         | 92/5625 [00:04<04:50, 19.06it/s]
  2%|▏         | 94/5625 [00:04<04:50, 19.03it/s]
  2%|▏         | 96/5625 [00:04<04:57, 18.57it/s]
  2%|▏         | 99/5625 [00:05<04:50, 19.04it/s]
  2%|▏         | 101/5625 [00:05<04:47, 19.23it/s]
  2%|▏         | 103/5625 [00:05<04:44, 19.39it/s]
  2%|▏         | 105/5625 [00:05<04:47, 19.19it/s]
  2%|▏         | 107/5625 [00:05<04:48, 19.13it/s]
  2%|▏         | 109/5625 [00:05<04:50, 18.96it/s]
  2%|▏         | 112/5625 [00:05<04:40, 19.66it/s]
  2%|▏         | 114/5625 [00:05<04:48, 19.11it/s]
  2%|▏         | 117/5625 [00:06<04:44, 19.36it/s]
  2%|▏         | 119/5625 [00:06<04:43, 19.44it/s]
  2%|▏         | 122/5625 [00:06<04:35, 19.99it/s]
  2%|▏         | 125/5625 [00:06<04:27, 20.56it/s]
  2%|▏         | 128/5625 [00:06<04:39, 19.64it/s]
  2%|▏         | 130/5625 [00:06<04:40, 19.58it/s]
  2%|▏         | 132/5625 [00:06<04:40, 19.58it/s]
  2%|▏         | 134/5625 [00:06<04:46, 19.14it/s]
  2%|▏         | 136/5625 [00:07<04:52, 18.74it/s]
  2%|▏         | 139/5625 [00:07<04:48, 18.99it/s]
  3%|▎         | 141/5625 [00:07<04:55, 18.56it/s]
  3%|▎         | 143/5625 [00:07<04:55, 18.58it/s]
  3%|▎         | 145/5625 [00:07<04:59, 18.27it/s]
  3%|▎         | 147/5625 [00:07<04:53, 18.64it/s]
  3%|▎         | 149/5625 [00:07<04:54, 18.61it/s]
  3%|▎         | 151/5625 [00:07<04:50, 18.86it/s]
  3%|▎         | 154/5625 [00:07<04:45, 19.17it/s]
  3%|▎         | 156/5625 [00:08<04:46, 19.08it/s]
  3%|▎         | 158/5625 [00:08<04:53, 18.64it/s]
  3%|▎         | 161/5625 [00:08<04:36, 19.75it/s]
  3%|▎         | 163/5625 [00:08<04:37, 19.68it/s]
  3%|▎         | 165/5625 [00:08<04:46, 19.03it/s]
  3%|▎         | 167/5625 [00:08<04:47, 19.01it/s]
  3%|▎         | 169/5625 [00:08<04:46, 19.03it/s]
  3%|▎         | 171/5625 [00:08<04:43, 19.24it/s]
  3%|▎         | 173/5625 [00:08<04:44, 19.16it/s]
  3%|▎         | 176/5625 [00:09<04:34, 19.83it/s]
  3%|▎         | 179/5625 [00:09<04:28, 20.26it/s]
  3%|▎         | 182/5625 [00:09<04:30, 20.13it/s]
  3%|▎         | 185/5625 [00:09<04:36, 19.70it/s]
  3%|▎         | 187/5625 [00:09<04:39, 19.42it/s]
  3%|▎         | 190/5625 [00:09<04:39, 19.42it/s]
  3%|▎         | 193/5625 [00:09<04:37, 19.58it/s]
  3%|▎         | 195/5625 [00:10<04:41, 19.28it/s]
  4%|▎         | 197/5625 [00:10<04:42, 19.20it/s]
  4%|▎         | 200/5625 [00:10<04:35, 19.68it/s]
  4%|▎         | 202/5625 [00:10<04:39, 19.37it/s]
  4%|▎         | 205/5625 [00:10<04:22, 20.61it/s]
  4%|▎         | 208/5625 [00:10<04:24, 20.51it/s]
  4%|▍         | 211/5625 [00:10<04:31, 19.97it/s]
  4%|▍         | 213/5625 [00:10<04:34, 19.71it/s]
  4%|▍         | 215/5625 [00:11<04:38, 19.39it/s]
  4%|▍         | 217/5625 [00:11<04:43, 19.08it/s]
  4%|▍         | 220/5625 [00:11<04:36, 19.52it/s]
  4%|▍         | 222/5625 [00:11<04:37, 19.46it/s]
  4%|▍         | 224/5625 [00:11<04:42, 19.13it/s]
  4%|▍         | 227/5625 [00:11<04:41, 19.20it/s]
  4%|▍         | 229/5625 [00:11<04:38, 19.35it/s]
  4%|▍         | 231/5625 [00:11<04:38, 19.36it/s]
  4%|▍         | 234/5625 [00:12<04:35, 19.54it/s]
  4%|▍         | 236/5625 [00:12<04:39, 19.30it/s]
  4%|▍         | 238/5625 [00:12<04:37, 19.44it/s]
  4%|▍         | 240/5625 [00:12<04:37, 19.38it/s]
  4%|▍         | 242/5625 [00:12<04:45, 18.82it/s]
  4%|▍         | 244/5625 [00:12<04:49, 18.59it/s]
  4%|▍         | 247/5625 [00:12<04:37, 19.40it/s]
  4%|▍         | 249/5625 [00:12<04:35, 19.53it/s]
  4%|▍         | 251/5625 [00:12<04:43, 18.98it/s]
  4%|▍         | 253/5625 [00:13<04:46, 18.74it/s]
  5%|▍         | 255/5625 [00:13<04:42, 19.01it/s]
  5%|▍         | 257/5625 [00:13<04:47, 18.66it/s]
  5%|▍         | 260/5625 [00:13<04:43, 18.93it/s]
  5%|▍         | 263/5625 [00:13<04:32, 19.69it/s]
  5%|▍         | 266/5625 [00:13<04:27, 20.03it/s]
  5%|▍         | 268/5625 [00:13<04:34, 19.55it/s]
  5%|▍         | 271/5625 [00:13<04:33, 19.55it/s]
  5%|▍         | 273/5625 [00:14<04:37, 19.26it/s]
  5%|▍         | 275/5625 [00:14<04:40, 19.06it/s]
  5%|▍         | 277/5625 [00:14<04:42, 18.94it/s]
  5%|▍         | 280/5625 [00:14<04:32, 19.65it/s]
  5%|▌         | 283/5625 [00:14<04:24, 20.16it/s]
  5%|▌         | 286/5625 [00:14<04:32, 19.58it/s]
  5%|▌         | 288/5625 [00:14<04:35, 19.37it/s]
  5%|▌         | 291/5625 [00:15<04:36, 19.27it/s]
  5%|▌         | 294/5625 [00:15<04:35, 19.39it/s]
  5%|▌         | 296/5625 [00:15<04:37, 19.24it/s]
  5%|▌         | 299/5625 [00:15<04:30, 19.71it/s]
  5%|▌         | 301/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 303/5625 [00:15<04:40, 18.97it/s]
  5%|▌         | 305/5625 [00:15<04:43, 18.78it/s]
  5%|▌         | 308/5625 [00:15<04:35, 19.32it/s]
  6%|▌         | 311/5625 [00:16<04:30, 19.65it/s]
  6%|▌         | 313/5625 [00:16<04:30, 19.62it/s]
  6%|▌         | 315/5625 [00:16<04:30, 19.61it/s]
  6%|▌         | 317/5625 [00:16<04:33, 19.40it/s]
  6%|▌         | 319/5625 [00:16<04:38, 19.04it/s]
  6%|▌         | 321/5625 [00:16<04:36, 19.20it/s]
  6%|▌         | 323/5625 [00:16<04:39, 18.98it/s]
  6%|▌         | 326/5625 [00:16<04:22, 20.18it/s]
  6%|▌         | 329/5625 [00:16<04:22, 20.20it/s]
  6%|▌         | 332/5625 [00:17<04:28, 19.75it/s]
  6%|▌         | 334/5625 [00:17<04:27, 19.77it/s]
  6%|▌         | 337/5625 [00:17<04:23, 20.06it/s]
  6%|▌         | 340/5625 [00:17<04:29, 19.64it/s]
  6%|▌         | 342/5625 [00:17<04:36, 19.12it/s]
  6%|▌         | 344/5625 [00:17<04:40, 18.84it/s]
  6%|▌         | 346/5625 [00:17<04:43, 18.61it/s]
  6%|▌         | 349/5625 [00:18<04:31, 19.43it/s]
  6%|▋         | 352/5625 [00:18<04:29, 19.58it/s]
  6%|▋         | 354/5625 [00:18<04:31, 19.38it/s]
  6%|▋         | 357/5625 [00:18<04:18, 20.37it/s]
  6%|▋         | 360/5625 [00:18<04:32, 19.35it/s]
  6%|▋         | 362/5625 [00:18<04:30, 19.44it/s]
  6%|▋         | 364/5625 [00:18<04:39, 18.85it/s]
  7%|▋         | 366/5625 [00:18<04:39, 18.78it/s]
  7%|▋         | 368/5625 [00:19<04:46, 18.35it/s]
  7%|▋         | 370/5625 [00:19<04:44, 18.44it/s]
  7%|▋         | 372/5625 [00:19<04:39, 18.79it/s]
  7%|▋         | 374/5625 [00:19<04:35, 19.07it/s]
  7%|▋         | 376/5625 [00:19<04:41, 18.63it/s]
  7%|▋         | 378/5625 [00:19<04:38, 18.87it/s]
  7%|▋         | 380/5625 [00:19<04:36, 18.97it/s]
  7%|▋         | 382/5625 [00:19<04:38, 18.81it/s]
  7%|▋         | 385/5625 [00:19<04:25, 19.75it/s]
  7%|▋         | 387/5625 [00:19<04:32, 19.21it/s]
  7%|▋         | 389/5625 [00:20<04:35, 19.01it/s]
  7%|▋         | 391/5625 [00:20<04:31, 19.25it/s]
  7%|▋         | 393/5625 [00:20<04:38, 18.80it/s]
  7%|▋         | 395/5625 [00:20<04:34, 19.06it/s]
  7%|▋         | 397/5625 [00:20<04:32, 19.22it/s]
  7%|▋         | 399/5625 [00:20<04:32, 19.15it/s]
  7%|▋         | 401/5625 [00:20<04:29, 19.38it/s]
  7%|▋         | 403/5625 [00:20<04:30, 19.27it/s]
  7%|▋         | 405/5625 [00:20<04:37, 18.80it/s]
  7%|▋         | 407/5625 [00:21<04:37, 18.80it/s]
  7%|▋         | 409/5625 [00:21<04:33, 19.05it/s]
  7%|▋         | 411/5625 [00:21<04:39, 18.63it/s]
  7%|▋         | 413/5625 [00:21<04:34, 18.96it/s]
  7%|▋         | 416/5625 [00:21<04:23, 19.80it/s]
  7%|▋         | 419/5625 [00:21<04:24, 19.68it/s]
  7%|▋         | 421/5625 [00:21<04:28, 19.38it/s]
  8%|▊         | 423/5625 [00:21<04:26, 19.52it/s]
  8%|▊         | 425/5625 [00:21<04:32, 19.11it/s]
  8%|▊         | 427/5625 [00:22<04:33, 19.01it/s]
  8%|▊         | 429/5625 [00:22<04:30, 19.20it/s]
  8%|▊         | 431/5625 [00:22<04:33, 18.99it/s]
  8%|▊         | 434/5625 [00:22<04:24, 19.62it/s]
  8%|▊         | 437/5625 [00:22<04:15, 20.29it/s]
  8%|▊         | 440/5625 [00:22<04:18, 20.02it/s]
  8%|▊         | 442/5625 [00:22<04:26, 19.45it/s]
  8%|▊         | 445/5625 [00:22<04:22, 19.75it/s]
  8%|▊         | 447/5625 [00:23<04:22, 19.72it/s]
  8%|▊         | 449/5625 [00:23<04:26, 19.44it/s]
  8%|▊         | 451/5625 [00:23<04:31, 19.08it/s]
  8%|▊         | 453/5625 [00:23<04:27, 19.31it/s]
  8%|▊         | 456/5625 [00:23<04:15, 20.21it/s]
  8%|▊         | 459/5625 [00:23<04:29, 19.17it/s]
  8%|▊         | 461/5625 [00:23<04:33, 18.90it/s]
  8%|▊         | 463/5625 [00:23<04:30, 19.11it/s]
  8%|▊         | 465/5625 [00:24<04:35, 18.75it/s]
  8%|▊         | 468/5625 [00:24<04:22, 19.62it/s]
  8%|▊         | 470/5625 [00:24<04:28, 19.22it/s]
  8%|▊         | 473/5625 [00:24<04:23, 19.58it/s]
  8%|▊         | 475/5625 [00:24<04:23, 19.57it/s]
  8%|▊         | 477/5625 [00:24<04:27, 19.28it/s]
  9%|▊         | 480/5625 [00:24<04:20, 19.71it/s]
  9%|▊         | 482/5625 [00:24<04:20, 19.74it/s]
  9%|▊         | 484/5625 [00:25<04:24, 19.42it/s]
  9%|▊         | 486/5625 [00:25<04:30, 18.96it/s]
  9%|▊         | 489/5625 [00:25<04:18, 19.88it/s]
  9%|▊         | 491/5625 [00:25<04:22, 19.56it/s]
  9%|▉         | 494/5625 [00:25<04:09, 20.59it/s]
  9%|▉         | 497/5625 [00:25<04:14, 20.17it/s]
  9%|▉         | 500/5625 [00:25<04:20, 19.69it/s]
  9%|▉         | 502/5625 [00:25<04:27, 19.13it/s]
  9%|▉         | 504/5625 [00:26<04:28, 19.08it/s]
  9%|▉         | 507/5625 [00:26<04:18, 19.83it/s]
  9%|▉         | 510/5625 [00:26<04:14, 20.08it/s]
  9%|▉         | 512/5625 [00:26<04:23, 19.38it/s]
  9%|▉         | 514/5625 [00:26<04:24, 19.32it/s]
  9%|▉         | 516/5625 [00:26<04:31, 18.83it/s]
  9%|▉         | 518/5625 [00:26<04:28, 19.02it/s]
  9%|▉         | 520/5625 [00:26<04:31, 18.82it/s]
  9%|▉         | 522/5625 [00:26<04:30, 18.89it/s]
  9%|▉         | 524/5625 [00:27<04:32, 18.72it/s]
  9%|▉         | 526/5625 [00:27<04:36, 18.44it/s]
  9%|▉         | 529/5625 [00:27<04:28, 18.96it/s]
  9%|▉         | 531/5625 [00:27<04:33, 18.61it/s]
  9%|▉         | 533/5625 [00:27<04:40, 18.15it/s]
 10%|▉         | 536/5625 [00:27<04:25, 19.19it/s]
 10%|▉         | 539/5625 [00:27<04:20, 19.51it/s]
 10%|▉         | 541/5625 [00:27<04:19, 19.57it/s]
 10%|▉         | 544/5625 [00:28<04:21, 19.46it/s]
 10%|▉         | 546/5625 [00:28<04:21, 19.39it/s]
 10%|▉         | 548/5625 [00:28<04:26, 19.08it/s]
 10%|▉         | 550/5625 [00:28<04:27, 18.97it/s]
 10%|▉         | 553/5625 [00:28<04:21, 19.38it/s]
 10%|▉         | 555/5625 [00:28<04:21, 19.42it/s]
 10%|▉         | 557/5625 [00:28<04:24, 19.15it/s]
 10%|▉         | 559/5625 [00:28<04:24, 19.15it/s]
 10%|▉         | 562/5625 [00:29<04:19, 19.51it/s]
 10%|█         | 564/5625 [00:29<04:25, 19.04it/s]
 10%|█         | 566/5625 [00:29<04:30, 18.70it/s]
 10%|█         | 568/5625 [00:29<04:33, 18.48it/s]
 10%|█         | 570/5625 [00:29<04:33, 18.46it/s]
 10%|█         | 573/5625 [00:29<04:25, 19.05it/s]
 10%|█         | 576/5625 [00:29<04:19, 19.49it/s]
 10%|█         | 578/5625 [00:29<04:22, 19.22it/s]
 10%|█         | 580/5625 [00:30<04:28, 18.80it/s]
 10%|█         | 583/5625 [00:30<04:25, 18.97it/s]
 10%|█         | 585/5625 [00:30<04:30, 18.62it/s]
 10%|█         | 587/5625 [00:30<04:31, 18.57it/s]
 10%|█         | 589/5625 [00:30<04:29, 18.68it/s]
 11%|█         | 592/5625 [00:30<04:20, 19.30it/s]
 11%|█         | 594/5625 [00:30<04:26, 18.90it/s]
 11%|█         | 596/5625 [00:30<04:25, 18.93it/s]
 11%|█         | 598/5625 [00:30<04:23, 19.09it/s]
 11%|█         | 601/5625 [00:31<04:15, 19.65it/s]
 11%|█         | 603/5625 [00:31<04:17, 19.51it/s]
 11%|█         | 605/5625 [00:31<04:25, 18.92it/s]
 11%|█         | 608/5625 [00:31<04:16, 19.56it/s]
 11%|█         | 610/5625 [00:31<04:19, 19.36it/s]
 11%|█         | 612/5625 [00:31<04:18, 19.37it/s]
 11%|█         | 614/5625 [00:31<04:23, 19.03it/s]
 11%|█         | 616/5625 [00:31<04:20, 19.25it/s]
 11%|█         | 618/5625 [00:32<04:25, 18.88it/s]
 11%|█         | 621/5625 [00:32<04:08, 20.16it/s]
 11%|█         | 623/5625 [00:32<04:13, 19.74it/s]
 11%|█         | 625/5625 [00:32<04:19, 19.24it/s]
 11%|█         | 627/5625 [00:32<04:20, 19.17it/s]
 11%|█         | 630/5625 [00:32<04:12, 19.77it/s]
 11%|█         | 632/5625 [00:32<04:17, 19.41it/s]
 11%|█▏        | 634/5625 [00:32<04:25, 18.80it/s]
 11%|█▏        | 636/5625 [00:32<04:25, 18.80it/s]
 11%|█▏        | 639/5625 [00:33<04:18, 19.27it/s]
 11%|█▏        | 641/5625 [00:33<04:20, 19.10it/s]
 11%|█▏        | 644/5625 [00:33<04:07, 20.16it/s]
 12%|█▏        | 647/5625 [00:33<04:20, 19.12it/s]
 12%|█▏        | 649/5625 [00:33<04:19, 19.16it/s]
 12%|█▏        | 651/5625 [00:33<04:25, 18.75it/s]
 12%|█▏        | 653/5625 [00:33<04:22, 18.92it/s]
 12%|█▏        | 656/5625 [00:33<04:11, 19.77it/s]
 12%|█▏        | 658/5625 [00:34<04:12, 19.63it/s]
 12%|█▏        | 661/5625 [00:34<04:13, 19.58it/s]
 12%|█▏        | 663/5625 [00:34<04:17, 19.29it/s]
 12%|█▏        | 665/5625 [00:34<04:22, 18.92it/s]
 12%|█▏        | 667/5625 [00:34<04:25, 18.67it/s]
 12%|█▏        | 669/5625 [00:34<04:27, 18.56it/s]
 12%|█▏        | 671/5625 [00:34<04:21, 18.92it/s]
 12%|█▏        | 673/5625 [00:34<04:21, 18.96it/s]
 12%|█▏        | 675/5625 [00:34<04:22, 18.84it/s]
 12%|█▏        | 677/5625 [00:35<04:29, 18.37it/s]
 12%|█▏        | 679/5625 [00:35<04:28, 18.41it/s]
 12%|█▏        | 681/5625 [00:35<04:27, 18.46it/s]
 12%|█▏        | 683/5625 [00:35<04:32, 18.12it/s]
 12%|█▏        | 685/5625 [00:35<04:28, 18.38it/s]
 12%|█▏        | 687/5625 [00:35<04:25, 18.58it/s]
 12%|█▏        | 689/5625 [00:35<04:22, 18.84it/s]
 12%|█▏        | 691/5625 [00:35<04:18, 19.10it/s]
 12%|█▏        | 693/5625 [00:35<04:22, 18.82it/s]
 12%|█▏        | 696/5625 [00:36<04:15, 19.31it/s]
 12%|█▏        | 699/5625 [00:36<04:14, 19.38it/s]
 12%|█▏        | 701/5625 [00:36<04:19, 18.96it/s]
 12%|█▏        | 703/5625 [00:36<04:23, 18.69it/s]
 13%|█▎        | 705/5625 [00:36<04:19, 18.94it/s]
 13%|█▎        | 707/5625 [00:36<04:20, 18.86it/s]
 13%|█▎        | 709/5625 [00:36<04:21, 18.78it/s]
 13%|█▎        | 711/5625 [00:36<04:24, 18.56it/s]
 13%|█▎        | 714/5625 [00:37<04:18, 19.01it/s]
 13%|█▎        | 716/5625 [00:37<04:16, 19.16it/s]
 13%|█▎        | 718/5625 [00:37<04:15, 19.20it/s]
 13%|█▎        | 720/5625 [00:37<04:16, 19.15it/s]
 13%|█▎        | 722/5625 [00:37<04:17, 19.04it/s]
 13%|█▎        | 725/5625 [00:37<04:13, 19.30it/s]
 13%|█▎        | 728/5625 [00:37<04:04, 20.02it/s]
 13%|█▎        | 730/5625 [00:37<04:12, 19.38it/s]
 13%|█▎        | 733/5625 [00:38<04:11, 19.43it/s]
 13%|█▎        | 735/5625 [00:38<04:13, 19.28it/s]
 13%|█▎        | 737/5625 [00:38<04:11, 19.46it/s]
 13%|█▎        | 739/5625 [00:38<04:18, 18.90it/s]
 13%|█▎        | 742/5625 [00:38<04:09, 19.54it/s]
 13%|█▎        | 745/5625 [00:38<04:08, 19.62it/s]
 13%|█▎        | 747/5625 [00:38<04:15, 19.06it/s]
 13%|█▎        | 750/5625 [00:38<04:08, 19.60it/s]
 13%|█▎        | 752/5625 [00:38<04:09, 19.51it/s]
 13%|█▎        | 754/5625 [00:39<04:12, 19.26it/s]
 13%|█▎        | 756/5625 [00:39<04:18, 18.86it/s]
 13%|█▎        | 758/5625 [00:39<04:16, 18.99it/s]
 14%|█▎        | 761/5625 [00:39<04:12, 19.30it/s]
 14%|█▎        | 763/5625 [00:39<04:12, 19.25it/s]
 14%|█▎        | 765/5625 [00:39<04:14, 19.13it/s]
 14%|█▎        | 767/5625 [00:39<04:16, 18.96it/s]
 14%|█▎        | 769/5625 [00:39<04:13, 19.18it/s]
 14%|█▎        | 771/5625 [00:40<04:14, 19.07it/s]
 14%|█▍        | 774/5625 [00:40<04:10, 19.33it/s]
 14%|█▍        | 776/5625 [00:40<04:15, 18.97it/s]
 14%|█▍        | 779/5625 [00:40<04:14, 19.03it/s]
 14%|█▍        | 782/5625 [00:40<04:07, 19.58it/s]
 14%|█▍        | 785/5625 [00:40<04:03, 19.87it/s]
 14%|█▍        | 787/5625 [00:40<04:11, 19.24it/s]
 14%|█▍        | 789/5625 [00:40<04:13, 19.04it/s]
 14%|█▍        | 791/5625 [00:41<04:18, 18.69it/s]
 14%|█▍        | 794/5625 [00:41<04:06, 19.63it/s]
 14%|█▍        | 796/5625 [00:41<04:11, 19.17it/s]
 14%|█▍        | 798/5625 [00:41<04:16, 18.82it/s]
 14%|█▍        | 800/5625 [00:41<04:20, 18.55it/s]
 14%|█▍        | 803/5625 [00:41<04:09, 19.36it/s]
 14%|█▍        | 805/5625 [00:41<04:15, 18.85it/s]
 14%|█▍        | 808/5625 [00:41<04:07, 19.48it/s]
 14%|█▍        | 810/5625 [00:42<04:10, 19.20it/s]
 14%|█▍        | 812/5625 [00:42<04:16, 18.78it/s]
 14%|█▍        | 815/5625 [00:42<04:06, 19.53it/s]
 15%|█▍        | 817/5625 [00:42<04:10, 19.22it/s]
 15%|█▍        | 819/5625 [00:42<04:16, 18.71it/s]
 15%|█▍        | 821/5625 [00:42<04:13, 18.99it/s]
 15%|█▍        | 823/5625 [00:42<04:14, 18.88it/s]
 15%|█▍        | 826/5625 [00:42<04:06, 19.44it/s]
 15%|█▍        | 829/5625 [00:43<04:04, 19.59it/s]
 15%|█▍        | 832/5625 [00:43<03:55, 20.32it/s]
 15%|█▍        | 835/5625 [00:43<03:57, 20.14it/s]
 15%|█▍        | 838/5625 [00:43<04:02, 19.75it/s]
 15%|█▍        | 840/5625 [00:43<04:06, 19.44it/s]
 15%|█▍        | 842/5625 [00:43<04:11, 19.02it/s]
 15%|█▌        | 844/5625 [00:43<04:09, 19.17it/s]
 15%|█▌        | 846/5625 [00:43<04:10, 19.09it/s]
 15%|█▌        | 848/5625 [00:44<04:16, 18.63it/s]
 15%|█▌        | 851/5625 [00:44<04:10, 19.06it/s]
 15%|█▌        | 854/5625 [00:44<04:08, 19.17it/s]
 15%|█▌        | 856/5625 [00:44<04:07, 19.24it/s]
 15%|█▌        | 859/5625 [00:44<04:01, 19.72it/s]
 15%|█▌        | 862/5625 [00:44<04:01, 19.69it/s]
 15%|█▌        | 864/5625 [00:44<04:08, 19.18it/s]
 15%|█▌        | 867/5625 [00:44<03:56, 20.10it/s]
 15%|█▌        | 869/5625 [00:45<04:02, 19.63it/s]
 16%|█▌        | 872/5625 [00:45<03:58, 19.93it/s]
 16%|█▌        | 874/5625 [00:45<04:01, 19.68it/s]
 16%|█▌        | 876/5625 [00:45<04:03, 19.51it/s]
 16%|█▌        | 879/5625 [00:45<04:01, 19.63it/s]
 16%|█▌        | 882/5625 [00:45<03:59, 19.81it/s]
 16%|█▌        | 885/5625 [00:45<03:58, 19.84it/s]
 16%|█▌        | 888/5625 [00:46<03:57, 19.93it/s]
 16%|█▌        | 890/5625 [00:46<04:01, 19.60it/s]
 16%|█▌        | 893/5625 [00:46<04:02, 19.53it/s]
 16%|█▌        | 895/5625 [00:46<04:10, 18.88it/s]
 16%|█▌        | 898/5625 [00:46<03:58, 19.84it/s]
 16%|█▌        | 901/5625 [00:46<03:55, 20.06it/s]
 16%|█▌        | 904/5625 [00:46<03:51, 20.39it/s]
 16%|█▌        | 907/5625 [00:46<03:56, 19.92it/s]
 16%|█▌        | 909/5625 [00:47<04:00, 19.61it/s]
 16%|█▌        | 912/5625 [00:47<03:53, 20.18it/s]
 16%|█▋        | 915/5625 [00:47<03:53, 20.17it/s]
 16%|█▋        | 918/5625 [00:47<03:59, 19.62it/s]
 16%|█▋        | 920/5625 [00:47<04:04, 19.27it/s]
 16%|█▋        | 922/5625 [00:47<04:03, 19.33it/s]
 16%|█▋        | 924/5625 [00:47<04:05, 19.12it/s]
 16%|█▋        | 926/5625 [00:47<04:02, 19.34it/s]
 16%|█▋        | 928/5625 [00:48<04:02, 19.36it/s]
 17%|█▋        | 930/5625 [00:48<04:03, 19.32it/s]
 17%|█▋        | 933/5625 [00:48<03:52, 20.20it/s]
 17%|█▋        | 936/5625 [00:48<03:53, 20.05it/s]
 17%|█▋        | 938/5625 [00:48<03:54, 19.95it/s]
 17%|█▋        | 940/5625 [00:48<03:55, 19.87it/s]
 17%|█▋        | 943/5625 [00:48<03:49, 20.37it/s]
 17%|█▋        | 946/5625 [00:48<03:59, 19.57it/s]
 17%|█▋        | 949/5625 [00:49<03:53, 20.00it/s]
 17%|█▋        | 952/5625 [00:49<03:56, 19.76it/s]
 17%|█▋        | 954/5625 [00:49<03:56, 19.74it/s]
 17%|█▋        | 957/5625 [00:49<03:53, 19.99it/s]
 17%|█▋        | 959/5625 [00:49<03:56, 19.74it/s]
 17%|█▋        | 961/5625 [00:49<04:03, 19.17it/s]
 17%|█▋        | 963/5625 [00:49<04:05, 18.96it/s]
 17%|█▋        | 966/5625 [00:49<03:59, 19.48it/s]
 17%|█▋        | 968/5625 [00:50<03:58, 19.56it/s]
 17%|█▋        | 970/5625 [00:50<03:58, 19.52it/s]
 17%|█▋        | 972/5625 [00:50<04:02, 19.23it/s]
 17%|█▋        | 974/5625 [00:50<03:59, 19.42it/s]
 17%|█▋        | 976/5625 [00:50<04:01, 19.27it/s]
 17%|█▋        | 979/5625 [00:50<03:58, 19.51it/s]
 17%|█▋        | 982/5625 [00:50<03:57, 19.55it/s]
 17%|█▋        | 984/5625 [00:50<04:03, 19.10it/s]
 18%|█▊        | 986/5625 [00:51<04:03, 19.01it/s]
 18%|█▊        | 988/5625 [00:51<04:05, 18.89it/s]
 18%|█▊        | 991/5625 [00:51<03:56, 19.58it/s]
 18%|█▊        | 994/5625 [00:51<03:55, 19.65it/s]
 18%|█▊        | 996/5625 [00:51<03:57, 19.50it/s]
 18%|█▊        | 998/5625 [00:51<03:56, 19.59it/s]
 18%|█▊        | 1000/5625 [00:51<03:56, 19.58it/s]
 18%|█▊        | 1002/5625 [00:51<03:57, 19.46it/s]
 18%|█▊        | 1005/5625 [00:52<03:56, 19.58it/s]
 18%|█▊        | 1008/5625 [00:52<03:48, 20.18it/s]
 18%|█▊        | 1011/5625 [00:52<03:50, 20.03it/s]
 18%|█▊        | 1013/5625 [00:52<03:53, 19.77it/s]
 18%|█▊        | 1015/5625 [00:52<03:53, 19.71it/s]
 18%|█▊        | 1017/5625 [00:52<03:56, 19.48it/s]
 18%|█▊        | 1020/5625 [00:52<03:49, 20.08it/s]
 18%|█▊        | 1022/5625 [00:52<03:54, 19.63it/s]
 18%|█▊        | 1024/5625 [00:52<04:00, 19.15it/s]
 18%|█▊        | 1027/5625 [00:53<03:56, 19.42it/s]
 18%|█▊        | 1030/5625 [00:53<03:57, 19.38it/s]
 18%|█▊        | 1032/5625 [00:53<03:59, 19.15it/s]
 18%|█▊        | 1034/5625 [00:53<04:05, 18.70it/s]
 18%|█▊        | 1037/5625 [00:53<03:57, 19.29it/s]
 18%|█▊        | 1040/5625 [00:53<03:58, 19.26it/s]
 19%|█▊        | 1042/5625 [00:53<03:58, 19.25it/s]
 19%|█▊        | 1044/5625 [00:54<04:03, 18.82it/s]
 19%|█▊        | 1047/5625 [00:54<03:53, 19.60it/s]
 19%|█▊        | 1050/5625 [00:54<03:46, 20.23it/s]
 19%|█▊        | 1053/5625 [00:54<03:48, 20.00it/s]
 19%|█▉        | 1056/5625 [00:54<03:47, 20.05it/s]
 19%|█▉        | 1059/5625 [00:54<03:52, 19.67it/s]
 19%|█▉        | 1061/5625 [00:54<03:52, 19.66it/s]
 19%|█▉        | 1063/5625 [00:54<03:56, 19.30it/s]
 19%|█▉        | 1066/5625 [00:55<03:49, 19.87it/s]
 19%|█▉        | 1068/5625 [00:55<03:53, 19.55it/s]
 19%|█▉        | 1070/5625 [00:55<03:58, 19.12it/s]
 19%|█▉        | 1072/5625 [00:55<03:59, 18.97it/s]
 19%|█▉        | 1074/5625 [00:55<03:59, 19.00it/s]
 19%|█▉        | 1076/5625 [00:55<04:01, 18.83it/s]
 19%|█▉        | 1078/5625 [00:55<04:05, 18.52it/s]
 19%|█▉        | 1081/5625 [00:55<04:01, 18.84it/s]
 19%|█▉        | 1084/5625 [00:56<03:56, 19.21it/s]
 19%|█▉        | 1086/5625 [00:56<03:54, 19.35it/s]
 19%|█▉        | 1089/5625 [00:56<03:45, 20.10it/s]
 19%|█▉        | 1092/5625 [00:56<03:50, 19.69it/s]
 19%|█▉        | 1094/5625 [00:56<03:53, 19.38it/s]
 19%|█▉        | 1096/5625 [00:56<03:52, 19.45it/s]
 20%|█▉        | 1099/5625 [00:56<03:46, 19.94it/s]
 20%|█▉        | 1101/5625 [00:56<03:48, 19.78it/s]
 20%|█▉        | 1104/5625 [00:57<03:50, 19.61it/s]
 20%|█▉        | 1107/5625 [00:57<03:51, 19.49it/s]
 20%|█▉        | 1110/5625 [00:57<03:47, 19.88it/s]
 20%|█▉        | 1113/5625 [00:57<03:42, 20.29it/s]
 20%|█▉        | 1116/5625 [00:57<03:48, 19.69it/s]
 20%|█▉        | 1119/5625 [00:57<03:43, 20.12it/s]
 20%|█▉        | 1122/5625 [00:57<03:54, 19.21it/s]
 20%|█▉        | 1124/5625 [00:58<03:54, 19.22it/s]
 20%|██        | 1126/5625 [00:58<03:53, 19.29it/s]
 20%|██        | 1128/5625 [00:58<03:57, 18.91it/s]
 20%|██        | 1130/5625 [00:58<03:58, 18.86it/s]
 20%|██        | 1133/5625 [00:58<03:47, 19.76it/s]
 20%|██        | 1135/5625 [00:58<03:50, 19.46it/s]
 20%|██        | 1137/5625 [00:58<03:56, 18.98it/s]
 20%|██        | 1139/5625 [00:58<04:00, 18.64it/s]
 20%|██        | 1141/5625 [00:58<03:57, 18.84it/s]
 20%|██        | 1143/5625 [00:59<04:01, 18.52it/s]
 20%|██        | 1146/5625 [00:59<03:48, 19.62it/s]
 20%|██        | 1148/5625 [00:59<03:51, 19.34it/s]
 20%|██        | 1150/5625 [00:59<03:51, 19.33it/s]
 20%|██        | 1153/5625 [00:59<03:42, 20.08it/s]
 21%|██        | 1155/5625 [00:59<03:44, 19.89it/s]
 21%|██        | 1157/5625 [00:59<03:53, 19.10it/s]
 21%|██        | 1159/5625 [00:59<03:59, 18.65it/s]
 21%|██        | 1162/5625 [01:00<03:47, 19.64it/s]
 21%|██        | 1164/5625 [01:00<03:53, 19.09it/s]
 21%|██        | 1166/5625 [01:00<03:56, 18.88it/s]
 21%|██        | 1169/5625 [01:00<03:46, 19.66it/s]
 21%|██        | 1171/5625 [01:00<03:49, 19.40it/s]
 21%|██        | 1173/5625 [01:00<03:52, 19.12it/s]
 21%|██        | 1176/5625 [01:00<03:42, 19.95it/s]
 21%|██        | 1178/5625 [01:00<03:42, 19.96it/s]
 21%|██        | 1180/5625 [01:00<03:44, 19.77it/s]
 21%|██        | 1182/5625 [01:01<03:47, 19.52it/s]
 21%|██        | 1185/5625 [01:01<03:44, 19.82it/s]
 21%|██        | 1188/5625 [01:01<03:44, 19.78it/s]
 21%|██        | 1190/5625 [01:01<03:44, 19.71it/s]
 21%|██        | 1192/5625 [01:01<03:45, 19.62it/s]
 21%|██        | 1194/5625 [01:01<03:49, 19.31it/s]
 21%|██▏       | 1196/5625 [01:01<03:52, 19.03it/s]
 21%|██▏       | 1199/5625 [01:01<03:38, 20.24it/s]
 21%|██▏       | 1202/5625 [01:02<03:31, 20.86it/s]
 21%|██▏       | 1205/5625 [01:02<03:34, 20.56it/s]
 21%|██▏       | 1208/5625 [01:02<03:40, 20.06it/s]
 22%|██▏       | 1211/5625 [01:02<03:39, 20.07it/s]
 22%|██▏       | 1214/5625 [01:02<03:38, 20.15it/s]
 22%|██▏       | 1217/5625 [01:02<03:39, 20.06it/s]
 22%|██▏       | 1220/5625 [01:02<03:34, 20.49it/s]
 22%|██▏       | 1223/5625 [01:03<03:42, 19.79it/s]
 22%|██▏       | 1225/5625 [01:03<03:44, 19.58it/s]
 22%|██▏       | 1227/5625 [01:03<03:51, 18.96it/s]
 22%|██▏       | 1229/5625 [01:03<03:57, 18.50it/s]
 22%|██▏       | 1231/5625 [01:03<03:56, 18.54it/s]
 22%|██▏       | 1233/5625 [01:03<03:58, 18.45it/s]
 22%|██▏       | 1236/5625 [01:03<03:46, 19.39it/s]
 22%|██▏       | 1238/5625 [01:03<03:51, 18.95it/s]
 22%|██▏       | 1241/5625 [01:04<03:43, 19.58it/s]
 22%|██▏       | 1243/5625 [01:04<03:43, 19.64it/s]
 22%|██▏       | 1245/5625 [01:04<03:45, 19.44it/s]
 22%|██▏       | 1248/5625 [01:04<03:42, 19.64it/s]
 22%|██▏       | 1250/5625 [01:04<03:46, 19.32it/s]
 22%|██▏       | 1253/5625 [01:04<03:38, 19.99it/s]
 22%|██▏       | 1256/5625 [01:04<03:34, 20.39it/s]
 22%|██▏       | 1259/5625 [01:04<03:34, 20.36it/s]
 22%|██▏       | 1262/5625 [01:05<03:31, 20.58it/s]
 22%|██▏       | 1265/5625 [01:05<03:36, 20.11it/s]
 23%|██▎       | 1268/5625 [01:05<03:40, 19.75it/s]
 23%|██▎       | 1270/5625 [01:05<03:42, 19.55it/s]
 23%|██▎       | 1272/5625 [01:05<03:42, 19.60it/s]
 23%|██▎       | 1274/5625 [01:05<03:43, 19.44it/s]
 23%|██▎       | 1276/5625 [01:05<03:51, 18.79it/s]
 23%|██▎       | 1278/5625 [01:05<03:56, 18.40it/s]
 23%|██▎       | 1280/5625 [01:06<03:55, 18.48it/s]
 23%|██▎       | 1283/5625 [01:06<03:46, 19.16it/s]
 23%|██▎       | 1286/5625 [01:06<03:38, 19.85it/s]
 23%|██▎       | 1289/5625 [01:06<03:37, 19.95it/s]
 23%|██▎       | 1291/5625 [01:06<03:45, 19.22it/s]
 23%|██▎       | 1293/5625 [01:06<03:48, 18.93it/s]
 23%|██▎       | 1295/5625 [01:06<03:47, 19.03it/s]
 23%|██▎       | 1297/5625 [01:06<03:45, 19.20it/s]
 23%|██▎       | 1299/5625 [01:07<03:44, 19.29it/s]
 23%|██▎       | 1301/5625 [01:07<03:50, 18.72it/s]
 23%|██▎       | 1303/5625 [01:07<03:56, 18.27it/s]
 23%|██▎       | 1305/5625 [01:07<03:56, 18.27it/s]
 23%|██▎       | 1307/5625 [01:07<03:54, 18.39it/s]
 23%|██▎       | 1309/5625 [01:07<03:52, 18.56it/s]
 23%|██▎       | 1312/5625 [01:07<03:41, 19.44it/s]
 23%|██▎       | 1314/5625 [01:07<03:41, 19.47it/s]
 23%|██▎       | 1317/5625 [01:08<03:37, 19.83it/s]
 23%|██▎       | 1319/5625 [01:08<03:40, 19.52it/s]
 23%|██▎       | 1321/5625 [01:08<03:40, 19.53it/s]
 24%|██▎       | 1323/5625 [01:08<03:40, 19.51it/s]
 24%|██▎       | 1325/5625 [01:08<03:43, 19.26it/s]
 24%|██▎       | 1328/5625 [01:08<03:39, 19.62it/s]
 24%|██▎       | 1331/5625 [01:08<03:35, 19.91it/s]
 24%|██▎       | 1333/5625 [01:08<03:40, 19.46it/s]
 24%|██▎       | 1335/5625 [01:08<03:42, 19.32it/s]
 24%|██▍       | 1337/5625 [01:09<03:40, 19.47it/s]
 24%|██▍       | 1340/5625 [01:09<03:41, 19.32it/s]
 24%|██▍       | 1343/5625 [01:09<03:41, 19.31it/s]
 24%|██▍       | 1346/5625 [01:09<03:38, 19.56it/s]
 24%|██▍       | 1348/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1351/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1354/5625 [01:09<03:31, 20.17it/s]
 24%|██▍       | 1357/5625 [01:10<03:29, 20.32it/s]
 24%|██▍       | 1360/5625 [01:10<03:35, 19.81it/s]
 24%|██▍       | 1362/5625 [01:10<03:34, 19.85it/s]
 24%|██▍       | 1365/5625 [01:10<03:37, 19.63it/s]
 24%|██▍       | 1367/5625 [01:10<03:37, 19.62it/s]
 24%|██▍       | 1369/5625 [01:10<03:40, 19.32it/s]
 24%|██▍       | 1371/5625 [01:10<03:43, 19.05it/s]
 24%|██▍       | 1373/5625 [01:10<03:45, 18.88it/s]
 24%|██▍       | 1375/5625 [01:10<03:42, 19.12it/s]
 24%|██▍       | 1377/5625 [01:11<03:40, 19.25it/s]
 25%|██▍       | 1379/5625 [01:11<03:43, 18.96it/s]
 25%|██▍       | 1381/5625 [01:11<03:43, 19.01it/s]
 25%|██▍       | 1384/5625 [01:11<03:41, 19.11it/s]
 25%|██▍       | 1386/5625 [01:11<03:39, 19.30it/s]
 25%|██▍       | 1389/5625 [01:11<03:32, 19.93it/s]
 25%|██▍       | 1391/5625 [01:11<03:36, 19.60it/s]
 25%|██▍       | 1393/5625 [01:11<03:35, 19.61it/s]
 25%|██▍       | 1396/5625 [01:12<03:34, 19.74it/s]
 25%|██▍       | 1398/5625 [01:12<03:33, 19.81it/s]
 25%|██▍       | 1401/5625 [01:12<03:29, 20.17it/s]
 25%|██▍       | 1404/5625 [01:12<03:29, 20.13it/s]
 25%|██▌       | 1407/5625 [01:12<03:36, 19.51it/s]
 25%|██▌       | 1409/5625 [01:12<03:41, 19.02it/s]
 25%|██▌       | 1412/5625 [01:12<03:28, 20.24it/s]
 25%|██▌       | 1415/5625 [01:13<03:24, 20.58it/s]
 25%|██▌       | 1418/5625 [01:13<03:32, 19.81it/s]
 25%|██▌       | 1420/5625 [01:13<03:33, 19.66it/s]
 25%|██▌       | 1422/5625 [01:13<03:36, 19.45it/s]
 25%|██▌       | 1424/5625 [01:13<03:39, 19.17it/s]
 25%|██▌       | 1427/5625 [01:13<03:35, 19.51it/s]
 25%|██▌       | 1429/5625 [01:13<03:34, 19.58it/s]
 25%|██▌       | 1432/5625 [01:13<03:33, 19.67it/s]
 25%|██▌       | 1434/5625 [01:13<03:36, 19.39it/s]
 26%|██▌       | 1436/5625 [01:14<03:37, 19.30it/s]
 26%|██▌       | 1438/5625 [01:14<03:42, 18.83it/s]
 26%|██▌       | 1440/5625 [01:14<03:46, 18.48it/s]
 26%|██▌       | 1442/5625 [01:14<03:45, 18.55it/s]
 26%|██▌       | 1444/5625 [01:14<03:44, 18.64it/s]
 26%|██▌       | 1446/5625 [01:14<03:41, 18.84it/s]
 26%|██▌       | 1449/5625 [01:14<03:24, 20.41it/s]
 26%|██▌       | 1452/5625 [01:14<03:24, 20.37it/s]
 26%|██▌       | 1455/5625 [01:15<03:33, 19.53it/s]
 26%|██▌       | 1457/5625 [01:15<03:33, 19.56it/s]
 26%|██▌       | 1459/5625 [01:15<03:32, 19.62it/s]
 26%|██▌       | 1461/5625 [01:15<03:34, 19.43it/s]
 26%|██▌       | 1464/5625 [01:15<03:29, 19.82it/s]
 26%|██▌       | 1466/5625 [01:15<03:31, 19.69it/s]
 26%|██▌       | 1468/5625 [01:15<03:32, 19.55it/s]
 26%|██▌       | 1470/5625 [01:15<03:33, 19.42it/s]
 26%|██▌       | 1472/5625 [01:15<03:33, 19.49it/s]
 26%|██▌       | 1474/5625 [01:16<03:33, 19.47it/s]
 26%|██▌       | 1476/5625 [01:16<03:37, 19.04it/s]
 26%|██▋       | 1479/5625 [01:16<03:26, 20.07it/s]
 26%|██▋       | 1481/5625 [01:16<03:31, 19.62it/s]
 26%|██▋       | 1484/5625 [01:16<03:27, 19.94it/s]
 26%|██▋       | 1487/5625 [01:16<03:20, 20.67it/s]
 26%|██▋       | 1490/5625 [01:16<03:28, 19.85it/s]
 27%|██▋       | 1492/5625 [01:16<03:34, 19.22it/s]
 27%|██▋       | 1494/5625 [01:17<03:33, 19.34it/s]
 27%|██▋       | 1496/5625 [01:17<03:35, 19.15it/s]
 27%|██▋       | 1498/5625 [01:17<03:40, 18.74it/s]
 27%|██▋       | 1500/5625 [01:17<03:36, 19.06it/s]
 27%|██▋       | 1502/5625 [01:17<03:34, 19.27it/s]
 27%|██▋       | 1504/5625 [01:17<03:37, 18.95it/s]
 27%|██▋       | 1506/5625 [01:17<03:37, 18.90it/s]
 27%|██▋       | 1508/5625 [01:17<03:40, 18.64it/s]
 27%|██▋       | 1511/5625 [01:17<03:36, 19.03it/s]
 27%|██▋       | 1513/5625 [01:18<03:40, 18.67it/s]
 27%|██▋       | 1515/5625 [01:18<03:40, 18.63it/s]
 27%|██▋       | 1517/5625 [01:18<03:42, 18.46it/s]
 27%|██▋       | 1520/5625 [01:18<03:32, 19.32it/s]
 27%|██▋       | 1523/5625 [01:18<03:30, 19.48it/s]
 27%|██▋       | 1526/5625 [01:18<03:28, 19.64it/s]
 27%|██▋       | 1529/5625 [01:18<03:23, 20.09it/s]
 27%|██▋       | 1532/5625 [01:19<03:28, 19.65it/s]
 27%|██▋       | 1535/5625 [01:19<03:28, 19.58it/s]
 27%|██▋       | 1538/5625 [01:19<03:26, 19.76it/s]
 27%|██▋       | 1540/5625 [01:19<03:27, 19.69it/s]
 27%|██▋       | 1542/5625 [01:19<03:30, 19.36it/s]
 27%|██▋       | 1544/5625 [01:19<03:33, 19.16it/s]
 27%|██▋       | 1546/5625 [01:19<03:31, 19.30it/s]
 28%|██▊       | 1549/5625 [01:19<03:30, 19.36it/s]
 28%|██▊       | 1551/5625 [01:20<03:30, 19.39it/s]
 28%|██▊       | 1554/5625 [01:20<03:25, 19.78it/s]
 28%|██▊       | 1556/5625 [01:20<03:32, 19.12it/s]
 28%|██▊       | 1558/5625 [01:20<03:34, 18.96it/s]
 28%|██▊       | 1560/5625 [01:20<03:33, 19.03it/s]
 28%|██▊       | 1562/5625 [01:20<03:33, 19.00it/s]
 28%|██▊       | 1564/5625 [01:20<03:30, 19.26it/s]
 28%|██▊       | 1566/5625 [01:20<03:34, 18.88it/s]
 28%|██▊       | 1569/5625 [01:20<03:27, 19.52it/s]
 28%|██▊       | 1571/5625 [01:21<03:30, 19.28it/s]
 28%|██▊       | 1574/5625 [01:21<03:30, 19.24it/s]
 28%|██▊       | 1577/5625 [01:21<03:27, 19.53it/s]
 28%|██▊       | 1579/5625 [01:21<03:28, 19.42it/s]
 28%|██▊       | 1582/5625 [01:21<03:20, 20.20it/s]
 28%|██▊       | 1585/5625 [01:21<03:22, 19.99it/s]
 28%|██▊       | 1587/5625 [01:21<03:23, 19.80it/s]
 28%|██▊       | 1589/5625 [01:21<03:26, 19.56it/s]
 28%|██▊       | 1592/5625 [01:22<03:22, 19.90it/s]
 28%|██▊       | 1594/5625 [01:22<03:27, 19.40it/s]
 28%|██▊       | 1596/5625 [01:22<03:30, 19.16it/s]
 28%|██▊       | 1598/5625 [01:22<03:30, 19.12it/s]
 28%|██▊       | 1600/5625 [01:22<03:30, 19.10it/s]
 28%|██▊       | 1602/5625 [01:22<03:34, 18.73it/s]
 29%|██▊       | 1604/5625 [01:22<03:31, 19.05it/s]
 29%|██▊       | 1606/5625 [01:22<03:29, 19.20it/s]
 29%|██▊       | 1608/5625 [01:22<03:27, 19.35it/s]
 29%|██▊       | 1610/5625 [01:23<03:30, 19.06it/s]
 29%|██▊       | 1613/5625 [01:23<03:29, 19.16it/s]
 29%|██▊       | 1616/5625 [01:23<03:22, 19.79it/s]
 29%|██▉       | 1619/5625 [01:23<03:18, 20.16it/s]
 29%|██▉       | 1622/5625 [01:23<03:19, 20.10it/s]
 29%|██▉       | 1625/5625 [01:23<03:23, 19.62it/s]
 29%|██▉       | 1628/5625 [01:23<03:21, 19.87it/s]
 29%|██▉       | 1630/5625 [01:24<03:22, 19.73it/s]
 29%|██▉       | 1633/5625 [01:24<03:16, 20.28it/s]
 29%|██▉       | 1636/5625 [01:24<03:18, 20.09it/s]
 29%|██▉       | 1639/5625 [01:24<03:20, 19.91it/s]
 29%|██▉       | 1641/5625 [01:24<03:21, 19.77it/s]
 29%|██▉       | 1643/5625 [01:24<03:26, 19.25it/s]
 29%|██▉       | 1645/5625 [01:24<03:32, 18.73it/s]
 29%|██▉       | 1648/5625 [01:25<03:24, 19.42it/s]
 29%|██▉       | 1650/5625 [01:25<03:28, 19.02it/s]
 29%|██▉       | 1652/5625 [01:25<03:31, 18.77it/s]
 29%|██▉       | 1654/5625 [01:25<03:33, 18.59it/s]
 29%|██▉       | 1656/5625 [01:25<03:35, 18.38it/s]
 29%|██▉       | 1658/5625 [01:25<03:32, 18.70it/s]
 30%|██▉       | 1660/5625 [01:25<03:33, 18.61it/s]
 30%|██▉       | 1662/5625 [01:25<03:34, 18.47it/s]
 30%|██▉       | 1665/5625 [01:25<03:31, 18.74it/s]
 30%|██▉       | 1667/5625 [01:26<03:32, 18.66it/s]
 30%|██▉       | 1669/5625 [01:26<03:31, 18.70it/s]
 30%|██▉       | 1672/5625 [01:26<03:22, 19.54it/s]
 30%|██▉       | 1674/5625 [01:26<03:25, 19.19it/s]
 30%|██▉       | 1677/5625 [01:26<03:17, 20.03it/s]
 30%|██▉       | 1679/5625 [01:26<03:24, 19.28it/s]
 30%|██▉       | 1681/5625 [01:26<03:23, 19.37it/s]
 30%|██▉       | 1683/5625 [01:26<03:30, 18.71it/s]
 30%|██▉       | 1685/5625 [01:26<03:34, 18.39it/s]
 30%|██▉       | 1687/5625 [01:27<03:32, 18.55it/s]
 30%|███       | 1689/5625 [01:27<03:30, 18.68it/s]
 30%|███       | 1691/5625 [01:27<03:27, 18.94it/s]
 30%|███       | 1694/5625 [01:27<03:18, 19.78it/s]
 30%|███       | 1697/5625 [01:27<03:20, 19.56it/s]
 30%|███       | 1699/5625 [01:27<03:21, 19.45it/s]
 30%|███       | 1701/5625 [01:27<03:27, 18.91it/s]
 30%|███       | 1703/5625 [01:27<03:27, 18.90it/s]
 30%|███       | 1706/5625 [01:28<03:26, 19.01it/s]
 30%|███       | 1708/5625 [01:28<03:27, 18.88it/s]
 30%|███       | 1711/5625 [01:28<03:24, 19.10it/s]
 30%|███       | 1713/5625 [01:28<03:29, 18.69it/s]
 30%|███       | 1715/5625 [01:28<03:32, 18.42it/s]
 31%|███       | 1718/5625 [01:28<03:19, 19.55it/s]
 31%|███       | 1720/5625 [01:28<03:25, 18.98it/s]
 31%|███       | 1722/5625 [01:28<03:25, 18.96it/s]
 31%|███       | 1724/5625 [01:29<03:25, 19.01it/s]
 31%|███       | 1727/5625 [01:29<03:21, 19.38it/s]
 31%|███       | 1729/5625 [01:29<03:20, 19.45it/s]
 31%|███       | 1732/5625 [01:29<03:13, 20.11it/s]
 31%|███       | 1735/5625 [01:29<03:11, 20.26it/s]
 31%|███       | 1738/5625 [01:29<03:16, 19.79it/s]
 31%|███       | 1740/5625 [01:29<03:23, 19.11it/s]
 31%|███       | 1742/5625 [01:29<03:23, 19.08it/s]
 31%|███       | 1745/5625 [01:30<03:20, 19.31it/s]
 31%|███       | 1748/5625 [01:30<03:11, 20.26it/s]
 31%|███       | 1751/5625 [01:30<03:15, 19.78it/s]
 31%|███       | 1753/5625 [01:30<03:18, 19.54it/s]
 31%|███       | 1755/5625 [01:30<03:18, 19.53it/s]
 31%|███       | 1757/5625 [01:30<03:20, 19.33it/s]
 31%|███▏      | 1759/5625 [01:30<03:22, 19.07it/s]
 31%|███▏      | 1761/5625 [01:30<03:23, 19.01it/s]
 31%|███▏      | 1763/5625 [01:31<03:24, 18.92it/s]
 31%|███▏      | 1765/5625 [01:31<03:27, 18.57it/s]
 31%|███▏      | 1767/5625 [01:31<03:26, 18.68it/s]
 31%|███▏      | 1769/5625 [01:31<03:29, 18.42it/s]
 31%|███▏      | 1771/5625 [01:31<03:27, 18.60it/s]
 32%|███▏      | 1774/5625 [01:31<03:19, 19.34it/s]
 32%|███▏      | 1776/5625 [01:31<03:25, 18.77it/s]
 32%|███▏      | 1778/5625 [01:31<03:22, 19.00it/s]
 32%|███▏      | 1780/5625 [01:31<03:19, 19.23it/s]
 32%|███▏      | 1782/5625 [01:32<03:18, 19.37it/s]
 32%|███▏      | 1784/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1786/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1788/5625 [01:32<03:24, 18.78it/s]
 32%|███▏      | 1791/5625 [01:32<03:16, 19.50it/s]
 32%|███▏      | 1794/5625 [01:32<03:15, 19.64it/s]
 32%|███▏      | 1797/5625 [01:32<03:07, 20.41it/s]
 32%|███▏      | 1800/5625 [01:32<03:08, 20.27it/s]
 32%|███▏      | 1803/5625 [01:33<03:07, 20.42it/s]
 32%|███▏      | 1806/5625 [01:33<03:08, 20.25it/s]
 32%|███▏      | 1809/5625 [01:33<03:05, 20.53it/s]
 32%|███▏      | 1812/5625 [01:33<03:06, 20.47it/s]
 32%|███▏      | 1815/5625 [01:33<03:10, 20.01it/s]
 32%|███▏      | 1818/5625 [01:33<03:15, 19.47it/s]
 32%|███▏      | 1820/5625 [01:33<03:14, 19.56it/s]
 32%|███▏      | 1822/5625 [01:34<03:16, 19.35it/s]
 32%|███▏      | 1824/5625 [01:34<03:20, 18.99it/s]
 32%|███▏      | 1827/5625 [01:34<03:15, 19.44it/s]
 33%|███▎      | 1829/5625 [01:34<03:21, 18.88it/s]
 33%|███▎      | 1831/5625 [01:34<03:25, 18.42it/s]
 33%|███▎      | 1834/5625 [01:34<03:21, 18.78it/s]
 33%|███▎      | 1836/5625 [01:34<03:25, 18.40it/s]
 33%|███▎      | 1838/5625 [01:34<03:23, 18.58it/s]
 33%|███▎      | 1841/5625 [01:35<03:20, 18.83it/s]
 33%|███▎      | 1844/5625 [01:35<03:12, 19.65it/s]
 33%|███▎      | 1846/5625 [01:35<03:19, 18.99it/s]
 33%|███▎      | 1848/5625 [01:35<03:20, 18.83it/s]
 33%|███▎      | 1851/5625 [01:35<03:11, 19.68it/s]
 33%|███▎      | 1854/5625 [01:35<03:07, 20.15it/s]
 33%|███▎      | 1857/5625 [01:35<03:07, 20.07it/s]
 33%|███▎      | 1859/5625 [01:35<03:12, 19.55it/s]
 33%|███▎      | 1861/5625 [01:36<03:17, 19.09it/s]
 33%|███▎      | 1863/5625 [01:36<03:16, 19.18it/s]
 33%|███▎      | 1865/5625 [01:36<03:19, 18.82it/s]
 33%|███▎      | 1867/5625 [01:36<03:17, 18.98it/s]
 33%|███▎      | 1869/5625 [01:36<03:21, 18.66it/s]
 33%|███▎      | 1871/5625 [01:36<03:17, 18.99it/s]
 33%|███▎      | 1873/5625 [01:36<03:16, 19.11it/s]
                                                   

 33%|███▎      | 1875/5625 [01:36<03:16, 19.11it/s]{'loss': 0.7907, 'learning_rate': 4.897373254598444e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.79it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.35it/s]

 21%|██        | 66/313 [00:00<00:01, 205.78it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.05it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.27it/s]

 40%|████      | 126/313 [00:00<00:01, 185.09it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.86it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.94it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.12it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.18it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.29it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.02it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.94it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.85it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.91it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.91it/s]
 33%|███▎      | 1875/5625 [01:38<03:16, 19.11it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 1876/5625 [01:39<24:43,  2.53it/s]
 33%|███▎      | 1878/5625 [01:39<18:57,  3.29it/s]
 33%|███▎      | 1880/5625 [01:39<14:40,  4.25it/s]
 33%|███▎      | 1882/5625 [01:39<11:29,  5.43it/s]
 34%|███▎      | 1885/5625 [01:40<08:22,  7.44it/s]
 34%|███▎      | 1887/5625 [01:40<07:02,  8.85it/s]
 34%|███▎      | 1889/5625 [01:40<06:03, 10.27it/s]
 34%|███▎      | 1891/5625 [01:40<05:17, 11.76it/s]
 34%|███▎      | 1894/5625 [01:40<04:30, 13.81it/s]
 34%|███▎      | 1896/5625 [01:40<04:12, 14.75it/s]
 34%|███▍      | 1899/5625 [01:40<03:45, 16.54it/s]
 34%|███▍      | 1902/5625 [01:40<03:29, 17.73it/s]
 34%|███▍      | 1904/5625 [01:41<03:29, 17.78it/s]
 34%|███▍      | 1906/5625 [01:41<03:24, 18.20it/s]
 34%|███▍      | 1908/5625 [01:41<03:26, 18.04it/s]
 34%|███▍      | 1910/5625 [01:41<03:27, 17.90it/s]
 34%|███▍      | 1912/5625 [01:41<03:21, 18.41it/s]
 34%|███▍      | 1915/5625 [01:41<03:16, 18.89it/s]
 34%|███▍      | 1918/5625 [01:41<03:05, 19.94it/s]
 34%|███▍      | 1921/5625 [01:41<03:13, 19.19it/s]
 34%|███▍      | 1923/5625 [01:42<03:14, 19.08it/s]
 34%|███▍      | 1925/5625 [01:42<03:12, 19.25it/s]
 34%|███▍      | 1927/5625 [01:42<03:14, 19.03it/s]
 34%|███▍      | 1930/5625 [01:42<03:09, 19.53it/s]
 34%|███▍      | 1932/5625 [01:42<03:08, 19.57it/s]
 34%|███▍      | 1934/5625 [01:42<03:10, 19.40it/s]
 34%|███▍      | 1937/5625 [01:42<03:05, 19.92it/s]
 34%|███▍      | 1939/5625 [01:42<03:10, 19.35it/s]
 35%|███▍      | 1942/5625 [01:42<03:06, 19.71it/s]
 35%|███▍      | 1944/5625 [01:43<03:10, 19.29it/s]
 35%|███▍      | 1946/5625 [01:43<03:14, 18.96it/s]
 35%|███▍      | 1949/5625 [01:43<03:12, 19.10it/s]
 35%|███▍      | 1951/5625 [01:43<03:12, 19.04it/s]
 35%|███▍      | 1953/5625 [01:43<03:17, 18.60it/s]
 35%|███▍      | 1955/5625 [01:43<03:16, 18.68it/s]
 35%|███▍      | 1958/5625 [01:43<03:11, 19.18it/s]
 35%|███▍      | 1960/5625 [01:43<03:16, 18.63it/s]
 35%|███▍      | 1963/5625 [01:44<03:12, 19.02it/s]
 35%|███▍      | 1965/5625 [01:44<03:13, 18.88it/s]
 35%|███▍      | 1968/5625 [01:44<03:09, 19.34it/s]
 35%|███▌      | 1970/5625 [01:44<03:10, 19.18it/s]
 35%|███▌      | 1972/5625 [01:44<03:10, 19.14it/s]
 35%|███▌      | 1975/5625 [01:44<03:02, 20.04it/s]
 35%|███▌      | 1977/5625 [01:44<03:02, 19.95it/s]
 35%|███▌      | 1980/5625 [01:44<02:57, 20.48it/s]
 35%|███▌      | 1983/5625 [01:45<03:05, 19.61it/s]
 35%|███▌      | 1986/5625 [01:45<03:04, 19.71it/s]
 35%|███▌      | 1988/5625 [01:45<03:06, 19.54it/s]
 35%|███▌      | 1990/5625 [01:45<03:11, 18.98it/s]
 35%|███▌      | 1992/5625 [01:45<03:11, 18.95it/s]
 35%|███▌      | 1994/5625 [01:45<03:13, 18.73it/s]
 35%|███▌      | 1996/5625 [01:45<03:12, 18.88it/s]
 36%|███▌      | 1999/5625 [01:45<03:04, 19.64it/s]
 36%|███▌      | 2001/5625 [01:46<03:05, 19.56it/s]
 36%|███▌      | 2004/5625 [01:46<03:00, 20.05it/s]
 36%|███▌      | 2006/5625 [01:46<03:00, 20.02it/s]
 36%|███▌      | 2008/5625 [01:46<03:06, 19.42it/s]
 36%|███▌      | 2010/5625 [01:46<03:08, 19.13it/s]
 36%|███▌      | 2012/5625 [01:46<03:08, 19.20it/s]
 36%|███▌      | 2015/5625 [01:46<03:00, 19.98it/s]
 36%|███▌      | 2017/5625 [01:46<03:01, 19.89it/s]
 36%|███▌      | 2019/5625 [01:46<03:03, 19.60it/s]
 36%|███▌      | 2021/5625 [01:47<03:07, 19.20it/s]
 36%|███▌      | 2023/5625 [01:47<03:05, 19.37it/s]
 36%|███▌      | 2025/5625 [01:47<03:04, 19.51it/s]
 36%|███▌      | 2027/5625 [01:47<03:08, 19.07it/s]
 36%|███▌      | 2029/5625 [01:47<03:10, 18.92it/s]
 36%|███▌      | 2031/5625 [01:47<03:12, 18.66it/s]
 36%|███▌      | 2033/5625 [01:47<03:11, 18.74it/s]
 36%|███▌      | 2036/5625 [01:47<03:01, 19.80it/s]
 36%|███▌      | 2038/5625 [01:47<03:04, 19.48it/s]
 36%|███▋      | 2041/5625 [01:48<03:05, 19.36it/s]
 36%|███▋      | 2043/5625 [01:48<03:08, 18.99it/s]
 36%|███▋      | 2045/5625 [01:48<03:09, 18.87it/s]
 36%|███▋      | 2047/5625 [01:48<03:15, 18.33it/s]
 36%|███▋      | 2049/5625 [01:48<03:13, 18.50it/s]
 36%|███▋      | 2051/5625 [01:48<03:09, 18.84it/s]
 37%|███▋      | 2054/5625 [01:48<03:06, 19.13it/s]
 37%|███▋      | 2057/5625 [01:48<03:01, 19.61it/s]
 37%|███▋      | 2059/5625 [01:49<03:02, 19.55it/s]
 37%|███▋      | 2061/5625 [01:49<03:04, 19.29it/s]
 37%|███▋      | 2064/5625 [01:49<03:04, 19.34it/s]
 37%|███▋      | 2067/5625 [01:49<02:56, 20.19it/s]
 37%|███▋      | 2070/5625 [01:49<03:03, 19.42it/s]
 37%|███▋      | 2072/5625 [01:49<03:03, 19.38it/s]
 37%|███▋      | 2074/5625 [01:49<03:07, 18.94it/s]
 37%|███▋      | 2077/5625 [01:49<03:00, 19.69it/s]
 37%|███▋      | 2080/5625 [01:50<02:58, 19.81it/s]
 37%|███▋      | 2082/5625 [01:50<03:02, 19.36it/s]
 37%|███▋      | 2084/5625 [01:50<03:04, 19.21it/s]
 37%|███▋      | 2086/5625 [01:50<03:07, 18.91it/s]
 37%|███▋      | 2088/5625 [01:50<03:10, 18.56it/s]
 37%|███▋      | 2090/5625 [01:50<03:13, 18.26it/s]
 37%|███▋      | 2092/5625 [01:50<03:10, 18.51it/s]
 37%|███▋      | 2094/5625 [01:50<03:52, 15.20it/s]
 37%|███▋      | 2096/5625 [01:51<03:37, 16.26it/s]
 37%|███▋      | 2099/5625 [01:51<03:15, 18.02it/s]
 37%|███▋      | 2101/5625 [01:51<03:13, 18.24it/s]
 37%|███▋      | 2103/5625 [01:51<03:15, 18.05it/s]
 37%|███▋      | 2106/5625 [01:51<03:06, 18.84it/s]
 37%|███▋      | 2109/5625 [01:51<03:00, 19.49it/s]
 38%|███▊      | 2111/5625 [01:51<03:03, 19.14it/s]
 38%|███▊      | 2113/5625 [01:51<03:01, 19.30it/s]
 38%|███▊      | 2116/5625 [01:52<02:56, 19.87it/s]
 38%|███▊      | 2118/5625 [01:52<02:59, 19.50it/s]
 38%|███▊      | 2120/5625 [01:52<03:05, 18.94it/s]
 38%|███▊      | 2122/5625 [01:52<03:06, 18.74it/s]
 38%|███▊      | 2124/5625 [01:52<03:08, 18.55it/s]
 38%|███▊      | 2126/5625 [01:52<03:11, 18.30it/s]
 38%|███▊      | 2128/5625 [01:52<03:10, 18.40it/s]
 38%|███▊      | 2130/5625 [01:52<03:09, 18.48it/s]
 38%|███▊      | 2132/5625 [01:52<03:07, 18.64it/s]
 38%|███▊      | 2134/5625 [01:53<03:07, 18.65it/s]
 38%|███▊      | 2137/5625 [01:53<03:04, 18.89it/s]
 38%|███▊      | 2139/5625 [01:53<03:05, 18.76it/s]
 38%|███▊      | 2141/5625 [01:53<03:05, 18.75it/s]
 38%|███▊      | 2143/5625 [01:53<03:03, 18.97it/s]
 38%|███▊      | 2146/5625 [01:53<03:02, 19.07it/s]
 38%|███▊      | 2148/5625 [01:53<03:06, 18.64it/s]
 38%|███▊      | 2150/5625 [01:53<03:08, 18.44it/s]
 38%|███▊      | 2153/5625 [01:54<02:58, 19.40it/s]
 38%|███▊      | 2155/5625 [01:54<03:02, 19.03it/s]
 38%|███▊      | 2158/5625 [01:54<02:55, 19.75it/s]
 38%|███▊      | 2160/5625 [01:54<02:55, 19.72it/s]
 38%|███▊      | 2162/5625 [01:54<02:59, 19.25it/s]
 38%|███▊      | 2165/5625 [01:54<02:49, 20.37it/s]
 39%|███▊      | 2168/5625 [01:54<02:52, 20.06it/s]
 39%|███▊      | 2171/5625 [01:54<02:48, 20.44it/s]
 39%|███▊      | 2174/5625 [01:55<02:54, 19.72it/s]
 39%|███▊      | 2176/5625 [01:55<02:56, 19.55it/s]
 39%|███▊      | 2178/5625 [01:55<02:59, 19.24it/s]
 39%|███▉      | 2180/5625 [01:55<02:57, 19.41it/s]
 39%|███▉      | 2182/5625 [01:55<03:03, 18.80it/s]
 39%|███▉      | 2185/5625 [01:55<02:55, 19.65it/s]
 39%|███▉      | 2187/5625 [01:55<02:55, 19.63it/s]
 39%|███▉      | 2190/5625 [01:55<02:52, 19.88it/s]
 39%|███▉      | 2192/5625 [01:56<03:35, 15.95it/s]
 39%|███▉      | 2195/5625 [01:56<03:14, 17.66it/s]
 39%|███▉      | 2197/5625 [01:56<03:08, 18.19it/s]
 39%|███▉      | 2199/5625 [01:56<03:05, 18.44it/s]
 39%|███▉      | 2201/5625 [01:56<03:06, 18.35it/s]
 39%|███▉      | 2203/5625 [01:56<03:07, 18.24it/s]
 39%|███▉      | 2205/5625 [01:56<03:03, 18.62it/s]
 39%|███▉      | 2207/5625 [01:56<03:00, 18.92it/s]
 39%|███▉      | 2209/5625 [01:57<02:57, 19.23it/s]
 39%|███▉      | 2211/5625 [01:57<02:59, 19.07it/s]
 39%|███▉      | 2213/5625 [01:57<03:00, 18.92it/s]
 39%|███▉      | 2216/5625 [01:57<02:55, 19.47it/s]
 39%|███▉      | 2218/5625 [01:57<02:55, 19.38it/s]
 39%|███▉      | 2220/5625 [01:57<02:57, 19.21it/s]
 40%|███▉      | 2222/5625 [01:57<03:01, 18.77it/s]
 40%|███▉      | 2224/5625 [01:57<02:59, 18.98it/s]
 40%|███▉      | 2226/5625 [01:57<03:03, 18.55it/s]
 40%|███▉      | 2228/5625 [01:58<03:00, 18.83it/s]
 40%|███▉      | 2230/5625 [01:58<03:04, 18.44it/s]
 40%|███▉      | 2232/5625 [01:58<03:03, 18.48it/s]
 40%|███▉      | 2234/5625 [01:58<03:01, 18.64it/s]
 40%|███▉      | 2236/5625 [01:58<03:00, 18.80it/s]
 40%|███▉      | 2238/5625 [01:58<03:01, 18.63it/s]
 40%|███▉      | 2240/5625 [01:58<03:05, 18.20it/s]
 40%|███▉      | 2242/5625 [01:58<03:03, 18.44it/s]
 40%|███▉      | 2244/5625 [01:58<03:02, 18.52it/s]
 40%|███▉      | 2246/5625 [01:58<03:02, 18.52it/s]
 40%|███▉      | 2248/5625 [01:59<02:59, 18.80it/s]
 40%|████      | 2250/5625 [01:59<02:59, 18.85it/s]
 40%|████      | 2253/5625 [01:59<02:55, 19.25it/s]
 40%|████      | 2255/5625 [01:59<02:57, 18.93it/s]
 40%|████      | 2257/5625 [01:59<03:01, 18.52it/s]
 40%|████      | 2259/5625 [01:59<03:01, 18.52it/s]
 40%|████      | 2261/5625 [01:59<02:57, 18.92it/s]
 40%|████      | 2264/5625 [01:59<02:48, 19.96it/s]
 40%|████      | 2266/5625 [02:00<02:51, 19.60it/s]
 40%|████      | 2269/5625 [02:00<02:51, 19.57it/s]
 40%|████      | 2271/5625 [02:00<02:52, 19.42it/s]
 40%|████      | 2274/5625 [02:00<02:49, 19.74it/s]
 40%|████      | 2277/5625 [02:00<02:49, 19.77it/s]
 41%|████      | 2279/5625 [02:00<02:53, 19.33it/s]
 41%|████      | 2281/5625 [02:00<02:52, 19.35it/s]
 41%|████      | 2283/5625 [02:00<02:52, 19.39it/s]
 41%|████      | 2285/5625 [02:00<02:52, 19.35it/s]
 41%|████      | 2287/5625 [02:01<02:54, 19.18it/s]
 41%|████      | 2289/5625 [02:01<02:57, 18.75it/s]
 41%|████      | 2292/5625 [02:01<02:52, 19.33it/s]
 41%|████      | 2294/5625 [02:01<02:56, 18.87it/s]
 41%|████      | 2296/5625 [02:01<02:57, 18.80it/s]
 41%|████      | 2298/5625 [02:01<02:58, 18.59it/s]
 41%|████      | 2300/5625 [02:01<02:55, 18.92it/s]
 41%|████      | 2302/5625 [02:01<02:58, 18.66it/s]
 41%|████      | 2305/5625 [02:02<02:48, 19.70it/s]
 41%|████      | 2308/5625 [02:02<02:46, 19.90it/s]
 41%|████      | 2310/5625 [02:02<02:47, 19.84it/s]
 41%|████      | 2312/5625 [02:02<02:51, 19.29it/s]
 41%|████      | 2314/5625 [02:02<02:54, 19.00it/s]
 41%|████      | 2317/5625 [02:02<02:45, 20.00it/s]
 41%|████      | 2320/5625 [02:02<02:39, 20.73it/s]
 41%|████▏     | 2323/5625 [02:02<02:45, 19.97it/s]
 41%|████▏     | 2325/5625 [02:03<02:50, 19.35it/s]
 41%|████▏     | 2327/5625 [02:03<02:51, 19.24it/s]
 41%|████▏     | 2330/5625 [02:03<02:48, 19.55it/s]
 41%|████▏     | 2332/5625 [02:03<02:52, 19.08it/s]
 41%|████▏     | 2334/5625 [02:03<02:51, 19.24it/s]
 42%|████▏     | 2336/5625 [02:03<02:55, 18.72it/s]
 42%|████▏     | 2339/5625 [02:03<02:54, 18.88it/s]
 42%|████▏     | 2341/5625 [02:03<02:58, 18.43it/s]
 42%|████▏     | 2343/5625 [02:04<02:57, 18.49it/s]
 42%|████▏     | 2345/5625 [02:04<02:58, 18.41it/s]
 42%|████▏     | 2347/5625 [02:04<02:54, 18.74it/s]
 42%|████▏     | 2349/5625 [02:04<02:53, 18.87it/s]
 42%|████▏     | 2351/5625 [02:04<02:52, 18.98it/s]
 42%|████▏     | 2353/5625 [02:04<02:53, 18.83it/s]
 42%|████▏     | 2355/5625 [02:04<02:50, 19.14it/s]
 42%|████▏     | 2358/5625 [02:04<02:50, 19.17it/s]
 42%|████▏     | 2361/5625 [02:04<02:47, 19.45it/s]
 42%|████▏     | 2363/5625 [02:05<02:48, 19.40it/s]
 42%|████▏     | 2365/5625 [02:05<02:47, 19.49it/s]
 42%|████▏     | 2367/5625 [02:05<02:48, 19.31it/s]
 42%|████▏     | 2369/5625 [02:05<02:48, 19.36it/s]
 42%|████▏     | 2371/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2374/5625 [02:05<02:44, 19.73it/s]
 42%|████▏     | 2376/5625 [02:05<02:44, 19.70it/s]
 42%|████▏     | 2378/5625 [02:05<02:48, 19.29it/s]
 42%|████▏     | 2380/5625 [02:05<02:53, 18.72it/s]
 42%|████▏     | 2382/5625 [02:06<02:54, 18.57it/s]
 42%|████▏     | 2384/5625 [02:06<03:52, 13.96it/s]
 42%|████▏     | 2387/5625 [02:06<03:20, 16.14it/s]
 42%|████▏     | 2389/5625 [02:06<03:10, 16.96it/s]
 43%|████▎     | 2391/5625 [02:06<03:02, 17.68it/s]
 43%|████▎     | 2393/5625 [02:06<03:00, 17.92it/s]
 43%|████▎     | 2395/5625 [02:06<02:57, 18.24it/s]
 43%|████▎     | 2398/5625 [02:06<02:44, 19.64it/s]
 43%|████▎     | 2400/5625 [02:07<02:47, 19.29it/s]
 43%|████▎     | 2402/5625 [02:07<02:48, 19.10it/s]
 43%|████▎     | 2404/5625 [02:07<02:48, 19.06it/s]
 43%|████▎     | 2407/5625 [02:07<02:44, 19.55it/s]
 43%|████▎     | 2410/5625 [02:07<02:43, 19.67it/s]
 43%|████▎     | 2413/5625 [02:07<02:41, 19.85it/s]
 43%|████▎     | 2415/5625 [02:07<02:46, 19.22it/s]
 43%|████▎     | 2418/5625 [02:07<02:41, 19.92it/s]
 43%|████▎     | 2420/5625 [02:08<02:44, 19.46it/s]
 43%|████▎     | 2422/5625 [02:08<02:44, 19.42it/s]
 43%|████▎     | 2425/5625 [02:08<02:43, 19.58it/s]
 43%|████▎     | 2427/5625 [02:08<02:44, 19.49it/s]
 43%|████▎     | 2429/5625 [02:08<02:43, 19.53it/s]
 43%|████▎     | 2432/5625 [02:08<02:35, 20.48it/s]
 43%|████▎     | 2435/5625 [02:08<02:31, 21.02it/s]
 43%|████▎     | 2438/5625 [02:08<02:33, 20.80it/s]
 43%|████▎     | 2441/5625 [02:09<02:36, 20.40it/s]
 43%|████▎     | 2444/5625 [02:09<02:33, 20.70it/s]
 44%|████▎     | 2447/5625 [02:09<02:39, 19.90it/s]
 44%|████▎     | 2450/5625 [02:09<02:36, 20.26it/s]
 44%|████▎     | 2453/5625 [02:09<02:36, 20.24it/s]
 44%|████▎     | 2456/5625 [02:09<02:35, 20.38it/s]
 44%|████▎     | 2459/5625 [02:10<02:38, 20.02it/s]
 44%|████▍     | 2462/5625 [02:10<02:40, 19.67it/s]
 44%|████▍     | 2465/5625 [02:10<02:38, 19.97it/s]
 44%|████▍     | 2468/5625 [02:10<02:44, 19.24it/s]
 44%|████▍     | 2470/5625 [02:10<02:43, 19.35it/s]
 44%|████▍     | 2473/5625 [02:10<02:39, 19.76it/s]
 44%|████▍     | 2475/5625 [02:10<02:40, 19.59it/s]
 44%|████▍     | 2477/5625 [02:10<02:41, 19.54it/s]
 44%|████▍     | 2479/5625 [02:11<02:45, 19.01it/s]
 44%|████▍     | 2482/5625 [02:11<02:37, 19.94it/s]
 44%|████▍     | 2485/5625 [02:11<02:35, 20.14it/s]
 44%|████▍     | 2488/5625 [02:11<02:41, 19.42it/s]
 44%|████▍     | 2490/5625 [02:11<02:43, 19.23it/s]
 44%|████▍     | 2492/5625 [02:11<02:46, 18.80it/s]
 44%|████▍     | 2495/5625 [02:11<02:43, 19.13it/s]
 44%|████▍     | 2497/5625 [02:12<02:46, 18.78it/s]
 44%|████▍     | 2499/5625 [02:12<02:46, 18.78it/s]
 44%|████▍     | 2502/5625 [02:12<02:38, 19.68it/s]
 45%|████▍     | 2504/5625 [02:12<02:38, 19.70it/s]
 45%|████▍     | 2507/5625 [02:12<02:31, 20.64it/s]
 45%|████▍     | 2510/5625 [02:12<02:36, 19.88it/s]
 45%|████▍     | 2513/5625 [02:12<02:31, 20.53it/s]
 45%|████▍     | 2516/5625 [02:12<02:30, 20.66it/s]
 45%|████▍     | 2519/5625 [02:13<02:30, 20.68it/s]
 45%|████▍     | 2522/5625 [02:13<02:36, 19.83it/s]
 45%|████▍     | 2525/5625 [02:13<02:33, 20.26it/s]
 45%|████▍     | 2528/5625 [02:13<02:38, 19.59it/s]
 45%|████▍     | 2530/5625 [02:13<02:38, 19.47it/s]
 45%|████▌     | 2532/5625 [02:13<02:42, 19.07it/s]
 45%|████▌     | 2534/5625 [02:13<02:45, 18.69it/s]
 45%|████▌     | 2536/5625 [02:13<02:45, 18.65it/s]
 45%|████▌     | 2538/5625 [02:14<02:47, 18.40it/s]
 45%|████▌     | 2540/5625 [02:14<02:50, 18.12it/s]
 45%|████▌     | 2542/5625 [02:14<02:47, 18.43it/s]
 45%|████▌     | 2545/5625 [02:14<02:39, 19.26it/s]
 45%|████▌     | 2547/5625 [02:14<02:43, 18.88it/s]
 45%|████▌     | 2549/5625 [02:14<02:42, 18.88it/s]
 45%|████▌     | 2551/5625 [02:14<02:41, 19.03it/s]
 45%|████▌     | 2553/5625 [02:14<02:39, 19.28it/s]
 45%|████▌     | 2555/5625 [02:14<02:41, 19.05it/s]
 45%|████▌     | 2557/5625 [02:15<02:39, 19.26it/s]
 45%|████▌     | 2559/5625 [02:15<02:40, 19.06it/s]
 46%|████▌     | 2561/5625 [02:15<02:40, 19.14it/s]
 46%|████▌     | 2563/5625 [02:15<02:39, 19.19it/s]
 46%|████▌     | 2565/5625 [02:15<02:43, 18.67it/s]
 46%|████▌     | 2568/5625 [02:15<02:40, 19.10it/s]
 46%|████▌     | 2571/5625 [02:15<02:33, 19.86it/s]
 46%|████▌     | 2574/5625 [02:15<02:33, 19.83it/s]
 46%|████▌     | 2576/5625 [02:16<02:39, 19.11it/s]
 46%|████▌     | 2579/5625 [02:16<02:37, 19.31it/s]
 46%|████▌     | 2581/5625 [02:16<03:10, 16.00it/s]
 46%|████▌     | 2583/5625 [02:16<03:06, 16.32it/s]
 46%|████▌     | 2586/5625 [02:16<02:53, 17.52it/s]
 46%|████▌     | 2589/5625 [02:16<02:43, 18.62it/s]
 46%|████▌     | 2591/5625 [02:16<02:44, 18.40it/s]
 46%|████▌     | 2594/5625 [02:17<02:41, 18.77it/s]
 46%|████▌     | 2596/5625 [02:17<02:43, 18.57it/s]
 46%|████▌     | 2598/5625 [02:17<02:45, 18.27it/s]
 46%|████▌     | 2601/5625 [02:17<02:40, 18.84it/s]
 46%|████▋     | 2603/5625 [02:17<02:42, 18.55it/s]
 46%|████▋     | 2605/5625 [02:17<02:45, 18.20it/s]
 46%|████▋     | 2607/5625 [02:17<02:43, 18.42it/s]
 46%|████▋     | 2609/5625 [02:17<02:42, 18.51it/s]
 46%|████▋     | 2611/5625 [02:18<02:45, 18.19it/s]
 46%|████▋     | 2613/5625 [02:18<02:45, 18.23it/s]
 47%|████▋     | 2616/5625 [02:18<02:39, 18.82it/s]
 47%|████▋     | 2618/5625 [02:18<02:39, 18.82it/s]
 47%|████▋     | 2620/5625 [02:18<02:40, 18.67it/s]
 47%|████▋     | 2623/5625 [02:18<02:36, 19.13it/s]
 47%|████▋     | 2625/5625 [02:18<02:37, 19.03it/s]
 47%|████▋     | 2627/5625 [02:18<02:39, 18.79it/s]
 47%|████▋     | 2629/5625 [02:18<02:40, 18.72it/s]
 47%|████▋     | 2632/5625 [02:19<02:34, 19.34it/s]
 47%|████▋     | 2634/5625 [02:19<02:36, 19.08it/s]
 47%|████▋     | 2636/5625 [02:19<02:37, 19.03it/s]
 47%|████▋     | 2638/5625 [02:19<02:35, 19.27it/s]
 47%|████▋     | 2640/5625 [02:19<02:35, 19.19it/s]
 47%|████▋     | 2643/5625 [02:19<02:29, 19.90it/s]
 47%|████▋     | 2645/5625 [02:19<02:30, 19.77it/s]
 47%|████▋     | 2647/5625 [02:19<02:33, 19.38it/s]
 47%|████▋     | 2649/5625 [02:19<02:34, 19.28it/s]
 47%|████▋     | 2651/5625 [02:20<02:37, 18.94it/s]
 47%|████▋     | 2653/5625 [02:20<02:39, 18.60it/s]
 47%|████▋     | 2655/5625 [02:20<02:40, 18.52it/s]
 47%|████▋     | 2658/5625 [02:20<02:32, 19.47it/s]
 47%|████▋     | 2661/5625 [02:20<02:26, 20.18it/s]
 47%|████▋     | 2664/5625 [02:20<02:27, 20.02it/s]
 47%|████▋     | 2666/5625 [02:20<02:30, 19.61it/s]
 47%|████▋     | 2669/5625 [02:21<02:27, 20.00it/s]
 47%|████▋     | 2671/5625 [02:21<02:29, 19.74it/s]
 48%|████▊     | 2673/5625 [02:21<02:29, 19.69it/s]
 48%|████▊     | 2676/5625 [02:21<02:30, 19.66it/s]
 48%|████▊     | 2678/5625 [02:21<02:32, 19.29it/s]
 48%|████▊     | 2680/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2682/5625 [02:21<02:31, 19.42it/s]
 48%|████▊     | 2684/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2686/5625 [02:21<02:30, 19.47it/s]
 48%|████▊     | 2688/5625 [02:21<02:31, 19.40it/s]
 48%|████▊     | 2691/5625 [02:22<02:30, 19.45it/s]
 48%|████▊     | 2693/5625 [02:22<02:34, 18.98it/s]
 48%|████▊     | 2696/5625 [02:22<02:27, 19.81it/s]
 48%|████▊     | 2699/5625 [02:22<02:24, 20.24it/s]
 48%|████▊     | 2702/5625 [02:22<02:27, 19.84it/s]
 48%|████▊     | 2704/5625 [02:22<02:29, 19.50it/s]
 48%|████▊     | 2706/5625 [02:22<02:33, 19.00it/s]
 48%|████▊     | 2709/5625 [02:23<02:30, 19.37it/s]
 48%|████▊     | 2711/5625 [02:23<02:33, 18.93it/s]
 48%|████▊     | 2713/5625 [02:23<02:34, 18.90it/s]
 48%|████▊     | 2715/5625 [02:23<02:37, 18.48it/s]
 48%|████▊     | 2717/5625 [02:23<02:34, 18.78it/s]
 48%|████▊     | 2719/5625 [02:23<02:38, 18.37it/s]
 48%|████▊     | 2721/5625 [02:23<02:35, 18.66it/s]
 48%|████▊     | 2723/5625 [02:23<02:35, 18.62it/s]
 48%|████▊     | 2725/5625 [02:23<02:34, 18.79it/s]
 48%|████▊     | 2727/5625 [02:24<02:31, 19.07it/s]
 49%|████▊     | 2730/5625 [02:24<02:28, 19.49it/s]
 49%|████▊     | 2732/5625 [02:24<02:29, 19.32it/s]
 49%|████▊     | 2734/5625 [02:24<02:32, 18.92it/s]
 49%|████▊     | 2737/5625 [02:24<02:26, 19.74it/s]
 49%|████▊     | 2739/5625 [02:24<02:26, 19.65it/s]
 49%|████▊     | 2741/5625 [02:24<02:29, 19.30it/s]
 49%|████▉     | 2743/5625 [02:24<02:31, 19.04it/s]
 49%|████▉     | 2746/5625 [02:25<02:29, 19.30it/s]
 49%|████▉     | 2748/5625 [02:25<02:28, 19.37it/s]
 49%|████▉     | 2750/5625 [02:25<02:27, 19.46it/s]
 49%|████▉     | 2752/5625 [02:25<02:27, 19.45it/s]
 49%|████▉     | 2754/5625 [02:25<02:28, 19.31it/s]
 49%|████▉     | 2757/5625 [02:25<02:29, 19.21it/s]
 49%|████▉     | 2760/5625 [02:25<02:25, 19.69it/s]
 49%|████▉     | 2762/5625 [02:25<02:27, 19.44it/s]
 49%|████▉     | 2764/5625 [02:25<02:30, 18.99it/s]
 49%|████▉     | 2767/5625 [02:26<02:25, 19.62it/s]
 49%|████▉     | 2770/5625 [02:26<02:24, 19.76it/s]
 49%|████▉     | 2772/5625 [02:26<02:28, 19.27it/s]
 49%|████▉     | 2774/5625 [02:26<02:27, 19.34it/s]
 49%|████▉     | 2776/5625 [02:26<02:26, 19.44it/s]
 49%|████▉     | 2778/5625 [02:26<02:28, 19.21it/s]
 49%|████▉     | 2780/5625 [02:26<02:29, 19.01it/s]
 49%|████▉     | 2783/5625 [02:26<02:27, 19.22it/s]
 50%|████▉     | 2785/5625 [02:27<02:29, 18.99it/s]
 50%|████▉     | 2788/5625 [02:27<02:23, 19.74it/s]
 50%|████▉     | 2790/5625 [02:27<02:26, 19.31it/s]
 50%|████▉     | 2792/5625 [02:27<02:28, 19.13it/s]
 50%|████▉     | 2794/5625 [02:27<02:26, 19.33it/s]
 50%|████▉     | 2796/5625 [02:27<02:31, 18.71it/s]
 50%|████▉     | 2798/5625 [02:27<02:29, 18.87it/s]
 50%|████▉     | 2800/5625 [02:27<02:27, 19.14it/s]
 50%|████▉     | 2802/5625 [02:27<02:32, 18.56it/s]
 50%|████▉     | 2804/5625 [02:28<02:29, 18.86it/s]
 50%|████▉     | 2806/5625 [02:28<02:29, 18.91it/s]
 50%|████▉     | 2809/5625 [02:28<02:27, 19.11it/s]
 50%|████▉     | 2811/5625 [02:28<02:26, 19.25it/s]
 50%|█████     | 2814/5625 [02:28<02:24, 19.51it/s]
 50%|█████     | 2816/5625 [02:28<02:25, 19.28it/s]
 50%|█████     | 2818/5625 [02:28<02:25, 19.30it/s]
 50%|█████     | 2820/5625 [02:28<02:29, 18.72it/s]
 50%|█████     | 2822/5625 [02:28<02:28, 18.90it/s]
 50%|█████     | 2824/5625 [02:29<02:26, 19.18it/s]
 50%|█████     | 2827/5625 [02:29<02:19, 20.03it/s]
 50%|█████     | 2829/5625 [02:29<02:22, 19.68it/s]
 50%|█████     | 2831/5625 [02:29<02:23, 19.41it/s]
 50%|█████     | 2833/5625 [02:29<02:26, 19.06it/s]
 50%|█████     | 2835/5625 [02:29<02:24, 19.25it/s]
 50%|█████     | 2838/5625 [02:29<02:20, 19.80it/s]
 50%|█████     | 2840/5625 [02:29<02:21, 19.72it/s]
 51%|█████     | 2843/5625 [02:30<02:16, 20.41it/s]
 51%|█████     | 2846/5625 [02:30<02:22, 19.50it/s]
 51%|█████     | 2849/5625 [02:30<02:21, 19.57it/s]
 51%|█████     | 2851/5625 [02:30<02:23, 19.36it/s]
 51%|█████     | 2853/5625 [02:30<02:25, 19.07it/s]
 51%|█████     | 2856/5625 [02:30<02:21, 19.60it/s]
 51%|█████     | 2858/5625 [02:30<02:25, 19.03it/s]
 51%|█████     | 2861/5625 [02:30<02:18, 19.94it/s]
 51%|█████     | 2863/5625 [02:31<02:20, 19.67it/s]
 51%|█████     | 2865/5625 [02:31<02:22, 19.39it/s]
 51%|█████     | 2867/5625 [02:31<02:21, 19.48it/s]
 51%|█████     | 2870/5625 [02:31<02:15, 20.30it/s]
 51%|█████     | 2873/5625 [02:31<02:18, 19.85it/s]
 51%|█████     | 2875/5625 [02:31<02:20, 19.57it/s]
 51%|█████     | 2877/5625 [02:31<02:21, 19.45it/s]
 51%|█████     | 2879/5625 [02:31<02:23, 19.15it/s]
 51%|█████     | 2882/5625 [02:32<02:21, 19.39it/s]
 51%|█████▏    | 2884/5625 [02:32<02:23, 19.14it/s]
 51%|█████▏    | 2887/5625 [02:32<02:16, 20.07it/s]
 51%|█████▏    | 2889/5625 [02:32<02:21, 19.29it/s]
 51%|█████▏    | 2891/5625 [02:32<02:20, 19.40it/s]
 51%|█████▏    | 2894/5625 [02:32<02:16, 19.98it/s]
 51%|█████▏    | 2896/5625 [02:32<02:19, 19.49it/s]
 52%|█████▏    | 2898/5625 [02:32<02:21, 19.33it/s]
 52%|█████▏    | 2900/5625 [02:32<02:26, 18.65it/s]
 52%|█████▏    | 2903/5625 [02:33<02:19, 19.55it/s]
 52%|█████▏    | 2906/5625 [02:33<02:15, 20.13it/s]
 52%|█████▏    | 2908/5625 [02:33<02:16, 19.85it/s]
 52%|█████▏    | 2910/5625 [02:33<02:16, 19.83it/s]
 52%|█████▏    | 2913/5625 [02:33<02:14, 20.11it/s]
 52%|█████▏    | 2915/5625 [02:33<02:17, 19.76it/s]
 52%|█████▏    | 2917/5625 [02:33<02:21, 19.20it/s]
 52%|█████▏    | 2919/5625 [02:33<02:24, 18.79it/s]
 52%|█████▏    | 2921/5625 [02:34<02:26, 18.44it/s]
 52%|█████▏    | 2923/5625 [02:34<02:23, 18.80it/s]
 52%|█████▏    | 2925/5625 [02:34<02:25, 18.60it/s]
 52%|█████▏    | 2927/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2929/5625 [02:34<02:22, 18.92it/s]
 52%|█████▏    | 2931/5625 [02:34<02:21, 19.11it/s]
 52%|█████▏    | 2934/5625 [02:34<02:20, 19.20it/s]
 52%|█████▏    | 2937/5625 [02:34<02:19, 19.23it/s]
 52%|█████▏    | 2940/5625 [02:35<02:13, 20.06it/s]
 52%|█████▏    | 2943/5625 [02:35<02:11, 20.43it/s]
 52%|█████▏    | 2946/5625 [02:35<02:14, 19.87it/s]
 52%|█████▏    | 2948/5625 [02:35<02:15, 19.75it/s]
 52%|█████▏    | 2950/5625 [02:35<02:18, 19.32it/s]
 52%|█████▏    | 2952/5625 [02:35<02:18, 19.34it/s]
 53%|█████▎    | 2954/5625 [02:35<02:20, 18.99it/s]
 53%|█████▎    | 2957/5625 [02:35<02:17, 19.44it/s]
 53%|█████▎    | 2960/5625 [02:36<02:15, 19.60it/s]
 53%|█████▎    | 2963/5625 [02:36<02:15, 19.65it/s]
 53%|█████▎    | 2965/5625 [02:36<02:19, 19.05it/s]
 53%|█████▎    | 2967/5625 [02:36<02:17, 19.26it/s]
 53%|█████▎    | 2970/5625 [02:36<02:16, 19.41it/s]
 53%|█████▎    | 2973/5625 [02:36<02:14, 19.65it/s]
 53%|█████▎    | 2976/5625 [02:36<02:14, 19.69it/s]
 53%|█████▎    | 2978/5625 [02:36<02:15, 19.51it/s]
 53%|█████▎    | 2980/5625 [02:37<02:17, 19.19it/s]
 53%|█████▎    | 2983/5625 [02:37<02:17, 19.24it/s]
 53%|█████▎    | 2985/5625 [02:37<02:19, 18.90it/s]
 53%|█████▎    | 2988/5625 [02:37<02:16, 19.36it/s]
 53%|█████▎    | 2990/5625 [02:37<02:18, 19.08it/s]
 53%|█████▎    | 2992/5625 [02:37<02:16, 19.29it/s]
 53%|█████▎    | 2995/5625 [02:37<02:12, 19.92it/s]
 53%|█████▎    | 2997/5625 [02:37<02:14, 19.58it/s]
 53%|█████▎    | 2999/5625 [02:38<02:16, 19.27it/s]
 53%|█████▎    | 3002/5625 [02:38<02:12, 19.74it/s]
 53%|█████▎    | 3005/5625 [02:38<02:09, 20.23it/s]
 53%|█████▎    | 3008/5625 [02:38<02:11, 19.92it/s]
 54%|█████▎    | 3010/5625 [02:38<02:14, 19.51it/s]
 54%|█████▎    | 3012/5625 [02:38<02:15, 19.35it/s]
 54%|█████▎    | 3014/5625 [02:38<02:17, 18.95it/s]
 54%|█████▎    | 3017/5625 [02:38<02:13, 19.57it/s]
 54%|█████▎    | 3019/5625 [02:39<02:14, 19.33it/s]
 54%|█████▎    | 3022/5625 [02:39<02:13, 19.56it/s]
 54%|█████▍    | 3024/5625 [02:39<02:12, 19.65it/s]
 54%|█████▍    | 3027/5625 [02:39<02:09, 20.05it/s]
 54%|█████▍    | 3029/5625 [02:39<02:11, 19.78it/s]
 54%|█████▍    | 3032/5625 [02:39<02:08, 20.11it/s]
 54%|█████▍    | 3034/5625 [02:39<02:09, 20.01it/s]
 54%|█████▍    | 3037/5625 [02:39<02:07, 20.26it/s]
 54%|█████▍    | 3040/5625 [02:40<02:13, 19.37it/s]
 54%|█████▍    | 3042/5625 [02:40<02:15, 19.05it/s]
 54%|█████▍    | 3044/5625 [02:40<02:16, 18.93it/s]
 54%|█████▍    | 3047/5625 [02:40<02:15, 19.09it/s]
 54%|█████▍    | 3050/5625 [02:40<02:10, 19.76it/s]
 54%|█████▍    | 3053/5625 [02:40<02:09, 19.80it/s]
 54%|█████▍    | 3056/5625 [02:40<02:06, 20.31it/s]
 54%|█████▍    | 3059/5625 [02:41<02:08, 19.90it/s]
 54%|█████▍    | 3061/5625 [02:41<02:09, 19.78it/s]
 54%|█████▍    | 3063/5625 [02:41<02:09, 19.80it/s]
 54%|█████▍    | 3065/5625 [02:41<02:12, 19.26it/s]
 55%|█████▍    | 3068/5625 [02:41<02:10, 19.59it/s]
 55%|█████▍    | 3070/5625 [02:41<02:12, 19.29it/s]
 55%|█████▍    | 3072/5625 [02:41<02:13, 19.19it/s]
 55%|█████▍    | 3074/5625 [02:41<02:14, 18.98it/s]
 55%|█████▍    | 3077/5625 [02:42<02:08, 19.86it/s]
 55%|█████▍    | 3079/5625 [02:42<02:09, 19.59it/s]
 55%|█████▍    | 3081/5625 [02:42<02:11, 19.37it/s]
 55%|█████▍    | 3084/5625 [02:42<02:10, 19.42it/s]
 55%|█████▍    | 3086/5625 [02:42<02:10, 19.51it/s]
 55%|█████▍    | 3088/5625 [02:42<02:09, 19.60it/s]
 55%|█████▍    | 3090/5625 [02:42<02:10, 19.43it/s]
 55%|█████▍    | 3092/5625 [02:42<02:10, 19.42it/s]
 55%|█████▌    | 3095/5625 [02:42<02:10, 19.33it/s]
 55%|█████▌    | 3097/5625 [02:43<02:12, 19.08it/s]
 55%|█████▌    | 3100/5625 [02:43<02:10, 19.41it/s]
 55%|█████▌    | 3103/5625 [02:43<02:04, 20.19it/s]
 55%|█████▌    | 3106/5625 [02:43<02:07, 19.82it/s]
 55%|█████▌    | 3109/5625 [02:43<02:03, 20.44it/s]
 55%|█████▌    | 3112/5625 [02:43<02:07, 19.64it/s]
 55%|█████▌    | 3114/5625 [02:43<02:09, 19.41it/s]
 55%|█████▌    | 3116/5625 [02:44<02:12, 18.94it/s]
 55%|█████▌    | 3118/5625 [02:44<02:14, 18.60it/s]
 55%|█████▌    | 3120/5625 [02:44<02:12, 18.88it/s]
 56%|█████▌    | 3123/5625 [02:44<02:09, 19.28it/s]
 56%|█████▌    | 3125/5625 [02:44<02:09, 19.26it/s]
 56%|█████▌    | 3127/5625 [02:44<02:11, 19.06it/s]
 56%|█████▌    | 3129/5625 [02:44<02:13, 18.68it/s]
 56%|█████▌    | 3132/5625 [02:44<02:10, 19.03it/s]
 56%|█████▌    | 3134/5625 [02:44<02:11, 19.00it/s]
 56%|█████▌    | 3136/5625 [02:45<02:13, 18.69it/s]
 56%|█████▌    | 3138/5625 [02:45<02:13, 18.61it/s]
 56%|█████▌    | 3140/5625 [02:45<02:15, 18.30it/s]
 56%|█████▌    | 3143/5625 [02:45<02:07, 19.40it/s]
 56%|█████▌    | 3146/5625 [02:45<02:02, 20.31it/s]
 56%|█████▌    | 3149/5625 [02:45<02:06, 19.59it/s]
 56%|█████▌    | 3152/5625 [02:45<02:06, 19.61it/s]
 56%|█████▌    | 3155/5625 [02:46<02:02, 20.10it/s]
 56%|█████▌    | 3158/5625 [02:46<02:03, 19.93it/s]
 56%|█████▌    | 3160/5625 [02:46<02:06, 19.55it/s]
 56%|█████▌    | 3162/5625 [02:46<02:10, 18.93it/s]
 56%|█████▌    | 3164/5625 [02:46<02:10, 18.79it/s]
 56%|█████▋    | 3166/5625 [02:46<02:09, 19.00it/s]
 56%|█████▋    | 3168/5625 [02:46<02:09, 18.91it/s]
 56%|█████▋    | 3170/5625 [02:46<02:12, 18.52it/s]
 56%|█████▋    | 3172/5625 [02:46<02:13, 18.43it/s]
 56%|█████▋    | 3174/5625 [02:47<02:14, 18.18it/s]
 56%|█████▋    | 3176/5625 [02:47<02:14, 18.23it/s]
 56%|█████▋    | 3178/5625 [02:47<02:15, 18.12it/s]
 57%|█████▋    | 3180/5625 [02:47<02:12, 18.47it/s]
 57%|█████▋    | 3183/5625 [02:47<02:09, 18.86it/s]
 57%|█████▋    | 3185/5625 [02:47<02:11, 18.60it/s]
 57%|█████▋    | 3187/5625 [02:47<02:11, 18.52it/s]
 57%|█████▋    | 3189/5625 [02:47<02:08, 18.89it/s]
 57%|█████▋    | 3191/5625 [02:48<02:10, 18.70it/s]
 57%|█████▋    | 3194/5625 [02:48<02:09, 18.81it/s]
 57%|█████▋    | 3196/5625 [02:48<02:07, 19.08it/s]
 57%|█████▋    | 3198/5625 [02:48<02:07, 19.05it/s]
 57%|█████▋    | 3200/5625 [02:48<02:07, 18.99it/s]
 57%|█████▋    | 3203/5625 [02:48<02:04, 19.46it/s]
 57%|█████▋    | 3206/5625 [02:48<02:05, 19.33it/s]
 57%|█████▋    | 3209/5625 [02:48<02:03, 19.61it/s]
 57%|█████▋    | 3211/5625 [02:49<02:03, 19.62it/s]
 57%|█████▋    | 3213/5625 [02:49<02:02, 19.64it/s]
 57%|█████▋    | 3216/5625 [02:49<02:01, 19.90it/s]
 57%|█████▋    | 3218/5625 [02:49<02:02, 19.66it/s]
 57%|█████▋    | 3220/5625 [02:49<02:05, 19.23it/s]
 57%|█████▋    | 3223/5625 [02:49<02:00, 19.86it/s]
 57%|█████▋    | 3226/5625 [02:49<01:58, 20.17it/s]
 57%|█████▋    | 3229/5625 [02:49<02:01, 19.70it/s]
 57%|█████▋    | 3231/5625 [02:50<02:03, 19.41it/s]
 57%|█████▋    | 3234/5625 [02:50<02:02, 19.54it/s]
 58%|█████▊    | 3237/5625 [02:50<02:03, 19.41it/s]
 58%|█████▊    | 3239/5625 [02:50<02:02, 19.52it/s]
 58%|█████▊    | 3241/5625 [02:50<02:06, 18.83it/s]
 58%|█████▊    | 3244/5625 [02:50<02:02, 19.37it/s]
 58%|█████▊    | 3246/5625 [02:50<02:03, 19.28it/s]
 58%|█████▊    | 3249/5625 [02:50<02:00, 19.78it/s]
 58%|█████▊    | 3251/5625 [02:51<02:01, 19.54it/s]
 58%|█████▊    | 3254/5625 [02:51<02:00, 19.73it/s]
 58%|█████▊    | 3257/5625 [02:51<01:58, 19.95it/s]
 58%|█████▊    | 3259/5625 [02:51<02:00, 19.65it/s]
 58%|█████▊    | 3262/5625 [02:51<01:59, 19.80it/s]
 58%|█████▊    | 3264/5625 [02:51<02:00, 19.54it/s]
 58%|█████▊    | 3267/5625 [02:51<02:00, 19.60it/s]
 58%|█████▊    | 3269/5625 [02:51<02:02, 19.30it/s]
 58%|█████▊    | 3272/5625 [02:52<02:00, 19.51it/s]
 58%|█████▊    | 3275/5625 [02:52<01:57, 19.99it/s]
 58%|█████▊    | 3277/5625 [02:52<01:57, 19.93it/s]
 58%|█████▊    | 3279/5625 [02:52<01:58, 19.78it/s]
 58%|█████▊    | 3281/5625 [02:52<02:00, 19.42it/s]
 58%|█████▊    | 3283/5625 [02:52<02:03, 19.02it/s]
 58%|█████▊    | 3285/5625 [02:52<02:01, 19.26it/s]
 58%|█████▊    | 3287/5625 [02:52<02:01, 19.18it/s]
 58%|█████▊    | 3289/5625 [02:53<02:03, 18.93it/s]
 59%|█████▊    | 3292/5625 [02:53<01:59, 19.57it/s]
 59%|█████▊    | 3294/5625 [02:53<02:02, 19.07it/s]
 59%|█████▊    | 3296/5625 [02:53<02:01, 19.20it/s]
 59%|█████▊    | 3299/5625 [02:53<01:56, 19.99it/s]
 59%|█████▊    | 3301/5625 [02:53<02:00, 19.27it/s]
 59%|█████▊    | 3303/5625 [02:53<02:00, 19.26it/s]
 59%|█████▉    | 3306/5625 [02:53<01:58, 19.58it/s]
 59%|█████▉    | 3308/5625 [02:53<01:59, 19.39it/s]
 59%|█████▉    | 3310/5625 [02:54<02:03, 18.76it/s]
 59%|█████▉    | 3312/5625 [02:54<02:03, 18.77it/s]
 59%|█████▉    | 3314/5625 [02:54<02:01, 19.01it/s]
 59%|█████▉    | 3316/5625 [02:54<02:04, 18.60it/s]
 59%|█████▉    | 3319/5625 [02:54<02:00, 19.06it/s]
 59%|█████▉    | 3321/5625 [02:54<02:01, 18.96it/s]
 59%|█████▉    | 3323/5625 [02:54<02:03, 18.67it/s]
 59%|█████▉    | 3325/5625 [02:54<02:00, 19.02it/s]
 59%|█████▉    | 3328/5625 [02:55<01:57, 19.60it/s]
 59%|█████▉    | 3330/5625 [02:55<02:00, 19.07it/s]
 59%|█████▉    | 3333/5625 [02:55<01:56, 19.65it/s]
 59%|█████▉    | 3335/5625 [02:55<01:57, 19.56it/s]
 59%|█████▉    | 3338/5625 [02:55<01:52, 20.25it/s]
 59%|█████▉    | 3341/5625 [02:55<01:54, 19.97it/s]
 59%|█████▉    | 3344/5625 [02:55<01:53, 20.14it/s]
 60%|█████▉    | 3347/5625 [02:55<01:53, 20.09it/s]
 60%|█████▉    | 3350/5625 [02:56<01:52, 20.14it/s]
 60%|█████▉    | 3353/5625 [02:56<01:55, 19.74it/s]
 60%|█████▉    | 3355/5625 [02:56<01:56, 19.46it/s]
 60%|█████▉    | 3357/5625 [02:56<01:56, 19.52it/s]
 60%|█████▉    | 3359/5625 [02:56<01:58, 19.05it/s]
 60%|█████▉    | 3362/5625 [02:56<01:56, 19.40it/s]
 60%|█████▉    | 3364/5625 [02:56<01:56, 19.47it/s]
 60%|█████▉    | 3366/5625 [02:56<01:57, 19.23it/s]
 60%|█████▉    | 3368/5625 [02:57<01:59, 18.95it/s]
 60%|█████▉    | 3370/5625 [02:57<01:57, 19.19it/s]
 60%|█████▉    | 3372/5625 [02:57<02:00, 18.66it/s]
 60%|██████    | 3375/5625 [02:57<01:55, 19.44it/s]
 60%|██████    | 3377/5625 [02:57<01:58, 18.89it/s]
 60%|██████    | 3380/5625 [02:57<01:55, 19.37it/s]
 60%|██████    | 3382/5625 [02:57<01:56, 19.24it/s]
 60%|██████    | 3385/5625 [02:57<01:51, 20.05it/s]
 60%|██████    | 3387/5625 [02:58<01:52, 19.88it/s]
 60%|██████    | 3389/5625 [02:58<01:53, 19.74it/s]
 60%|██████    | 3391/5625 [02:58<01:56, 19.20it/s]
 60%|██████    | 3393/5625 [02:58<01:58, 18.88it/s]
 60%|██████    | 3395/5625 [02:58<01:58, 18.89it/s]
 60%|██████    | 3397/5625 [02:58<01:57, 18.92it/s]
 60%|██████    | 3399/5625 [02:58<01:57, 18.87it/s]
 60%|██████    | 3402/5625 [02:58<01:56, 19.05it/s]
 61%|██████    | 3404/5625 [02:58<01:57, 18.83it/s]
 61%|██████    | 3406/5625 [02:59<02:00, 18.42it/s]
 61%|██████    | 3409/5625 [02:59<01:58, 18.67it/s]
 61%|██████    | 3411/5625 [02:59<01:58, 18.76it/s]
 61%|██████    | 3414/5625 [02:59<01:50, 19.93it/s]
 61%|██████    | 3416/5625 [02:59<01:52, 19.56it/s]
 61%|██████    | 3418/5625 [02:59<01:53, 19.47it/s]
 61%|██████    | 3420/5625 [02:59<01:54, 19.22it/s]
 61%|██████    | 3423/5625 [02:59<01:53, 19.46it/s]
 61%|██████    | 3426/5625 [03:00<01:50, 19.83it/s]
 61%|██████    | 3428/5625 [03:00<01:53, 19.37it/s]
 61%|██████    | 3431/5625 [03:00<01:51, 19.64it/s]
 61%|██████    | 3433/5625 [03:00<01:53, 19.27it/s]
 61%|██████    | 3436/5625 [03:00<01:51, 19.64it/s]
 61%|██████    | 3438/5625 [03:00<01:53, 19.21it/s]
 61%|██████    | 3440/5625 [03:00<01:56, 18.80it/s]
 61%|██████    | 3442/5625 [03:00<01:58, 18.39it/s]
 61%|██████    | 3444/5625 [03:01<01:59, 18.31it/s]
 61%|██████▏   | 3446/5625 [03:01<01:56, 18.70it/s]
 61%|██████▏   | 3449/5625 [03:01<01:50, 19.69it/s]
 61%|██████▏   | 3451/5625 [03:01<01:52, 19.34it/s]
 61%|██████▏   | 3453/5625 [03:01<01:54, 19.03it/s]
 61%|██████▏   | 3456/5625 [03:01<01:51, 19.50it/s]
 61%|██████▏   | 3459/5625 [03:01<01:48, 20.00it/s]
 62%|██████▏   | 3462/5625 [03:01<01:48, 20.01it/s]
 62%|██████▏   | 3464/5625 [03:02<01:50, 19.56it/s]
 62%|██████▏   | 3466/5625 [03:02<01:51, 19.34it/s]
 62%|██████▏   | 3469/5625 [03:02<01:50, 19.59it/s]
 62%|██████▏   | 3471/5625 [03:02<01:50, 19.57it/s]
 62%|██████▏   | 3473/5625 [03:02<01:49, 19.65it/s]
 62%|██████▏   | 3475/5625 [03:02<01:49, 19.69it/s]
 62%|██████▏   | 3477/5625 [03:02<01:51, 19.32it/s]
 62%|██████▏   | 3479/5625 [03:02<01:50, 19.38it/s]
 62%|██████▏   | 3481/5625 [03:02<01:50, 19.44it/s]
 62%|██████▏   | 3484/5625 [03:03<01:45, 20.37it/s]
 62%|██████▏   | 3487/5625 [03:03<01:49, 19.54it/s]
 62%|██████▏   | 3489/5625 [03:03<01:52, 18.97it/s]
 62%|██████▏   | 3492/5625 [03:03<01:49, 19.48it/s]
 62%|██████▏   | 3494/5625 [03:03<01:51, 19.09it/s]
 62%|██████▏   | 3496/5625 [03:03<01:53, 18.75it/s]
 62%|██████▏   | 3498/5625 [03:03<01:51, 19.02it/s]
 62%|██████▏   | 3501/5625 [03:03<01:47, 19.78it/s]
 62%|██████▏   | 3503/5625 [03:04<01:47, 19.66it/s]
 62%|██████▏   | 3506/5625 [03:04<01:44, 20.22it/s]
 62%|██████▏   | 3509/5625 [03:04<01:46, 19.78it/s]
 62%|██████▏   | 3511/5625 [03:04<01:50, 19.11it/s]
 62%|██████▏   | 3514/5625 [03:04<01:49, 19.24it/s]
 63%|██████▎   | 3516/5625 [03:04<01:53, 18.64it/s]
 63%|██████▎   | 3518/5625 [03:04<01:54, 18.46it/s]
 63%|██████▎   | 3521/5625 [03:05<01:49, 19.25it/s]
 63%|██████▎   | 3524/5625 [03:05<01:47, 19.55it/s]
 63%|██████▎   | 3527/5625 [03:05<01:44, 20.13it/s]
 63%|██████▎   | 3530/5625 [03:05<01:46, 19.67it/s]
 63%|██████▎   | 3532/5625 [03:05<01:48, 19.26it/s]
 63%|██████▎   | 3535/5625 [03:05<01:48, 19.28it/s]
 63%|██████▎   | 3537/5625 [03:05<01:50, 18.91it/s]
 63%|██████▎   | 3540/5625 [03:05<01:45, 19.73it/s]
 63%|██████▎   | 3542/5625 [03:06<01:46, 19.59it/s]
 63%|██████▎   | 3545/5625 [03:06<01:43, 20.05it/s]
 63%|██████▎   | 3547/5625 [03:06<01:44, 19.90it/s]
 63%|██████▎   | 3549/5625 [03:06<01:45, 19.67it/s]
 63%|██████▎   | 3551/5625 [03:06<01:48, 19.13it/s]
 63%|██████▎   | 3554/5625 [03:06<01:44, 19.79it/s]
 63%|██████▎   | 3556/5625 [03:06<01:47, 19.29it/s]
 63%|██████▎   | 3559/5625 [03:06<01:42, 20.10it/s]
 63%|██████▎   | 3562/5625 [03:07<01:41, 20.41it/s]
 63%|██████▎   | 3565/5625 [03:07<01:42, 20.07it/s]
 63%|██████▎   | 3567/5625 [03:07<01:44, 19.68it/s]
 63%|██████▎   | 3569/5625 [03:07<01:45, 19.46it/s]
 63%|██████▎   | 3571/5625 [03:07<01:46, 19.26it/s]
 64%|██████▎   | 3573/5625 [03:07<01:47, 19.16it/s]
 64%|██████▎   | 3575/5625 [03:07<01:48, 18.94it/s]
 64%|██████▎   | 3577/5625 [03:07<01:48, 18.87it/s]
 64%|██████▎   | 3579/5625 [03:07<01:50, 18.49it/s]
 64%|██████▎   | 3581/5625 [03:08<01:48, 18.89it/s]
 64%|██████▎   | 3583/5625 [03:08<01:48, 18.76it/s]
 64%|██████▍   | 3586/5625 [03:08<01:45, 19.29it/s]
 64%|██████▍   | 3588/5625 [03:08<01:44, 19.42it/s]
 64%|██████▍   | 3590/5625 [03:08<01:48, 18.79it/s]
 64%|██████▍   | 3592/5625 [03:08<01:49, 18.53it/s]
 64%|██████▍   | 3594/5625 [03:08<01:52, 18.06it/s]
 64%|██████▍   | 3596/5625 [03:08<01:51, 18.19it/s]
 64%|██████▍   | 3598/5625 [03:09<01:49, 18.50it/s]
 64%|██████▍   | 3600/5625 [03:09<01:50, 18.30it/s]
 64%|██████▍   | 3602/5625 [03:09<01:49, 18.48it/s]
 64%|██████▍   | 3604/5625 [03:09<01:48, 18.70it/s]
 64%|██████▍   | 3606/5625 [03:09<01:47, 18.72it/s]
 64%|██████▍   | 3608/5625 [03:09<01:46, 19.01it/s]
 64%|██████▍   | 3610/5625 [03:09<01:44, 19.28it/s]
 64%|██████▍   | 3613/5625 [03:09<01:42, 19.63it/s]
 64%|██████▍   | 3616/5625 [03:09<01:39, 20.13it/s]
 64%|██████▍   | 3619/5625 [03:10<01:41, 19.75it/s]
 64%|██████▍   | 3621/5625 [03:10<01:42, 19.64it/s]
 64%|██████▍   | 3623/5625 [03:10<01:44, 19.23it/s]
 64%|██████▍   | 3625/5625 [03:10<01:46, 18.84it/s]
 64%|██████▍   | 3628/5625 [03:10<01:42, 19.53it/s]
 65%|██████▍   | 3630/5625 [03:10<01:43, 19.33it/s]
 65%|██████▍   | 3632/5625 [03:10<01:46, 18.76it/s]
 65%|██████▍   | 3635/5625 [03:10<01:44, 18.98it/s]
 65%|██████▍   | 3638/5625 [03:11<01:39, 19.97it/s]
 65%|██████▍   | 3641/5625 [03:11<01:38, 20.18it/s]
 65%|██████▍   | 3644/5625 [03:11<01:40, 19.72it/s]
 65%|██████▍   | 3647/5625 [03:11<01:39, 19.85it/s]
 65%|██████▍   | 3649/5625 [03:11<01:40, 19.58it/s]
 65%|██████▍   | 3651/5625 [03:11<01:40, 19.57it/s]
 65%|██████▍   | 3653/5625 [03:11<01:43, 18.99it/s]
 65%|██████▍   | 3656/5625 [03:11<01:41, 19.34it/s]
 65%|██████▌   | 3658/5625 [03:12<01:43, 19.06it/s]
 65%|██████▌   | 3661/5625 [03:12<01:41, 19.30it/s]
 65%|██████▌   | 3663/5625 [03:12<01:40, 19.46it/s]
 65%|██████▌   | 3665/5625 [03:12<01:42, 19.05it/s]
 65%|██████▌   | 3667/5625 [03:12<01:41, 19.29it/s]
 65%|██████▌   | 3669/5625 [03:12<01:41, 19.19it/s]
 65%|██████▌   | 3671/5625 [03:12<01:44, 18.62it/s]
 65%|██████▌   | 3673/5625 [03:12<01:43, 18.93it/s]
 65%|██████▌   | 3675/5625 [03:12<01:42, 19.01it/s]
 65%|██████▌   | 3677/5625 [03:13<01:41, 19.11it/s]
 65%|██████▌   | 3680/5625 [03:13<01:41, 19.25it/s]
 65%|██████▌   | 3682/5625 [03:13<01:41, 19.17it/s]
 66%|██████▌   | 3685/5625 [03:13<01:41, 19.11it/s]
 66%|██████▌   | 3687/5625 [03:13<01:41, 19.05it/s]
 66%|██████▌   | 3690/5625 [03:13<01:40, 19.17it/s]
 66%|██████▌   | 3692/5625 [03:13<01:40, 19.17it/s]
 66%|██████▌   | 3694/5625 [03:13<01:41, 18.98it/s]
 66%|██████▌   | 3696/5625 [03:14<01:43, 18.55it/s]
 66%|██████▌   | 3698/5625 [03:14<01:43, 18.54it/s]
 66%|██████▌   | 3700/5625 [03:14<01:44, 18.47it/s]
 66%|██████▌   | 3702/5625 [03:14<01:44, 18.44it/s]
 66%|██████▌   | 3704/5625 [03:14<01:42, 18.80it/s]
 66%|██████▌   | 3706/5625 [03:14<01:40, 19.00it/s]
 66%|██████▌   | 3708/5625 [03:14<01:41, 18.80it/s]
 66%|██████▌   | 3710/5625 [03:14<01:40, 19.06it/s]
 66%|██████▌   | 3713/5625 [03:15<01:39, 19.22it/s]
 66%|██████▌   | 3715/5625 [03:15<01:41, 18.76it/s]
 66%|██████▌   | 3717/5625 [03:15<01:40, 19.05it/s]
 66%|██████▌   | 3719/5625 [03:15<01:42, 18.62it/s]
 66%|██████▌   | 3721/5625 [03:15<01:43, 18.43it/s]
 66%|██████▌   | 3724/5625 [03:15<01:35, 19.91it/s]
 66%|██████▌   | 3726/5625 [03:15<01:36, 19.76it/s]
 66%|██████▋   | 3728/5625 [03:15<01:38, 19.34it/s]
 66%|██████▋   | 3731/5625 [03:15<01:37, 19.52it/s]
 66%|██████▋   | 3734/5625 [03:16<01:36, 19.65it/s]
 66%|██████▋   | 3736/5625 [03:16<01:36, 19.66it/s]
 66%|██████▋   | 3738/5625 [03:16<01:37, 19.31it/s]
 66%|██████▋   | 3740/5625 [03:16<01:37, 19.28it/s]
 67%|██████▋   | 3743/5625 [03:16<01:36, 19.57it/s]
 67%|██████▋   | 3745/5625 [03:16<01:37, 19.33it/s]
 67%|██████▋   | 3747/5625 [03:16<01:37, 19.36it/s]
 67%|██████▋   | 3749/5625 [03:16<01:39, 18.89it/s]
                                                   

 67%|██████▋   | 3750/5625 [03:16<01:39, 18.89it/s]{'eval_loss': 0.7023520469665527, 'eval_accuracy': 0.6936, 'eval_f1': 0.6942449512298212, 'eval_runtime': 1.7312, 'eval_samples_per_second': 1444.127, 'eval_steps_per_second': 180.805, 'epoch': 1.0}
{'loss': 0.518, 'learning_rate': 1.7581323506173327e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.69it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.28it/s]

 21%|██        | 66/313 [00:00<00:01, 205.66it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.88it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.05it/s]

 40%|████      | 126/313 [00:00<00:01, 184.82it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.65it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.65it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.78it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.79it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 166.88it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.60it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.35it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.29it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.41it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.41it/s]
 67%|██████▋   | 3750/5625 [03:18<01:39, 18.89it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 3751/5625 [03:19<13:32,  2.31it/s]
 67%|██████▋   | 3753/5625 [03:19<10:05,  3.09it/s]
 67%|██████▋   | 3755/5625 [03:19<07:37,  4.09it/s]
 67%|██████▋   | 3757/5625 [03:19<05:52,  5.30it/s]
 67%|██████▋   | 3760/5625 [03:20<04:08,  7.50it/s]
 67%|██████▋   | 3762/5625 [03:20<03:28,  8.94it/s]
 67%|██████▋   | 3764/5625 [03:20<02:57, 10.48it/s]
 67%|██████▋   | 3766/5625 [03:20<02:35, 11.98it/s]
 67%|██████▋   | 3769/5625 [03:20<02:10, 14.19it/s]
 67%|██████▋   | 3771/5625 [03:20<02:01, 15.23it/s]
 67%|██████▋   | 3774/5625 [03:20<01:51, 16.60it/s]
 67%|██████▋   | 3776/5625 [03:20<01:47, 17.17it/s]
 67%|██████▋   | 3778/5625 [03:21<01:43, 17.77it/s]
 67%|██████▋   | 3781/5625 [03:21<01:39, 18.60it/s]
 67%|██████▋   | 3784/5625 [03:21<01:36, 19.08it/s]
 67%|██████▋   | 3786/5625 [03:21<01:36, 18.96it/s]
 67%|██████▋   | 3788/5625 [03:21<01:38, 18.62it/s]
 67%|██████▋   | 3790/5625 [03:21<01:38, 18.59it/s]
 67%|██████▋   | 3792/5625 [03:21<01:37, 18.75it/s]
 67%|██████▋   | 3795/5625 [03:21<01:32, 19.73it/s]
 68%|██████▊   | 3797/5625 [03:22<01:35, 19.09it/s]
 68%|██████▊   | 3800/5625 [03:22<01:34, 19.25it/s]
 68%|██████▊   | 3802/5625 [03:22<01:34, 19.30it/s]
 68%|██████▊   | 3804/5625 [03:22<01:35, 19.10it/s]
 68%|██████▊   | 3807/5625 [03:22<01:33, 19.47it/s]
 68%|██████▊   | 3809/5625 [03:22<01:34, 19.21it/s]
 68%|██████▊   | 3811/5625 [03:22<01:36, 18.76it/s]
 68%|██████▊   | 3813/5625 [03:22<01:35, 18.94it/s]
 68%|██████▊   | 3816/5625 [03:23<01:32, 19.46it/s]
 68%|██████▊   | 3818/5625 [03:23<01:33, 19.23it/s]
 68%|██████▊   | 3820/5625 [03:23<01:32, 19.41it/s]
 68%|██████▊   | 3822/5625 [03:23<01:33, 19.38it/s]
 68%|██████▊   | 3824/5625 [03:23<01:35, 18.91it/s]
 68%|██████▊   | 3827/5625 [03:23<01:34, 19.05it/s]
 68%|██████▊   | 3830/5625 [03:23<01:33, 19.27it/s]
 68%|██████▊   | 3832/5625 [03:23<01:33, 19.19it/s]
 68%|██████▊   | 3835/5625 [03:23<01:33, 19.24it/s]
 68%|██████▊   | 3837/5625 [03:24<01:32, 19.39it/s]
 68%|██████▊   | 3840/5625 [03:24<01:30, 19.65it/s]
 68%|██████▊   | 3842/5625 [03:24<01:32, 19.20it/s]
 68%|██████▊   | 3844/5625 [03:24<01:32, 19.18it/s]
 68%|██████▊   | 3846/5625 [03:24<01:33, 19.08it/s]
 68%|██████▊   | 3848/5625 [03:24<01:35, 18.64it/s]
 68%|██████▊   | 3851/5625 [03:24<01:31, 19.33it/s]
 69%|██████▊   | 3854/5625 [03:24<01:28, 20.02it/s]
 69%|██████▊   | 3856/5625 [03:25<01:29, 19.81it/s]
 69%|██████▊   | 3858/5625 [03:25<01:32, 19.17it/s]
 69%|██████▊   | 3860/5625 [03:25<01:34, 18.74it/s]
 69%|██████▊   | 3863/5625 [03:25<01:30, 19.56it/s]
 69%|██████▊   | 3866/5625 [03:25<01:27, 20.03it/s]
 69%|██████▉   | 3869/5625 [03:25<01:27, 20.12it/s]
 69%|██████▉   | 3872/5625 [03:25<01:29, 19.54it/s]
 69%|██████▉   | 3874/5625 [03:25<01:29, 19.57it/s]
 69%|██████▉   | 3876/5625 [03:26<01:30, 19.26it/s]
 69%|██████▉   | 3878/5625 [03:26<01:31, 19.18it/s]
 69%|██████▉   | 3880/5625 [03:26<01:30, 19.28it/s]
 69%|██████▉   | 3882/5625 [03:26<01:29, 19.45it/s]
 69%|██████▉   | 3885/5625 [03:26<01:28, 19.56it/s]
 69%|██████▉   | 3888/5625 [03:26<01:26, 20.05it/s]
 69%|██████▉   | 3890/5625 [03:26<01:26, 20.02it/s]
 69%|██████▉   | 3893/5625 [03:26<01:26, 19.94it/s]
 69%|██████▉   | 3895/5625 [03:27<01:27, 19.66it/s]
 69%|██████▉   | 3897/5625 [03:27<01:27, 19.67it/s]
 69%|██████▉   | 3899/5625 [03:27<01:29, 19.22it/s]
 69%|██████▉   | 3901/5625 [03:27<01:29, 19.25it/s]
 69%|██████▉   | 3903/5625 [03:27<01:30, 19.02it/s]
 69%|██████▉   | 3905/5625 [03:27<01:29, 19.20it/s]
 69%|██████▉   | 3907/5625 [03:27<01:31, 18.72it/s]
 70%|██████▉   | 3910/5625 [03:27<01:27, 19.63it/s]
 70%|██████▉   | 3912/5625 [03:27<01:29, 19.13it/s]
 70%|██████▉   | 3915/5625 [03:28<01:27, 19.48it/s]
 70%|██████▉   | 3918/5625 [03:28<01:25, 20.06it/s]
 70%|██████▉   | 3921/5625 [03:28<01:25, 19.91it/s]
 70%|██████▉   | 3923/5625 [03:28<01:28, 19.20it/s]
 70%|██████▉   | 3926/5625 [03:28<01:24, 20.04it/s]
 70%|██████▉   | 3928/5625 [03:28<01:26, 19.51it/s]
 70%|██████▉   | 3931/5625 [03:28<01:24, 20.15it/s]
 70%|██████▉   | 3933/5625 [03:29<01:24, 19.99it/s]
 70%|██████▉   | 3936/5625 [03:29<01:25, 19.81it/s]
 70%|███████   | 3938/5625 [03:29<01:28, 19.14it/s]
 70%|███████   | 3941/5625 [03:29<01:26, 19.43it/s]
 70%|███████   | 3943/5625 [03:29<01:25, 19.56it/s]
 70%|███████   | 3946/5625 [03:29<01:25, 19.67it/s]
 70%|███████   | 3948/5625 [03:29<01:26, 19.44it/s]
 70%|███████   | 3950/5625 [03:29<01:26, 19.34it/s]
 70%|███████   | 3952/5625 [03:30<01:28, 18.80it/s]
 70%|███████   | 3955/5625 [03:30<01:23, 20.12it/s]
 70%|███████   | 3957/5625 [03:30<01:23, 19.92it/s]
 70%|███████   | 3960/5625 [03:30<01:19, 21.06it/s]
 70%|███████   | 3963/5625 [03:30<01:21, 20.35it/s]
 71%|███████   | 3966/5625 [03:30<01:24, 19.55it/s]
 71%|███████   | 3968/5625 [03:30<01:26, 19.18it/s]
 71%|███████   | 3970/5625 [03:30<01:26, 19.15it/s]
 71%|███████   | 3973/5625 [03:31<01:23, 19.74it/s]
 71%|███████   | 3976/5625 [03:31<01:22, 19.87it/s]
 71%|███████   | 3978/5625 [03:31<01:24, 19.50it/s]
 71%|███████   | 3980/5625 [03:31<01:24, 19.46it/s]
 71%|███████   | 3982/5625 [03:31<01:24, 19.54it/s]
 71%|███████   | 3985/5625 [03:31<01:22, 19.82it/s]
 71%|███████   | 3987/5625 [03:31<01:22, 19.84it/s]
 71%|███████   | 3989/5625 [03:31<01:24, 19.47it/s]
 71%|███████   | 3991/5625 [03:31<01:25, 19.04it/s]
 71%|███████   | 3994/5625 [03:32<01:24, 19.31it/s]
 71%|███████   | 3997/5625 [03:32<01:23, 19.51it/s]
 71%|███████   | 3999/5625 [03:32<01:24, 19.35it/s]
 71%|███████   | 4001/5625 [03:32<01:23, 19.41it/s]
 71%|███████   | 4004/5625 [03:32<01:19, 20.33it/s]
 71%|███████   | 4007/5625 [03:32<01:21, 19.96it/s]
 71%|███████▏  | 4010/5625 [03:32<01:20, 20.15it/s]
 71%|███████▏  | 4013/5625 [03:33<01:21, 19.77it/s]
 71%|███████▏  | 4015/5625 [03:33<01:23, 19.24it/s]
 71%|███████▏  | 4017/5625 [03:33<01:33, 17.28it/s]
 71%|███████▏  | 4020/5625 [03:33<01:28, 18.18it/s]
 72%|███████▏  | 4022/5625 [03:33<01:28, 18.18it/s]
 72%|███████▏  | 4024/5625 [03:33<01:27, 18.27it/s]
 72%|███████▏  | 4027/5625 [03:33<01:24, 18.83it/s]
 72%|███████▏  | 4029/5625 [03:33<01:23, 19.11it/s]
 72%|███████▏  | 4031/5625 [03:34<01:24, 18.96it/s]
 72%|███████▏  | 4034/5625 [03:34<01:19, 20.11it/s]
 72%|███████▏  | 4037/5625 [03:34<01:22, 19.35it/s]
 72%|███████▏  | 4040/5625 [03:34<01:18, 20.11it/s]
 72%|███████▏  | 4043/5625 [03:34<01:21, 19.47it/s]
 72%|███████▏  | 4045/5625 [03:34<01:20, 19.51it/s]
 72%|███████▏  | 4047/5625 [03:34<01:21, 19.45it/s]
 72%|███████▏  | 4050/5625 [03:35<01:20, 19.64it/s]
 72%|███████▏  | 4052/5625 [03:35<01:22, 19.09it/s]
 72%|███████▏  | 4054/5625 [03:35<01:22, 19.06it/s]
 72%|███████▏  | 4056/5625 [03:35<01:22, 18.91it/s]
 72%|███████▏  | 4059/5625 [03:35<01:21, 19.18it/s]
 72%|███████▏  | 4061/5625 [03:35<01:21, 19.13it/s]
 72%|███████▏  | 4063/5625 [03:35<01:23, 18.75it/s]
 72%|███████▏  | 4066/5625 [03:35<01:18, 19.80it/s]
 72%|███████▏  | 4068/5625 [03:35<01:19, 19.56it/s]
 72%|███████▏  | 4070/5625 [03:36<01:19, 19.48it/s]
 72%|███████▏  | 4073/5625 [03:36<01:16, 20.41it/s]
 72%|███████▏  | 4076/5625 [03:36<01:14, 20.80it/s]
 73%|███████▎  | 4079/5625 [03:36<01:16, 20.13it/s]
 73%|███████▎  | 4082/5625 [03:36<01:19, 19.34it/s]
 73%|███████▎  | 4085/5625 [03:36<01:16, 20.10it/s]
 73%|███████▎  | 4088/5625 [03:36<01:18, 19.68it/s]
 73%|███████▎  | 4090/5625 [03:37<01:19, 19.27it/s]
 73%|███████▎  | 4092/5625 [03:37<01:21, 18.89it/s]
 73%|███████▎  | 4094/5625 [03:37<01:21, 18.85it/s]
 73%|███████▎  | 4097/5625 [03:37<01:16, 19.93it/s]
 73%|███████▎  | 4099/5625 [03:37<01:19, 19.31it/s]
 73%|███████▎  | 4101/5625 [03:37<01:19, 19.21it/s]
 73%|███████▎  | 4103/5625 [03:37<01:21, 18.75it/s]
 73%|███████▎  | 4106/5625 [03:37<01:15, 20.16it/s]
 73%|███████▎  | 4108/5625 [03:37<01:15, 20.11it/s]
 73%|███████▎  | 4110/5625 [03:38<01:15, 20.07it/s]
 73%|███████▎  | 4113/5625 [03:38<01:16, 19.79it/s]
 73%|███████▎  | 4115/5625 [03:38<01:17, 19.42it/s]
 73%|███████▎  | 4118/5625 [03:38<01:16, 19.72it/s]
 73%|███████▎  | 4120/5625 [03:38<01:18, 19.20it/s]
 73%|███████▎  | 4122/5625 [03:38<01:19, 19.01it/s]
 73%|███████▎  | 4124/5625 [03:38<01:18, 19.23it/s]
 73%|███████▎  | 4126/5625 [03:38<01:18, 19.17it/s]
 73%|███████▎  | 4128/5625 [03:39<01:19, 18.84it/s]
 73%|███████▎  | 4130/5625 [03:39<01:18, 19.11it/s]
 73%|███████▎  | 4132/5625 [03:39<01:19, 18.89it/s]
 73%|███████▎  | 4134/5625 [03:39<01:19, 18.69it/s]
 74%|███████▎  | 4136/5625 [03:39<01:20, 18.41it/s]
 74%|███████▎  | 4138/5625 [03:39<01:21, 18.36it/s]
 74%|███████▎  | 4141/5625 [03:39<01:18, 18.88it/s]
 74%|███████▎  | 4143/5625 [03:39<01:19, 18.74it/s]
 74%|███████▎  | 4145/5625 [03:39<01:19, 18.57it/s]
 74%|███████▎  | 4147/5625 [03:40<01:18, 18.94it/s]
 74%|███████▍  | 4149/5625 [03:40<01:18, 18.89it/s]
 74%|███████▍  | 4151/5625 [03:40<01:17, 18.93it/s]
 74%|███████▍  | 4153/5625 [03:40<01:19, 18.57it/s]
 74%|███████▍  | 4155/5625 [03:40<01:17, 18.89it/s]
 74%|███████▍  | 4158/5625 [03:40<01:15, 19.44it/s]
 74%|███████▍  | 4161/5625 [03:40<01:15, 19.47it/s]
 74%|███████▍  | 4164/5625 [03:40<01:14, 19.58it/s]
 74%|███████▍  | 4167/5625 [03:41<01:11, 20.48it/s]
 74%|███████▍  | 4170/5625 [03:41<01:12, 19.94it/s]
 74%|███████▍  | 4172/5625 [03:41<01:14, 19.42it/s]
 74%|███████▍  | 4174/5625 [03:41<01:14, 19.49it/s]
 74%|███████▍  | 4176/5625 [03:41<01:14, 19.34it/s]
 74%|███████▍  | 4179/5625 [03:41<01:14, 19.36it/s]
 74%|███████▍  | 4181/5625 [03:41<01:14, 19.36it/s]
 74%|███████▍  | 4184/5625 [03:41<01:14, 19.39it/s]
 74%|███████▍  | 4186/5625 [03:42<01:15, 19.05it/s]
 74%|███████▍  | 4188/5625 [03:42<01:15, 18.94it/s]
 75%|███████▍  | 4191/5625 [03:42<01:13, 19.45it/s]
 75%|███████▍  | 4193/5625 [03:42<01:14, 19.24it/s]
 75%|███████▍  | 4196/5625 [03:42<01:14, 19.13it/s]
 75%|███████▍  | 4199/5625 [03:42<01:12, 19.71it/s]
 75%|███████▍  | 4201/5625 [03:42<01:13, 19.35it/s]
 75%|███████▍  | 4203/5625 [03:42<01:14, 19.00it/s]
 75%|███████▍  | 4205/5625 [03:43<01:15, 18.93it/s]
 75%|███████▍  | 4207/5625 [03:43<01:15, 18.85it/s]
 75%|███████▍  | 4209/5625 [03:43<01:16, 18.54it/s]
 75%|███████▍  | 4211/5625 [03:43<01:15, 18.83it/s]
 75%|███████▍  | 4213/5625 [03:43<01:21, 17.43it/s]
 75%|███████▍  | 4215/5625 [03:43<01:20, 17.58it/s]
 75%|███████▍  | 4217/5625 [03:43<01:19, 17.61it/s]
 75%|███████▌  | 4220/5625 [03:43<01:15, 18.62it/s]
 75%|███████▌  | 4223/5625 [03:44<01:11, 19.69it/s]
 75%|███████▌  | 4226/5625 [03:44<01:09, 20.17it/s]
 75%|███████▌  | 4229/5625 [03:44<01:09, 20.00it/s]
 75%|███████▌  | 4231/5625 [03:44<01:11, 19.44it/s]
 75%|███████▌  | 4234/5625 [03:44<01:08, 20.29it/s]
 75%|███████▌  | 4237/5625 [03:44<01:11, 19.42it/s]
 75%|███████▌  | 4239/5625 [03:44<01:11, 19.34it/s]
 75%|███████▌  | 4242/5625 [03:44<01:09, 19.88it/s]
 75%|███████▌  | 4244/5625 [03:45<01:09, 19.75it/s]
 75%|███████▌  | 4246/5625 [03:45<01:11, 19.21it/s]
 76%|███████▌  | 4249/5625 [03:45<01:08, 20.15it/s]
 76%|███████▌  | 4252/5625 [03:45<01:10, 19.55it/s]
 76%|███████▌  | 4254/5625 [03:45<01:11, 19.05it/s]
 76%|███████▌  | 4256/5625 [03:45<01:11, 19.19it/s]
 76%|███████▌  | 4258/5625 [03:45<01:13, 18.69it/s]
 76%|███████▌  | 4260/5625 [03:45<01:12, 18.80it/s]
 76%|███████▌  | 4262/5625 [03:46<01:12, 18.89it/s]
 76%|███████▌  | 4264/5625 [03:46<01:12, 18.64it/s]
 76%|███████▌  | 4266/5625 [03:46<01:13, 18.52it/s]
 76%|███████▌  | 4268/5625 [03:46<01:12, 18.60it/s]
 76%|███████▌  | 4271/5625 [03:46<01:11, 19.00it/s]
 76%|███████▌  | 4273/5625 [03:46<01:10, 19.23it/s]
 76%|███████▌  | 4275/5625 [03:46<01:10, 19.27it/s]
 76%|███████▌  | 4277/5625 [03:46<01:11, 18.73it/s]
 76%|███████▌  | 4279/5625 [03:46<01:11, 18.73it/s]
 76%|███████▌  | 4281/5625 [03:47<01:12, 18.45it/s]
 76%|███████▌  | 4283/5625 [03:47<01:12, 18.59it/s]
 76%|███████▌  | 4286/5625 [03:47<01:10, 19.09it/s]
 76%|███████▌  | 4289/5625 [03:47<01:07, 19.68it/s]
 76%|███████▋  | 4291/5625 [03:47<01:09, 19.20it/s]
 76%|███████▋  | 4293/5625 [03:47<01:11, 18.67it/s]
 76%|███████▋  | 4295/5625 [03:47<01:11, 18.63it/s]
 76%|███████▋  | 4297/5625 [03:47<01:11, 18.62it/s]
 76%|███████▋  | 4300/5625 [03:48<01:09, 19.05it/s]
 76%|███████▋  | 4302/5625 [03:48<01:11, 18.60it/s]
 77%|███████▋  | 4305/5625 [03:48<01:08, 19.38it/s]
 77%|███████▋  | 4307/5625 [03:48<01:09, 18.97it/s]
 77%|███████▋  | 4309/5625 [03:48<01:35, 13.84it/s]
 77%|███████▋  | 4311/5625 [03:48<01:28, 14.85it/s]
 77%|███████▋  | 4313/5625 [03:48<01:22, 15.90it/s]
 77%|███████▋  | 4315/5625 [03:48<01:19, 16.55it/s]
 77%|███████▋  | 4317/5625 [03:49<01:16, 17.09it/s]
 77%|███████▋  | 4319/5625 [03:49<01:15, 17.31it/s]
 77%|███████▋  | 4322/5625 [03:49<01:11, 18.14it/s]
 77%|███████▋  | 4325/5625 [03:49<01:07, 19.26it/s]
 77%|███████▋  | 4327/5625 [03:49<01:07, 19.36it/s]
 77%|███████▋  | 4329/5625 [03:49<01:08, 18.89it/s]
 77%|███████▋  | 4332/5625 [03:49<01:07, 19.11it/s]
 77%|███████▋  | 4335/5625 [03:50<01:06, 19.45it/s]
 77%|███████▋  | 4337/5625 [03:50<01:07, 19.21it/s]
 77%|███████▋  | 4339/5625 [03:50<01:08, 18.86it/s]
 77%|███████▋  | 4342/5625 [03:50<01:05, 19.65it/s]
 77%|███████▋  | 4344/5625 [03:50<01:05, 19.57it/s]
 77%|███████▋  | 4347/5625 [03:50<01:04, 19.75it/s]
 77%|███████▋  | 4349/5625 [03:50<01:05, 19.37it/s]
 77%|███████▋  | 4351/5625 [03:50<01:07, 18.83it/s]
 77%|███████▋  | 4353/5625 [03:50<01:08, 18.47it/s]
 77%|███████▋  | 4356/5625 [03:51<01:05, 19.49it/s]
 77%|███████▋  | 4358/5625 [03:51<01:04, 19.56it/s]
 78%|███████▊  | 4360/5625 [03:51<01:04, 19.54it/s]
 78%|███████▊  | 4363/5625 [03:51<01:03, 19.95it/s]
 78%|███████▊  | 4365/5625 [03:51<01:04, 19.42it/s]
 78%|███████▊  | 4368/5625 [03:51<01:04, 19.53it/s]
 78%|███████▊  | 4371/5625 [03:51<01:04, 19.38it/s]
 78%|███████▊  | 4373/5625 [03:51<01:04, 19.27it/s]
 78%|███████▊  | 4375/5625 [03:52<01:06, 18.82it/s]
 78%|███████▊  | 4377/5625 [03:52<01:05, 19.11it/s]
 78%|███████▊  | 4379/5625 [03:52<01:06, 18.83it/s]
 78%|███████▊  | 4381/5625 [03:52<01:05, 19.05it/s]
 78%|███████▊  | 4383/5625 [03:52<01:05, 18.95it/s]
 78%|███████▊  | 4386/5625 [03:52<01:02, 19.88it/s]
 78%|███████▊  | 4389/5625 [03:52<01:02, 19.73it/s]
 78%|███████▊  | 4391/5625 [03:52<01:02, 19.78it/s]
 78%|███████▊  | 4394/5625 [03:53<01:02, 19.59it/s]
 78%|███████▊  | 4397/5625 [03:53<01:02, 19.60it/s]
 78%|███████▊  | 4399/5625 [03:53<01:03, 19.41it/s]
 78%|███████▊  | 4401/5625 [03:53<01:03, 19.17it/s]
 78%|███████▊  | 4403/5625 [03:53<01:03, 19.34it/s]
 78%|███████▊  | 4405/5625 [03:53<01:04, 18.87it/s]
 78%|███████▊  | 4407/5625 [03:53<01:04, 18.84it/s]
 78%|███████▊  | 4409/5625 [03:53<01:03, 19.06it/s]
 78%|███████▊  | 4411/5625 [03:53<01:03, 19.21it/s]
 78%|███████▊  | 4413/5625 [03:54<01:02, 19.40it/s]
 79%|███████▊  | 4416/5625 [03:54<01:01, 19.53it/s]
 79%|███████▊  | 4419/5625 [03:54<01:01, 19.46it/s]
 79%|███████▊  | 4421/5625 [03:54<01:04, 18.79it/s]
 79%|███████▊  | 4424/5625 [03:54<01:03, 19.04it/s]
 79%|███████▊  | 4426/5625 [03:54<01:04, 18.62it/s]
 79%|███████▊  | 4429/5625 [03:54<01:02, 19.18it/s]
 79%|███████▉  | 4431/5625 [03:55<01:03, 18.91it/s]
 79%|███████▉  | 4433/5625 [03:55<01:02, 18.94it/s]
 79%|███████▉  | 4436/5625 [03:55<01:00, 19.70it/s]
 79%|███████▉  | 4439/5625 [03:55<00:59, 19.78it/s]
 79%|███████▉  | 4441/5625 [03:55<00:59, 19.74it/s]
 79%|███████▉  | 4443/5625 [03:55<00:59, 19.74it/s]
 79%|███████▉  | 4445/5625 [03:55<01:01, 19.23it/s]
 79%|███████▉  | 4447/5625 [03:55<01:02, 18.96it/s]
 79%|███████▉  | 4449/5625 [03:55<01:02, 18.87it/s]
 79%|███████▉  | 4452/5625 [03:56<01:00, 19.23it/s]
 79%|███████▉  | 4454/5625 [03:56<01:01, 19.14it/s]
 79%|███████▉  | 4456/5625 [03:56<01:00, 19.32it/s]
 79%|███████▉  | 4459/5625 [03:56<00:59, 19.64it/s]
 79%|███████▉  | 4462/5625 [03:56<00:58, 19.74it/s]
 79%|███████▉  | 4464/5625 [03:56<00:58, 19.76it/s]
 79%|███████▉  | 4466/5625 [03:56<00:58, 19.79it/s]
 79%|███████▉  | 4468/5625 [03:56<00:58, 19.80it/s]
 79%|███████▉  | 4470/5625 [03:57<00:59, 19.25it/s]
 80%|███████▉  | 4472/5625 [03:57<00:59, 19.36it/s]
 80%|███████▉  | 4474/5625 [03:57<01:01, 18.87it/s]
 80%|███████▉  | 4476/5625 [03:57<01:00, 18.94it/s]
 80%|███████▉  | 4478/5625 [03:57<01:01, 18.70it/s]
 80%|███████▉  | 4481/5625 [03:57<00:59, 19.14it/s]
 80%|███████▉  | 4484/5625 [03:57<00:55, 20.47it/s]
 80%|███████▉  | 4487/5625 [03:57<00:56, 20.09it/s]
 80%|███████▉  | 4490/5625 [03:58<00:57, 19.68it/s]
 80%|███████▉  | 4492/5625 [03:58<00:57, 19.74it/s]
 80%|███████▉  | 4494/5625 [03:58<00:57, 19.51it/s]
 80%|███████▉  | 4497/5625 [03:58<00:55, 20.24it/s]
 80%|████████  | 4500/5625 [03:58<00:54, 20.46it/s]
 80%|████████  | 4503/5625 [03:58<00:53, 21.17it/s]
 80%|████████  | 4506/5625 [03:58<00:53, 20.84it/s]
 80%|████████  | 4509/5625 [03:58<00:54, 20.53it/s]
 80%|████████  | 4512/5625 [03:59<00:55, 20.07it/s]
 80%|████████  | 4515/5625 [03:59<00:57, 19.30it/s]
 80%|████████  | 4518/5625 [03:59<00:57, 19.36it/s]
 80%|████████  | 4521/5625 [03:59<00:54, 20.27it/s]
 80%|████████  | 4524/5625 [03:59<00:55, 19.89it/s]
 80%|████████  | 4527/5625 [03:59<00:53, 20.48it/s]
 81%|████████  | 4530/5625 [04:00<00:55, 19.72it/s]
 81%|████████  | 4533/5625 [04:00<00:55, 19.75it/s]
 81%|████████  | 4535/5625 [04:00<00:55, 19.70it/s]
 81%|████████  | 4537/5625 [04:00<00:55, 19.55it/s]
 81%|████████  | 4539/5625 [04:00<00:56, 19.34it/s]
 81%|████████  | 4542/5625 [04:00<00:54, 19.72it/s]
 81%|████████  | 4544/5625 [04:00<00:54, 19.67it/s]
 81%|████████  | 4546/5625 [04:00<00:55, 19.41it/s]
 81%|████████  | 4548/5625 [04:00<00:55, 19.49it/s]
 81%|████████  | 4551/5625 [04:01<00:52, 20.33it/s]
 81%|████████  | 4554/5625 [04:01<00:50, 21.08it/s]
 81%|████████  | 4557/5625 [04:01<00:50, 21.16it/s]
 81%|████████  | 4560/5625 [04:01<00:52, 20.26it/s]
 81%|████████  | 4563/5625 [04:01<00:53, 19.71it/s]
 81%|████████  | 4566/5625 [04:01<00:53, 19.63it/s]
 81%|████████  | 4568/5625 [04:01<00:54, 19.23it/s]
 81%|████████  | 4570/5625 [04:02<00:54, 19.27it/s]
 81%|████████▏ | 4572/5625 [04:02<00:56, 18.80it/s]
 81%|████████▏ | 4575/5625 [04:02<00:54, 19.11it/s]
 81%|████████▏ | 4577/5625 [04:02<00:54, 19.30it/s]
 81%|████████▏ | 4579/5625 [04:02<00:54, 19.19it/s]
 81%|████████▏ | 4581/5625 [04:02<00:54, 19.14it/s]
 81%|████████▏ | 4583/5625 [04:02<00:54, 19.09it/s]
 82%|████████▏ | 4585/5625 [04:02<00:53, 19.33it/s]
 82%|████████▏ | 4587/5625 [04:02<00:54, 19.08it/s]
 82%|████████▏ | 4589/5625 [04:03<00:55, 18.77it/s]
 82%|████████▏ | 4592/5625 [04:03<00:53, 19.31it/s]
 82%|████████▏ | 4594/5625 [04:03<00:54, 19.05it/s]
 82%|████████▏ | 4597/5625 [04:03<00:52, 19.52it/s]
 82%|████████▏ | 4599/5625 [04:03<00:52, 19.61it/s]
 82%|████████▏ | 4601/5625 [04:03<00:52, 19.64it/s]
 82%|████████▏ | 4603/5625 [04:03<00:52, 19.32it/s]
 82%|████████▏ | 4605/5625 [04:03<00:52, 19.28it/s]
 82%|████████▏ | 4607/5625 [04:03<00:53, 18.86it/s]
 82%|████████▏ | 4609/5625 [04:04<00:54, 18.61it/s]
 82%|████████▏ | 4611/5625 [04:04<00:55, 18.20it/s]
 82%|████████▏ | 4613/5625 [04:04<00:54, 18.62it/s]
 82%|████████▏ | 4615/5625 [04:04<00:53, 18.91it/s]
 82%|████████▏ | 4617/5625 [04:04<00:53, 18.89it/s]
 82%|████████▏ | 4619/5625 [04:04<00:52, 19.18it/s]
 82%|████████▏ | 4621/5625 [04:04<00:52, 19.22it/s]
 82%|████████▏ | 4623/5625 [04:04<00:53, 18.74it/s]
 82%|████████▏ | 4625/5625 [04:04<00:53, 18.63it/s]
 82%|████████▏ | 4627/5625 [04:05<00:53, 18.62it/s]
 82%|████████▏ | 4629/5625 [04:05<00:53, 18.69it/s]
 82%|████████▏ | 4631/5625 [04:05<00:54, 18.40it/s]
 82%|████████▏ | 4634/5625 [04:05<00:50, 19.74it/s]
 82%|████████▏ | 4637/5625 [04:05<00:50, 19.60it/s]
 82%|████████▏ | 4639/5625 [04:05<00:50, 19.54it/s]
 83%|████████▎ | 4641/5625 [04:05<00:50, 19.55it/s]
 83%|████████▎ | 4643/5625 [04:05<00:51, 18.99it/s]
 83%|████████▎ | 4645/5625 [04:05<00:51, 19.05it/s]
 83%|████████▎ | 4647/5625 [04:06<00:51, 19.01it/s]
 83%|████████▎ | 4649/5625 [04:06<00:52, 18.71it/s]
 83%|████████▎ | 4651/5625 [04:06<00:52, 18.64it/s]
 83%|████████▎ | 4653/5625 [04:06<00:51, 19.01it/s]
 83%|████████▎ | 4655/5625 [04:06<00:51, 18.92it/s]
 83%|████████▎ | 4657/5625 [04:06<00:50, 19.20it/s]
 83%|████████▎ | 4659/5625 [04:06<00:51, 18.92it/s]
 83%|████████▎ | 4661/5625 [04:06<00:50, 18.96it/s]
 83%|████████▎ | 4663/5625 [04:06<00:52, 18.47it/s]
 83%|████████▎ | 4665/5625 [04:07<00:52, 18.33it/s]
 83%|████████▎ | 4667/5625 [04:07<00:51, 18.75it/s]
 83%|████████▎ | 4670/5625 [04:07<00:49, 19.35it/s]
 83%|████████▎ | 4672/5625 [04:07<00:50, 18.86it/s]
 83%|████████▎ | 4675/5625 [04:07<00:49, 19.31it/s]
 83%|████████▎ | 4677/5625 [04:07<00:50, 18.89it/s]
 83%|████████▎ | 4680/5625 [04:07<00:48, 19.55it/s]
 83%|████████▎ | 4682/5625 [04:07<00:48, 19.60it/s]
 83%|████████▎ | 4684/5625 [04:08<00:48, 19.51it/s]
 83%|████████▎ | 4686/5625 [04:08<00:48, 19.46it/s]
 83%|████████▎ | 4688/5625 [04:08<00:48, 19.38it/s]
 83%|████████▎ | 4691/5625 [04:08<00:47, 19.72it/s]
 83%|████████▎ | 4693/5625 [04:08<00:47, 19.63it/s]
 83%|████████▎ | 4695/5625 [04:08<00:47, 19.59it/s]
 84%|████████▎ | 4697/5625 [04:08<00:48, 19.21it/s]
 84%|████████▎ | 4699/5625 [04:08<00:47, 19.37it/s]
 84%|████████▎ | 4701/5625 [04:08<00:48, 19.03it/s]
 84%|████████▎ | 4703/5625 [04:09<00:49, 18.47it/s]
 84%|████████▎ | 4706/5625 [04:09<00:47, 19.15it/s]
 84%|████████▎ | 4709/5625 [04:09<00:47, 19.49it/s]
 84%|████████▍ | 4711/5625 [04:09<00:47, 19.15it/s]
 84%|████████▍ | 4713/5625 [04:09<00:47, 19.09it/s]
 84%|████████▍ | 4715/5625 [04:09<00:48, 18.58it/s]
 84%|████████▍ | 4717/5625 [04:09<00:49, 18.46it/s]
 84%|████████▍ | 4719/5625 [04:09<00:49, 18.41it/s]
 84%|████████▍ | 4722/5625 [04:10<00:46, 19.42it/s]
 84%|████████▍ | 4724/5625 [04:10<00:47, 18.97it/s]
 84%|████████▍ | 4727/5625 [04:10<00:45, 19.70it/s]
 84%|████████▍ | 4730/5625 [04:10<00:44, 20.19it/s]
 84%|████████▍ | 4733/5625 [04:10<00:43, 20.28it/s]
 84%|████████▍ | 4736/5625 [04:10<00:45, 19.68it/s]
 84%|████████▍ | 4738/5625 [04:10<00:45, 19.68it/s]
 84%|████████▍ | 4740/5625 [04:10<00:45, 19.40it/s]
 84%|████████▍ | 4742/5625 [04:11<00:45, 19.28it/s]
 84%|████████▍ | 4744/5625 [04:11<00:46, 19.12it/s]
 84%|████████▍ | 4746/5625 [04:11<00:46, 18.76it/s]
 84%|████████▍ | 4748/5625 [04:11<00:46, 19.06it/s]
 84%|████████▍ | 4751/5625 [04:11<00:44, 19.84it/s]
 84%|████████▍ | 4753/5625 [04:11<00:45, 19.18it/s]
 85%|████████▍ | 4755/5625 [04:11<00:45, 19.09it/s]
 85%|████████▍ | 4757/5625 [04:11<00:44, 19.29it/s]
 85%|████████▍ | 4759/5625 [04:11<00:46, 18.81it/s]
 85%|████████▍ | 4761/5625 [04:12<00:46, 18.74it/s]
 85%|████████▍ | 4764/5625 [04:12<00:43, 19.69it/s]
 85%|████████▍ | 4766/5625 [04:12<00:43, 19.76it/s]
 85%|████████▍ | 4769/5625 [04:12<00:41, 20.40it/s]
 85%|████████▍ | 4772/5625 [04:12<00:44, 19.22it/s]
 85%|████████▍ | 4775/5625 [04:12<00:42, 19.84it/s]
 85%|████████▍ | 4777/5625 [04:12<00:43, 19.63it/s]
 85%|████████▍ | 4779/5625 [04:12<00:43, 19.53it/s]
 85%|████████▍ | 4781/5625 [04:13<00:43, 19.32it/s]
 85%|████████▌ | 4784/5625 [04:13<00:43, 19.28it/s]
 85%|████████▌ | 4786/5625 [04:13<00:44, 18.81it/s]
 85%|████████▌ | 4788/5625 [04:13<00:44, 18.74it/s]
 85%|████████▌ | 4791/5625 [04:13<00:41, 19.93it/s]
 85%|████████▌ | 4794/5625 [04:13<00:40, 20.34it/s]
 85%|████████▌ | 4797/5625 [04:13<00:40, 20.21it/s]
 85%|████████▌ | 4800/5625 [04:13<00:39, 20.72it/s]
 85%|████████▌ | 4803/5625 [04:14<00:40, 20.23it/s]
 85%|████████▌ | 4806/5625 [04:14<00:41, 19.55it/s]
 85%|████████▌ | 4808/5625 [04:14<00:41, 19.56it/s]
 86%|████████▌ | 4810/5625 [04:14<00:42, 18.99it/s]
 86%|████████▌ | 4813/5625 [04:14<00:40, 19.85it/s]
 86%|████████▌ | 4815/5625 [04:14<00:41, 19.56it/s]
 86%|████████▌ | 4818/5625 [04:14<00:40, 19.97it/s]
 86%|████████▌ | 4820/5625 [04:15<00:41, 19.38it/s]
 86%|████████▌ | 4822/5625 [04:15<00:42, 18.99it/s]
 86%|████████▌ | 4824/5625 [04:15<00:42, 18.95it/s]
 86%|████████▌ | 4826/5625 [04:15<00:41, 19.22it/s]
 86%|████████▌ | 4829/5625 [04:15<00:41, 19.41it/s]
 86%|████████▌ | 4832/5625 [04:15<00:39, 20.09it/s]
 86%|████████▌ | 4834/5625 [04:15<00:39, 19.86it/s]
 86%|████████▌ | 4836/5625 [04:15<00:39, 19.82it/s]
 86%|████████▌ | 4839/5625 [04:15<00:39, 20.13it/s]
 86%|████████▌ | 4842/5625 [04:16<00:38, 20.55it/s]
 86%|████████▌ | 4845/5625 [04:16<00:38, 20.51it/s]
 86%|████████▌ | 4848/5625 [04:16<00:38, 20.12it/s]
 86%|████████▌ | 4851/5625 [04:16<00:38, 20.16it/s]
 86%|████████▋ | 4854/5625 [04:16<00:39, 19.55it/s]
 86%|████████▋ | 4856/5625 [04:16<00:39, 19.57it/s]
 86%|████████▋ | 4858/5625 [04:16<00:39, 19.47it/s]
 86%|████████▋ | 4861/5625 [04:17<00:38, 19.83it/s]
 86%|████████▋ | 4863/5625 [04:17<00:38, 19.63it/s]
 86%|████████▋ | 4865/5625 [04:17<00:39, 19.42it/s]
 87%|████████▋ | 4868/5625 [04:17<00:37, 20.02it/s]
 87%|████████▋ | 4871/5625 [04:17<00:37, 20.18it/s]
 87%|████████▋ | 4874/5625 [04:17<00:36, 20.47it/s]
 87%|████████▋ | 4877/5625 [04:17<00:37, 19.83it/s]
 87%|████████▋ | 4879/5625 [04:17<00:38, 19.59it/s]
 87%|████████▋ | 4881/5625 [04:18<00:38, 19.17it/s]
 87%|████████▋ | 4883/5625 [04:18<00:38, 19.37it/s]
 87%|████████▋ | 4886/5625 [04:18<00:37, 19.81it/s]
 87%|████████▋ | 4888/5625 [04:18<00:37, 19.45it/s]
 87%|████████▋ | 4890/5625 [04:18<00:38, 19.24it/s]
 87%|████████▋ | 4893/5625 [04:18<00:37, 19.34it/s]
 87%|████████▋ | 4896/5625 [04:18<00:37, 19.64it/s]
 87%|████████▋ | 4899/5625 [04:19<00:36, 19.78it/s]
 87%|████████▋ | 4902/5625 [04:19<00:36, 19.98it/s]
 87%|████████▋ | 4904/5625 [04:19<00:36, 19.64it/s]
 87%|████████▋ | 4906/5625 [04:19<00:37, 19.30it/s]
 87%|████████▋ | 4908/5625 [04:19<00:36, 19.48it/s]
 87%|████████▋ | 4910/5625 [04:19<00:37, 19.25it/s]
 87%|████████▋ | 4913/5625 [04:19<00:35, 19.90it/s]
 87%|████████▋ | 4915/5625 [04:19<00:35, 19.81it/s]
 87%|████████▋ | 4917/5625 [04:19<00:35, 19.68it/s]
 87%|████████▋ | 4919/5625 [04:20<00:36, 19.36it/s]
 87%|████████▋ | 4921/5625 [04:20<00:36, 19.46it/s]
 88%|████████▊ | 4924/5625 [04:20<00:35, 19.87it/s]
 88%|████████▊ | 4927/5625 [04:20<00:34, 20.32it/s]
 88%|████████▊ | 4930/5625 [04:20<00:35, 19.46it/s]
 88%|████████▊ | 4932/5625 [04:20<00:35, 19.34it/s]
 88%|████████▊ | 4934/5625 [04:20<00:36, 18.82it/s]
 88%|████████▊ | 4936/5625 [04:20<00:36, 18.83it/s]
 88%|████████▊ | 4939/5625 [04:21<00:35, 19.40it/s]
 88%|████████▊ | 4942/5625 [04:21<00:34, 19.73it/s]
 88%|████████▊ | 4945/5625 [04:21<00:33, 20.29it/s]
 88%|████████▊ | 4948/5625 [04:21<00:34, 19.87it/s]
 88%|████████▊ | 4950/5625 [04:21<00:34, 19.50it/s]
 88%|████████▊ | 4952/5625 [04:21<00:34, 19.37it/s]
 88%|████████▊ | 4955/5625 [04:21<00:32, 20.44it/s]
 88%|████████▊ | 4958/5625 [04:22<00:33, 19.88it/s]
 88%|████████▊ | 4960/5625 [04:22<00:33, 19.88it/s]
 88%|████████▊ | 4962/5625 [04:22<00:34, 19.20it/s]
 88%|████████▊ | 4964/5625 [04:22<00:34, 19.04it/s]
 88%|████████▊ | 4966/5625 [04:22<00:34, 19.23it/s]
 88%|████████▊ | 4968/5625 [04:22<00:34, 18.84it/s]
 88%|████████▊ | 4970/5625 [04:22<00:34, 19.10it/s]
 88%|████████▊ | 4972/5625 [04:22<00:34, 18.75it/s]
 88%|████████▊ | 4974/5625 [04:22<00:34, 18.62it/s]
 88%|████████▊ | 4976/5625 [04:22<00:35, 18.45it/s]
 89%|████████▊ | 4979/5625 [04:23<00:33, 19.22it/s]
 89%|████████▊ | 4981/5625 [04:23<00:33, 19.28it/s]
 89%|████████▊ | 4984/5625 [04:23<00:32, 19.74it/s]
 89%|████████▊ | 4987/5625 [04:23<00:31, 19.99it/s]
 89%|████████▊ | 4989/5625 [04:23<00:32, 19.39it/s]
 89%|████████▊ | 4992/5625 [04:23<00:30, 20.63it/s]
 89%|████████▉ | 4995/5625 [04:23<00:31, 19.90it/s]
 89%|████████▉ | 4997/5625 [04:24<00:31, 19.65it/s]
 89%|████████▉ | 5000/5625 [04:24<00:30, 20.35it/s]
 89%|████████▉ | 5003/5625 [04:24<00:31, 19.71it/s]
 89%|████████▉ | 5005/5625 [04:24<00:32, 19.20it/s]
 89%|████████▉ | 5007/5625 [04:24<00:32, 19.28it/s]
 89%|████████▉ | 5009/5625 [04:24<00:32, 19.13it/s]
 89%|████████▉ | 5011/5625 [04:24<00:32, 18.68it/s]
 89%|████████▉ | 5013/5625 [04:24<00:32, 18.88it/s]
 89%|████████▉ | 5015/5625 [04:24<00:32, 18.79it/s]
 89%|████████▉ | 5018/5625 [04:25<00:30, 19.71it/s]
 89%|████████▉ | 5021/5625 [04:25<00:30, 19.50it/s]
 89%|████████▉ | 5024/5625 [04:25<00:30, 19.85it/s]
 89%|████████▉ | 5027/5625 [04:25<00:29, 20.20it/s]
 89%|████████▉ | 5030/5625 [04:25<00:28, 20.55it/s]
 89%|████████▉ | 5033/5625 [04:25<00:29, 20.30it/s]
 90%|████████▉ | 5036/5625 [04:26<00:29, 19.80it/s]
 90%|████████▉ | 5038/5625 [04:26<00:30, 19.44it/s]
 90%|████████▉ | 5041/5625 [04:26<00:29, 19.63it/s]
 90%|████████▉ | 5044/5625 [04:26<00:29, 20.02it/s]
 90%|████████▉ | 5046/5625 [04:26<00:29, 19.83it/s]
 90%|████████▉ | 5048/5625 [04:26<00:29, 19.33it/s]
 90%|████████▉ | 5050/5625 [04:26<00:29, 19.43it/s]
 90%|████████▉ | 5052/5625 [04:26<00:29, 19.55it/s]
 90%|████████▉ | 5054/5625 [04:26<00:29, 19.59it/s]
 90%|████████▉ | 5056/5625 [04:27<00:29, 19.29it/s]
 90%|████████▉ | 5058/5625 [04:27<00:29, 19.12it/s]
 90%|████████▉ | 5060/5625 [04:27<00:29, 19.04it/s]
 90%|█████████ | 5063/5625 [04:27<00:28, 20.05it/s]
 90%|█████████ | 5065/5625 [04:27<00:28, 19.81it/s]
 90%|█████████ | 5067/5625 [04:27<00:29, 19.20it/s]
 90%|█████████ | 5070/5625 [04:27<00:28, 19.35it/s]
 90%|█████████ | 5072/5625 [04:27<00:28, 19.20it/s]
 90%|█████████ | 5074/5625 [04:27<00:28, 19.33it/s]
 90%|█████████ | 5076/5625 [04:28<00:28, 19.06it/s]
 90%|█████████ | 5078/5625 [04:28<00:28, 19.03it/s]
 90%|█████████ | 5080/5625 [04:28<00:28, 19.01it/s]
 90%|█████████ | 5082/5625 [04:28<00:28, 19.27it/s]
 90%|█████████ | 5084/5625 [04:28<00:28, 19.05it/s]
 90%|█████████ | 5087/5625 [04:28<00:27, 19.34it/s]
 90%|█████████ | 5089/5625 [04:28<00:28, 19.04it/s]
 91%|█████████ | 5091/5625 [04:28<00:27, 19.24it/s]
 91%|█████████ | 5094/5625 [04:29<00:26, 19.67it/s]
 91%|█████████ | 5096/5625 [04:29<00:27, 19.16it/s]
 91%|█████████ | 5098/5625 [04:29<00:27, 18.96it/s]
 91%|█████████ | 5100/5625 [04:29<00:27, 18.89it/s]
 91%|█████████ | 5102/5625 [04:29<00:27, 19.14it/s]
 91%|█████████ | 5105/5625 [04:29<00:25, 20.45it/s]
 91%|█████████ | 5108/5625 [04:29<00:24, 20.91it/s]
 91%|█████████ | 5111/5625 [04:29<00:24, 20.79it/s]
 91%|█████████ | 5114/5625 [04:30<00:25, 19.80it/s]
 91%|█████████ | 5116/5625 [04:30<00:26, 19.28it/s]
 91%|█████████ | 5119/5625 [04:30<00:25, 19.97it/s]
 91%|█████████ | 5122/5625 [04:30<00:25, 19.83it/s]
 91%|█████████ | 5124/5625 [04:30<00:25, 19.63it/s]
 91%|█████████ | 5127/5625 [04:30<00:24, 20.31it/s]
 91%|█████████ | 5130/5625 [04:30<00:25, 19.73it/s]
 91%|█████████ | 5132/5625 [04:30<00:25, 19.51it/s]
 91%|█████████▏| 5134/5625 [04:31<00:25, 19.41it/s]
 91%|█████████▏| 5137/5625 [04:31<00:24, 19.82it/s]
 91%|█████████▏| 5139/5625 [04:31<00:25, 19.19it/s]
 91%|█████████▏| 5141/5625 [04:31<00:25, 18.96it/s]
 91%|█████████▏| 5143/5625 [04:31<00:25, 18.63it/s]
 91%|█████████▏| 5145/5625 [04:31<00:26, 18.22it/s]
 92%|█████████▏| 5147/5625 [04:31<00:26, 18.14it/s]
 92%|█████████▏| 5150/5625 [04:31<00:25, 18.68it/s]
 92%|█████████▏| 5152/5625 [04:32<00:25, 18.54it/s]
 92%|█████████▏| 5155/5625 [04:32<00:24, 19.04it/s]
 92%|█████████▏| 5158/5625 [04:32<00:24, 19.26it/s]
 92%|█████████▏| 5160/5625 [04:32<00:24, 19.01it/s]
 92%|█████████▏| 5162/5625 [04:32<00:24, 19.16it/s]
 92%|█████████▏| 5164/5625 [04:32<00:24, 19.14it/s]
 92%|█████████▏| 5166/5625 [04:32<00:24, 19.09it/s]
 92%|█████████▏| 5168/5625 [04:32<00:24, 18.65it/s]
 92%|█████████▏| 5170/5625 [04:32<00:24, 18.36it/s]
 92%|█████████▏| 5173/5625 [04:33<00:23, 18.93it/s]
 92%|█████████▏| 5176/5625 [04:33<00:23, 19.44it/s]
 92%|█████████▏| 5179/5625 [04:33<00:22, 19.93it/s]
 92%|█████████▏| 5181/5625 [04:33<00:22, 19.61it/s]
 92%|█████████▏| 5183/5625 [04:33<00:22, 19.55it/s]
 92%|█████████▏| 5186/5625 [04:33<00:22, 19.83it/s]
 92%|█████████▏| 5188/5625 [04:33<00:22, 19.29it/s]
 92%|█████████▏| 5190/5625 [04:33<00:23, 18.77it/s]
 92%|█████████▏| 5192/5625 [04:34<00:22, 18.99it/s]
 92%|█████████▏| 5194/5625 [04:34<00:22, 19.11it/s]
 92%|█████████▏| 5197/5625 [04:34<00:22, 19.34it/s]
 92%|█████████▏| 5199/5625 [04:34<00:21, 19.49it/s]
 92%|█████████▏| 5201/5625 [04:34<00:22, 19.25it/s]
 92%|█████████▏| 5203/5625 [04:34<00:22, 18.81it/s]
 93%|█████████▎| 5205/5625 [04:34<00:22, 18.62it/s]
 93%|█████████▎| 5207/5625 [04:34<00:22, 18.95it/s]
 93%|█████████▎| 5209/5625 [04:34<00:21, 19.23it/s]
 93%|█████████▎| 5211/5625 [04:35<00:21, 19.41it/s]
 93%|█████████▎| 5214/5625 [04:35<00:20, 19.72it/s]
 93%|█████████▎| 5216/5625 [04:35<00:21, 19.37it/s]
 93%|█████████▎| 5219/5625 [04:35<00:20, 20.14it/s]
 93%|█████████▎| 5222/5625 [04:35<00:20, 19.31it/s]
 93%|█████████▎| 5224/5625 [04:35<00:21, 19.08it/s]
 93%|█████████▎| 5226/5625 [04:35<00:21, 18.92it/s]
 93%|█████████▎| 5228/5625 [04:35<00:20, 18.99it/s]
 93%|█████████▎| 5231/5625 [04:36<00:20, 19.59it/s]
 93%|█████████▎| 5233/5625 [04:36<00:20, 19.08it/s]
 93%|█████████▎| 5235/5625 [04:36<00:20, 19.22it/s]
 93%|█████████▎| 5238/5625 [04:36<00:19, 19.84it/s]
 93%|█████████▎| 5240/5625 [04:36<00:19, 19.45it/s]
 93%|█████████▎| 5242/5625 [04:36<00:20, 19.10it/s]
 93%|█████████▎| 5245/5625 [04:36<00:19, 19.33it/s]
 93%|█████████▎| 5247/5625 [04:36<00:19, 19.22it/s]
 93%|█████████▎| 5249/5625 [04:37<00:20, 18.74it/s]
 93%|█████████▎| 5251/5625 [04:37<00:20, 18.61it/s]
 93%|█████████▎| 5254/5625 [04:37<00:19, 19.01it/s]
 93%|█████████▎| 5256/5625 [04:37<00:19, 19.04it/s]
 93%|█████████▎| 5258/5625 [04:37<00:19, 18.88it/s]
 94%|█████████▎| 5260/5625 [04:37<00:19, 18.70it/s]
 94%|█████████▎| 5263/5625 [04:37<00:18, 19.25it/s]
 94%|█████████▎| 5265/5625 [04:37<00:18, 19.22it/s]
 94%|█████████▎| 5267/5625 [04:37<00:18, 19.36it/s]
 94%|█████████▎| 5270/5625 [04:38<00:17, 19.78it/s]
 94%|█████████▎| 5272/5625 [04:38<00:18, 19.43it/s]
 94%|█████████▍| 5274/5625 [04:38<00:18, 18.85it/s]
 94%|█████████▍| 5276/5625 [04:38<00:18, 18.90it/s]
 94%|█████████▍| 5278/5625 [04:38<00:18, 18.80it/s]
 94%|█████████▍| 5280/5625 [04:38<00:18, 18.73it/s]
 94%|█████████▍| 5282/5625 [04:38<00:18, 19.00it/s]
 94%|█████████▍| 5284/5625 [04:38<00:18, 18.63it/s]
 94%|█████████▍| 5286/5625 [04:39<00:18, 18.58it/s]
 94%|█████████▍| 5288/5625 [04:39<00:18, 18.51it/s]
 94%|█████████▍| 5291/5625 [04:39<00:17, 18.88it/s]
 94%|█████████▍| 5293/5625 [04:39<00:17, 18.61it/s]
 94%|█████████▍| 5295/5625 [04:39<00:17, 18.36it/s]
 94%|█████████▍| 5297/5625 [04:39<00:17, 18.52it/s]
 94%|█████████▍| 5299/5625 [04:39<00:17, 18.31it/s]
 94%|█████████▍| 5301/5625 [04:39<00:17, 18.55it/s]
 94%|█████████▍| 5304/5625 [04:39<00:16, 19.03it/s]
 94%|█████████▍| 5306/5625 [04:40<00:16, 19.06it/s]
 94%|█████████▍| 5308/5625 [04:40<00:16, 19.30it/s]
 94%|█████████▍| 5310/5625 [04:40<00:16, 19.36it/s]
 94%|█████████▍| 5312/5625 [04:40<00:16, 18.93it/s]
 94%|█████████▍| 5315/5625 [04:40<00:16, 19.16it/s]
 95%|█████████▍| 5318/5625 [04:40<00:15, 19.51it/s]
 95%|█████████▍| 5320/5625 [04:40<00:15, 19.20it/s]
 95%|█████████▍| 5322/5625 [04:40<00:15, 19.24it/s]
 95%|█████████▍| 5324/5625 [04:41<00:15, 19.12it/s]
 95%|█████████▍| 5327/5625 [04:41<00:15, 19.34it/s]
 95%|█████████▍| 5329/5625 [04:41<00:15, 19.11it/s]
 95%|█████████▍| 5331/5625 [04:41<00:15, 19.17it/s]
 95%|█████████▍| 5334/5625 [04:41<00:15, 19.34it/s]
 95%|█████████▍| 5337/5625 [04:41<00:14, 19.43it/s]
 95%|█████████▍| 5339/5625 [04:41<00:15, 18.96it/s]
 95%|█████████▍| 5341/5625 [04:41<00:15, 18.84it/s]
 95%|█████████▍| 5343/5625 [04:42<00:15, 18.45it/s]
 95%|█████████▌| 5345/5625 [04:42<00:14, 18.71it/s]
 95%|█████████▌| 5348/5625 [04:42<00:14, 19.63it/s]
 95%|█████████▌| 5351/5625 [04:42<00:13, 19.61it/s]
 95%|█████████▌| 5353/5625 [04:42<00:13, 19.45it/s]
 95%|█████████▌| 5356/5625 [04:42<00:13, 19.80it/s]
 95%|█████████▌| 5358/5625 [04:42<00:13, 19.25it/s]
 95%|█████████▌| 5360/5625 [04:42<00:13, 19.22it/s]
 95%|█████████▌| 5362/5625 [04:42<00:14, 18.71it/s]
 95%|█████████▌| 5364/5625 [04:43<00:13, 18.66it/s]
 95%|█████████▌| 5366/5625 [04:43<00:13, 18.80it/s]
 95%|█████████▌| 5369/5625 [04:43<00:12, 20.03it/s]
 95%|█████████▌| 5371/5625 [04:43<00:13, 19.43it/s]
 96%|█████████▌| 5373/5625 [04:43<00:13, 19.31it/s]
 96%|█████████▌| 5375/5625 [04:43<00:13, 19.00it/s]
 96%|█████████▌| 5378/5625 [04:43<00:12, 19.92it/s]
 96%|█████████▌| 5381/5625 [04:43<00:12, 20.28it/s]
 96%|█████████▌| 5384/5625 [04:44<00:11, 20.72it/s]
 96%|█████████▌| 5387/5625 [04:44<00:12, 19.80it/s]
 96%|█████████▌| 5389/5625 [04:44<00:12, 19.17it/s]
 96%|█████████▌| 5391/5625 [04:44<00:12, 18.78it/s]
 96%|█████████▌| 5393/5625 [04:44<00:12, 18.78it/s]
 96%|█████████▌| 5395/5625 [04:44<00:12, 18.77it/s]
 96%|█████████▌| 5398/5625 [04:44<00:11, 19.67it/s]
 96%|█████████▌| 5400/5625 [04:44<00:11, 18.96it/s]
 96%|█████████▌| 5402/5625 [04:45<00:11, 18.71it/s]
 96%|█████████▌| 5405/5625 [04:45<00:11, 18.99it/s]
 96%|█████████▌| 5408/5625 [04:45<00:10, 20.00it/s]
 96%|█████████▌| 5410/5625 [04:45<00:10, 19.77it/s]
 96%|█████████▌| 5412/5625 [04:45<00:11, 19.18it/s]
 96%|█████████▌| 5414/5625 [04:45<00:11, 18.58it/s]
 96%|█████████▋| 5416/5625 [04:45<00:11, 18.63it/s]
 96%|█████████▋| 5419/5625 [04:45<00:10, 19.12it/s]
 96%|█████████▋| 5422/5625 [04:46<00:10, 19.46it/s]
 96%|█████████▋| 5424/5625 [04:46<00:10, 19.06it/s]
 96%|█████████▋| 5426/5625 [04:46<00:10, 18.84it/s]
 96%|█████████▋| 5428/5625 [04:46<00:10, 19.05it/s]
 97%|█████████▋| 5430/5625 [04:46<00:10, 19.14it/s]
 97%|█████████▋| 5433/5625 [04:46<00:09, 19.52it/s]
 97%|█████████▋| 5435/5625 [04:46<00:09, 19.57it/s]
 97%|█████████▋| 5437/5625 [04:46<00:09, 19.46it/s]
 97%|█████████▋| 5439/5625 [04:46<00:09, 18.88it/s]
 97%|█████████▋| 5441/5625 [04:47<00:09, 18.81it/s]
 97%|█████████▋| 5443/5625 [04:47<00:09, 18.42it/s]
 97%|█████████▋| 5445/5625 [04:47<00:09, 18.69it/s]
 97%|█████████▋| 5447/5625 [04:47<00:09, 18.73it/s]
 97%|█████████▋| 5449/5625 [04:47<00:09, 18.96it/s]
 97%|█████████▋| 5451/5625 [04:47<00:09, 19.22it/s]
 97%|█████████▋| 5453/5625 [04:47<00:08, 19.16it/s]
 97%|█████████▋| 5455/5625 [04:47<00:08, 19.27it/s]
 97%|█████████▋| 5458/5625 [04:47<00:08, 19.34it/s]
 97%|█████████▋| 5460/5625 [04:48<00:08, 18.97it/s]
 97%|█████████▋| 5462/5625 [04:48<00:08, 18.43it/s]
 97%|█████████▋| 5464/5625 [04:48<00:08, 18.42it/s]
 97%|█████████▋| 5466/5625 [04:48<00:08, 18.50it/s]
 97%|█████████▋| 5468/5625 [04:48<00:08, 18.40it/s]
 97%|█████████▋| 5470/5625 [04:48<00:08, 18.47it/s]
 97%|█████████▋| 5473/5625 [04:48<00:08, 18.74it/s]
 97%|█████████▋| 5475/5625 [04:48<00:08, 18.52it/s]
 97%|█████████▋| 5478/5625 [04:49<00:07, 19.28it/s]
 97%|█████████▋| 5481/5625 [04:49<00:07, 20.31it/s]
 97%|█████████▋| 5484/5625 [04:49<00:07, 19.35it/s]
 98%|█████████▊| 5486/5625 [04:49<00:07, 19.02it/s]
 98%|█████████▊| 5489/5625 [04:49<00:07, 19.37it/s]
 98%|█████████▊| 5491/5625 [04:49<00:07, 19.03it/s]
 98%|█████████▊| 5494/5625 [04:49<00:06, 19.40it/s]
 98%|█████████▊| 5496/5625 [04:49<00:06, 19.08it/s]
 98%|█████████▊| 5498/5625 [04:50<00:06, 18.82it/s]
 98%|█████████▊| 5500/5625 [04:50<00:06, 19.10it/s]
 98%|█████████▊| 5502/5625 [04:50<00:06, 18.56it/s]
 98%|█████████▊| 5505/5625 [04:50<00:06, 18.73it/s]
 98%|█████████▊| 5507/5625 [04:50<00:06, 18.40it/s]
 98%|█████████▊| 5509/5625 [04:50<00:06, 18.22it/s]
 98%|█████████▊| 5511/5625 [04:50<00:06, 18.06it/s]
 98%|█████████▊| 5514/5625 [04:50<00:05, 19.00it/s]
 98%|█████████▊| 5516/5625 [04:51<00:05, 18.81it/s]
 98%|█████████▊| 5518/5625 [04:51<00:05, 19.05it/s]
 98%|█████████▊| 5521/5625 [04:51<00:05, 19.36it/s]
 98%|█████████▊| 5523/5625 [04:51<00:05, 19.26it/s]
 98%|█████████▊| 5526/5625 [04:51<00:05, 19.48it/s]
 98%|█████████▊| 5528/5625 [04:51<00:05, 19.30it/s]
 98%|█████████▊| 5530/5625 [04:51<00:04, 19.25it/s]
 98%|█████████▊| 5533/5625 [04:51<00:04, 19.73it/s]
 98%|█████████▊| 5535/5625 [04:52<00:04, 19.71it/s]
 98%|█████████▊| 5538/5625 [04:52<00:04, 20.27it/s]
 99%|█████████▊| 5541/5625 [04:52<00:04, 20.55it/s]
 99%|█████████▊| 5544/5625 [04:52<00:03, 20.36it/s]
 99%|█████████▊| 5547/5625 [04:52<00:03, 19.73it/s]
 99%|█████████▊| 5549/5625 [04:52<00:03, 19.60it/s]
 99%|█████████▊| 5551/5625 [04:52<00:03, 19.27it/s]
 99%|█████████▊| 5553/5625 [04:52<00:03, 19.10it/s]
 99%|█████████▉| 5556/5625 [04:53<00:03, 19.48it/s]
 99%|█████████▉| 5558/5625 [04:53<00:03, 18.91it/s]
 99%|█████████▉| 5560/5625 [04:53<00:03, 19.11it/s]
 99%|█████████▉| 5562/5625 [04:53<00:03, 18.97it/s]
 99%|█████████▉| 5565/5625 [04:53<00:03, 19.45it/s]
 99%|█████████▉| 5568/5625 [04:53<00:02, 19.66it/s]
 99%|█████████▉| 5570/5625 [04:53<00:02, 19.36it/s]
 99%|█████████▉| 5573/5625 [04:53<00:02, 19.62it/s]
 99%|█████████▉| 5576/5625 [04:54<00:02, 19.73it/s]
 99%|█████████▉| 5578/5625 [04:54<00:02, 19.37it/s]
 99%|█████████▉| 5580/5625 [04:54<00:02, 19.10it/s]
 99%|█████████▉| 5583/5625 [04:54<00:02, 19.89it/s]
 99%|█████████▉| 5586/5625 [04:54<00:01, 20.28it/s]
 99%|█████████▉| 5589/5625 [04:54<00:01, 19.64it/s]
 99%|█████████▉| 5591/5625 [04:54<00:01, 19.09it/s]
 99%|█████████▉| 5593/5625 [04:54<00:01, 19.20it/s]
 99%|█████████▉| 5595/5625 [04:55<00:01, 19.18it/s]
100%|█████████▉| 5597/5625 [04:55<00:01, 19.05it/s]
100%|█████████▉| 5599/5625 [04:55<00:01, 19.16it/s]
100%|█████████▉| 5602/5625 [04:55<00:01, 19.25it/s]
100%|█████████▉| 5604/5625 [04:55<00:01, 18.98it/s]
100%|█████████▉| 5606/5625 [04:55<00:01, 18.96it/s]
100%|█████████▉| 5608/5625 [04:55<00:00, 18.44it/s]
100%|█████████▉| 5610/5625 [04:55<00:00, 18.78it/s]
100%|█████████▉| 5613/5625 [04:56<00:00, 19.41it/s]
100%|█████████▉| 5616/5625 [04:56<00:00, 19.52it/s]
100%|█████████▉| 5618/5625 [04:56<00:00, 19.33it/s]
100%|█████████▉| 5620/5625 [04:56<00:00, 19.24it/s]
100%|█████████▉| 5622/5625 [04:56<00:00, 19.03it/s]
100%|█████████▉| 5624/5625 [04:56<00:00, 18.56it/s]
                                                   

100%|██████████| 5625/5625 [04:56<00:00, 18.56it/s]{'eval_loss': 0.7078651785850525, 'eval_accuracy': 0.7088, 'eval_f1': 0.7064138859634208, 'eval_runtime': 1.7344, 'eval_samples_per_second': 1441.384, 'eval_steps_per_second': 180.461, 'epoch': 2.0}
{'loss': 0.2351, 'learning_rate': 8.943619431542328e-11, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.71it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.49it/s]

 21%|██        | 66/313 [00:00<00:01, 205.83it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.07it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.44it/s]

 40%|████      | 126/313 [00:00<00:01, 185.18it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.09it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.11it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.22it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.29it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.26it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.94it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.65it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.62it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.40it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.40it/s]
100%|██████████| 5625/5625 [04:58<00:00, 18.56it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 5625/5625 [04:59<00:00, 18.56it/s]
100%|██████████| 5625/5625 [04:59<00:00, 18.78it/s]
[I 2023-10-26 22:56:57,922] Trial 20 finished with value: 0.7146657998068633 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 5.804944592736865e-05, 'per_device_train_batch_size': 16, 'weight_decay': 1.0052320265799857e-06}. Best is trial 18 with value: 0.7197401896178178.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.9487231373786926, 'eval_accuracy': 0.7136, 'eval_f1': 0.7146657998068633, 'eval_runtime': 1.7326, 'eval_samples_per_second': 1442.898, 'eval_steps_per_second': 180.651, 'epoch': 3.0}
{'train_runtime': 299.4688, 'train_samples_per_second': 300.532, 'train_steps_per_second': 18.783, 'train_loss': 0.51456298828125, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.69it/s]
  0%|          | 2/705 [00:00<03:10,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:42,  3.96it/s]
  9%|▉         | 63/705 [00:16<02:44,  3.89it/s]
  9%|▉         | 64/705 [00:16<02:45,  3.88it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.82it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.86it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.84it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.79it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:27<02:59,  3.36it/s]
 15%|█▍        | 103/705 [00:27<02:53,  3.48it/s]
 15%|█▍        | 104/705 [00:27<02:48,  3.56it/s]
 15%|█▍        | 105/705 [00:27<02:43,  3.66it/s]
 15%|█▌        | 106/705 [00:28<02:40,  3.74it/s]
 15%|█▌        | 107/705 [00:28<02:40,  3.73it/s]
 15%|█▌        | 108/705 [00:28<02:39,  3.74it/s]
 15%|█▌        | 109/705 [00:28<02:38,  3.75it/s]
 16%|█▌        | 110/705 [00:29<02:38,  3.75it/s]
 16%|█▌        | 111/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.76it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.82it/s]
 16%|█▌        | 114/705 [00:30<02:35,  3.81it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:36,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:32<02:43,  3.58it/s]
 17%|█▋        | 122/705 [00:32<02:40,  3.63it/s]
 17%|█▋        | 123/705 [00:32<02:37,  3.69it/s]
 18%|█▊        | 124/705 [00:32<02:32,  3.81it/s]
 18%|█▊        | 125/705 [00:33<02:32,  3.81it/s]
 18%|█▊        | 126/705 [00:33<02:31,  3.82it/s]
 18%|█▊        | 127/705 [00:33<02:31,  3.83it/s]
 18%|█▊        | 128/705 [00:33<02:30,  3.84it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.84it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.90it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:39<02:22,  3.91it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.83it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:17,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.79it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:20,  3.76it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.85it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:11,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.79it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]{'loss': 0.8212, 'learning_rate': 2.8358038168025603e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.17it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.27it/s]

 21%|██        | 66/313 [00:00<00:01, 205.77it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.05it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.44it/s]

 40%|████      | 126/313 [00:00<00:01, 185.18it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.04it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.12it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.31it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.40it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.45it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.03it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.60it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.38it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.54it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.54it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:06,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:16,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:00,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.21it/s]
 34%|███▍      | 241/705 [01:06<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.94it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:13<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.80it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.84it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:46,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.78it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 313/705 [01:24<01:43,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.88it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.80it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:45,  3.53it/s]
 47%|████▋     | 333/705 [01:30<01:43,  3.59it/s]
 47%|████▋     | 334/705 [01:30<01:42,  3.63it/s]
 48%|████▊     | 335/705 [01:30<01:40,  3.69it/s]
 48%|████▊     | 336/705 [01:30<01:39,  3.72it/s]
 48%|████▊     | 337/705 [01:31<01:38,  3.72it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 339/705 [01:31<01:38,  3.73it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.73it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.72it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.83it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:47,  3.29it/s]
 50%|████▉     | 352/705 [01:35<01:42,  3.45it/s]
 50%|█████     | 353/705 [01:35<01:39,  3.54it/s]
 50%|█████     | 354/705 [01:35<01:37,  3.59it/s]
 50%|█████     | 355/705 [01:35<01:36,  3.62it/s]
 50%|█████     | 356/705 [01:36<01:35,  3.66it/s]
 51%|█████     | 357/705 [01:36<01:34,  3.67it/s]
 51%|█████     | 358/705 [01:36<01:34,  3.68it/s]
 51%|█████     | 359/705 [01:37<01:33,  3.70it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.73it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.73it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.73it/s]
 51%|█████▏    | 363/705 [01:38<01:31,  3.73it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:22,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.77it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.83it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:21,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.86it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.82it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.80it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:09,  3.76it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.78it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.88it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]{'eval_loss': 0.6819888949394226, 'eval_accuracy': 0.6972, 'eval_f1': 0.6957143308710738, 'eval_runtime': 1.7319, 'eval_samples_per_second': 1443.479, 'eval_steps_per_second': 180.724, 'epoch': 1.0}
{'loss': 0.5827, 'learning_rate': 1.0217280640510334e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.90it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.15it/s]

 20%|██        | 63/313 [00:00<00:01, 202.72it/s]

 27%|██▋       | 84/313 [00:00<00:01, 195.04it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.27it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.74it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.41it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.58it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.55it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.60it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 168.21it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 165.19it/s]

 82%|████████▏ | 256/313 [00:01<00:00, 181.44it/s]

 88%|████████▊ | 276/313 [00:01<00:00, 186.39it/s]

 94%|█████████▍| 295/313 [00:01<00:00, 178.89it/s]

100%|██████████| 313/313 [00:01<00:00, 176.50it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 176.50it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:05,  1.05s/it]
 67%|██████▋   | 472/705 [02:09<03:09,  1.23it/s]
 67%|██████▋   | 473/705 [02:09<02:30,  1.54it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:44,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:31,  2.51it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.78it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:04,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.55it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.63it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.82it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:56,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.77it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:49,  3.31it/s]
 77%|███████▋  | 543/705 [02:28<00:47,  3.43it/s]
 77%|███████▋  | 544/705 [02:28<00:45,  3.53it/s]
 77%|███████▋  | 545/705 [02:28<00:44,  3.58it/s]
 77%|███████▋  | 546/705 [02:28<00:43,  3.67it/s]
 78%|███████▊  | 547/705 [02:29<00:42,  3.73it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.76it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.81it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.82it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.79it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.76it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.74it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.72it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.84it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.82it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.84it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.96it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.94it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.79it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:38<00:41,  2.96it/s]
 83%|████████▎ | 582/705 [02:38<00:39,  3.14it/s]
 83%|████████▎ | 583/705 [02:38<00:37,  3.29it/s]
 83%|████████▎ | 584/705 [02:39<00:34,  3.47it/s]
 83%|████████▎ | 585/705 [02:39<00:33,  3.56it/s]
 83%|████████▎ | 586/705 [02:39<00:32,  3.62it/s]
 83%|████████▎ | 587/705 [02:39<00:32,  3.66it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.69it/s]
 84%|████████▎ | 589/705 [02:40<00:31,  3.70it/s]
 84%|████████▎ | 590/705 [02:40<00:31,  3.70it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.70it/s]
 84%|████████▍ | 592/705 [02:41<00:30,  3.76it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.75it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.73it/s]
 84%|████████▍ | 595/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.78it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.01it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.91it/s]
 86%|████████▌ | 603/705 [02:44<00:26,  3.87it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.86it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.86it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.80it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.80it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.94it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.89it/s]
 91%|█████████ | 642/705 [02:54<00:15,  3.94it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.83it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.80it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.85it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.83it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.78it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.88it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.673531711101532, 'eval_accuracy': 0.7188, 'eval_f1': 0.7163432251369968, 'eval_runtime': 1.731, 'eval_samples_per_second': 1444.229, 'eval_steps_per_second': 180.817, 'epoch': 2.0}
{'loss': 0.4488, 'learning_rate': 2.058640691782657e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.60it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.69it/s]

 21%|██        | 65/313 [00:00<00:01, 204.68it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.02it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.22it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.80it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.44it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.38it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.09it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.09it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.96it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.06it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.38it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.97it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.21it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.21it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.64it/s]
[I 2023-10-26 23:00:12,130] Trial 21 finished with value: 0.7253378617867058 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 3.35366905276931e-05, 'per_device_train_batch_size': 128, 'weight_decay': 2.684934234800217e-05}. Best is trial 21 with value: 0.7253378617867058.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6873573064804077, 'eval_accuracy': 0.7256, 'eval_f1': 0.7253378617867058, 'eval_runtime': 1.7312, 'eval_samples_per_second': 1444.058, 'eval_steps_per_second': 180.796, 'epoch': 3.0}
{'train_runtime': 193.4374, 'train_samples_per_second': 465.267, 'train_steps_per_second': 3.645, 'train_loss': 0.6175379543439716, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.81it/s]
  1%|          | 8/705 [00:02<03:01,  3.85it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:42,  3.96it/s]
  9%|▉         | 63/705 [00:16<02:44,  3.89it/s]
  9%|▉         | 64/705 [00:16<02:45,  3.88it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.82it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.86it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.86it/s]
 10%|█         | 71/705 [00:18<02:45,  3.84it/s]
 10%|█         | 72/705 [00:18<02:41,  3.93it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:43,  3.85it/s]
 11%|█         | 75/705 [00:19<02:44,  3.82it/s]
 11%|█         | 76/705 [00:19<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.73it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.79it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.77it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.75it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:38,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:54,  3.34it/s]
 18%|█▊        | 124/705 [00:32<02:44,  3.54it/s]
 18%|█▊        | 125/705 [00:33<02:40,  3.62it/s]
 18%|█▊        | 126/705 [00:33<02:37,  3.68it/s]
 18%|█▊        | 127/705 [00:33<02:35,  3.72it/s]
 18%|█▊        | 128/705 [00:33<02:33,  3.76it/s]
 18%|█▊        | 129/705 [00:34<02:32,  3.78it/s]
 18%|█▊        | 130/705 [00:34<02:32,  3.78it/s]
 19%|█▊        | 131/705 [00:34<02:31,  3.78it/s]
 19%|█▊        | 132/705 [00:34<02:30,  3.80it/s]
 19%|█▉        | 133/705 [00:35<02:31,  3.79it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:39<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.80it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.83it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:23,  3.77it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:17,  3.89it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:18,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.76it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8123, 'learning_rate': 3.308038138544911e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.96it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.78it/s]

 21%|██        | 65/313 [00:00<00:01, 204.62it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.95it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.21it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.94it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.54it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.29it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.02it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.95it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.81it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.91it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.30it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.91it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.98it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.98it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:09,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:18,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:07,  1.88it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:03,  2.53it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.03it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.94it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.86it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:16<01:50,  3.83it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.82it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.84it/s]
 41%|████      | 290/705 [01:18<01:47,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:46,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.88it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.84it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 313/705 [01:24<01:43,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:50,  3.54it/s]
 45%|████▍     | 316/705 [01:25<01:47,  3.61it/s]
 45%|████▍     | 317/705 [01:25<01:45,  3.69it/s]
 45%|████▌     | 318/705 [01:26<01:44,  3.70it/s]
 45%|████▌     | 319/705 [01:26<01:44,  3.70it/s]
 45%|████▌     | 320/705 [01:26<01:44,  3.70it/s]
 46%|████▌     | 321/705 [01:26<01:42,  3.74it/s]
 46%|████▌     | 322/705 [01:27<01:42,  3.75it/s]
 46%|████▌     | 323/705 [01:27<01:42,  3.73it/s]
 46%|████▌     | 324/705 [01:27<01:42,  3.73it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.76it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:30<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.75it/s]
 48%|████▊     | 335/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.81it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:45,  3.35it/s]
 50%|█████     | 354/705 [01:35<01:41,  3.45it/s]
 50%|█████     | 355/705 [01:35<01:39,  3.52it/s]
 50%|█████     | 356/705 [01:36<01:37,  3.59it/s]
 51%|█████     | 357/705 [01:36<01:36,  3.62it/s]
 51%|█████     | 358/705 [01:36<01:35,  3.64it/s]
 51%|█████     | 359/705 [01:37<01:34,  3.68it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.71it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.72it/s]
 51%|█████▏    | 362/705 [01:37<01:32,  3.73it/s]
 51%|█████▏    | 363/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.78it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.78it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:29,  3.73it/s]
 53%|█████▎    | 373/705 [01:40<01:28,  3.74it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.73it/s]
 53%|█████▎    | 375/705 [01:41<01:28,  3.74it/s]
 53%|█████▎    | 376/705 [01:41<01:28,  3.73it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.83it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.81it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.80it/s]
 55%|█████▍    | 385/705 [01:43<01:24,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:22,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.83it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:21,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.90it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.84it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.81it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.80it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.88it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.85it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:05,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6824406981468201, 'eval_accuracy': 0.6992, 'eval_f1': 0.6960295844451185, 'eval_runtime': 1.7326, 'eval_samples_per_second': 1442.938, 'eval_steps_per_second': 180.656, 'epoch': 1.0}
{'loss': 0.5679, 'learning_rate': 1.1918720833493395e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.71it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.82it/s]

 21%|██        | 65/313 [00:00<00:01, 204.81it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.06it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.28it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.02it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.67it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.35it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.65it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.61it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.89it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.21it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.34it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.93it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.14it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.14it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:05,  1.05s/it]
 67%|██████▋   | 472/705 [02:09<03:09,  1.23it/s]
 67%|██████▋   | 473/705 [02:09<02:30,  1.54it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:44,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:31,  2.51it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.78it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.88it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.78it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.81it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.80it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.76it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:46,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:46,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.76it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.80it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.76it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.74it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.79it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.79it/s]
 77%|███████▋  | 542/705 [02:28<00:54,  3.01it/s]
 77%|███████▋  | 543/705 [02:28<00:50,  3.20it/s]
 77%|███████▋  | 544/705 [02:28<00:48,  3.35it/s]
 77%|███████▋  | 545/705 [02:28<00:46,  3.45it/s]
 77%|███████▋  | 546/705 [02:29<00:44,  3.58it/s]
 78%|███████▊  | 547/705 [02:29<00:43,  3.66it/s]
 78%|███████▊  | 548/705 [02:29<00:42,  3.71it/s]
 78%|███████▊  | 549/705 [02:29<00:41,  3.77it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.79it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.79it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.78it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.75it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.73it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.84it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.82it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.84it/s]
 80%|███████▉  | 561/705 [02:33<00:42,  3.37it/s]
 80%|███████▉  | 562/705 [02:33<00:39,  3.64it/s]
 80%|███████▉  | 563/705 [02:33<00:38,  3.70it/s]
 80%|████████  | 564/705 [02:33<00:35,  3.95it/s]
 80%|████████  | 565/705 [02:34<00:34,  4.03it/s]
 80%|████████  | 566/705 [02:34<00:35,  3.92it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.87it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.85it/s]
 81%|████████  | 569/705 [02:35<00:34,  3.93it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.93it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.92it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.85it/s]
 81%|████████▏ | 573/705 [02:36<00:34,  3.80it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.81it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.79it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:39<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:40<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:41<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.81it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:43<00:33,  3.13it/s]
 85%|████████▌ | 601/705 [02:43<00:29,  3.48it/s]
 85%|████████▌ | 602/705 [02:43<00:29,  3.54it/s]
 86%|████████▌ | 603/705 [02:44<00:28,  3.61it/s]
 86%|████████▌ | 604/705 [02:44<00:27,  3.66it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.71it/s]
 86%|████████▌ | 606/705 [02:45<00:26,  3.72it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  3.92it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.88it/s]
 86%|████████▋ | 609/705 [02:45<00:25,  3.83it/s]
 87%|████████▋ | 610/705 [02:46<00:24,  3.89it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.97it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.92it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 614/705 [02:47<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:48<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:23,  3.59it/s]
 88%|████████▊ | 621/705 [02:48<00:22,  3.69it/s]
 88%|████████▊ | 622/705 [02:49<00:22,  3.69it/s]
 88%|████████▊ | 623/705 [02:49<00:22,  3.72it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.76it/s]
 89%|████████▊ | 625/705 [02:49<00:21,  3.76it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.77it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.76it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 629/705 [02:51<00:19,  3.80it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:52<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.85it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:53<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:54<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.77it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:57<00:14,  3.77it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.80it/s]
 93%|█████████▎| 656/705 [02:58<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:59<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.90it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.83it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.83it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:02<00:08,  3.79it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.78it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.90it/s]
 96%|█████████▌| 675/705 [03:03<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:04<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:06<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:08<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:09<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6727696657180786, 'eval_accuracy': 0.7252, 'eval_f1': 0.7232036156954051, 'eval_runtime': 1.7316, 'eval_samples_per_second': 1443.784, 'eval_steps_per_second': 180.762, 'epoch': 2.0}
{'loss': 0.4172, 'learning_rate': 2.4014573510434244e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.85it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.11it/s]

 20%|██        | 63/313 [00:00<00:01, 202.54it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.95it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.15it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.62it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.20it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.32it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.34it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.49it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 168.04it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 165.00it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.35it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.63it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 179.06it/s]

100%|██████████| 313/313 [00:01<00:00, 175.86it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.86it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.64it/s]
[I 2023-10-26 23:03:26,539] Trial 22 finished with value: 0.7303298984454403 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 3.912141264809884e-05, 'per_device_train_batch_size': 128, 'weight_decay': 5.220051265759252e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6969540119171143, 'eval_accuracy': 0.73, 'eval_f1': 0.7303298984454403, 'eval_runtime': 1.7344, 'eval_samples_per_second': 1441.456, 'eval_steps_per_second': 180.47, 'epoch': 3.0}
{'train_runtime': 193.653, 'train_samples_per_second': 464.749, 'train_steps_per_second': 3.641, 'train_loss': 0.5991300109430407, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:13,  3.64it/s]
  0%|          | 2/705 [00:00<03:10,  3.68it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<02:59,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.76it/s]
  7%|▋         | 48/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.77it/s]
  7%|▋         | 50/705 [00:13<02:54,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<03:02,  3.53it/s]
  9%|▉         | 63/705 [00:16<02:58,  3.59it/s]
  9%|▉         | 64/705 [00:16<02:55,  3.66it/s]
  9%|▉         | 65/705 [00:17<02:54,  3.67it/s]
  9%|▉         | 66/705 [00:17<02:53,  3.69it/s]
 10%|▉         | 67/705 [00:17<02:52,  3.69it/s]
 10%|▉         | 68/705 [00:18<02:49,  3.76it/s]
 10%|▉         | 69/705 [00:18<02:46,  3.82it/s]
 10%|▉         | 70/705 [00:18<02:45,  3.83it/s]
 10%|█         | 71/705 [00:18<02:46,  3.81it/s]
 10%|█         | 72/705 [00:19<02:42,  3.91it/s]
 10%|█         | 73/705 [00:19<02:43,  3.87it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:46,  3.78it/s]
 11%|█         | 77/705 [00:20<02:46,  3.77it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<03:12,  3.24it/s]
 12%|█▏        | 82/705 [00:21<03:05,  3.37it/s]
 12%|█▏        | 83/705 [00:22<02:57,  3.50it/s]
 12%|█▏        | 84/705 [00:22<02:50,  3.63it/s]
 12%|█▏        | 85/705 [00:22<02:48,  3.67it/s]
 12%|█▏        | 86/705 [00:22<02:48,  3.68it/s]
 12%|█▏        | 87/705 [00:23<02:47,  3.70it/s]
 12%|█▏        | 88/705 [00:23<02:46,  3.72it/s]
 13%|█▎        | 89/705 [00:23<02:44,  3.74it/s]
 13%|█▎        | 90/705 [00:23<02:45,  3.73it/s]
 13%|█▎        | 91/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:25<02:42,  3.75it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:42,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:26<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<03:08,  3.20it/s]
 14%|█▍        | 101/705 [00:27<03:00,  3.35it/s]
 14%|█▍        | 102/705 [00:27<02:55,  3.44it/s]
 15%|█▍        | 103/705 [00:27<02:50,  3.54it/s]
 15%|█▍        | 104/705 [00:27<02:46,  3.61it/s]
 15%|█▍        | 105/705 [00:28<02:42,  3.70it/s]
 15%|█▌        | 106/705 [00:28<02:39,  3.76it/s]
 15%|█▌        | 107/705 [00:28<02:39,  3.74it/s]
 15%|█▌        | 108/705 [00:28<02:39,  3.75it/s]
 15%|█▌        | 109/705 [00:29<02:38,  3.76it/s]
 16%|█▌        | 110/705 [00:29<02:38,  3.76it/s]
 16%|█▌        | 111/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:30<02:34,  3.82it/s]
 16%|█▌        | 114/705 [00:30<02:35,  3.81it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.77it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:31<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:32<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:32<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:33<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.84it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:35<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:36<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:37<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:38<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:39<02:24,  3.87it/s]
 21%|██        | 148/705 [00:39<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:40<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:41<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:42<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:43<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:44<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.83it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:45<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:46<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:49<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:52<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:54<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:55<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:56<02:07,  3.88it/s]
 30%|███       | 213/705 [00:56<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:57<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [01:00<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:01<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7973, 'learning_rate': 5.302137110002265e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.35it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.42it/s]

 21%|██        | 66/313 [00:00<00:01, 205.78it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.12it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.36it/s]

 40%|████      | 126/313 [00:00<00:01, 185.02it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.76it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.61it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.81it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.94it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.15it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.94it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.72it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.61it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.72it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.72it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:08,  1.04s/it]
 34%|███▎      | 237/705 [01:05<06:17,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:06<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:07<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:08<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.71it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:09<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:10<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:11<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:12<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:13<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:14<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:15<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:16<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:17<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.79it/s]
 41%|████      | 287/705 [01:18<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.83it/s]
 41%|████▏     | 291/705 [01:19<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.88it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.92it/s]
 42%|████▏     | 298/705 [01:21<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:22<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:23<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<02:06,  3.10it/s]
 44%|████▍     | 313/705 [01:25<01:59,  3.27it/s]
 45%|████▍     | 314/705 [01:25<01:48,  3.60it/s]
 45%|████▍     | 315/705 [01:25<01:47,  3.64it/s]
 45%|████▍     | 316/705 [01:25<01:45,  3.68it/s]
 45%|████▍     | 317/705 [01:26<01:43,  3.75it/s]
 45%|████▌     | 318/705 [01:26<01:43,  3.74it/s]
 45%|████▌     | 319/705 [01:26<01:43,  3.73it/s]
 45%|████▌     | 320/705 [01:26<01:43,  3.71it/s]
 46%|████▌     | 321/705 [01:27<01:42,  3.75it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.76it/s]
 46%|████▌     | 323/705 [01:27<01:42,  3.73it/s]
 46%|████▌     | 324/705 [01:28<01:42,  3.73it/s]
 46%|████▌     | 325/705 [01:28<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:40,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:29<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:29<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:48,  3.44it/s]
 47%|████▋     | 332/705 [01:30<01:46,  3.52it/s]
 47%|████▋     | 333/705 [01:30<01:43,  3.58it/s]
 47%|████▋     | 334/705 [01:30<01:42,  3.63it/s]
 48%|████▊     | 335/705 [01:31<01:40,  3.69it/s]
 48%|████▊     | 336/705 [01:31<01:39,  3.72it/s]
 48%|████▊     | 337/705 [01:31<01:39,  3.72it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 339/705 [01:32<01:38,  3.73it/s]
 48%|████▊     | 340/705 [01:32<01:37,  3.72it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.72it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.87it/s]
 49%|████▊     | 343/705 [01:33<01:34,  3.84it/s]
 49%|████▉     | 344/705 [01:33<01:35,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:34<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:35<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:36<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:36<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:37<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:37<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:38<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:38<01:31,  3.73it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:39<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 369/705 [01:40<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:40<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:41<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:42<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:43<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:44<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.79it/s]
 55%|█████▌    | 388/705 [01:45<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:22,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.77it/s]
 56%|█████▌    | 392/705 [01:46<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:47<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:49<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:50<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:51<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:52<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.90it/s]
 59%|█████▉    | 419/705 [01:53<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:55<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:56<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:57<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.77it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:59<01:09,  3.76it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [02:00<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:01<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:05,  3.83it/s]
 64%|██████▍   | 453/705 [02:02<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 457/705 [02:03<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:05<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:06<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6683141589164734, 'eval_accuracy': 0.7052, 'eval_f1': 0.7048193009114859, 'eval_runtime': 1.7328, 'eval_samples_per_second': 1442.717, 'eval_steps_per_second': 180.628, 'epoch': 1.0}
{'loss': 0.534, 'learning_rate': 1.9000847314177288e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.93it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.88it/s]

 21%|██        | 65/313 [00:00<00:01, 205.05it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.38it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.57it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.20it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.82it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.64it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.11it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.97it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.85it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.95it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.04it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.47it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.77it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.77it/s]
 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:04,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:10<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:11<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:12<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:12<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:13<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.82it/s]
 69%|██████▉   | 489/705 [02:14<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:15<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:16<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:17<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:17<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:19<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.81it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.76it/s]
 74%|███████▎  | 519/705 [02:22<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:23<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:46,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:46,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:24<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.76it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:26<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:26<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:27<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:28<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.81it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.77it/s]
 77%|███████▋  | 546/705 [02:29<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.83it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.86it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.86it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:31<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.75it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:33<00:37,  3.85it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:34<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.94it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:35<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:36<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:41,  3.07it/s]
 82%|████████▏ | 579/705 [02:37<00:38,  3.23it/s]
 82%|████████▏ | 580/705 [02:38<00:37,  3.36it/s]
 82%|████████▏ | 581/705 [02:38<00:35,  3.51it/s]
 83%|████████▎ | 582/705 [02:38<00:34,  3.56it/s]
 83%|████████▎ | 583/705 [02:38<00:33,  3.60it/s]
 83%|████████▎ | 584/705 [02:39<00:32,  3.70it/s]
 83%|████████▎ | 585/705 [02:39<00:32,  3.72it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.74it/s]
 83%|████████▎ | 587/705 [02:40<00:31,  3.75it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.75it/s]
 84%|████████▎ | 589/705 [02:40<00:31,  3.74it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 591/705 [02:41<00:30,  3.71it/s]
 84%|████████▍ | 592/705 [02:41<00:29,  3.77it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.76it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 597/705 [02:42<00:29,  3.70it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.71it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.80it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.79it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.02it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.91it/s]
 86%|████████▌ | 603/705 [02:44<00:26,  3.87it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 606/705 [02:45<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:46<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 614/705 [02:47<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.85it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:48<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.92it/s]
 88%|████████▊ | 622/705 [02:49<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:52<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:53<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.77it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:54<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:57<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:58<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.80it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.81it/s]
 94%|█████████▎| 660/705 [02:59<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.85it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:03<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:04<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.76it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:07<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 694/705 [03:08<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:09<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.75it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.79it/s]
100%|██████████| 705/705 [03:10<00:00,  4.53it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.53it/s]{'eval_loss': 0.6855406165122986, 'eval_accuracy': 0.7168, 'eval_f1': 0.7146074484665857, 'eval_runtime': 1.7317, 'eval_samples_per_second': 1443.654, 'eval_steps_per_second': 180.746, 'epoch': 2.0}
{'loss': 0.3325, 'learning_rate': 0.0, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.65it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.75it/s]

 21%|██        | 65/313 [00:00<00:01, 204.68it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.16it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.44it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.15it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.91it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.70it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.30it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.07it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.96it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.02it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.17it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.80it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.95it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.95it/s]
100%|██████████| 705/705 [03:12<00:00,  4.53it/s]

                                                  
100%|██████████| 705/705 [03:12<00:00,  3.66it/s]
[I 2023-10-26 23:06:40,058] Trial 23 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7373828887939453, 'eval_accuracy': 0.7176, 'eval_f1': 0.7169485029346326, 'eval_runtime': 1.7315, 'eval_samples_per_second': 1443.837, 'eval_steps_per_second': 180.768, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:42,  3.95it/s]
  9%|▉         | 63/705 [00:16<02:45,  3.89it/s]
  9%|▉         | 64/705 [00:16<02:45,  3.88it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.82it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.86it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:38,  3.79it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.77it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.76it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:25,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.80it/s]
 24%|██▍       | 172/705 [00:45<02:21,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.84it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.77it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8133, 'learning_rate': 3.2910318767061685e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.74it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.68it/s]

 21%|██        | 65/313 [00:00<00:01, 204.72it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.07it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.20it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.83it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.39it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.26it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.94it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.79it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.69it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.85it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.15it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.75it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.81it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.81it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:06,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:15,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:00,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.79it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:16<02:01,  3.48it/s]
 40%|████      | 284/705 [01:17<01:56,  3.62it/s]
 40%|████      | 285/705 [01:17<01:54,  3.66it/s]
 41%|████      | 286/705 [01:17<01:53,  3.68it/s]
 41%|████      | 287/705 [01:17<01:52,  3.73it/s]
 41%|████      | 288/705 [01:18<01:52,  3.72it/s]
 41%|████      | 289/705 [01:18<01:49,  3.79it/s]
 41%|████      | 290/705 [01:18<01:48,  3.81it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.80it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.87it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.84it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.81it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:43,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.76it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.89it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 356/705 [01:35<01:32,  3.76it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:38,  3.51it/s]
 51%|█████     | 361/705 [01:37<01:36,  3.57it/s]
 51%|█████▏    | 362/705 [01:37<01:34,  3.62it/s]
 51%|█████▏    | 363/705 [01:37<01:33,  3.65it/s]
 52%|█████▏    | 364/705 [01:38<01:33,  3.67it/s]
 52%|█████▏    | 365/705 [01:38<01:32,  3.68it/s]
 52%|█████▏    | 366/705 [01:38<01:31,  3.71it/s]
 52%|█████▏    | 367/705 [01:38<01:29,  3.77it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:27,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.75it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:31,  3.57it/s]
 54%|█████▍    | 380/705 [01:42<01:29,  3.64it/s]
 54%|█████▍    | 381/705 [01:42<01:28,  3.68it/s]
 54%|█████▍    | 382/705 [01:42<01:27,  3.71it/s]
 54%|█████▍    | 383/705 [01:43<01:25,  3.77it/s]
 54%|█████▍    | 384/705 [01:43<01:25,  3.74it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.73it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.78it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.77it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.74it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:47<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.82it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:57<01:11,  3.74it/s]
 62%|██████▏   | 440/705 [01:58<01:11,  3.73it/s]
 63%|██████▎   | 441/705 [01:58<01:11,  3.72it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.73it/s]
 63%|██████▎   | 443/705 [01:59<01:09,  3.79it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.76it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.83it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.76it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.72it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.75it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:05<00:51,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:51,  4.52it/s]{'eval_loss': 0.6761783957481384, 'eval_accuracy': 0.7024, 'eval_f1': 0.6994756909957616, 'eval_runtime': 1.7335, 'eval_samples_per_second': 1442.151, 'eval_steps_per_second': 180.557, 'epoch': 1.0}
{'loss': 0.5677, 'learning_rate': 1.1857447994793167e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.69it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.84it/s]

 21%|██        | 65/313 [00:00<00:01, 204.81it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.25it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.50it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.19it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.76it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.58it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.07it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.09it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.14it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.34it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.38it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.88it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.12it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.12it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:08<04:04,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.23it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:13<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:18<00:51,  3.81it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.80it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.76it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:46,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:23<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.76it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.80it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.84it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.76it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.74it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:27<00:42,  3.81it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:28<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.86it/s]
 78%|███████▊  | 550/705 [02:29<00:40,  3.86it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:30<00:40,  3.75it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 558/705 [02:31<00:38,  3.84it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.84it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:32<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:33<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.94it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:35<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:36<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.77it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.80it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:38<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:39<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:39<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.73it/s]
 84%|████████▍ | 592/705 [02:40<00:29,  3.79it/s]
 84%|████████▍ | 593/705 [02:40<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.75it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.81it/s]
 85%|████████▍ | 596/705 [02:41<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:42<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:42<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.94it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.89it/s]
 86%|████████▌ | 604/705 [02:43<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:44<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:45<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:46<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.93it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:47<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:47<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:48<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:48<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:49<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:50<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:51<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.78it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.77it/s]
 91%|█████████ | 639/705 [02:52<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:53<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:54<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:55<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:56<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:57<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.81it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:58<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [02:59<00:10,  3.90it/s]
 94%|█████████▍| 666/705 [02:59<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:00<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:01<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:02<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:03<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:04<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:05<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.78it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:07<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:09<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:09<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6748281121253967, 'eval_accuracy': 0.7244, 'eval_f1': 0.721705481219827, 'eval_runtime': 1.7305, 'eval_samples_per_second': 1444.667, 'eval_steps_per_second': 180.872, 'epoch': 2.0}
{'loss': 0.4172, 'learning_rate': 2.3891117217622637e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.93it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.85it/s]

 21%|██        | 65/313 [00:00<00:01, 204.83it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.26it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.48it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.06it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.64it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.30it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.74it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.66it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.63it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.85it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.11it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.86it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.99it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.99it/s]
100%|██████████| 705/705 [03:11<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:12<00:00,  4.54it/s]
100%|██████████| 705/705 [03:12<00:00,  3.65it/s]
[I 2023-10-26 23:09:53,759] Trial 24 finished with value: 0.7221557010556365 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 3.8920293749485504e-05, 'per_device_train_batch_size': 128, 'weight_decay': 7.005198279315943e-06}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6966218948364258, 'eval_accuracy': 0.7224, 'eval_f1': 0.7221557010556365, 'eval_runtime': 1.7325, 'eval_samples_per_second': 1443.026, 'eval_steps_per_second': 180.667, 'epoch': 3.0}
{'train_runtime': 192.9147, 'train_samples_per_second': 466.528, 'train_steps_per_second': 3.654, 'train_loss': 0.599400546026568, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.69it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.76it/s]
  7%|▋         | 48/705 [00:12<02:54,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:19<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:42,  3.87it/s]
 11%|█         | 78/705 [00:20<02:40,  3.91it/s]
 11%|█         | 79/705 [00:20<02:42,  3.85it/s]
 11%|█▏        | 80/705 [00:21<02:43,  3.82it/s]
 11%|█▏        | 81/705 [00:21<02:44,  3.78it/s]
 12%|█▏        | 82/705 [00:21<02:45,  3.76it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.79it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:35,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.80it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.79it/s]
 16%|█▌        | 110/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:46,  3.55it/s]
 16%|█▌        | 113/705 [00:29<02:41,  3.67it/s]
 16%|█▌        | 114/705 [00:30<02:39,  3.70it/s]
 16%|█▋        | 115/705 [00:30<02:39,  3.70it/s]
 16%|█▋        | 116/705 [00:30<02:38,  3.72it/s]
 17%|█▋        | 117/705 [00:30<02:36,  3.75it/s]
 17%|█▋        | 118/705 [00:31<02:35,  3.78it/s]
 17%|█▋        | 119/705 [00:31<02:36,  3.75it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.78it/s]
 17%|█▋        | 121/705 [00:31<02:32,  3.83it/s]
 17%|█▋        | 122/705 [00:32<02:33,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:38<02:22,  3.91it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.83it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:29,  3.57it/s]
 24%|██▍       | 172/705 [00:45<02:27,  3.61it/s]
 25%|██▍       | 173/705 [00:45<02:26,  3.64it/s]
 25%|██▍       | 174/705 [00:45<02:24,  3.68it/s]
 25%|██▍       | 175/705 [00:46<02:18,  3.82it/s]
 25%|██▍       | 176/705 [00:46<02:18,  3.81it/s]
 25%|██▌       | 177/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 178/705 [00:46<02:20,  3.75it/s]
 25%|██▌       | 179/705 [00:47<02:17,  3.84it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.80it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:23,  3.59it/s]
 27%|██▋       | 191/705 [00:50<02:20,  3.65it/s]
 27%|██▋       | 192/705 [00:50<02:19,  3.68it/s]
 27%|██▋       | 193/705 [00:50<02:18,  3.70it/s]
 28%|██▊       | 194/705 [00:51<02:17,  3.73it/s]
 28%|██▊       | 195/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 196/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.82it/s]
 28%|██▊       | 198/705 [00:52<02:12,  3.83it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.86it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.80it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8264, 'learning_rate': 2.570666106741055e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.77it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.20it/s]

 20%|██        | 63/313 [00:00<00:01, 202.65it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.76it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.07it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.59it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.27it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.31it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.08it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.24it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 167.95it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 165.02it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.36it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.73it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 179.18it/s]

100%|██████████| 313/313 [00:01<00:00, 175.98it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.98it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:05,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:15,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:59,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.55it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.87it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:16<01:50,  3.83it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.84it/s]
 41%|████      | 290/705 [01:18<01:47,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.88it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.76it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.78it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.80it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.77it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.76it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:38,  3.75it/s]
 48%|████▊     | 335/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:49,  3.30it/s]
 49%|████▉     | 345/705 [01:33<01:43,  3.47it/s]
 49%|████▉     | 346/705 [01:33<01:40,  3.57it/s]
 49%|████▉     | 347/705 [01:33<01:38,  3.64it/s]
 49%|████▉     | 348/705 [01:34<01:37,  3.67it/s]
 50%|████▉     | 349/705 [01:34<01:34,  3.76it/s]
 50%|████▉     | 350/705 [01:34<01:34,  3.74it/s]
 50%|████▉     | 351/705 [01:34<01:34,  3.73it/s]
 50%|████▉     | 352/705 [01:35<01:33,  3.78it/s]
 50%|█████     | 353/705 [01:35<01:33,  3.78it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.75it/s]
 51%|█████▏    | 363/705 [01:38<01:44,  3.27it/s]
 52%|█████▏    | 364/705 [01:38<01:40,  3.38it/s]
 52%|█████▏    | 365/705 [01:38<01:37,  3.48it/s]
 52%|█████▏    | 366/705 [01:38<01:35,  3.56it/s]
 52%|█████▏    | 367/705 [01:39<01:32,  3.66it/s]
 52%|█████▏    | 368/705 [01:39<01:31,  3.70it/s]
 52%|█████▏    | 369/705 [01:39<01:30,  3.72it/s]
 52%|█████▏    | 370/705 [01:40<01:29,  3.76it/s]
 53%|█████▎    | 371/705 [01:40<01:27,  3.82it/s]
 53%|█████▎    | 372/705 [01:40<01:28,  3.78it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.78it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.75it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:22,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.77it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6892269849777222, 'eval_accuracy': 0.6972, 'eval_f1': 0.6961325427795154, 'eval_runtime': 1.7346, 'eval_samples_per_second': 1441.246, 'eval_steps_per_second': 180.444, 'epoch': 1.0}
{'loss': 0.5916, 'learning_rate': 9.311737862025194e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.65it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.69it/s]

 21%|██        | 65/313 [00:00<00:01, 204.61it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.87it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.19it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.96it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.66it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.43it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.02it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.89it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.80it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.90it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.97it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.54it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.62it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.62it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:07<01:03,  3.68it/s]
[I 2023-10-26 23:12:02,391] Trial 25 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6776857972145081, 'eval_accuracy': 0.7148, 'eval_f1': 0.7123256076868314, 'eval_runtime': 1.7336, 'eval_samples_per_second': 1442.063, 'eval_steps_per_second': 180.546, 'epoch': 2.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.79it/s]
  2%|▏         | 13/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.76it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:54,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.79it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:42,  3.95it/s]
  9%|▉         | 63/705 [00:16<02:45,  3.89it/s]
  9%|▉         | 64/705 [00:16<02:45,  3.88it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.82it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:44,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.84it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:45,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.79it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.86it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.79it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8209, 'learning_rate': 2.847591255157561e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.61it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.73it/s]

 21%|██        | 66/313 [00:00<00:01, 205.98it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.30it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.66it/s]

 40%|████      | 126/313 [00:00<00:01, 185.45it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.31it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.22it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.02it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.15it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.53it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.32it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.84it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.58it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.57it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.57it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:04,  1.03s/it]
 34%|███▎      | 237/705 [01:04<06:14,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:59,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:05,  1.90it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:44,  2.81it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.94it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.86it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:16<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.83it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.88it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.86it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:21<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:22<01:43,  3.84it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.88it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:57,  3.25it/s]
 46%|████▌     | 325/705 [01:27<01:51,  3.41it/s]
 46%|████▌     | 326/705 [01:28<01:47,  3.53it/s]
 46%|████▋     | 327/705 [01:28<01:45,  3.58it/s]
 47%|████▋     | 328/705 [01:28<01:44,  3.61it/s]
 47%|████▋     | 329/705 [01:28<01:41,  3.71it/s]
 47%|████▋     | 330/705 [01:29<01:40,  3.71it/s]
 47%|████▋     | 331/705 [01:29<01:40,  3.73it/s]
 47%|████▋     | 332/705 [01:29<01:40,  3.72it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.73it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.73it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.76it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.77it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.74it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:34,  3.60it/s]
 52%|█████▏    | 364/705 [01:38<01:33,  3.63it/s]
 52%|█████▏    | 365/705 [01:38<01:32,  3.66it/s]
 52%|█████▏    | 366/705 [01:38<01:31,  3.69it/s]
 52%|█████▏    | 367/705 [01:38<01:30,  3.75it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.76it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:33,  3.45it/s]
 54%|█████▍    | 383/705 [01:43<01:30,  3.58it/s]
 54%|█████▍    | 384/705 [01:43<01:28,  3.61it/s]
 55%|█████▍    | 385/705 [01:43<01:28,  3.63it/s]
 55%|█████▍    | 386/705 [01:44<01:26,  3.71it/s]
 55%|█████▍    | 387/705 [01:44<01:25,  3.72it/s]
 55%|█████▌    | 388/705 [01:44<01:25,  3.71it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.77it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.77it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.74it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.78it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.76it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.82it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.84it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.77it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.84it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6763812303543091, 'eval_accuracy': 0.7048, 'eval_f1': 0.7048823913861489, 'eval_runtime': 1.7309, 'eval_samples_per_second': 1444.325, 'eval_steps_per_second': 180.829, 'epoch': 1.0}
{'loss': 0.5794, 'learning_rate': 1.0259750279979806e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.94it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.69it/s]

 21%|██        | 65/313 [00:00<00:01, 204.59it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.02it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.27it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.90it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.47it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.26it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.83it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.91it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.00it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.18it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.02it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 185.02it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 178.41it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.41it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:07<01:03,  3.68it/s]
[I 2023-10-26 23:14:10,868] Trial 26 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6782585978507996, 'eval_accuracy': 0.7156, 'eval_f1': 0.7122809315300063, 'eval_runtime': 1.7328, 'eval_samples_per_second': 1442.786, 'eval_steps_per_second': 180.637, 'epoch': 2.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:51,  3.81it/s]
  7%|▋         | 52/705 [00:13<02:52,  3.79it/s]
  8%|▊         | 53/705 [00:13<02:48,  3.88it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.87it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:49,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.78it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:23,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:11,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.88it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.80it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.77it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.81it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.77it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:02,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]{'loss': 0.8089, 'learning_rate': 4.055545325388284e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.84it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.77it/s]

 21%|██        | 65/313 [00:00<00:01, 204.90it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.15it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.34it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.94it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.57it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.36it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.06it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.90it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.82it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.90it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.91it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 184.88it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 178.29it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.29it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.60it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:04,  1.03s/it]
 34%|███▎      | 237/705 [01:04<06:14,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:59,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:05,  1.90it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.81it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.71it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.93it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.06it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.87it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.80it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:16<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.77it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:21<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:51,  3.60it/s]
 43%|████▎     | 305/705 [01:22<01:47,  3.73it/s]
 43%|████▎     | 306/705 [01:22<01:46,  3.74it/s]
 44%|████▎     | 307/705 [01:23<01:46,  3.72it/s]
 44%|████▎     | 308/705 [01:23<01:46,  3.71it/s]
 44%|████▍     | 309/705 [01:23<01:45,  3.76it/s]
 44%|████▍     | 310/705 [01:23<01:45,  3.74it/s]
 44%|████▍     | 311/705 [01:24<01:45,  3.75it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.75it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.75it/s]
 45%|████▍     | 314/705 [01:24<01:37,  3.99it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.91it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:25<01:41,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:49,  3.31it/s]
 49%|████▉     | 344/705 [01:32<01:45,  3.42it/s]
 49%|████▉     | 345/705 [01:33<01:40,  3.57it/s]
 49%|████▉     | 346/705 [01:33<01:38,  3.64it/s]
 49%|████▉     | 347/705 [01:33<01:36,  3.69it/s]
 49%|████▉     | 348/705 [01:33<01:36,  3.71it/s]
 50%|████▉     | 349/705 [01:34<01:34,  3.79it/s]
 50%|████▉     | 350/705 [01:34<01:34,  3.76it/s]
 50%|████▉     | 351/705 [01:34<01:34,  3.74it/s]
 50%|████▉     | 352/705 [01:35<01:33,  3.79it/s]
 50%|█████     | 353/705 [01:35<01:33,  3.78it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.71it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.73it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.74it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:38,  3.49it/s]
 51%|█████▏    | 363/705 [01:38<01:36,  3.56it/s]
 52%|█████▏    | 364/705 [01:38<01:34,  3.60it/s]
 52%|█████▏    | 365/705 [01:38<01:33,  3.63it/s]
 52%|█████▏    | 366/705 [01:38<01:32,  3.67it/s]
 52%|█████▏    | 367/705 [01:39<01:30,  3.74it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.75it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.76it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:26,  3.73it/s]
 54%|█████▍    | 382/705 [01:43<01:26,  3.74it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.80it/s]
 54%|█████▍    | 384/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.74it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.79it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.77it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.80it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.75it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.84it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.86it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.87it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.84it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.83it/s]
 65%|██████▍   | 457/705 [02:02<01:05,  3.81it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]{'eval_loss': 0.6650069355964661, 'eval_accuracy': 0.7028, 'eval_f1': 0.6964877634146409, 'eval_runtime': 1.7332, 'eval_samples_per_second': 1442.383, 'eval_steps_per_second': 180.586, 'epoch': 1.0}
{'loss': 0.5494, 'learning_rate': 1.4611957461331986e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.77it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.70it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.94it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.19it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.92it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.56it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.23it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.52it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.50it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.50it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.65it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.77it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.40it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.57it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.57it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:03,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.89it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:04,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:57,  3.33it/s]
 73%|███████▎  | 514/705 [02:20<00:55,  3.44it/s]
 73%|███████▎  | 515/705 [02:20<00:53,  3.53it/s]
 73%|███████▎  | 516/705 [02:21<00:52,  3.59it/s]
 73%|███████▎  | 517/705 [02:21<00:51,  3.64it/s]
 73%|███████▎  | 518/705 [02:21<00:50,  3.67it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.72it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.80it/s]
 74%|███████▍  | 521/705 [02:22<00:48,  3.81it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.81it/s]
 74%|███████▍  | 524/705 [02:23<00:47,  3.84it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.82it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.75it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:50,  3.41it/s]
 76%|███████▌  | 533/705 [02:25<00:48,  3.52it/s]
 76%|███████▌  | 534/705 [02:25<00:47,  3.58it/s]
 76%|███████▌  | 535/705 [02:26<00:46,  3.69it/s]
 76%|███████▌  | 536/705 [02:26<00:45,  3.69it/s]
 76%|███████▌  | 537/705 [02:26<00:45,  3.71it/s]
 76%|███████▋  | 538/705 [02:26<00:45,  3.70it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.70it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.75it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.76it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.83it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.79it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:29<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:30<00:49,  3.09it/s]
 78%|███████▊  | 552/705 [02:30<00:46,  3.26it/s]
 78%|███████▊  | 553/705 [02:31<00:45,  3.38it/s]
 79%|███████▊  | 554/705 [02:31<00:43,  3.47it/s]
 79%|███████▊  | 555/705 [02:31<00:42,  3.53it/s]
 79%|███████▉  | 556/705 [02:31<00:40,  3.70it/s]
 79%|███████▉  | 557/705 [02:32<00:39,  3.72it/s]
 79%|███████▉  | 558/705 [02:32<00:39,  3.76it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.76it/s]
 79%|███████▉  | 560/705 [02:32<00:38,  3.80it/s]
 80%|███████▉  | 561/705 [02:33<00:37,  3.83it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.01it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.95it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.15it/s]
 80%|████████  | 565/705 [02:34<00:33,  4.17it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:35<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:37,  3.59it/s]
 81%|████████  | 572/705 [02:35<00:36,  3.62it/s]
 81%|████████▏ | 573/705 [02:36<00:36,  3.64it/s]
 81%|████████▏ | 574/705 [02:36<00:35,  3.67it/s]
 82%|████████▏ | 575/705 [02:36<00:35,  3.70it/s]
 82%|████████▏ | 576/705 [02:37<00:34,  3.78it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.77it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.77it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 580/705 [02:38<00:33,  3.73it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.78it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.75it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:40<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:41<00:38,  2.98it/s]
 84%|████████▍ | 591/705 [02:41<00:36,  3.16it/s]
 84%|████████▍ | 592/705 [02:41<00:33,  3.36it/s]
 84%|████████▍ | 593/705 [02:41<00:32,  3.46it/s]
 84%|████████▍ | 594/705 [02:42<00:31,  3.53it/s]
 84%|████████▍ | 595/705 [02:42<00:30,  3.65it/s]
 85%|████████▍ | 596/705 [02:42<00:29,  3.68it/s]
 85%|████████▍ | 597/705 [02:42<00:29,  3.71it/s]
 85%|████████▍ | 598/705 [02:43<00:28,  3.71it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.81it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.80it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.03it/s]
 85%|████████▌ | 602/705 [02:44<00:26,  3.92it/s]
 86%|████████▌ | 603/705 [02:44<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 606/705 [02:45<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:46<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 614/705 [02:47<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.85it/s]
 87%|████████▋ | 616/705 [02:47<00:23,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:48<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.92it/s]
 88%|████████▊ | 622/705 [02:49<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:50<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.82it/s]
 89%|████████▉ | 629/705 [02:51<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:52<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.85it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:53<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.77it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:54<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:55<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:56<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:57<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.83it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:58<00:12,  3.78it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.80it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.81it/s]
 94%|█████████▎| 660/705 [02:59<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.81it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [03:00<00:11,  3.77it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.85it/s]
 95%|█████████▍| 667/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:02<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:03<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:04<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.74it/s]
 97%|█████████▋| 682/705 [03:05<00:06,  3.74it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.75it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:06<00:05,  3.73it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.76it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:07<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:08<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:09<00:01,  3.86it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:10<00:01,  3.78it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.75it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6752833724021912, 'eval_accuracy': 0.7248, 'eval_f1': 0.7218324801277506, 'eval_runtime': 1.735, 'eval_samples_per_second': 1440.938, 'eval_steps_per_second': 180.405, 'epoch': 2.0}
{'loss': 0.3778, 'learning_rate': 2.9441072703071764e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.78it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.76it/s]

 21%|██        | 65/313 [00:00<00:01, 204.65it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.98it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.18it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.87it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.52it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.35it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.07it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.92it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.80it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.96it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.12it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.73it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.07it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.07it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.64it/s]
[I 2023-10-26 23:17:25,372] Trial 27 finished with value: 0.7279764491878725 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 4.7961557739891005e-05, 'per_device_train_batch_size': 128, 'weight_decay': 0.0001638040864204698}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7147634029388428, 'eval_accuracy': 0.7284, 'eval_f1': 0.7279764491878725, 'eval_runtime': 1.7321, 'eval_samples_per_second': 1443.368, 'eval_steps_per_second': 180.71, 'epoch': 3.0}
{'train_runtime': 193.7677, 'train_samples_per_second': 464.474, 'train_steps_per_second': 3.638, 'train_loss': 0.5787245513699579, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:11,  3.68it/s]
  0%|          | 2/705 [00:00<03:11,  3.68it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.76it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:51,  3.81it/s]
  7%|▋         | 52/705 [00:13<02:52,  3.78it/s]
  8%|▊         | 53/705 [00:13<02:48,  3.87it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.86it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.89it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<03:19,  3.17it/s]
 10%|█         | 74/705 [00:19<03:09,  3.33it/s]
 11%|█         | 75/705 [00:19<03:02,  3.44it/s]
 11%|█         | 76/705 [00:20<02:58,  3.52it/s]
 11%|█         | 77/705 [00:20<02:55,  3.59it/s]
 11%|█         | 78/705 [00:20<02:49,  3.70it/s]
 11%|█         | 79/705 [00:20<02:49,  3.70it/s]
 11%|█▏        | 80/705 [00:21<02:48,  3.72it/s]
 11%|█▏        | 81/705 [00:21<02:48,  3.71it/s]
 12%|█▏        | 82/705 [00:21<02:48,  3.70it/s]
 12%|█▏        | 83/705 [00:22<02:45,  3.75it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 85/705 [00:22<02:43,  3.80it/s]
 12%|█▏        | 86/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 87/705 [00:23<02:44,  3.76it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:24<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:57,  3.46it/s]
 13%|█▎        | 93/705 [00:24<02:53,  3.53it/s]
 13%|█▎        | 94/705 [00:25<02:50,  3.59it/s]
 13%|█▎        | 95/705 [00:25<02:47,  3.64it/s]
 14%|█▎        | 96/705 [00:25<02:45,  3.68it/s]
 14%|█▍        | 97/705 [00:25<02:45,  3.68it/s]
 14%|█▍        | 98/705 [00:26<02:43,  3.71it/s]
 14%|█▍        | 99/705 [00:26<02:43,  3.71it/s]
 14%|█▍        | 100/705 [00:26<02:42,  3.72it/s]
 14%|█▍        | 101/705 [00:26<02:42,  3.72it/s]
 14%|█▍        | 102/705 [00:27<02:42,  3.71it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:28<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:30<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:32<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 128/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:35<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:36<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:39<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:40<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:41<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:42<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.79it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:46<02:21,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:52<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:54<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:57<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8117, 'learning_rate': 4.075758576717743e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.00it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.58it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.93it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.12it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.76it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.36it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.10it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.50it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.58it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.84it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.17it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.31it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.84it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.80it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.80it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:07,  1.04s/it]
 34%|███▎      | 237/705 [01:05<06:17,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:06<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.94it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:10<01:56,  3.85it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:11<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:12<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:13<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:17<02:03,  3.43it/s]
 40%|████      | 284/705 [01:17<01:57,  3.58it/s]
 40%|████      | 285/705 [01:17<01:55,  3.63it/s]
 41%|████      | 286/705 [01:17<01:54,  3.66it/s]
 41%|████      | 287/705 [01:18<01:52,  3.71it/s]
 41%|████      | 288/705 [01:18<01:52,  3.70it/s]
 41%|████      | 289/705 [01:18<01:50,  3.78it/s]
 41%|████      | 290/705 [01:18<01:49,  3.80it/s]
 41%|████▏     | 291/705 [01:19<01:49,  3.79it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.87it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.84it/s]
 42%|████▏     | 294/705 [01:20<01:47,  3.81it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.78it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:21<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:22<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:23<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:25<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:26<01:40,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:27<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:28<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:29<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:30<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 336/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:32<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:33<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:36<01:33,  3.75it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:37<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:38,  3.51it/s]
 51%|█████     | 361/705 [01:37<01:36,  3.57it/s]
 51%|█████▏    | 362/705 [01:37<01:34,  3.62it/s]
 51%|█████▏    | 363/705 [01:38<01:33,  3.65it/s]
 52%|█████▏    | 364/705 [01:38<01:33,  3.66it/s]
 52%|█████▏    | 365/705 [01:38<01:32,  3.68it/s]
 52%|█████▏    | 366/705 [01:39<01:31,  3.71it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:40<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.75it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 379/705 [01:42<01:33,  3.47it/s]
 54%|█████▍    | 380/705 [01:42<01:30,  3.57it/s]
 54%|█████▍    | 381/705 [01:43<01:29,  3.63it/s]
 54%|█████▍    | 382/705 [01:43<01:27,  3.67it/s]
 54%|█████▍    | 383/705 [01:43<01:25,  3.74it/s]
 54%|█████▍    | 384/705 [01:43<01:26,  3.73it/s]
 55%|█████▍    | 385/705 [01:44<01:26,  3.71it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.77it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.74it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.78it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:47<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:53<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.77it/s]
 62%|██████▏   | 435/705 [01:57<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:59<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.87it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.84it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:03<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6708019375801086, 'eval_accuracy': 0.7036, 'eval_f1': 0.6989002531302076, 'eval_runtime': 1.7338, 'eval_samples_per_second': 1441.943, 'eval_steps_per_second': 180.531, 'epoch': 1.0}
{'loss': 0.5559, 'learning_rate': 1.4684784946881786e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.55it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.60it/s]

 21%|██        | 65/313 [00:00<00:01, 204.61it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.01it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.29it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.97it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.67it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.52it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.04it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.92it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.87it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.97it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.05it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.65it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.69it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.69it/s]
 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:08<01:04,  3.67it/s]
[I 2023-10-26 23:19:34,172] Trial 28 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6757230758666992, 'eval_accuracy': 0.718, 'eval_f1': 0.7146348685954527, 'eval_runtime': 1.7332, 'eval_samples_per_second': 1442.445, 'eval_steps_per_second': 180.594, 'epoch': 2.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:10,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.85it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:52,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.84it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.77it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.74it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.79it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.80it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.79it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:30,  3.77it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.88it/s]
 20%|██        | 143/705 [00:37<02:27,  3.82it/s]
 20%|██        | 144/705 [00:37<02:25,  3.84it/s]
 21%|██        | 145/705 [00:38<02:27,  3.79it/s]
 21%|██        | 146/705 [00:38<02:28,  3.76it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7592, 'learning_rate': 9.470397463715269e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.77it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.56it/s]

 21%|██        | 65/313 [00:00<00:01, 204.50it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.15it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.29it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.85it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.45it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.32it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.05it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.00it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.94it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.10it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.36it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.93it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.19it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.19it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:10,  1.05s/it]
 34%|███▎      | 237/705 [01:04<06:18,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:02,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:07,  1.88it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:03,  2.53it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.03it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.73it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.82it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 295/705 [01:19<01:49,  3.76it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.80it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.91it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.86it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.90it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:44,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.80it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:46,  3.48it/s]
 47%|████▋     | 334/705 [01:30<01:44,  3.55it/s]
 48%|████▊     | 335/705 [01:30<01:41,  3.63it/s]
 48%|████▊     | 336/705 [01:30<01:40,  3.68it/s]
 48%|████▊     | 337/705 [01:31<01:39,  3.69it/s]
 48%|████▊     | 338/705 [01:31<01:38,  3.73it/s]
 48%|████▊     | 339/705 [01:31<01:38,  3.72it/s]
 48%|████▊     | 340/705 [01:31<01:38,  3.72it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.71it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.87it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:35<01:37,  3.62it/s]
 50%|█████     | 353/705 [01:35<01:35,  3.67it/s]
 50%|█████     | 354/705 [01:35<01:35,  3.68it/s]
 50%|█████     | 355/705 [01:35<01:35,  3.68it/s]
 50%|█████     | 356/705 [01:36<01:34,  3.71it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.70it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.70it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.72it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.74it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.73it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.73it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:28,  3.79it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.79it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:27,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:42<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.77it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:47<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 443/705 [01:58<01:08,  3.81it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]{'eval_loss': 0.6828030347824097, 'eval_accuracy': 0.6964, 'eval_f1': 0.6971488943307722, 'eval_runtime': 1.7315, 'eval_samples_per_second': 1443.855, 'eval_steps_per_second': 180.771, 'epoch': 1.0}
{'loss': 0.5194, 'learning_rate': 9.470397463715269e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.02it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.66it/s]

 21%|██        | 66/313 [00:00<00:01, 206.51it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.78it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.88it/s]

 40%|████      | 126/313 [00:00<00:01, 185.55it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.26it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.15it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.15it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.23it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.37it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.03it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.85it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.55it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.59it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.59it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:07<01:03,  3.68it/s]
[I 2023-10-26 23:21:42,602] Trial 29 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7432745099067688, 'eval_accuracy': 0.702, 'eval_f1': 0.6943837350703834, 'eval_runtime': 1.7306, 'eval_samples_per_second': 1444.611, 'eval_steps_per_second': 180.865, 'epoch': 2.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:48,  3.85it/s]
  8%|▊         | 58/705 [00:15<02:49,  3.81it/s]
  8%|▊         | 59/705 [00:15<02:51,  3.77it/s]
  9%|▊         | 60/705 [00:15<02:50,  3.78it/s]
  9%|▊         | 61/705 [00:16<02:49,  3.80it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.91it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.80it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.90it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.82it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.83it/s]
 30%|███       | 215/705 [00:56<02:09,  3.80it/s]
 31%|███       | 216/705 [00:56<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8193, 'learning_rate': 2.6815576983299477e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.93it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.93it/s]

 21%|██        | 65/313 [00:00<00:01, 204.77it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.10it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.39it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.12it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.82it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.55it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.05it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.90it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.96it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.22it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.43it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.04it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.08it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.08it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:05,  1.03s/it]
 34%|███▎      | 237/705 [01:04<06:15,  1.25it/s]
 34%|███▍      | 238/705 [01:05<04:59,  1.56it/s]
 34%|███▍      | 239/705 [01:05<04:05,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:29,  2.22it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.55it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.82it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.79it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.84it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.86it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.80it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:16<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:21<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:22<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.80it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:27<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.75it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.78it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:31<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:32<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.83it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:35<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:36<01:32,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.73it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:38<01:29,  3.78it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.78it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:39<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:40<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:41<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 381/705 [01:42<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:42<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.83it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:43<01:24,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.78it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 390/705 [01:45<01:41,  3.11it/s]
 55%|█████▌    | 391/705 [01:45<01:36,  3.27it/s]
 56%|█████▌    | 392/705 [01:45<01:31,  3.44it/s]
 56%|█████▌    | 393/705 [01:45<01:28,  3.52it/s]
 56%|█████▌    | 394/705 [01:46<01:25,  3.63it/s]
 56%|█████▌    | 395/705 [01:46<01:24,  3.66it/s]
 56%|█████▌    | 396/705 [01:46<01:24,  3.67it/s]
 56%|█████▋    | 397/705 [01:46<01:23,  3.69it/s]
 56%|█████▋    | 398/705 [01:47<01:22,  3.70it/s]
 57%|█████▋    | 399/705 [01:47<01:22,  3.73it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.73it/s]
 57%|█████▋    | 401/705 [01:47<01:19,  3.84it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.79it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.76it/s]
 57%|█████▋    | 404/705 [01:48<01:17,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.83it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.81it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.79it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.77it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.84it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.84it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]{'eval_loss': 0.6811266541481018, 'eval_accuracy': 0.7004, 'eval_f1': 0.7002088833886521, 'eval_runtime': 1.7311, 'eval_samples_per_second': 1444.151, 'eval_steps_per_second': 180.808, 'epoch': 1.0}
{'loss': 0.5818, 'learning_rate': 9.661538430556953e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.78it/s]

 14%|█▎        | 43/313 [00:00<00:01, 198.04it/s]

 21%|██        | 65/313 [00:00<00:01, 204.95it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.32it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.52it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.22it/s]

 46%|████▌     | 144/313 [00:00<00:00, 184.01it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.86it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.32it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.14it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.04it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.17it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.28it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.82it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.94it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.94it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:07<01:03,  3.68it/s]
[I 2023-10-26 23:23:51,049] Trial 30 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6762523651123047, 'eval_accuracy': 0.7172, 'eval_f1': 0.7141536826286307, 'eval_runtime': 1.7308, 'eval_samples_per_second': 1444.444, 'eval_steps_per_second': 180.844, 'epoch': 2.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.81it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:58,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:42,  3.95it/s]
  9%|▉         | 63/705 [00:16<02:45,  3.89it/s]
  9%|▉         | 64/705 [00:16<02:45,  3.88it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.82it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:35,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.80it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.89it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 130/705 [00:34<02:29,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.83it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:39<02:23,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.83it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.86it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.81it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:06,  3.85it/s]
 31%|███       | 217/705 [00:56<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:05,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.79it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]{'loss': 0.8141, 'learning_rate': 3.1842084516216045e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.23it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.58it/s]

 21%|██        | 66/313 [00:00<00:01, 205.87it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.11it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.50it/s]

 40%|████      | 126/313 [00:00<00:01, 185.25it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.12it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.09it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.29it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.40it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.53it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.22it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.82it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.58it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.52it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.52it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 23:24:55,080] Trial 31 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6735076904296875, 'eval_accuracy': 0.6972, 'eval_f1': 0.6941566002461635, 'eval_runtime': 1.7317, 'eval_samples_per_second': 1443.646, 'eval_steps_per_second': 180.745, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.71it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:08,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:52,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:54,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.79it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:52,  3.81it/s]
  7%|▋         | 50/705 [00:13<02:53,  3.78it/s]
  7%|▋         | 51/705 [00:13<02:52,  3.80it/s]
  7%|▋         | 52/705 [00:13<02:53,  3.77it/s]
  8%|▊         | 53/705 [00:13<02:48,  3.86it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.86it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.84it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.87it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:43,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:36,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.83it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:39<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:25,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.79it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.84it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:12,  3.84it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.86it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.84it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7971, 'learning_rate': 6.153066495439397e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.51it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.56it/s]

 21%|██        | 66/313 [00:00<00:01, 206.01it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.12it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.41it/s]

 40%|████      | 126/313 [00:00<00:01, 185.17it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.97it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.89it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.86it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.13it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.33it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.02it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.73it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.50it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.40it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.40it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:07,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:16,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:00,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.94it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:56,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:15<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:16<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:57,  3.57it/s]
 41%|████      | 288/705 [01:18<01:55,  3.61it/s]
 41%|████      | 289/705 [01:18<01:52,  3.71it/s]
 41%|████      | 290/705 [01:18<01:50,  3.75it/s]
 41%|████▏     | 291/705 [01:18<01:50,  3.76it/s]
 41%|████▏     | 292/705 [01:19<01:47,  3.84it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 294/705 [01:19<01:48,  3.80it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.81it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.80it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.91it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:44,  3.61it/s]
 46%|████▋     | 327/705 [01:28<01:43,  3.64it/s]
 47%|████▋     | 328/705 [01:28<01:43,  3.65it/s]
 47%|████▋     | 329/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 330/705 [01:29<01:40,  3.74it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.73it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.74it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.77it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:35,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.83it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.75it/s]
 50%|█████     | 356/705 [01:36<01:32,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.75it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.74it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:38<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:28,  3.79it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:39<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:27,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.75it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:24,  3.81it/s]
 54%|█████▍    | 382/705 [01:42<01:24,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:43<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.78it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:47<01:18,  3.86it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:48<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:49<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.83it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.81it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.81it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:53<01:14,  3.77it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:54<01:13,  3.75it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.79it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.84it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:58<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [01:59<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 462/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.75it/s]
 66%|██████▌   | 466/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.76it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.74it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:05<00:52,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:52,  4.52it/s]{'eval_loss': 0.6737310290336609, 'eval_accuracy': 0.7004, 'eval_f1': 0.7008578247071986, 'eval_runtime': 1.7333, 'eval_samples_per_second': 1442.338, 'eval_steps_per_second': 180.581, 'epoch': 1.0}
{'loss': 0.5298, 'learning_rate': 2.2169237099945272e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.85it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.66it/s]

 21%|██        | 65/313 [00:00<00:01, 204.63it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.02it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.25it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.93it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.57it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.41it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.79it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.67it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.62it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.75it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.73it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 184.82it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 178.29it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.29it/s]
 67%|██████▋   | 470/705 [02:07<00:52,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:08<04:03,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.89it/s]
 67%|██████▋   | 475/705 [02:09<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:10<01:10,  3.21it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.82it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:13<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:14<00:56,  3.76it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:15<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:16<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:18<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:19<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:20<00:50,  3.75it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.83it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:46,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.75it/s]
 75%|███████▍  | 528/705 [02:23<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:24<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.84it/s]
 76%|███████▌  | 536/705 [02:25<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.74it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:27<00:42,  3.81it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.77it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:28<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:29<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.80it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:30<00:40,  3.74it/s]
 79%|███████▊  | 555/705 [02:31<00:45,  3.29it/s]
 79%|███████▉  | 556/705 [02:31<00:42,  3.51it/s]
 79%|███████▉  | 557/705 [02:31<00:41,  3.59it/s]
 79%|███████▉  | 558/705 [02:31<00:40,  3.66it/s]
 79%|███████▉  | 559/705 [02:32<00:39,  3.69it/s]
 79%|███████▉  | 560/705 [02:32<00:38,  3.75it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.80it/s]
 80%|███████▉  | 562/705 [02:32<00:35,  3.98it/s]
 80%|███████▉  | 563/705 [02:33<00:36,  3.93it/s]
 80%|████████  | 564/705 [02:33<00:34,  4.14it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 566/705 [02:33<00:34,  4.01it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:34<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:35<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:36<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:38<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:39<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:39<00:30,  3.75it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:40<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:40<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:34,  3.24it/s]
 84%|████████▍ | 595/705 [02:41<00:32,  3.43it/s]
 85%|████████▍ | 596/705 [02:41<00:30,  3.52it/s]
 85%|████████▍ | 597/705 [02:42<00:30,  3.59it/s]
 85%|████████▍ | 598/705 [02:42<00:29,  3.63it/s]
 85%|████████▍ | 599/705 [02:42<00:28,  3.75it/s]
 85%|████████▌ | 600/705 [02:42<00:27,  3.76it/s]
 85%|████████▌ | 601/705 [02:43<00:26,  3.99it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.90it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.86it/s]
 86%|████████▌ | 604/705 [02:43<00:26,  3.83it/s]
 86%|████████▌ | 605/705 [02:44<00:26,  3.84it/s]
 86%|████████▌ | 606/705 [02:44<00:26,  3.80it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:44<00:24,  3.92it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:47<00:21,  3.96it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.92it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:48<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:49<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:50<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.81it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 646/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.78it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:55<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:56<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.80it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.81it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.77it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [02:59<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.83it/s]
 95%|█████████▍| 669/705 [03:00<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.79it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 673/705 [03:01<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:04<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:05<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:09<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6775581240653992, 'eval_accuracy': 0.72, 'eval_f1': 0.7181830161666749, 'eval_runtime': 1.7339, 'eval_samples_per_second': 1441.799, 'eval_steps_per_second': 180.513, 'epoch': 2.0}
{'loss': 0.3102, 'learning_rate': 4.466794561634506e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.54it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.65it/s]

 21%|██        | 65/313 [00:00<00:01, 204.57it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.89it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.18it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.86it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.65it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.39it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.80it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.74it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.73it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.91it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.05it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.61it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.76it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.76it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.65it/s]
[I 2023-10-26 23:28:08,853] Trial 32 finished with value: 0.7219469975828652 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 7.276719413070575e-05, 'per_device_train_batch_size': 128, 'weight_decay': 3.8786127055137866e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7559046745300293, 'eval_accuracy': 0.722, 'eval_f1': 0.7219469975828652, 'eval_runtime': 1.7336, 'eval_samples_per_second': 1442.126, 'eval_steps_per_second': 180.554, 'epoch': 3.0}
{'train_runtime': 193.0528, 'train_samples_per_second': 466.194, 'train_steps_per_second': 3.652, 'train_loss': 0.5456765032829123, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.80it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.81it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.77it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:51,  3.82it/s]
  7%|▋         | 52/705 [00:13<02:52,  3.79it/s]
  8%|▊         | 53/705 [00:13<02:48,  3.88it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.87it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.77it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.78it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.73it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.81it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:41,  3.41it/s]
 22%|██▏       | 155/705 [00:40<02:36,  3.51it/s]
 22%|██▏       | 156/705 [00:41<02:31,  3.62it/s]
 22%|██▏       | 157/705 [00:41<02:24,  3.78it/s]
 22%|██▏       | 158/705 [00:41<02:24,  3.77it/s]
 23%|██▎       | 159/705 [00:41<02:25,  3.75it/s]
 23%|██▎       | 160/705 [00:42<02:25,  3.74it/s]
 23%|██▎       | 161/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.74it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.75it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:21,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:19,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.76it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.84it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:07,  3.91it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8078, 'learning_rate': 4.088461137749333e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.69it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.72it/s]

 21%|██        | 66/313 [00:00<00:01, 205.93it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.16it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.43it/s]

 40%|████      | 126/313 [00:00<00:01, 185.13it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.89it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.83it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.80it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.00it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.40it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.24it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.86it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.56it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.58it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.58it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:07,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:17,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.71it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.93it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.86it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.80it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.83it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.74it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:33,  3.64it/s]
 52%|█████▏    | 366/705 [01:38<01:32,  3.68it/s]
 52%|█████▏    | 367/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.75it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.76it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:27,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.78it/s]
 53%|█████▎    | 374/705 [01:40<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.82it/s]
 54%|█████▍    | 381/705 [01:42<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:42<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.83it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:43<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.76it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:47<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:48<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.81it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.85it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:58<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [01:59<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]{'eval_loss': 0.6645672917366028, 'eval_accuracy': 0.706, 'eval_f1': 0.7013876427298699, 'eval_runtime': 1.7325, 'eval_samples_per_second': 1443.023, 'eval_steps_per_second': 180.667, 'epoch': 1.0}
{'loss': 0.5491, 'learning_rate': 1.4730551734465598e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.61it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.71it/s]

 21%|██        | 65/313 [00:00<00:01, 204.65it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.77it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.19it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.95it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.76it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.58it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.12it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.00it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.92it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.01it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.27it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.83it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.04it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.04it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:08<04:04,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:09<01:43,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:13<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:14<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:15<00:53,  3.88it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:18<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:19<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.75it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.83it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.82it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.75it/s]
 75%|███████▍  | 528/705 [02:23<00:47,  3.74it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.81it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.81it/s]
 75%|███████▌  | 532/705 [02:24<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:27<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.79it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:28<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:29<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.80it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:30<00:40,  3.75it/s]
 79%|███████▊  | 555/705 [02:31<00:41,  3.59it/s]
 79%|███████▉  | 556/705 [02:31<00:39,  3.74it/s]
 79%|███████▉  | 557/705 [02:31<00:39,  3.75it/s]
 79%|███████▉  | 558/705 [02:31<00:38,  3.78it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.77it/s]
 79%|███████▉  | 560/705 [02:32<00:38,  3.81it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.84it/s]
 80%|███████▉  | 562/705 [02:32<00:35,  4.02it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.96it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:33<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.94it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:34<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.93it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:35<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:36<00:33,  3.79it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:38<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:39<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:39<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:40<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:40<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.81it/s]
 85%|████████▍ | 596/705 [02:41<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:41<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:42<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:42<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:42<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.93it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:43<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:44<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:45<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.85it/s]
 87%|████████▋ | 616/705 [02:46<00:23,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:47<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:47<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:48<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:48<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:49<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:49<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:49<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:50<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:51<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:52<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:53<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:54<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:55<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.86it/s]
 93%|█████████▎| 654/705 [02:56<00:13,  3.83it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:57<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:58<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [02:59<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [02:59<00:10,  3.85it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:00<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:01<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:02<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.75it/s]
 97%|█████████▋| 681/705 [03:03<00:06,  3.74it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.74it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.75it/s]
 97%|█████████▋| 684/705 [03:04<00:05,  3.73it/s]
 97%|█████████▋| 685/705 [03:04<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.76it/s]
 98%|█████████▊| 688/705 [03:05<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:06<00:03,  3.82it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:07<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.86it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.83it/s]
 99%|█████████▉| 700/705 [03:08<00:01,  3.83it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:09<00:00,  3.75it/s]
100%|█████████▉| 704/705 [03:09<00:00,  3.79it/s]
100%|██████████| 705/705 [03:10<00:00,  4.53it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.53it/s]{'eval_loss': 0.6766915321350098, 'eval_accuracy': 0.722, 'eval_f1': 0.7183960161106067, 'eval_runtime': 1.7316, 'eval_samples_per_second': 1443.782, 'eval_steps_per_second': 180.762, 'epoch': 2.0}
{'loss': 0.3769, 'learning_rate': 2.968002375577872e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.58it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.88it/s]

 21%|██        | 65/313 [00:00<00:01, 204.81it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.20it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.46it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.11it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.74it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.60it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.21it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.01it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.93it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.08it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.25it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.83it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.13it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.13it/s]
100%|██████████| 705/705 [03:11<00:00,  4.53it/s]

                                                  
100%|██████████| 705/705 [03:11<00:00,  3.67it/s]
[I 2023-10-26 23:31:21,443] Trial 33 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7165464162826538, 'eval_accuracy': 0.722, 'eval_f1': 0.7214632244269048, 'eval_runtime': 1.7308, 'eval_samples_per_second': 1444.435, 'eval_steps_per_second': 180.843, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.71it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:08,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:52,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 64/705 [00:16<02:44,  3.89it/s]
  9%|▉         | 65/705 [00:17<02:47,  3.83it/s]
  9%|▉         | 66/705 [00:17<02:48,  3.79it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.76it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:45,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:36,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.76it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:32,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:30,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.84it/s]
 18%|█▊        | 128/705 [00:33<02:30,  3.84it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:30,  3.81it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:30,  3.77it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.76it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:25,  3.80it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.77it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.81it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.87it/s]
 23%|██▎       | 159/705 [00:41<02:23,  3.81it/s]
 23%|██▎       | 160/705 [00:42<02:24,  3.78it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.78it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:21,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:21,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.75it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.77it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.78it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.80it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:15,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.84it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.77it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:09,  3.76it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8388, 'learning_rate': 1.9393058106575336e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.13it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.38it/s]

 21%|██        | 66/313 [00:00<00:01, 205.84it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.02it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.40it/s]

 40%|████      | 126/313 [00:00<00:01, 185.08it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.91it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.94it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.04it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.29it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.35it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.01it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.71it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.62it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.44it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.44it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<07:59,  1.02s/it]
 34%|███▎      | 237/705 [01:04<06:11,  1.26it/s]
 34%|███▍      | 238/705 [01:05<04:57,  1.57it/s]
 34%|███▍      | 239/705 [01:05<04:04,  1.91it/s]
 34%|███▍      | 240/705 [01:05<03:28,  2.23it/s]
 34%|███▍      | 241/705 [01:05<03:01,  2.56it/s]
 34%|███▍      | 242/705 [01:06<02:44,  2.81it/s]
 34%|███▍      | 243/705 [01:06<02:31,  3.05it/s]
 35%|███▍      | 244/705 [01:06<02:20,  3.28it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.41it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.49it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.55it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:07<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.71it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.93it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:08<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:09<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<02:07,  3.32it/s]
 40%|███▉      | 281/705 [01:16<02:02,  3.45it/s]
 40%|████      | 282/705 [01:16<01:57,  3.59it/s]
 40%|████      | 283/705 [01:16<01:56,  3.63it/s]
 40%|████      | 284/705 [01:17<01:52,  3.73it/s]
 40%|████      | 285/705 [01:17<01:52,  3.73it/s]
 41%|████      | 286/705 [01:17<01:52,  3.73it/s]
 41%|████      | 287/705 [01:17<01:51,  3.76it/s]
 41%|████      | 288/705 [01:18<01:51,  3.74it/s]
 41%|████      | 289/705 [01:18<01:49,  3.81it/s]
 41%|████      | 290/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.81it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.88it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.84it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.81it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.78it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.88it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:45,  3.64it/s]
 45%|████▌     | 320/705 [01:26<01:45,  3.66it/s]
 46%|████▌     | 321/705 [01:26<01:43,  3.71it/s]
 46%|████▌     | 322/705 [01:27<01:42,  3.73it/s]
 46%|████▌     | 323/705 [01:27<01:42,  3.72it/s]
 46%|████▌     | 324/705 [01:27<01:42,  3.72it/s]
 46%|████▌     | 325/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 326/705 [01:28<01:40,  3.78it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.75it/s]
 47%|████▋     | 328/705 [01:28<01:41,  3.73it/s]
 47%|████▋     | 329/705 [01:28<01:39,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.77it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.77it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.89it/s]
 49%|████▊     | 343/705 [01:32<01:33,  3.86it/s]
 49%|████▉     | 344/705 [01:32<01:34,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.86it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.75it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.74it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:38<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:28,  3.79it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.79it/s]
 52%|█████▏    | 370/705 [01:39<01:27,  3.81it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.86it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.81it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:40<01:27,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.77it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:41<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:42<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:42<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:43<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:23,  3.79it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:22,  3.80it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:21,  3.77it/s]
 56%|█████▋    | 397/705 [01:46<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:47<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:48<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.90it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 439/705 [01:57<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:58<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.78it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [01:59<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.88it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:05<00:51,  4.53it/s]{'eval_loss': 0.6912168860435486, 'eval_accuracy': 0.7032, 'eval_f1': 0.7025434255070927, 'eval_runtime': 1.7331, 'eval_samples_per_second': 1442.467, 'eval_steps_per_second': 180.597, 'epoch': 1.0}
{'loss': 0.6175, 'learning_rate': 6.987236422300075e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.99it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.24it/s]

 20%|██        | 63/313 [00:00<00:01, 202.65it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.85it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.20it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.70it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.29it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.39it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.34it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.53it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 168.06it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.93it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.17it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.36it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 178.85it/s]

100%|█████████▉| 312/313 [00:01<00:00, 174.90it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 174.90it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.53it/s]

                                                  
 67%|██████▋   | 470/705 [02:07<01:03,  3.68it/s]
[I 2023-10-26 23:33:29,838] Trial 34 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6758553385734558, 'eval_accuracy': 0.7128, 'eval_f1': 0.7093650282476459, 'eval_runtime': 1.7349, 'eval_samples_per_second': 1440.978, 'eval_steps_per_second': 180.41, 'epoch': 2.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:04,  1.92it/s]
  1%|          | 2/354 [00:01<03:01,  1.94it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:54,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:55,  1.99it/s]
  2%|▏         | 6/354 [00:03<02:53,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.05it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.02it/s]
  3%|▎         | 9/354 [00:04<02:52,  2.00it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:50,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:51,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:51,  1.99it/s]
  4%|▍         | 14/354 [00:07<02:51,  1.98it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.98it/s]
  5%|▍         | 16/354 [00:08<02:50,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:50,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:46,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:46,  2.00it/s]
  6%|▌         | 22/354 [00:11<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:47,  1.98it/s]
  7%|▋         | 24/354 [00:12<02:46,  1.99it/s]
  7%|▋         | 25/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:46,  1.97it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.02it/s]
  8%|▊         | 28/354 [00:14<02:41,  2.01it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:43,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:16<02:40,  2.01it/s]
  9%|▉         | 33/354 [00:16<02:40,  2.00it/s]
 10%|▉         | 34/354 [00:17<02:41,  1.99it/s]
 10%|▉         | 35/354 [00:17<02:37,  2.02it/s]
 10%|█         | 36/354 [00:17<02:35,  2.05it/s]
 10%|█         | 37/354 [00:18<02:34,  2.05it/s]
 11%|█         | 38/354 [00:18<02:35,  2.03it/s]
 11%|█         | 39/354 [00:19<02:36,  2.02it/s]
 11%|█▏        | 40/354 [00:19<02:37,  2.00it/s]
 12%|█▏        | 41/354 [00:20<02:37,  1.99it/s]
 12%|█▏        | 42/354 [00:20<02:34,  2.03it/s]
 12%|█▏        | 43/354 [00:21<02:35,  2.01it/s]
 12%|█▏        | 44/354 [00:21<02:34,  2.00it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:22<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:23<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:26<02:32,  1.98it/s]
 15%|█▍        | 53/354 [00:26<02:28,  2.03it/s]
 15%|█▌        | 54/354 [00:26<02:29,  2.01it/s]
 16%|█▌        | 55/354 [00:27<02:29,  2.01it/s]
 16%|█▌        | 56/354 [00:27<02:29,  2.00it/s]
 16%|█▌        | 57/354 [00:28<02:26,  2.03it/s]
 16%|█▋        | 58/354 [00:28<02:27,  2.01it/s]
 17%|█▋        | 59/354 [00:29<02:24,  2.04it/s]
 17%|█▋        | 60/354 [00:29<02:26,  2.01it/s]
 17%|█▋        | 61/354 [00:30<02:25,  2.01it/s]
 18%|█▊        | 62/354 [00:30<02:23,  2.04it/s]
 18%|█▊        | 63/354 [00:31<02:21,  2.06it/s]
 18%|█▊        | 64/354 [00:31<02:19,  2.07it/s]
 18%|█▊        | 65/354 [00:32<02:20,  2.06it/s]
 19%|█▊        | 66/354 [00:32<02:20,  2.05it/s]
 19%|█▉        | 67/354 [00:33<02:20,  2.04it/s]
 19%|█▉        | 68/354 [00:33<02:20,  2.03it/s]
 19%|█▉        | 69/354 [00:34<02:18,  2.05it/s]
 20%|█▉        | 70/354 [00:34<02:20,  2.02it/s]
 20%|██        | 71/354 [00:35<02:21,  2.01it/s]
 20%|██        | 72/354 [00:35<02:21,  1.99it/s]
 21%|██        | 73/354 [00:36<02:21,  1.98it/s]
 21%|██        | 74/354 [00:36<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.02it/s]
 21%|██▏       | 76/354 [00:37<02:15,  2.05it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:38<02:17,  2.01it/s]
 22%|██▏       | 79/354 [00:39<02:16,  2.01it/s]
 23%|██▎       | 80/354 [00:39<02:17,  1.99it/s]
 23%|██▎       | 81/354 [00:40<02:17,  1.99it/s]
 23%|██▎       | 82/354 [00:40<02:16,  1.99it/s]
 23%|██▎       | 83/354 [00:41<02:14,  2.01it/s]
 24%|██▎       | 84/354 [00:41<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:13,  2.02it/s]
 24%|██▍       | 86/354 [00:42<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  1.99it/s]
 25%|██▍       | 88/354 [00:43<02:12,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:44<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.98it/s]
 26%|██▌       | 92/354 [00:45<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.01it/s]
 27%|██▋       | 94/354 [00:46<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 96/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:48<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.10it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:04,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  1.99it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  1.99it/s]
 31%|███       | 109/354 [00:54<02:03,  1.98it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:59,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.8168, 'learning_rate': 6.290303423704617e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.84it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.83it/s]

 21%|██        | 65/313 [00:00<00:01, 204.73it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.19it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.36it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.00it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.64it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.38it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.02it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.04it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.90it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.05it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.09it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.50it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.84it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.84it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 34%|███▎      | 119/354 [01:01<04:45,  1.22s/it]
 34%|███▍      | 120/354 [01:01<03:54,  1.00s/it]
 34%|███▍      | 121/354 [01:02<03:19,  1.17it/s]
 34%|███▍      | 122/354 [01:03<02:54,  1.33it/s]
 35%|███▍      | 123/354 [01:03<02:36,  1.48it/s]
 35%|███▌      | 124/354 [01:04<02:24,  1.60it/s]
 35%|███▌      | 125/354 [01:04<02:13,  1.72it/s]
 36%|███▌      | 126/354 [01:05<02:07,  1.78it/s]
 36%|███▌      | 127/354 [01:05<02:01,  1.87it/s]
 36%|███▌      | 128/354 [01:05<01:59,  1.90it/s]
 36%|███▋      | 129/354 [01:06<01:57,  1.91it/s]
 37%|███▋      | 130/354 [01:06<01:55,  1.94it/s]
 37%|███▋      | 131/354 [01:07<01:54,  1.95it/s]
 37%|███▋      | 132/354 [01:08<01:53,  1.95it/s]
 38%|███▊      | 133/354 [01:08<01:52,  1.97it/s]
 38%|███▊      | 134/354 [01:09<01:51,  1.97it/s]
 38%|███▊      | 135/354 [01:09<01:51,  1.97it/s]
 38%|███▊      | 136/354 [01:10<01:48,  2.00it/s]
 39%|███▊      | 137/354 [01:10<01:46,  2.03it/s]
 39%|███▉      | 138/354 [01:10<01:47,  2.02it/s]
 39%|███▉      | 139/354 [01:11<01:44,  2.06it/s]
 40%|███▉      | 140/354 [01:11<01:45,  2.02it/s]
 40%|███▉      | 141/354 [01:12<01:45,  2.02it/s]
 40%|████      | 142/354 [01:12<01:45,  2.01it/s]
 40%|████      | 143/354 [01:13<01:45,  2.01it/s]
 41%|████      | 144/354 [01:13<01:45,  2.00it/s]
 41%|████      | 145/354 [01:14<01:45,  1.99it/s]
 41%|████      | 146/354 [01:14<01:44,  1.99it/s]
 42%|████▏     | 147/354 [01:15<01:42,  2.01it/s]
 42%|████▏     | 148/354 [01:15<01:42,  2.00it/s]
 42%|████▏     | 149/354 [01:16<01:40,  2.04it/s]
 42%|████▏     | 150/354 [01:16<01:40,  2.03it/s]
 43%|████▎     | 151/354 [01:17<01:38,  2.05it/s]
 43%|████▎     | 152/354 [01:17<01:39,  2.03it/s]
 43%|████▎     | 153/354 [01:18<01:40,  2.00it/s]
 44%|████▎     | 154/354 [01:18<01:40,  1.99it/s]
 44%|████▍     | 155/354 [01:19<01:40,  1.98it/s]
 44%|████▍     | 156/354 [01:19<01:40,  1.97it/s]
 44%|████▍     | 157/354 [01:20<01:39,  1.98it/s]
 45%|████▍     | 158/354 [01:20<01:38,  1.98it/s]
 45%|████▍     | 159/354 [01:21<01:37,  1.99it/s]
 45%|████▌     | 160/354 [01:21<01:37,  1.98it/s]
 45%|████▌     | 161/354 [01:22<01:37,  1.97it/s]
 46%|████▌     | 162/354 [01:22<01:37,  1.97it/s]
 46%|████▌     | 163/354 [01:23<01:36,  1.97it/s]
 46%|████▋     | 164/354 [01:24<01:36,  1.97it/s]
 47%|████▋     | 165/354 [01:24<01:36,  1.97it/s]
 47%|████▋     | 166/354 [01:25<01:35,  1.97it/s]
 47%|████▋     | 167/354 [01:25<01:34,  1.97it/s]
 47%|████▋     | 168/354 [01:26<01:34,  1.97it/s]
 48%|████▊     | 169/354 [01:26<01:33,  1.98it/s]
 48%|████▊     | 170/354 [01:27<01:33,  1.97it/s]
 48%|████▊     | 171/354 [01:27<01:33,  1.97it/s]
 49%|████▊     | 172/354 [01:28<01:30,  2.00it/s]
 49%|████▉     | 173/354 [01:28<01:30,  1.99it/s]
 49%|████▉     | 174/354 [01:29<01:28,  2.02it/s]
 49%|████▉     | 175/354 [01:29<01:28,  2.02it/s]
 50%|████▉     | 176/354 [01:30<01:29,  2.00it/s]
 50%|█████     | 177/354 [01:30<01:27,  2.03it/s]
 50%|█████     | 178/354 [01:31<01:27,  2.01it/s]
 51%|█████     | 179/354 [01:31<01:27,  1.99it/s]
 51%|█████     | 180/354 [01:32<01:27,  1.98it/s]
 51%|█████     | 181/354 [01:32<01:27,  1.98it/s]
 51%|█████▏    | 182/354 [01:33<01:26,  1.98it/s]
 52%|█████▏    | 183/354 [01:33<01:26,  1.98it/s]
 52%|█████▏    | 184/354 [01:34<01:24,  2.01it/s]
 52%|█████▏    | 185/354 [01:34<01:23,  2.04it/s]
 53%|█████▎    | 186/354 [01:34<01:21,  2.06it/s]
 53%|█████▎    | 187/354 [01:35<01:22,  2.03it/s]
 53%|█████▎    | 188/354 [01:36<01:22,  2.01it/s]
 53%|█████▎    | 189/354 [01:36<01:22,  1.99it/s]
 54%|█████▎    | 190/354 [01:37<01:21,  2.01it/s]
 54%|█████▍    | 191/354 [01:37<01:20,  2.02it/s]
 54%|█████▍    | 192/354 [01:37<01:19,  2.03it/s]
 55%|█████▍    | 193/354 [01:38<01:20,  2.01it/s]
 55%|█████▍    | 194/354 [01:38<01:19,  2.00it/s]
 55%|█████▌    | 195/354 [01:39<01:19,  1.99it/s]
 55%|█████▌    | 196/354 [01:40<01:19,  1.98it/s]
 56%|█████▌    | 197/354 [01:40<01:19,  1.99it/s]
 56%|█████▌    | 198/354 [01:41<01:18,  1.99it/s]
 56%|█████▌    | 199/354 [01:41<01:18,  1.98it/s]
 56%|█████▋    | 200/354 [01:42<01:17,  1.99it/s]
 57%|█████▋    | 201/354 [01:42<01:16,  1.99it/s]
 57%|█████▋    | 202/354 [01:43<01:16,  1.98it/s]
 57%|█████▋    | 203/354 [01:43<01:15,  2.00it/s]
 58%|█████▊    | 204/354 [01:44<01:15,  1.99it/s]
 58%|█████▊    | 205/354 [01:44<01:14,  2.00it/s]
 58%|█████▊    | 206/354 [01:45<01:14,  2.00it/s]
 58%|█████▊    | 207/354 [01:45<01:12,  2.03it/s]
 59%|█████▉    | 208/354 [01:46<01:12,  2.02it/s]
 59%|█████▉    | 209/354 [01:46<01:10,  2.05it/s]
 59%|█████▉    | 210/354 [01:46<01:09,  2.07it/s]
 60%|█████▉    | 211/354 [01:47<01:09,  2.05it/s]
 60%|█████▉    | 212/354 [01:47<01:10,  2.02it/s]
 60%|██████    | 213/354 [01:48<01:09,  2.02it/s]
 60%|██████    | 214/354 [01:48<01:09,  2.01it/s]
 61%|██████    | 215/354 [01:49<01:09,  2.00it/s]
 61%|██████    | 216/354 [01:49<01:09,  1.99it/s]
 61%|██████▏   | 217/354 [01:50<01:08,  1.99it/s]
 62%|██████▏   | 218/354 [01:50<01:08,  2.00it/s]
 62%|██████▏   | 219/354 [01:51<01:07,  2.00it/s]
 62%|██████▏   | 220/354 [01:51<01:06,  2.00it/s]
 62%|██████▏   | 221/354 [01:52<01:06,  1.99it/s]
 63%|██████▎   | 222/354 [01:52<01:05,  2.02it/s]
 63%|██████▎   | 223/354 [01:53<01:05,  2.00it/s]
 63%|██████▎   | 224/354 [01:53<01:03,  2.03it/s]
 64%|██████▎   | 225/354 [01:54<01:03,  2.04it/s]
 64%|██████▍   | 226/354 [01:54<01:03,  2.01it/s]
 64%|██████▍   | 227/354 [01:55<01:01,  2.05it/s]
 64%|██████▍   | 228/354 [01:55<01:01,  2.04it/s]
 65%|██████▍   | 229/354 [01:56<01:01,  2.04it/s]
 65%|██████▍   | 230/354 [01:56<01:01,  2.03it/s]
 65%|██████▌   | 231/354 [01:57<01:00,  2.02it/s]
 66%|██████▌   | 232/354 [01:57<01:00,  2.00it/s]
 66%|██████▌   | 233/354 [01:58<01:00,  1.99it/s]
 66%|██████▌   | 234/354 [01:58<01:00,  1.98it/s]
 66%|██████▋   | 235/354 [01:59<00:59,  1.99it/s]
 67%|██████▋   | 236/354 [01:59<00:45,  2.57it/s]
                                                 

 67%|██████▋   | 236/354 [01:59<00:45,  2.57it/s]{'eval_loss': 0.7275411486625671, 'eval_accuracy': 0.6648, 'eval_f1': 0.6600727398906447, 'eval_runtime': 1.7323, 'eval_samples_per_second': 1443.206, 'eval_steps_per_second': 180.689, 'epoch': 1.0}
{'loss': 0.5541, 'learning_rate': 2.256104467900045e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.82it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.90it/s]

 21%|██        | 65/313 [00:00<00:01, 204.88it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.26it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.50it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.16it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.76it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.48it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.84it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.75it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.65it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.82it/s]

 83%|████████▎ | 259/313 [00:01<00:00, 183.88it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.67it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.72it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.72it/s]
 67%|██████▋   | 236/354 [02:01<00:45,  2.57it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 237/354 [02:02<02:23,  1.23s/it]
 67%|██████▋   | 238/354 [02:03<01:56,  1.00s/it]
 68%|██████▊   | 239/354 [02:03<01:38,  1.17it/s]
 68%|██████▊   | 240/354 [02:04<01:25,  1.33it/s]
 68%|██████▊   | 241/354 [02:04<01:16,  1.48it/s]
 68%|██████▊   | 242/354 [02:05<01:10,  1.60it/s]
 69%|██████▊   | 243/354 [02:05<01:05,  1.69it/s]
 69%|██████▉   | 244/354 [02:06<01:02,  1.77it/s]
 69%|██████▉   | 245/354 [02:06<00:59,  1.83it/s]
 69%|██████▉   | 246/354 [02:07<00:57,  1.87it/s]
 70%|██████▉   | 247/354 [02:07<00:56,  1.90it/s]
 70%|███████   | 248/354 [02:08<00:55,  1.92it/s]
 70%|███████   | 249/354 [02:08<00:53,  1.97it/s]
 71%|███████   | 250/354 [02:09<00:52,  1.97it/s]
 71%|███████   | 251/354 [02:09<00:51,  1.99it/s]
 71%|███████   | 252/354 [02:10<00:50,  2.01it/s]
 71%|███████▏  | 253/354 [02:10<00:50,  1.99it/s]
 72%|███████▏  | 254/354 [02:11<00:50,  1.99it/s]
 72%|███████▏  | 255/354 [02:11<00:49,  1.98it/s]
 72%|███████▏  | 256/354 [02:12<00:49,  1.98it/s]
 73%|███████▎  | 257/354 [02:12<00:48,  2.01it/s]
 73%|███████▎  | 258/354 [02:13<00:48,  2.00it/s]
 73%|███████▎  | 259/354 [02:13<00:47,  2.00it/s]
 73%|███████▎  | 260/354 [02:14<00:47,  2.00it/s]
 74%|███████▎  | 261/354 [02:14<00:45,  2.03it/s]
 74%|███████▍  | 262/354 [02:15<00:44,  2.06it/s]
 74%|███████▍  | 263/354 [02:15<00:44,  2.05it/s]
 75%|███████▍  | 264/354 [02:16<00:44,  2.03it/s]
 75%|███████▍  | 265/354 [02:16<00:44,  2.01it/s]
 75%|███████▌  | 266/354 [02:17<00:43,  2.02it/s]
 75%|███████▌  | 267/354 [02:17<00:43,  2.00it/s]
 76%|███████▌  | 268/354 [02:18<00:43,  1.99it/s]
 76%|███████▌  | 269/354 [02:18<00:42,  1.98it/s]
 76%|███████▋  | 270/354 [02:19<00:42,  1.98it/s]
 77%|███████▋  | 271/354 [02:19<00:42,  1.97it/s]
 77%|███████▋  | 272/354 [02:20<00:41,  1.98it/s]
 77%|███████▋  | 273/354 [02:20<00:40,  1.98it/s]
 77%|███████▋  | 274/354 [02:21<00:40,  1.98it/s]
 78%|███████▊  | 275/354 [02:21<00:39,  2.02it/s]
 78%|███████▊  | 276/354 [02:22<00:38,  2.05it/s]
 78%|███████▊  | 277/354 [02:22<00:37,  2.03it/s]
 79%|███████▊  | 278/354 [02:23<00:37,  2.01it/s]
 79%|███████▉  | 279/354 [02:23<00:37,  1.99it/s]
 79%|███████▉  | 280/354 [02:24<00:36,  2.02it/s]
 79%|███████▉  | 281/354 [02:24<00:36,  2.02it/s]
 80%|███████▉  | 282/354 [02:25<00:35,  2.05it/s]
 80%|███████▉  | 283/354 [02:25<00:34,  2.07it/s]
 80%|████████  | 284/354 [02:26<00:34,  2.04it/s]
 81%|████████  | 285/354 [02:26<00:34,  2.02it/s]
 81%|████████  | 286/354 [02:27<00:32,  2.06it/s]
 81%|████████  | 287/354 [02:27<00:32,  2.03it/s]
 81%|████████▏ | 288/354 [02:28<00:34,  1.90it/s]
 82%|████████▏ | 289/354 [02:28<00:33,  1.94it/s]
 82%|████████▏ | 290/354 [02:29<00:32,  1.96it/s]
 82%|████████▏ | 291/354 [02:29<00:32,  1.96it/s]
 82%|████████▏ | 292/354 [02:30<00:31,  1.96it/s]
 83%|████████▎ | 293/354 [02:30<00:31,  1.96it/s]
 83%|████████▎ | 294/354 [02:31<00:30,  1.98it/s]
 83%|████████▎ | 295/354 [02:31<00:29,  1.99it/s]
 84%|████████▎ | 296/354 [02:32<00:29,  1.98it/s]
 84%|████████▍ | 297/354 [02:32<00:28,  1.97it/s]
 84%|████████▍ | 298/354 [02:33<00:28,  1.97it/s]
 84%|████████▍ | 299/354 [02:33<00:27,  1.98it/s]
 85%|████████▍ | 300/354 [02:34<00:27,  1.98it/s]
 85%|████████▌ | 301/354 [02:34<00:26,  1.99it/s]
 85%|████████▌ | 302/354 [02:35<00:26,  1.98it/s]
 86%|████████▌ | 303/354 [02:35<00:25,  2.00it/s]
 86%|████████▌ | 304/354 [02:36<00:25,  2.00it/s]
 86%|████████▌ | 305/354 [02:36<00:24,  2.02it/s]
 86%|████████▋ | 306/354 [02:37<00:23,  2.01it/s]
 87%|████████▋ | 307/354 [02:37<00:23,  2.04it/s]
 87%|████████▋ | 308/354 [02:38<00:22,  2.01it/s]
 87%|████████▋ | 309/354 [02:38<00:22,  2.04it/s]
 88%|████████▊ | 310/354 [02:39<00:21,  2.03it/s]
 88%|████████▊ | 311/354 [02:39<00:20,  2.05it/s]
 88%|████████▊ | 312/354 [02:40<00:20,  2.02it/s]
 88%|████████▊ | 313/354 [02:40<00:20,  2.04it/s]
 89%|████████▊ | 314/354 [02:41<00:19,  2.04it/s]
 89%|████████▉ | 315/354 [02:41<00:19,  2.02it/s]
 89%|████████▉ | 316/354 [02:42<00:18,  2.02it/s]
 90%|████████▉ | 317/354 [02:42<00:18,  2.00it/s]
 90%|████████▉ | 318/354 [02:43<00:17,  2.04it/s]
 90%|█████████ | 319/354 [02:43<00:17,  2.02it/s]
 90%|█████████ | 320/354 [02:44<00:16,  2.01it/s]
 91%|█████████ | 321/354 [02:44<00:16,  2.04it/s]
 91%|█████████ | 322/354 [02:45<00:15,  2.04it/s]
 91%|█████████ | 323/354 [02:45<00:15,  2.02it/s]
 92%|█████████▏| 324/354 [02:46<00:14,  2.01it/s]
 92%|█████████▏| 325/354 [02:46<00:14,  2.00it/s]
 92%|█████████▏| 326/354 [02:47<00:13,  2.01it/s]
 92%|█████████▏| 327/354 [02:47<00:13,  2.00it/s]
 93%|█████████▎| 328/354 [02:48<00:12,  2.01it/s]
 93%|█████████▎| 329/354 [02:48<00:12,  2.00it/s]
 93%|█████████▎| 330/354 [02:49<00:11,  2.03it/s]
 94%|█████████▎| 331/354 [02:49<00:11,  2.03it/s]
 94%|█████████▍| 332/354 [02:50<00:10,  2.01it/s]
 94%|█████████▍| 333/354 [02:50<00:10,  2.00it/s]
 94%|█████████▍| 334/354 [02:51<00:09,  2.01it/s]
 95%|█████████▍| 335/354 [02:51<00:09,  2.01it/s]
 95%|█████████▍| 336/354 [02:52<00:09,  2.00it/s]
 95%|█████████▌| 337/354 [02:52<00:08,  2.00it/s]
 95%|█████████▌| 338/354 [02:53<00:07,  2.05it/s]
 96%|█████████▌| 339/354 [02:53<00:07,  2.02it/s]
 96%|█████████▌| 340/354 [02:54<00:06,  2.00it/s]
 96%|█████████▋| 341/354 [02:54<00:06,  2.00it/s]
 97%|█████████▋| 342/354 [02:55<00:06,  1.99it/s]
 97%|█████████▋| 343/354 [02:55<00:05,  1.98it/s]
 97%|█████████▋| 344/354 [02:56<00:05,  1.98it/s]
 97%|█████████▋| 345/354 [02:56<00:04,  2.01it/s]
 98%|█████████▊| 346/354 [02:57<00:04,  2.00it/s]
 98%|█████████▊| 347/354 [02:57<00:03,  2.03it/s]
 98%|█████████▊| 348/354 [02:58<00:02,  2.01it/s]
 99%|█████████▊| 349/354 [02:58<00:02,  1.99it/s]
 99%|█████████▉| 350/354 [02:59<00:01,  2.04it/s]
 99%|█████████▉| 351/354 [02:59<00:01,  2.03it/s]
 99%|█████████▉| 352/354 [03:00<00:00,  2.01it/s]
100%|█████████▉| 353/354 [03:00<00:00,  2.01it/s]
100%|██████████| 354/354 [03:00<00:00,  2.60it/s]
                                                 

100%|██████████| 354/354 [03:00<00:00,  2.60it/s]{'eval_loss': 0.6823190450668335, 'eval_accuracy': 0.7184, 'eval_f1': 0.7150418874101152, 'eval_runtime': 1.7324, 'eval_samples_per_second': 1443.091, 'eval_steps_per_second': 180.675, 'epoch': 2.0}
{'loss': 0.3771, 'learning_rate': 0.0, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.04it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.64it/s]

 21%|██        | 66/313 [00:00<00:01, 206.00it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.27it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.46it/s]

 40%|████      | 126/313 [00:00<00:01, 185.10it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.86it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.75it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.94it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.20it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.36it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.03it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.53it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.30it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.40it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.40it/s]
100%|██████████| 354/354 [03:02<00:00,  2.60it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 354/354 [03:03<00:00,  2.60it/s]
100%|██████████| 354/354 [03:03<00:00,  1.93it/s]
[I 2023-10-26 23:36:34,037] Trial 35 finished with value: 0.7207954336293969 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 7.446663213379826e-05, 'per_device_train_batch_size': 256, 'weight_decay': 4.22715377210383e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7142072319984436, 'eval_accuracy': 0.7208, 'eval_f1': 0.7207954336293969, 'eval_runtime': 1.7327, 'eval_samples_per_second': 1442.858, 'eval_steps_per_second': 180.646, 'epoch': 3.0}
{'train_runtime': 183.4809, 'train_samples_per_second': 490.514, 'train_steps_per_second': 1.929, 'train_loss': 0.582629769535388, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:12,  3.66it/s]
  0%|          | 2/705 [00:00<03:10,  3.68it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:09<02:50,  3.90it/s]
  6%|▌         | 39/705 [00:10<02:52,  3.87it/s]
  6%|▌         | 40/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 41/705 [00:10<02:54,  3.80it/s]
  6%|▌         | 42/705 [00:11<02:54,  3.80it/s]
  6%|▌         | 43/705 [00:11<02:55,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:53,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:43,  3.85it/s]
 11%|█         | 75/705 [00:19<02:44,  3.82it/s]
 11%|█         | 76/705 [00:20<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.84it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.75it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:51,  3.49it/s]
 15%|█▌        | 108/705 [00:28<02:47,  3.57it/s]
 15%|█▌        | 109/705 [00:28<02:44,  3.63it/s]
 16%|█▌        | 110/705 [00:29<02:42,  3.66it/s]
 16%|█▌        | 111/705 [00:29<02:39,  3.71it/s]
 16%|█▌        | 112/705 [00:29<02:39,  3.72it/s]
 16%|█▌        | 113/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 114/705 [00:30<02:36,  3.79it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.76it/s]
 16%|█▋        | 116/705 [00:30<02:36,  3.76it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:45,  3.51it/s]
 18%|█▊        | 127/705 [00:33<02:40,  3.60it/s]
 18%|█▊        | 128/705 [00:33<02:37,  3.67it/s]
 18%|█▊        | 129/705 [00:34<02:34,  3.72it/s]
 18%|█▊        | 130/705 [00:34<02:33,  3.74it/s]
 19%|█▊        | 131/705 [00:34<02:33,  3.75it/s]
 19%|█▊        | 132/705 [00:34<02:31,  3.78it/s]
 19%|█▉        | 133/705 [00:35<02:31,  3.77it/s]
 19%|█▉        | 134/705 [00:35<02:31,  3.77it/s]
 19%|█▉        | 135/705 [00:35<02:31,  3.77it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.79it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:51,  3.27it/s]
 21%|██        | 146/705 [00:38<02:44,  3.39it/s]
 21%|██        | 147/705 [00:39<02:35,  3.58it/s]
 21%|██        | 148/705 [00:39<02:31,  3.69it/s]
 21%|██        | 149/705 [00:39<02:29,  3.71it/s]
 21%|██▏       | 150/705 [00:39<02:29,  3.70it/s]
 21%|██▏       | 151/705 [00:40<02:27,  3.75it/s]
 22%|██▏       | 152/705 [00:40<02:25,  3.81it/s]
 22%|██▏       | 153/705 [00:40<02:26,  3.77it/s]
 22%|██▏       | 154/705 [00:40<02:26,  3.76it/s]
 22%|██▏       | 155/705 [00:41<02:26,  3.76it/s]
 22%|██▏       | 156/705 [00:41<02:24,  3.80it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.92it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.87it/s]
 23%|██▎       | 159/705 [00:42<02:23,  3.81it/s]
 23%|██▎       | 160/705 [00:42<02:24,  3.78it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.78it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.83it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:45<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:46<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.86it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:52<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:54<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:56<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:57<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.77it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:01<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.61it/s]{'loss': 0.8018, 'learning_rate': 1.775145116482584e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.92it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.82it/s]

 21%|██        | 65/313 [00:00<00:01, 204.82it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.17it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.23it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.83it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.33it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.08it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.73it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.69it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.72it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.84it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.86it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.38it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.73it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.73it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:07,  3.69it/s]
[I 2023-10-26 23:37:38,426] Trial 36 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7050243020057678, 'eval_accuracy': 0.694, 'eval_f1': 0.692552409929252, 'eval_runtime': 1.7339, 'eval_samples_per_second': 1441.841, 'eval_steps_per_second': 180.518, 'epoch': 1.0}

  0%|          | 0/5625 [00:00<?, ?it/s]
  0%|          | 2/5625 [00:00<04:51, 19.28it/s]
  0%|          | 4/5625 [00:00<04:56, 18.93it/s]
  0%|          | 6/5625 [00:00<04:52, 19.22it/s]
  0%|          | 8/5625 [00:00<04:55, 19.00it/s]
  0%|          | 10/5625 [00:00<04:58, 18.82it/s]
  0%|          | 12/5625 [00:00<04:53, 19.14it/s]
  0%|          | 14/5625 [00:00<05:03, 18.49it/s]
  0%|          | 17/5625 [00:00<04:48, 19.44it/s]
  0%|          | 20/5625 [00:01<04:47, 19.50it/s]
  0%|          | 22/5625 [00:01<04:53, 19.11it/s]
  0%|          | 24/5625 [00:01<04:57, 18.83it/s]
  0%|          | 26/5625 [00:01<05:05, 18.35it/s]
  0%|          | 28/5625 [00:01<05:05, 18.30it/s]
  1%|          | 30/5625 [00:01<04:59, 18.67it/s]
  1%|          | 33/5625 [00:01<04:51, 19.21it/s]
  1%|          | 36/5625 [00:01<04:46, 19.48it/s]
  1%|          | 39/5625 [00:02<04:35, 20.28it/s]
  1%|          | 42/5625 [00:02<04:43, 19.67it/s]
  1%|          | 45/5625 [00:02<04:35, 20.27it/s]
  1%|          | 48/5625 [00:02<04:32, 20.49it/s]
  1%|          | 51/5625 [00:02<04:35, 20.24it/s]
  1%|          | 54/5625 [00:02<04:39, 19.96it/s]
  1%|          | 56/5625 [00:02<04:45, 19.51it/s]
  1%|          | 58/5625 [00:02<04:47, 19.34it/s]
  1%|          | 60/5625 [00:03<04:47, 19.39it/s]
  1%|          | 63/5625 [00:03<04:38, 19.96it/s]
  1%|          | 66/5625 [00:03<04:33, 20.29it/s]
  1%|          | 69/5625 [00:03<04:34, 20.21it/s]
  1%|▏         | 72/5625 [00:03<04:37, 20.04it/s]
  1%|▏         | 75/5625 [00:03<04:42, 19.61it/s]
  1%|▏         | 77/5625 [00:03<04:52, 18.99it/s]
  1%|▏         | 79/5625 [00:04<04:59, 18.52it/s]
  1%|▏         | 82/5625 [00:04<04:49, 19.16it/s]
  1%|▏         | 84/5625 [00:04<04:47, 19.26it/s]
  2%|▏         | 86/5625 [00:04<04:45, 19.40it/s]
  2%|▏         | 88/5625 [00:04<04:45, 19.37it/s]
  2%|▏         | 90/5625 [00:04<04:48, 19.21it/s]
  2%|▏         | 92/5625 [00:04<04:51, 18.99it/s]
  2%|▏         | 94/5625 [00:04<04:51, 19.00it/s]
  2%|▏         | 96/5625 [00:04<04:58, 18.55it/s]
  2%|▏         | 99/5625 [00:05<04:50, 19.04it/s]
  2%|▏         | 101/5625 [00:05<04:47, 19.22it/s]
  2%|▏         | 103/5625 [00:05<04:44, 19.41it/s]
  2%|▏         | 105/5625 [00:05<04:47, 19.21it/s]
  2%|▏         | 107/5625 [00:05<04:48, 19.15it/s]
  2%|▏         | 109/5625 [00:05<04:50, 18.97it/s]
  2%|▏         | 112/5625 [00:05<04:40, 19.67it/s]
  2%|▏         | 114/5625 [00:05<04:48, 19.11it/s]
  2%|▏         | 117/5625 [00:06<04:44, 19.35it/s]
  2%|▏         | 119/5625 [00:06<04:43, 19.43it/s]
  2%|▏         | 122/5625 [00:06<04:35, 20.01it/s]
  2%|▏         | 125/5625 [00:06<04:27, 20.57it/s]
  2%|▏         | 128/5625 [00:06<04:39, 19.64it/s]
  2%|▏         | 130/5625 [00:06<04:40, 19.58it/s]
  2%|▏         | 132/5625 [00:06<04:40, 19.58it/s]
  2%|▏         | 134/5625 [00:06<04:46, 19.14it/s]
  2%|▏         | 136/5625 [00:07<04:52, 18.74it/s]
  2%|▏         | 139/5625 [00:07<04:48, 18.98it/s]
  3%|▎         | 141/5625 [00:07<04:55, 18.55it/s]
  3%|▎         | 143/5625 [00:07<04:55, 18.57it/s]
  3%|▎         | 145/5625 [00:07<05:00, 18.26it/s]
  3%|▎         | 147/5625 [00:07<04:54, 18.62it/s]
  3%|▎         | 149/5625 [00:07<04:54, 18.60it/s]
  3%|▎         | 151/5625 [00:07<04:50, 18.87it/s]
  3%|▎         | 154/5625 [00:07<04:45, 19.17it/s]
  3%|▎         | 156/5625 [00:08<04:46, 19.08it/s]
  3%|▎         | 158/5625 [00:08<04:53, 18.64it/s]
  3%|▎         | 161/5625 [00:08<04:36, 19.75it/s]
  3%|▎         | 163/5625 [00:08<04:37, 19.68it/s]
  3%|▎         | 165/5625 [00:08<04:46, 19.02it/s]
  3%|▎         | 167/5625 [00:08<04:47, 19.00it/s]
  3%|▎         | 169/5625 [00:08<04:46, 19.04it/s]
  3%|▎         | 171/5625 [00:08<04:43, 19.24it/s]
  3%|▎         | 173/5625 [00:08<04:44, 19.14it/s]
  3%|▎         | 176/5625 [00:09<04:35, 19.79it/s]
  3%|▎         | 179/5625 [00:09<04:29, 20.24it/s]
  3%|▎         | 182/5625 [00:09<04:22, 20.75it/s]
  3%|▎         | 185/5625 [00:09<04:30, 20.09it/s]
  3%|▎         | 188/5625 [00:09<04:38, 19.55it/s]
  3%|▎         | 191/5625 [00:09<04:36, 19.69it/s]
  3%|▎         | 193/5625 [00:09<04:35, 19.74it/s]
  3%|▎         | 195/5625 [00:10<04:39, 19.40it/s]
  4%|▎         | 197/5625 [00:10<04:41, 19.28it/s]
  4%|▎         | 199/5625 [00:10<04:39, 19.38it/s]
  4%|▎         | 201/5625 [00:10<04:49, 18.76it/s]
  4%|▎         | 204/5625 [00:10<04:32, 19.91it/s]
  4%|▎         | 207/5625 [00:10<04:24, 20.45it/s]
  4%|▎         | 210/5625 [00:10<04:34, 19.71it/s]
  4%|▍         | 212/5625 [00:10<04:35, 19.68it/s]
  4%|▍         | 215/5625 [00:11<04:38, 19.43it/s]
  4%|▍         | 217/5625 [00:11<04:42, 19.14it/s]
  4%|▍         | 220/5625 [00:11<04:36, 19.55it/s]
  4%|▍         | 222/5625 [00:11<04:37, 19.49it/s]
  4%|▍         | 224/5625 [00:11<04:41, 19.18it/s]
  4%|▍         | 227/5625 [00:11<04:40, 19.21it/s]
  4%|▍         | 229/5625 [00:11<04:38, 19.37it/s]
  4%|▍         | 231/5625 [00:11<04:38, 19.38it/s]
  4%|▍         | 234/5625 [00:12<04:35, 19.56it/s]
  4%|▍         | 236/5625 [00:12<04:39, 19.32it/s]
  4%|▍         | 238/5625 [00:12<04:36, 19.46it/s]
  4%|▍         | 240/5625 [00:12<04:37, 19.38it/s]
  4%|▍         | 242/5625 [00:12<04:45, 18.84it/s]
  4%|▍         | 244/5625 [00:12<04:49, 18.61it/s]
  4%|▍         | 247/5625 [00:12<04:36, 19.42it/s]
  4%|▍         | 249/5625 [00:12<04:34, 19.56it/s]
  4%|▍         | 251/5625 [00:12<04:42, 19.01it/s]
  4%|▍         | 253/5625 [00:13<04:46, 18.76it/s]
  5%|▍         | 255/5625 [00:13<04:41, 19.05it/s]
  5%|▍         | 257/5625 [00:13<04:47, 18.69it/s]
  5%|▍         | 260/5625 [00:13<04:42, 18.97it/s]
  5%|▍         | 263/5625 [00:13<04:32, 19.71it/s]
  5%|▍         | 266/5625 [00:13<04:27, 20.06it/s]
  5%|▍         | 268/5625 [00:13<04:33, 19.58it/s]
  5%|▍         | 271/5625 [00:13<04:33, 19.57it/s]
  5%|▍         | 273/5625 [00:14<04:37, 19.29it/s]
  5%|▍         | 275/5625 [00:14<04:40, 19.08it/s]
  5%|▍         | 277/5625 [00:14<04:42, 18.96it/s]
  5%|▍         | 280/5625 [00:14<04:31, 19.67it/s]
  5%|▌         | 283/5625 [00:14<04:24, 20.20it/s]
  5%|▌         | 286/5625 [00:14<04:32, 19.60it/s]
  5%|▌         | 288/5625 [00:14<04:35, 19.39it/s]
  5%|▌         | 291/5625 [00:15<04:36, 19.29it/s]
  5%|▌         | 294/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 296/5625 [00:15<04:36, 19.25it/s]
  5%|▌         | 299/5625 [00:15<04:30, 19.72it/s]
  5%|▌         | 301/5625 [00:15<04:34, 19.40it/s]
  5%|▌         | 303/5625 [00:15<04:40, 18.99it/s]
  5%|▌         | 305/5625 [00:15<04:43, 18.80it/s]
  5%|▌         | 308/5625 [00:15<04:35, 19.33it/s]
  6%|▌         | 311/5625 [00:16<04:30, 19.67it/s]
  6%|▌         | 313/5625 [00:16<04:30, 19.63it/s]
  6%|▌         | 315/5625 [00:16<04:30, 19.62it/s]
  6%|▌         | 317/5625 [00:16<04:33, 19.42it/s]
  6%|▌         | 319/5625 [00:16<04:38, 19.06it/s]
  6%|▌         | 321/5625 [00:16<04:36, 19.22it/s]
  6%|▌         | 323/5625 [00:16<04:39, 19.00it/s]
  6%|▌         | 326/5625 [00:16<04:22, 20.20it/s]
  6%|▌         | 329/5625 [00:16<04:21, 20.22it/s]
  6%|▌         | 332/5625 [00:17<04:27, 19.77it/s]
  6%|▌         | 334/5625 [00:17<04:27, 19.79it/s]
  6%|▌         | 337/5625 [00:17<04:23, 20.08it/s]
  6%|▌         | 340/5625 [00:17<04:28, 19.65it/s]
  6%|▌         | 342/5625 [00:17<04:36, 19.13it/s]
  6%|▌         | 344/5625 [00:17<04:39, 18.86it/s]
  6%|▌         | 346/5625 [00:17<04:43, 18.63it/s]
  6%|▌         | 349/5625 [00:18<04:31, 19.45it/s]
  6%|▋         | 352/5625 [00:18<04:28, 19.61it/s]
  6%|▋         | 354/5625 [00:18<04:31, 19.42it/s]
  6%|▋         | 357/5625 [00:18<04:18, 20.40it/s]
  6%|▋         | 360/5625 [00:18<04:31, 19.40it/s]
  6%|▋         | 362/5625 [00:18<04:30, 19.47it/s]
  6%|▋         | 364/5625 [00:18<04:38, 18.89it/s]
  7%|▋         | 366/5625 [00:18<04:39, 18.82it/s]
  7%|▋         | 368/5625 [00:19<04:45, 18.38it/s]
  7%|▋         | 370/5625 [00:19<04:44, 18.47it/s]
  7%|▋         | 372/5625 [00:19<04:39, 18.80it/s]
  7%|▋         | 374/5625 [00:19<04:35, 19.07it/s]
  7%|▋         | 376/5625 [00:19<04:41, 18.64it/s]
  7%|▋         | 378/5625 [00:19<04:37, 18.89it/s]
  7%|▋         | 380/5625 [00:19<04:36, 18.99it/s]
  7%|▋         | 382/5625 [00:19<04:38, 18.82it/s]
  7%|▋         | 385/5625 [00:19<04:25, 19.76it/s]
  7%|▋         | 387/5625 [00:19<04:32, 19.22it/s]
  7%|▋         | 389/5625 [00:20<04:35, 19.03it/s]
  7%|▋         | 391/5625 [00:20<04:31, 19.25it/s]
  7%|▋         | 393/5625 [00:20<04:38, 18.79it/s]
  7%|▋         | 395/5625 [00:20<04:34, 19.05it/s]
  7%|▋         | 397/5625 [00:20<04:32, 19.22it/s]
  7%|▋         | 399/5625 [00:20<04:32, 19.16it/s]
  7%|▋         | 401/5625 [00:20<04:29, 19.39it/s]
  7%|▋         | 403/5625 [00:20<04:30, 19.29it/s]
  7%|▋         | 405/5625 [00:20<04:37, 18.82it/s]
  7%|▋         | 407/5625 [00:21<04:37, 18.82it/s]
  7%|▋         | 409/5625 [00:21<04:33, 19.07it/s]
  7%|▋         | 411/5625 [00:21<04:39, 18.66it/s]
  7%|▋         | 413/5625 [00:21<04:34, 18.99it/s]
  7%|▋         | 416/5625 [00:21<04:22, 19.85it/s]
  7%|▋         | 419/5625 [00:21<04:23, 19.74it/s]
  7%|▋         | 421/5625 [00:21<04:27, 19.43it/s]
  8%|▊         | 423/5625 [00:21<04:25, 19.56it/s]
  8%|▊         | 425/5625 [00:21<04:31, 19.15it/s]
  8%|▊         | 427/5625 [00:22<04:33, 19.04it/s]
  8%|▊         | 429/5625 [00:22<04:30, 19.23it/s]
  8%|▊         | 431/5625 [00:22<04:33, 19.02it/s]
  8%|▊         | 434/5625 [00:22<04:24, 19.65it/s]
  8%|▊         | 437/5625 [00:22<04:15, 20.33it/s]
  8%|▊         | 440/5625 [00:22<04:18, 20.04it/s]
  8%|▊         | 442/5625 [00:22<04:25, 19.49it/s]
  8%|▊         | 445/5625 [00:22<04:21, 19.80it/s]
  8%|▊         | 447/5625 [00:23<04:21, 19.77it/s]
  8%|▊         | 449/5625 [00:23<04:25, 19.48it/s]
  8%|▊         | 451/5625 [00:23<04:30, 19.11it/s]
  8%|▊         | 453/5625 [00:23<04:27, 19.34it/s]
  8%|▊         | 456/5625 [00:23<04:15, 20.25it/s]
  8%|▊         | 459/5625 [00:23<04:29, 19.20it/s]
  8%|▊         | 461/5625 [00:23<04:32, 18.94it/s]
  8%|▊         | 463/5625 [00:23<04:29, 19.15it/s]
  8%|▊         | 465/5625 [00:24<04:34, 18.77it/s]
  8%|▊         | 468/5625 [00:24<04:22, 19.64it/s]
  8%|▊         | 470/5625 [00:24<04:27, 19.24it/s]
  8%|▊         | 473/5625 [00:24<04:23, 19.58it/s]
  8%|▊         | 475/5625 [00:24<04:22, 19.59it/s]
  8%|▊         | 477/5625 [00:24<04:26, 19.29it/s]
  9%|▊         | 480/5625 [00:24<04:20, 19.72it/s]
  9%|▊         | 482/5625 [00:24<04:20, 19.74it/s]
  9%|▊         | 484/5625 [00:24<04:24, 19.44it/s]
  9%|▊         | 486/5625 [00:25<04:30, 18.99it/s]
  9%|▊         | 489/5625 [00:25<04:18, 19.87it/s]
  9%|▊         | 491/5625 [00:25<04:22, 19.54it/s]
  9%|▉         | 494/5625 [00:25<04:09, 20.57it/s]
  9%|▉         | 497/5625 [00:25<04:14, 20.17it/s]
  9%|▉         | 500/5625 [00:25<04:20, 19.68it/s]
  9%|▉         | 502/5625 [00:25<04:27, 19.14it/s]
  9%|▉         | 504/5625 [00:26<04:28, 19.09it/s]
  9%|▉         | 507/5625 [00:26<04:17, 19.84it/s]
  9%|▉         | 510/5625 [00:26<04:14, 20.09it/s]
  9%|▉         | 512/5625 [00:26<04:23, 19.39it/s]
  9%|▉         | 514/5625 [00:26<04:24, 19.33it/s]
  9%|▉         | 516/5625 [00:26<04:31, 18.83it/s]
  9%|▉         | 518/5625 [00:26<04:28, 19.03it/s]
  9%|▉         | 520/5625 [00:26<04:31, 18.83it/s]
  9%|▉         | 522/5625 [00:26<04:29, 18.91it/s]
  9%|▉         | 524/5625 [00:27<04:32, 18.74it/s]
  9%|▉         | 526/5625 [00:27<04:36, 18.46it/s]
  9%|▉         | 529/5625 [00:27<04:28, 19.00it/s]
  9%|▉         | 531/5625 [00:27<04:33, 18.65it/s]
  9%|▉         | 533/5625 [00:27<04:39, 18.20it/s]
 10%|▉         | 536/5625 [00:27<04:24, 19.24it/s]
 10%|▉         | 539/5625 [00:27<04:20, 19.54it/s]
 10%|▉         | 541/5625 [00:27<04:19, 19.59it/s]
 10%|▉         | 544/5625 [00:28<04:21, 19.47it/s]
 10%|▉         | 546/5625 [00:28<04:21, 19.41it/s]
 10%|▉         | 548/5625 [00:28<04:26, 19.08it/s]
 10%|▉         | 550/5625 [00:28<04:27, 18.98it/s]
 10%|▉         | 553/5625 [00:28<04:21, 19.39it/s]
 10%|▉         | 555/5625 [00:28<04:20, 19.44it/s]
 10%|▉         | 557/5625 [00:28<04:24, 19.16it/s]
 10%|▉         | 559/5625 [00:28<04:24, 19.16it/s]
 10%|▉         | 562/5625 [00:29<04:19, 19.53it/s]
 10%|█         | 564/5625 [00:29<04:25, 19.05it/s]
 10%|█         | 566/5625 [00:29<04:30, 18.72it/s]
 10%|█         | 568/5625 [00:29<04:33, 18.48it/s]
 10%|█         | 570/5625 [00:29<04:33, 18.49it/s]
 10%|█         | 573/5625 [00:29<04:24, 19.07it/s]
 10%|█         | 576/5625 [00:29<04:18, 19.50it/s]
 10%|█         | 578/5625 [00:29<04:22, 19.25it/s]
 10%|█         | 580/5625 [00:29<04:27, 18.83it/s]
 10%|█         | 583/5625 [00:30<04:25, 18.99it/s]
 10%|█         | 585/5625 [00:30<04:30, 18.63it/s]
 10%|█         | 587/5625 [00:30<04:31, 18.58it/s]
 10%|█         | 589/5625 [00:30<04:29, 18.71it/s]
 11%|█         | 592/5625 [00:30<04:20, 19.31it/s]
 11%|█         | 594/5625 [00:30<04:26, 18.90it/s]
 11%|█         | 596/5625 [00:30<04:25, 18.92it/s]
 11%|█         | 598/5625 [00:30<04:23, 19.09it/s]
 11%|█         | 601/5625 [00:31<04:15, 19.65it/s]
 11%|█         | 603/5625 [00:31<04:17, 19.51it/s]
 11%|█         | 605/5625 [00:31<04:25, 18.94it/s]
 11%|█         | 608/5625 [00:31<04:16, 19.58it/s]
 11%|█         | 610/5625 [00:31<04:18, 19.38it/s]
 11%|█         | 612/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 614/5625 [00:31<04:22, 19.06it/s]
 11%|█         | 616/5625 [00:31<04:19, 19.28it/s]
 11%|█         | 618/5625 [00:31<04:24, 18.92it/s]
 11%|█         | 621/5625 [00:32<04:07, 20.18it/s]
 11%|█         | 624/5625 [00:32<04:15, 19.57it/s]
 11%|█         | 626/5625 [00:32<04:21, 19.15it/s]
 11%|█         | 628/5625 [00:32<04:18, 19.35it/s]
 11%|█         | 631/5625 [00:32<04:10, 19.92it/s]
 11%|█▏        | 633/5625 [00:32<04:20, 19.13it/s]
 11%|█▏        | 635/5625 [00:32<04:23, 18.95it/s]
 11%|█▏        | 637/5625 [00:32<04:22, 19.00it/s]
 11%|█▏        | 640/5625 [00:33<04:16, 19.41it/s]
 11%|█▏        | 642/5625 [00:33<04:16, 19.41it/s]
 11%|█▏        | 645/5625 [00:33<04:11, 19.80it/s]
 12%|█▏        | 647/5625 [00:33<04:20, 19.12it/s]
 12%|█▏        | 649/5625 [00:33<04:19, 19.16it/s]
 12%|█▏        | 651/5625 [00:33<04:25, 18.73it/s]
 12%|█▏        | 653/5625 [00:33<04:22, 18.94it/s]
 12%|█▏        | 656/5625 [00:33<04:10, 19.81it/s]
 12%|█▏        | 658/5625 [00:34<04:12, 19.65it/s]
 12%|█▏        | 661/5625 [00:34<04:13, 19.60it/s]
 12%|█▏        | 663/5625 [00:34<04:17, 19.30it/s]
 12%|█▏        | 665/5625 [00:34<04:21, 18.94it/s]
 12%|█▏        | 667/5625 [00:34<04:25, 18.69it/s]
 12%|█▏        | 669/5625 [00:34<04:26, 18.57it/s]
 12%|█▏        | 671/5625 [00:34<04:21, 18.93it/s]
 12%|█▏        | 673/5625 [00:34<04:21, 18.97it/s]
 12%|█▏        | 675/5625 [00:34<04:22, 18.86it/s]
 12%|█▏        | 677/5625 [00:35<04:29, 18.38it/s]
 12%|█▏        | 679/5625 [00:35<04:28, 18.41it/s]
 12%|█▏        | 681/5625 [00:35<04:27, 18.46it/s]
 12%|█▏        | 683/5625 [00:35<04:32, 18.12it/s]
 12%|█▏        | 685/5625 [00:35<04:28, 18.39it/s]
 12%|█▏        | 687/5625 [00:35<04:25, 18.59it/s]
 12%|█▏        | 689/5625 [00:35<04:21, 18.84it/s]
 12%|█▏        | 691/5625 [00:35<04:18, 19.11it/s]
 12%|█▏        | 693/5625 [00:35<04:21, 18.83it/s]
 12%|█▏        | 696/5625 [00:36<04:15, 19.32it/s]
 12%|█▏        | 699/5625 [00:36<04:14, 19.38it/s]
 12%|█▏        | 701/5625 [00:36<04:19, 18.97it/s]
 12%|█▏        | 703/5625 [00:36<04:23, 18.69it/s]
 13%|█▎        | 705/5625 [00:36<04:19, 18.94it/s]
 13%|█▎        | 707/5625 [00:36<04:20, 18.86it/s]
 13%|█▎        | 709/5625 [00:36<04:21, 18.79it/s]
 13%|█▎        | 711/5625 [00:36<04:24, 18.57it/s]
 13%|█▎        | 714/5625 [00:37<04:18, 19.02it/s]
 13%|█▎        | 716/5625 [00:37<04:16, 19.17it/s]
 13%|█▎        | 718/5625 [00:37<04:15, 19.20it/s]
 13%|█▎        | 720/5625 [00:37<04:16, 19.15it/s]
 13%|█▎        | 722/5625 [00:37<04:17, 19.05it/s]
 13%|█▎        | 725/5625 [00:37<04:13, 19.30it/s]
 13%|█▎        | 728/5625 [00:37<04:04, 20.03it/s]
 13%|█▎        | 730/5625 [00:37<04:12, 19.39it/s]
 13%|█▎        | 733/5625 [00:37<04:11, 19.43it/s]
 13%|█▎        | 735/5625 [00:38<04:13, 19.31it/s]
 13%|█▎        | 737/5625 [00:38<04:10, 19.47it/s]
 13%|█▎        | 739/5625 [00:38<04:18, 18.90it/s]
 13%|█▎        | 742/5625 [00:38<04:09, 19.55it/s]
 13%|█▎        | 745/5625 [00:38<04:08, 19.62it/s]
 13%|█▎        | 747/5625 [00:38<04:15, 19.07it/s]
 13%|█▎        | 750/5625 [00:38<04:08, 19.61it/s]
 13%|█▎        | 752/5625 [00:38<04:09, 19.50it/s]
 13%|█▎        | 754/5625 [00:39<04:12, 19.26it/s]
 13%|█▎        | 756/5625 [00:39<04:18, 18.86it/s]
 13%|█▎        | 758/5625 [00:39<04:16, 18.99it/s]
 14%|█▎        | 761/5625 [00:39<04:12, 19.30it/s]
 14%|█▎        | 763/5625 [00:39<04:12, 19.26it/s]
 14%|█▎        | 765/5625 [00:39<04:14, 19.13it/s]
 14%|█▎        | 767/5625 [00:39<04:16, 18.97it/s]
 14%|█▎        | 769/5625 [00:39<04:13, 19.19it/s]
 14%|█▎        | 771/5625 [00:39<04:14, 19.06it/s]
 14%|█▍        | 774/5625 [00:40<04:10, 19.34it/s]
 14%|█▍        | 776/5625 [00:40<04:15, 18.99it/s]
 14%|█▍        | 779/5625 [00:40<04:14, 19.03it/s]
 14%|█▍        | 782/5625 [00:40<04:07, 19.59it/s]
 14%|█▍        | 785/5625 [00:40<04:03, 19.89it/s]
 14%|█▍        | 787/5625 [00:40<04:11, 19.26it/s]
 14%|█▍        | 789/5625 [00:40<04:13, 19.06it/s]
 14%|█▍        | 791/5625 [00:41<04:18, 18.69it/s]
 14%|█▍        | 794/5625 [00:41<04:05, 19.64it/s]
 14%|█▍        | 796/5625 [00:41<04:11, 19.18it/s]
 14%|█▍        | 798/5625 [00:41<04:16, 18.83it/s]
 14%|█▍        | 800/5625 [00:41<04:20, 18.54it/s]
 14%|█▍        | 803/5625 [00:41<04:09, 19.36it/s]
 14%|█▍        | 805/5625 [00:41<04:15, 18.85it/s]
 14%|█▍        | 808/5625 [00:41<04:07, 19.49it/s]
 14%|█▍        | 810/5625 [00:42<04:10, 19.20it/s]
 14%|█▍        | 812/5625 [00:42<04:16, 18.79it/s]
 14%|█▍        | 815/5625 [00:42<04:06, 19.54it/s]
 15%|█▍        | 817/5625 [00:42<04:10, 19.23it/s]
 15%|█▍        | 819/5625 [00:42<04:16, 18.72it/s]
 15%|█▍        | 821/5625 [00:42<04:12, 19.00it/s]
 15%|█▍        | 823/5625 [00:42<04:14, 18.90it/s]
 15%|█▍        | 826/5625 [00:42<04:06, 19.47it/s]
 15%|█▍        | 829/5625 [00:42<04:04, 19.62it/s]
 15%|█▍        | 832/5625 [00:43<03:55, 20.35it/s]
 15%|█▍        | 835/5625 [00:43<03:57, 20.15it/s]
 15%|█▍        | 838/5625 [00:43<04:02, 19.75it/s]
 15%|█▍        | 840/5625 [00:43<04:06, 19.44it/s]
 15%|█▍        | 842/5625 [00:43<04:11, 19.04it/s]
 15%|█▌        | 844/5625 [00:43<04:09, 19.19it/s]
 15%|█▌        | 846/5625 [00:43<04:10, 19.10it/s]
 15%|█▌        | 848/5625 [00:43<04:16, 18.64it/s]
 15%|█▌        | 851/5625 [00:44<04:10, 19.07it/s]
 15%|█▌        | 854/5625 [00:44<04:08, 19.19it/s]
 15%|█▌        | 856/5625 [00:44<04:07, 19.26it/s]
 15%|█▌        | 859/5625 [00:44<04:01, 19.73it/s]
 15%|█▌        | 862/5625 [00:44<04:01, 19.69it/s]
 15%|█▌        | 864/5625 [00:44<04:08, 19.18it/s]
 15%|█▌        | 867/5625 [00:44<03:56, 20.12it/s]
 15%|█▌        | 870/5625 [00:45<03:58, 19.96it/s]
 16%|█▌        | 872/5625 [00:45<03:59, 19.86it/s]
 16%|█▌        | 874/5625 [00:45<04:02, 19.62it/s]
 16%|█▌        | 876/5625 [00:45<04:03, 19.47it/s]
 16%|█▌        | 879/5625 [00:45<04:02, 19.60it/s]
 16%|█▌        | 882/5625 [00:45<03:59, 19.80it/s]
 16%|█▌        | 885/5625 [00:45<03:58, 19.84it/s]
 16%|█▌        | 888/5625 [00:45<03:57, 19.93it/s]
 16%|█▌        | 890/5625 [00:46<04:01, 19.60it/s]
 16%|█▌        | 893/5625 [00:46<04:02, 19.54it/s]
 16%|█▌        | 895/5625 [00:46<04:10, 18.89it/s]
 16%|█▌        | 898/5625 [00:46<03:58, 19.85it/s]
 16%|█▌        | 901/5625 [00:46<03:55, 20.07it/s]
 16%|█▌        | 904/5625 [00:46<03:51, 20.40it/s]
 16%|█▌        | 907/5625 [00:46<03:56, 19.93it/s]
 16%|█▌        | 909/5625 [00:47<04:00, 19.61it/s]
 16%|█▌        | 912/5625 [00:47<03:53, 20.20it/s]
 16%|█▋        | 915/5625 [00:47<03:53, 20.18it/s]
 16%|█▋        | 918/5625 [00:47<03:59, 19.64it/s]
 16%|█▋        | 920/5625 [00:47<04:03, 19.30it/s]
 16%|█▋        | 922/5625 [00:47<04:02, 19.35it/s]
 16%|█▋        | 924/5625 [00:47<04:05, 19.13it/s]
 16%|█▋        | 926/5625 [00:47<04:02, 19.34it/s]
 16%|█▋        | 928/5625 [00:48<04:02, 19.36it/s]
 17%|█▋        | 930/5625 [00:48<04:03, 19.32it/s]
 17%|█▋        | 933/5625 [00:48<03:51, 20.22it/s]
 17%|█▋        | 936/5625 [00:48<03:53, 20.08it/s]
 17%|█▋        | 939/5625 [00:48<03:52, 20.18it/s]
 17%|█▋        | 942/5625 [00:48<03:51, 20.24it/s]
 17%|█▋        | 945/5625 [00:48<03:55, 19.87it/s]
 17%|█▋        | 947/5625 [00:48<03:56, 19.75it/s]
 17%|█▋        | 950/5625 [00:49<03:52, 20.12it/s]
 17%|█▋        | 953/5625 [00:49<04:00, 19.41it/s]
 17%|█▋        | 955/5625 [00:49<03:59, 19.53it/s]
 17%|█▋        | 958/5625 [00:49<03:54, 19.91it/s]
 17%|█▋        | 960/5625 [00:49<03:57, 19.62it/s]
 17%|█▋        | 962/5625 [00:49<04:03, 19.17it/s]
 17%|█▋        | 964/5625 [00:49<04:01, 19.33it/s]
 17%|█▋        | 966/5625 [00:49<03:59, 19.49it/s]
 17%|█▋        | 968/5625 [00:50<03:58, 19.56it/s]
 17%|█▋        | 970/5625 [00:50<03:58, 19.51it/s]
 17%|█▋        | 972/5625 [00:50<04:02, 19.21it/s]
 17%|█▋        | 974/5625 [00:50<03:59, 19.41it/s]
 17%|█▋        | 976/5625 [00:50<04:01, 19.26it/s]
 17%|█▋        | 979/5625 [00:50<03:58, 19.49it/s]
 17%|█▋        | 982/5625 [00:50<03:57, 19.54it/s]
 17%|█▋        | 984/5625 [00:50<04:03, 19.08it/s]
 18%|█▊        | 986/5625 [00:51<04:04, 19.00it/s]
 18%|█▊        | 988/5625 [00:51<04:05, 18.88it/s]
 18%|█▊        | 991/5625 [00:51<03:56, 19.57it/s]
 18%|█▊        | 994/5625 [00:51<03:55, 19.63it/s]
 18%|█▊        | 996/5625 [00:51<03:57, 19.48it/s]
 18%|█▊        | 998/5625 [00:51<03:56, 19.60it/s]
 18%|█▊        | 1000/5625 [00:51<03:56, 19.59it/s]
 18%|█▊        | 1002/5625 [00:51<03:57, 19.48it/s]
 18%|█▊        | 1005/5625 [00:51<03:55, 19.60it/s]
 18%|█▊        | 1008/5625 [00:52<03:48, 20.20it/s]
 18%|█▊        | 1011/5625 [00:52<03:50, 20.05it/s]
 18%|█▊        | 1014/5625 [00:52<03:50, 19.97it/s]
 18%|█▊        | 1016/5625 [00:52<03:56, 19.47it/s]
 18%|█▊        | 1018/5625 [00:52<03:55, 19.55it/s]
 18%|█▊        | 1021/5625 [00:52<03:50, 19.95it/s]
 18%|█▊        | 1023/5625 [00:52<03:55, 19.53it/s]
 18%|█▊        | 1025/5625 [00:52<03:55, 19.56it/s]
 18%|█▊        | 1027/5625 [00:53<03:56, 19.42it/s]
 18%|█▊        | 1030/5625 [00:53<03:57, 19.37it/s]
 18%|█▊        | 1032/5625 [00:53<03:59, 19.14it/s]
 18%|█▊        | 1034/5625 [00:53<04:05, 18.68it/s]
 18%|█▊        | 1037/5625 [00:53<03:57, 19.32it/s]
 18%|█▊        | 1040/5625 [00:53<03:57, 19.28it/s]
 19%|█▊        | 1042/5625 [00:53<03:57, 19.26it/s]
 19%|█▊        | 1044/5625 [00:53<04:03, 18.83it/s]
 19%|█▊        | 1047/5625 [00:54<03:53, 19.62it/s]
 19%|█▊        | 1050/5625 [00:54<03:46, 20.24it/s]
 19%|█▊        | 1053/5625 [00:54<03:48, 20.01it/s]
 19%|█▉        | 1056/5625 [00:54<03:48, 20.04it/s]
 19%|█▉        | 1058/5625 [00:54<03:48, 19.97it/s]
 19%|█▉        | 1060/5625 [00:54<03:56, 19.32it/s]
 19%|█▉        | 1063/5625 [00:54<03:56, 19.31it/s]
 19%|█▉        | 1066/5625 [00:55<03:49, 19.87it/s]
 19%|█▉        | 1068/5625 [00:55<03:53, 19.55it/s]
 19%|█▉        | 1070/5625 [00:55<03:58, 19.13it/s]
 19%|█▉        | 1072/5625 [00:55<03:59, 18.99it/s]
 19%|█▉        | 1074/5625 [00:55<03:59, 19.01it/s]
 19%|█▉        | 1076/5625 [00:55<04:01, 18.84it/s]
 19%|█▉        | 1078/5625 [00:55<04:05, 18.53it/s]
 19%|█▉        | 1081/5625 [00:55<04:01, 18.85it/s]
 19%|█▉        | 1084/5625 [00:56<03:56, 19.22it/s]
 19%|█▉        | 1086/5625 [00:56<03:54, 19.36it/s]
 19%|█▉        | 1089/5625 [00:56<03:45, 20.12it/s]
 19%|█▉        | 1092/5625 [00:56<03:49, 19.71it/s]
 19%|█▉        | 1094/5625 [00:56<03:53, 19.38it/s]
 19%|█▉        | 1096/5625 [00:56<03:52, 19.45it/s]
 20%|█▉        | 1099/5625 [00:56<03:46, 19.96it/s]
 20%|█▉        | 1101/5625 [00:56<03:48, 19.78it/s]
 20%|█▉        | 1104/5625 [00:57<03:50, 19.63it/s]
 20%|█▉        | 1107/5625 [00:57<03:51, 19.50it/s]
 20%|█▉        | 1110/5625 [00:57<03:47, 19.89it/s]
 20%|█▉        | 1113/5625 [00:57<03:42, 20.29it/s]
 20%|█▉        | 1116/5625 [00:57<03:48, 19.69it/s]
 20%|█▉        | 1119/5625 [00:57<03:43, 20.13it/s]
 20%|█▉        | 1122/5625 [00:57<03:54, 19.23it/s]
 20%|█▉        | 1124/5625 [00:58<03:54, 19.23it/s]
 20%|██        | 1126/5625 [00:58<03:52, 19.31it/s]
 20%|██        | 1128/5625 [00:58<03:57, 18.93it/s]
 20%|██        | 1130/5625 [00:58<03:57, 18.89it/s]
 20%|██        | 1133/5625 [00:58<03:47, 19.78it/s]
 20%|██        | 1135/5625 [00:58<03:50, 19.49it/s]
 20%|██        | 1137/5625 [00:58<03:56, 19.01it/s]
 20%|██        | 1139/5625 [00:58<04:00, 18.65it/s]
 20%|██        | 1141/5625 [00:58<03:57, 18.85it/s]
 20%|██        | 1143/5625 [00:59<04:02, 18.52it/s]
 20%|██        | 1146/5625 [00:59<03:48, 19.62it/s]
 20%|██        | 1148/5625 [00:59<03:51, 19.35it/s]
 20%|██        | 1150/5625 [00:59<03:51, 19.34it/s]
 20%|██        | 1153/5625 [00:59<03:42, 20.09it/s]
 21%|██        | 1155/5625 [00:59<03:44, 19.90it/s]
 21%|██        | 1157/5625 [00:59<03:53, 19.11it/s]
 21%|██        | 1159/5625 [00:59<03:59, 18.64it/s]
 21%|██        | 1162/5625 [01:00<03:47, 19.62it/s]
 21%|██        | 1164/5625 [01:00<03:53, 19.09it/s]
 21%|██        | 1166/5625 [01:00<03:56, 18.89it/s]
 21%|██        | 1169/5625 [01:00<03:46, 19.66it/s]
 21%|██        | 1171/5625 [01:00<03:49, 19.40it/s]
 21%|██        | 1173/5625 [01:00<03:52, 19.12it/s]
 21%|██        | 1176/5625 [01:00<03:42, 19.95it/s]
 21%|██        | 1178/5625 [01:00<03:42, 19.95it/s]
 21%|██        | 1180/5625 [01:00<03:44, 19.76it/s]
 21%|██        | 1182/5625 [01:01<03:47, 19.51it/s]
 21%|██        | 1185/5625 [01:01<03:44, 19.82it/s]
 21%|██        | 1188/5625 [01:01<03:44, 19.79it/s]
 21%|██        | 1190/5625 [01:01<03:44, 19.73it/s]
 21%|██        | 1192/5625 [01:01<03:45, 19.63it/s]
 21%|██        | 1194/5625 [01:01<03:49, 19.33it/s]
 21%|██▏       | 1196/5625 [01:01<03:52, 19.04it/s]
 21%|██▏       | 1199/5625 [01:01<03:38, 20.26it/s]
 21%|██▏       | 1202/5625 [01:02<03:31, 20.88it/s]
 21%|██▏       | 1205/5625 [01:02<03:34, 20.57it/s]
 21%|██▏       | 1208/5625 [01:02<03:39, 20.09it/s]
 22%|██▏       | 1211/5625 [01:02<03:39, 20.10it/s]
 22%|██▏       | 1214/5625 [01:02<03:38, 20.17it/s]
 22%|██▏       | 1217/5625 [01:02<03:39, 20.06it/s]
 22%|██▏       | 1220/5625 [01:02<03:34, 20.49it/s]
 22%|██▏       | 1223/5625 [01:03<03:42, 19.81it/s]
 22%|██▏       | 1225/5625 [01:03<03:44, 19.60it/s]
 22%|██▏       | 1227/5625 [01:03<03:51, 18.97it/s]
 22%|██▏       | 1229/5625 [01:03<03:57, 18.52it/s]
 22%|██▏       | 1231/5625 [01:03<03:56, 18.55it/s]
 22%|██▏       | 1233/5625 [01:03<03:57, 18.47it/s]
 22%|██▏       | 1236/5625 [01:03<03:46, 19.40it/s]
 22%|██▏       | 1238/5625 [01:03<03:51, 18.97it/s]
 22%|██▏       | 1241/5625 [01:04<03:43, 19.60it/s]
 22%|██▏       | 1243/5625 [01:04<03:42, 19.66it/s]
 22%|██▏       | 1245/5625 [01:04<03:45, 19.45it/s]
 22%|██▏       | 1248/5625 [01:04<03:42, 19.63it/s]
 22%|██▏       | 1250/5625 [01:04<03:46, 19.32it/s]
 22%|██▏       | 1253/5625 [01:04<03:38, 19.98it/s]
 22%|██▏       | 1256/5625 [01:04<03:34, 20.37it/s]
 22%|██▏       | 1259/5625 [01:04<03:34, 20.32it/s]
 22%|██▏       | 1262/5625 [01:05<03:32, 20.54it/s]
 22%|██▏       | 1265/5625 [01:05<03:37, 20.08it/s]
 23%|██▎       | 1268/5625 [01:05<03:40, 19.73it/s]
 23%|██▎       | 1270/5625 [01:05<03:42, 19.54it/s]
 23%|██▎       | 1272/5625 [01:05<03:42, 19.60it/s]
 23%|██▎       | 1274/5625 [01:05<03:43, 19.43it/s]
 23%|██▎       | 1276/5625 [01:05<03:51, 18.79it/s]
 23%|██▎       | 1278/5625 [01:05<03:56, 18.40it/s]
 23%|██▎       | 1280/5625 [01:06<03:55, 18.48it/s]
 23%|██▎       | 1283/5625 [01:06<03:46, 19.16it/s]
 23%|██▎       | 1286/5625 [01:06<03:38, 19.83it/s]
 23%|██▎       | 1289/5625 [01:06<03:37, 19.92it/s]
 23%|██▎       | 1291/5625 [01:06<03:45, 19.19it/s]
 23%|██▎       | 1293/5625 [01:06<03:49, 18.91it/s]
 23%|██▎       | 1295/5625 [01:06<03:47, 19.01it/s]
 23%|██▎       | 1297/5625 [01:06<03:45, 19.18it/s]
 23%|██▎       | 1299/5625 [01:07<03:44, 19.26it/s]
 23%|██▎       | 1301/5625 [01:07<03:51, 18.69it/s]
 23%|██▎       | 1303/5625 [01:07<03:56, 18.25it/s]
 23%|██▎       | 1305/5625 [01:07<03:56, 18.27it/s]
 23%|██▎       | 1307/5625 [01:07<03:54, 18.40it/s]
 23%|██▎       | 1309/5625 [01:07<03:52, 18.57it/s]
 23%|██▎       | 1312/5625 [01:07<03:41, 19.44it/s]
 23%|██▎       | 1314/5625 [01:07<03:41, 19.46it/s]
 23%|██▎       | 1317/5625 [01:07<03:37, 19.81it/s]
 23%|██▎       | 1319/5625 [01:08<03:40, 19.50it/s]
 23%|██▎       | 1321/5625 [01:08<03:40, 19.51it/s]
 24%|██▎       | 1323/5625 [01:08<03:40, 19.50it/s]
 24%|██▎       | 1325/5625 [01:08<03:43, 19.28it/s]
 24%|██▎       | 1328/5625 [01:08<03:38, 19.65it/s]
 24%|██▎       | 1331/5625 [01:08<03:35, 19.93it/s]
 24%|██▎       | 1333/5625 [01:08<03:40, 19.48it/s]
 24%|██▎       | 1335/5625 [01:08<03:42, 19.32it/s]
 24%|██▍       | 1337/5625 [01:09<03:40, 19.45it/s]
 24%|██▍       | 1340/5625 [01:09<03:41, 19.32it/s]
 24%|██▍       | 1343/5625 [01:09<03:41, 19.32it/s]
 24%|██▍       | 1346/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1348/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1351/5625 [01:09<03:38, 19.57it/s]
 24%|██▍       | 1354/5625 [01:09<03:31, 20.15it/s]
 24%|██▍       | 1357/5625 [01:10<03:29, 20.33it/s]
 24%|██▍       | 1360/5625 [01:10<03:35, 19.81it/s]
 24%|██▍       | 1362/5625 [01:10<03:34, 19.84it/s]
 24%|██▍       | 1365/5625 [01:10<03:37, 19.63it/s]
 24%|██▍       | 1367/5625 [01:10<03:37, 19.61it/s]
 24%|██▍       | 1369/5625 [01:10<03:40, 19.32it/s]
 24%|██▍       | 1371/5625 [01:10<03:43, 19.04it/s]
 24%|██▍       | 1373/5625 [01:10<03:45, 18.86it/s]
 24%|██▍       | 1375/5625 [01:10<03:42, 19.10it/s]
 24%|██▍       | 1377/5625 [01:11<03:40, 19.23it/s]
 25%|██▍       | 1379/5625 [01:11<03:44, 18.95it/s]
 25%|██▍       | 1381/5625 [01:11<03:43, 18.99it/s]
 25%|██▍       | 1384/5625 [01:11<03:42, 19.09it/s]
 25%|██▍       | 1386/5625 [01:11<03:39, 19.29it/s]
 25%|██▍       | 1389/5625 [01:11<03:32, 19.92it/s]
 25%|██▍       | 1391/5625 [01:11<03:36, 19.58it/s]
 25%|██▍       | 1393/5625 [01:11<03:35, 19.60it/s]
 25%|██▍       | 1396/5625 [01:12<03:34, 19.76it/s]
 25%|██▍       | 1399/5625 [01:12<03:35, 19.65it/s]
 25%|██▍       | 1402/5625 [01:12<03:28, 20.26it/s]
 25%|██▍       | 1405/5625 [01:12<03:29, 20.10it/s]
 25%|██▌       | 1408/5625 [01:12<03:38, 19.34it/s]
 25%|██▌       | 1410/5625 [01:12<03:37, 19.41it/s]
 25%|██▌       | 1413/5625 [01:12<03:25, 20.46it/s]
 25%|██▌       | 1416/5625 [01:13<03:27, 20.29it/s]
 25%|██▌       | 1419/5625 [01:13<03:36, 19.47it/s]
 25%|██▌       | 1421/5625 [01:13<03:34, 19.59it/s]
 25%|██▌       | 1423/5625 [01:13<03:35, 19.50it/s]
 25%|██▌       | 1425/5625 [01:13<03:34, 19.62it/s]
 25%|██▌       | 1427/5625 [01:13<03:35, 19.44it/s]
 25%|██▌       | 1429/5625 [01:13<03:34, 19.56it/s]
 25%|██▌       | 1432/5625 [01:13<03:33, 19.69it/s]
 25%|██▌       | 1434/5625 [01:13<03:36, 19.38it/s]
 26%|██▌       | 1436/5625 [01:14<03:37, 19.29it/s]
 26%|██▌       | 1438/5625 [01:14<03:42, 18.80it/s]
 26%|██▌       | 1440/5625 [01:14<03:46, 18.46it/s]
 26%|██▌       | 1442/5625 [01:14<03:45, 18.52it/s]
 26%|██▌       | 1444/5625 [01:14<03:44, 18.61it/s]
 26%|██▌       | 1446/5625 [01:14<03:42, 18.81it/s]
 26%|██▌       | 1449/5625 [01:14<03:24, 20.38it/s]
 26%|██▌       | 1452/5625 [01:14<03:24, 20.36it/s]
 26%|██▌       | 1455/5625 [01:15<03:33, 19.51it/s]
 26%|██▌       | 1457/5625 [01:15<03:33, 19.54it/s]
 26%|██▌       | 1459/5625 [01:15<03:32, 19.61it/s]
 26%|██▌       | 1461/5625 [01:15<03:34, 19.43it/s]
 26%|██▌       | 1464/5625 [01:15<03:30, 19.81it/s]
 26%|██▌       | 1466/5625 [01:15<03:31, 19.68it/s]
 26%|██▌       | 1468/5625 [01:15<03:32, 19.54it/s]
 26%|██▌       | 1470/5625 [01:15<03:33, 19.42it/s]
 26%|██▌       | 1472/5625 [01:15<03:32, 19.51it/s]
 26%|██▌       | 1474/5625 [01:16<03:33, 19.48it/s]
 26%|██▌       | 1476/5625 [01:16<03:37, 19.06it/s]
 26%|██▋       | 1479/5625 [01:16<03:26, 20.07it/s]
 26%|██▋       | 1481/5625 [01:16<03:31, 19.62it/s]
 26%|██▋       | 1484/5625 [01:16<03:27, 19.94it/s]
 26%|██▋       | 1487/5625 [01:16<03:20, 20.66it/s]
 26%|██▋       | 1490/5625 [01:16<03:28, 19.85it/s]
 27%|██▋       | 1492/5625 [01:16<03:34, 19.23it/s]
 27%|██▋       | 1494/5625 [01:17<03:33, 19.35it/s]
 27%|██▋       | 1496/5625 [01:17<03:35, 19.16it/s]
 27%|██▋       | 1498/5625 [01:17<03:39, 18.76it/s]
 27%|██▋       | 1500/5625 [01:17<03:36, 19.08it/s]
 27%|██▋       | 1502/5625 [01:17<03:33, 19.29it/s]
 27%|██▋       | 1504/5625 [01:17<03:37, 18.95it/s]
 27%|██▋       | 1506/5625 [01:17<03:37, 18.90it/s]
 27%|██▋       | 1508/5625 [01:17<03:40, 18.65it/s]
 27%|██▋       | 1511/5625 [01:17<03:36, 19.04it/s]
 27%|██▋       | 1513/5625 [01:18<03:40, 18.69it/s]
 27%|██▋       | 1515/5625 [01:18<03:40, 18.65it/s]
 27%|██▋       | 1517/5625 [01:18<03:42, 18.48it/s]
 27%|██▋       | 1520/5625 [01:18<03:32, 19.34it/s]
 27%|██▋       | 1523/5625 [01:18<03:30, 19.51it/s]
 27%|██▋       | 1526/5625 [01:18<03:28, 19.65it/s]
 27%|██▋       | 1529/5625 [01:18<03:23, 20.10it/s]
 27%|██▋       | 1532/5625 [01:19<03:28, 19.65it/s]
 27%|██▋       | 1535/5625 [01:19<03:28, 19.58it/s]
 27%|██▋       | 1538/5625 [01:19<03:26, 19.75it/s]
 27%|██▋       | 1540/5625 [01:19<03:27, 19.68it/s]
 27%|██▋       | 1542/5625 [01:19<03:30, 19.36it/s]
 27%|██▋       | 1544/5625 [01:19<03:33, 19.13it/s]
 27%|██▋       | 1546/5625 [01:19<03:31, 19.28it/s]
 28%|██▊       | 1549/5625 [01:19<03:30, 19.36it/s]
 28%|██▊       | 1551/5625 [01:20<03:30, 19.38it/s]
 28%|██▊       | 1554/5625 [01:20<03:25, 19.78it/s]
 28%|██▊       | 1556/5625 [01:20<03:32, 19.11it/s]
 28%|██▊       | 1558/5625 [01:20<03:34, 18.97it/s]
 28%|██▊       | 1560/5625 [01:20<03:33, 19.04it/s]
 28%|██▊       | 1562/5625 [01:20<03:33, 19.00it/s]
 28%|██▊       | 1564/5625 [01:20<03:30, 19.25it/s]
 28%|██▊       | 1566/5625 [01:20<03:35, 18.87it/s]
 28%|██▊       | 1569/5625 [01:20<03:27, 19.50it/s]
 28%|██▊       | 1571/5625 [01:21<03:30, 19.28it/s]
 28%|██▊       | 1573/5625 [01:21<03:28, 19.46it/s]
 28%|██▊       | 1575/5625 [01:21<03:30, 19.25it/s]
 28%|██▊       | 1578/5625 [01:21<03:27, 19.49it/s]
 28%|██▊       | 1581/5625 [01:21<03:19, 20.24it/s]
 28%|██▊       | 1584/5625 [01:21<03:24, 19.75it/s]
 28%|██▊       | 1586/5625 [01:21<03:23, 19.81it/s]
 28%|██▊       | 1588/5625 [01:21<03:26, 19.56it/s]
 28%|██▊       | 1591/5625 [01:22<03:20, 20.11it/s]
 28%|██▊       | 1594/5625 [01:22<03:27, 19.44it/s]
 28%|██▊       | 1596/5625 [01:22<03:29, 19.22it/s]
 28%|██▊       | 1598/5625 [01:22<03:30, 19.16it/s]
 28%|██▊       | 1600/5625 [01:22<03:30, 19.14it/s]
 28%|██▊       | 1602/5625 [01:22<03:34, 18.78it/s]
 29%|██▊       | 1604/5625 [01:22<03:30, 19.08it/s]
 29%|██▊       | 1606/5625 [01:22<03:28, 19.24it/s]
 29%|██▊       | 1608/5625 [01:22<03:27, 19.40it/s]
 29%|██▊       | 1610/5625 [01:23<03:30, 19.09it/s]
 29%|██▊       | 1613/5625 [01:23<03:29, 19.18it/s]
 29%|██▊       | 1616/5625 [01:23<03:22, 19.80it/s]
 29%|██▉       | 1619/5625 [01:23<03:18, 20.15it/s]
 29%|██▉       | 1622/5625 [01:23<03:19, 20.11it/s]
 29%|██▉       | 1625/5625 [01:23<03:23, 19.63it/s]
 29%|██▉       | 1628/5625 [01:23<03:21, 19.88it/s]
 29%|██▉       | 1630/5625 [01:24<03:22, 19.73it/s]
 29%|██▉       | 1633/5625 [01:24<03:16, 20.29it/s]
 29%|██▉       | 1636/5625 [01:24<03:18, 20.09it/s]
 29%|██▉       | 1639/5625 [01:24<03:20, 19.92it/s]
 29%|██▉       | 1641/5625 [01:24<03:21, 19.77it/s]
 29%|██▉       | 1643/5625 [01:24<03:26, 19.26it/s]
 29%|██▉       | 1645/5625 [01:24<03:32, 18.73it/s]
 29%|██▉       | 1648/5625 [01:24<03:24, 19.42it/s]
 29%|██▉       | 1650/5625 [01:25<03:29, 19.02it/s]
 29%|██▉       | 1652/5625 [01:25<03:31, 18.77it/s]
 29%|██▉       | 1654/5625 [01:25<03:33, 18.59it/s]
 29%|██▉       | 1656/5625 [01:25<03:35, 18.38it/s]
 29%|██▉       | 1658/5625 [01:25<03:32, 18.70it/s]
 30%|██▉       | 1660/5625 [01:25<03:32, 18.63it/s]
 30%|██▉       | 1662/5625 [01:25<03:34, 18.48it/s]
 30%|██▉       | 1665/5625 [01:25<03:31, 18.77it/s]
 30%|██▉       | 1667/5625 [01:26<03:31, 18.69it/s]
 30%|██▉       | 1669/5625 [01:26<03:31, 18.72it/s]
 30%|██▉       | 1672/5625 [01:26<03:22, 19.55it/s]
 30%|██▉       | 1674/5625 [01:26<03:25, 19.19it/s]
 30%|██▉       | 1677/5625 [01:26<03:17, 20.02it/s]
 30%|██▉       | 1679/5625 [01:26<03:24, 19.29it/s]
 30%|██▉       | 1681/5625 [01:26<03:23, 19.37it/s]
 30%|██▉       | 1683/5625 [01:26<03:30, 18.73it/s]
 30%|██▉       | 1685/5625 [01:26<03:34, 18.39it/s]
 30%|██▉       | 1687/5625 [01:27<03:32, 18.54it/s]
 30%|███       | 1689/5625 [01:27<03:30, 18.67it/s]
 30%|███       | 1691/5625 [01:27<03:27, 18.94it/s]
 30%|███       | 1694/5625 [01:27<03:18, 19.81it/s]
 30%|███       | 1697/5625 [01:27<03:20, 19.58it/s]
 30%|███       | 1699/5625 [01:27<03:21, 19.47it/s]
 30%|███       | 1701/5625 [01:27<03:27, 18.92it/s]
 30%|███       | 1703/5625 [01:27<03:27, 18.92it/s]
 30%|███       | 1706/5625 [01:28<03:26, 19.02it/s]
 30%|███       | 1708/5625 [01:28<03:27, 18.90it/s]
 30%|███       | 1711/5625 [01:28<03:24, 19.12it/s]
 30%|███       | 1713/5625 [01:28<03:29, 18.71it/s]
 30%|███       | 1715/5625 [01:28<03:32, 18.42it/s]
 31%|███       | 1718/5625 [01:28<03:19, 19.54it/s]
 31%|███       | 1720/5625 [01:28<03:25, 18.98it/s]
 31%|███       | 1722/5625 [01:28<03:25, 18.97it/s]
 31%|███       | 1724/5625 [01:28<03:25, 19.02it/s]
 31%|███       | 1727/5625 [01:29<03:21, 19.38it/s]
 31%|███       | 1729/5625 [01:29<03:20, 19.45it/s]
 31%|███       | 1732/5625 [01:29<03:13, 20.13it/s]
 31%|███       | 1735/5625 [01:29<03:11, 20.28it/s]
 31%|███       | 1738/5625 [01:29<03:16, 19.82it/s]
 31%|███       | 1740/5625 [01:29<03:23, 19.13it/s]
 31%|███       | 1742/5625 [01:29<03:23, 19.10it/s]
 31%|███       | 1745/5625 [01:30<03:20, 19.34it/s]
 31%|███       | 1748/5625 [01:30<03:11, 20.28it/s]
 31%|███       | 1751/5625 [01:30<03:15, 19.79it/s]
 31%|███       | 1753/5625 [01:30<03:18, 19.54it/s]
 31%|███       | 1755/5625 [01:30<03:18, 19.52it/s]
 31%|███       | 1757/5625 [01:30<03:20, 19.33it/s]
 31%|███▏      | 1759/5625 [01:30<03:22, 19.07it/s]
 31%|███▏      | 1761/5625 [01:30<03:23, 18.98it/s]
 31%|███▏      | 1763/5625 [01:30<03:24, 18.89it/s]
 31%|███▏      | 1765/5625 [01:31<03:28, 18.55it/s]
 31%|███▏      | 1767/5625 [01:31<03:26, 18.68it/s]
 31%|███▏      | 1769/5625 [01:31<03:29, 18.43it/s]
 31%|███▏      | 1771/5625 [01:31<03:27, 18.60it/s]
 32%|███▏      | 1774/5625 [01:31<03:18, 19.35it/s]
 32%|███▏      | 1776/5625 [01:31<03:25, 18.77it/s]
 32%|███▏      | 1778/5625 [01:31<03:22, 19.00it/s]
 32%|███▏      | 1780/5625 [01:31<03:19, 19.23it/s]
 32%|███▏      | 1782/5625 [01:31<03:18, 19.37it/s]
 32%|███▏      | 1784/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1786/5625 [01:32<03:24, 18.75it/s]
 32%|███▏      | 1788/5625 [01:32<03:24, 18.78it/s]
 32%|███▏      | 1791/5625 [01:32<03:16, 19.50it/s]
 32%|███▏      | 1794/5625 [01:32<03:14, 19.66it/s]
 32%|███▏      | 1797/5625 [01:32<03:07, 20.42it/s]
 32%|███▏      | 1800/5625 [01:32<03:08, 20.29it/s]
 32%|███▏      | 1803/5625 [01:33<03:07, 20.43it/s]
 32%|███▏      | 1806/5625 [01:33<03:08, 20.26it/s]
 32%|███▏      | 1809/5625 [01:33<03:05, 20.54it/s]
 32%|███▏      | 1812/5625 [01:33<03:06, 20.47it/s]
 32%|███▏      | 1815/5625 [01:33<03:10, 20.01it/s]
 32%|███▏      | 1818/5625 [01:33<03:15, 19.48it/s]
 32%|███▏      | 1820/5625 [01:33<03:14, 19.56it/s]
 32%|███▏      | 1822/5625 [01:34<03:16, 19.34it/s]
 32%|███▏      | 1824/5625 [01:34<03:20, 18.99it/s]
 32%|███▏      | 1827/5625 [01:34<03:15, 19.43it/s]
 33%|███▎      | 1829/5625 [01:34<03:21, 18.88it/s]
 33%|███▎      | 1831/5625 [01:34<03:25, 18.42it/s]
 33%|███▎      | 1834/5625 [01:34<03:21, 18.78it/s]
 33%|███▎      | 1836/5625 [01:34<03:25, 18.42it/s]
 33%|███▎      | 1838/5625 [01:34<03:23, 18.60it/s]
 33%|███▎      | 1840/5625 [01:34<03:19, 18.96it/s]
 33%|███▎      | 1843/5625 [01:35<03:15, 19.36it/s]
 33%|███▎      | 1845/5625 [01:35<03:15, 19.30it/s]
 33%|███▎      | 1847/5625 [01:35<03:18, 19.07it/s]
 33%|███▎      | 1849/5625 [01:35<03:19, 18.95it/s]
 33%|███▎      | 1852/5625 [01:35<03:07, 20.11it/s]
 33%|███▎      | 1855/5625 [01:35<03:07, 20.12it/s]
 33%|███▎      | 1858/5625 [01:35<03:10, 19.78it/s]
 33%|███▎      | 1860/5625 [01:35<03:14, 19.34it/s]
 33%|███▎      | 1862/5625 [01:36<03:16, 19.12it/s]
 33%|███▎      | 1864/5625 [01:36<03:18, 18.99it/s]
 33%|███▎      | 1866/5625 [01:36<03:19, 18.87it/s]
 33%|███▎      | 1868/5625 [01:36<03:18, 18.90it/s]
 33%|███▎      | 1870/5625 [01:36<03:16, 19.16it/s]
 33%|███▎      | 1872/5625 [01:36<03:15, 19.21it/s]
 33%|███▎      | 1875/5625 [01:36<03:12, 19.45it/s]
                                                   

 33%|███▎      | 1875/5625 [01:36<03:12, 19.45it/s]{'loss': 0.7835, 'learning_rate': 4.048896463792234e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.17it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.25it/s]

 21%|██        | 66/313 [00:00<00:01, 205.56it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.97it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.35it/s]

 40%|████      | 126/313 [00:00<00:01, 185.10it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.87it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.89it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.01it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.15it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.25it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.96it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.61it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.49it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.31it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.31it/s]
 33%|███▎      | 1875/5625 [01:38<03:12, 19.45it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 1877/5625 [01:39<25:44,  2.43it/s]
 33%|███▎      | 1879/5625 [01:39<19:35,  3.19it/s]
 33%|███▎      | 1881/5625 [01:39<15:00,  4.16it/s]
 33%|███▎      | 1883/5625 [01:39<11:37,  5.36it/s]
 34%|███▎      | 1885/5625 [01:40<09:12,  6.77it/s]
 34%|███▎      | 1887/5625 [01:40<07:28,  8.33it/s]
 34%|███▎      | 1889/5625 [01:40<06:17,  9.89it/s]
 34%|███▎      | 1891/5625 [01:40<05:25, 11.48it/s]
 34%|███▎      | 1894/5625 [01:40<04:33, 13.64it/s]
 34%|███▎      | 1896/5625 [01:40<04:14, 14.63it/s]
 34%|███▍      | 1899/5625 [01:40<03:46, 16.47it/s]
 34%|███▍      | 1902/5625 [01:40<03:30, 17.69it/s]
 34%|███▍      | 1904/5625 [01:41<03:29, 17.73it/s]
 34%|███▍      | 1906/5625 [01:41<03:24, 18.15it/s]
 34%|███▍      | 1908/5625 [01:41<03:26, 17.97it/s]
 34%|███▍      | 1910/5625 [01:41<03:28, 17.84it/s]
 34%|███▍      | 1912/5625 [01:41<03:22, 18.35it/s]
 34%|███▍      | 1915/5625 [01:41<03:16, 18.85it/s]
 34%|███▍      | 1918/5625 [01:41<03:06, 19.91it/s]
 34%|███▍      | 1921/5625 [01:41<03:13, 19.16it/s]
 34%|███▍      | 1923/5625 [01:41<03:14, 19.07it/s]
 34%|███▍      | 1925/5625 [01:42<03:12, 19.24it/s]
 34%|███▍      | 1927/5625 [01:42<03:14, 19.02it/s]
 34%|███▍      | 1930/5625 [01:42<03:09, 19.53it/s]
 34%|███▍      | 1932/5625 [01:42<03:08, 19.57it/s]
 34%|███▍      | 1934/5625 [01:42<03:10, 19.41it/s]
 34%|███▍      | 1937/5625 [01:42<03:05, 19.92it/s]
 34%|███▍      | 1939/5625 [01:42<03:10, 19.35it/s]
 35%|███▍      | 1942/5625 [01:42<03:06, 19.71it/s]
 35%|███▍      | 1944/5625 [01:43<03:10, 19.29it/s]
 35%|███▍      | 1946/5625 [01:43<03:14, 18.96it/s]
 35%|███▍      | 1949/5625 [01:43<03:12, 19.11it/s]
 35%|███▍      | 1951/5625 [01:43<03:12, 19.04it/s]
 35%|███▍      | 1953/5625 [01:43<03:17, 18.59it/s]
 35%|███▍      | 1955/5625 [01:43<03:16, 18.69it/s]
 35%|███▍      | 1958/5625 [01:43<03:11, 19.18it/s]
 35%|███▍      | 1960/5625 [01:43<03:16, 18.63it/s]
 35%|███▍      | 1963/5625 [01:44<03:12, 19.02it/s]
 35%|███▍      | 1965/5625 [01:44<03:13, 18.87it/s]
 35%|███▍      | 1968/5625 [01:44<03:09, 19.32it/s]
 35%|███▌      | 1970/5625 [01:44<03:10, 19.17it/s]
 35%|███▌      | 1972/5625 [01:44<03:10, 19.13it/s]
 35%|███▌      | 1975/5625 [01:44<03:02, 20.03it/s]
 35%|███▌      | 1977/5625 [01:44<03:02, 19.94it/s]
 35%|███▌      | 1980/5625 [01:44<02:57, 20.48it/s]
 35%|███▌      | 1983/5625 [01:45<03:05, 19.60it/s]
 35%|███▌      | 1986/5625 [01:45<03:04, 19.71it/s]
 35%|███▌      | 1988/5625 [01:45<03:06, 19.54it/s]
 35%|███▌      | 1990/5625 [01:45<03:11, 18.98it/s]
 35%|███▌      | 1992/5625 [01:45<03:11, 18.96it/s]
 35%|███▌      | 1994/5625 [01:45<03:13, 18.74it/s]
 35%|███▌      | 1996/5625 [01:45<03:12, 18.89it/s]
 36%|███▌      | 1999/5625 [01:45<03:04, 19.64it/s]
 36%|███▌      | 2001/5625 [01:46<03:05, 19.56it/s]
 36%|███▌      | 2004/5625 [01:46<03:00, 20.05it/s]
 36%|███▌      | 2006/5625 [01:46<03:00, 20.03it/s]
 36%|███▌      | 2008/5625 [01:46<03:06, 19.43it/s]
 36%|███▌      | 2010/5625 [01:46<03:08, 19.14it/s]
 36%|███▌      | 2012/5625 [01:46<03:08, 19.20it/s]
 36%|███▌      | 2015/5625 [01:46<03:00, 19.98it/s]
 36%|███▌      | 2017/5625 [01:46<03:01, 19.89it/s]
 36%|███▌      | 2019/5625 [01:46<03:03, 19.60it/s]
 36%|███▌      | 2021/5625 [01:47<03:07, 19.21it/s]
 36%|███▌      | 2023/5625 [01:47<03:06, 19.35it/s]
 36%|███▌      | 2025/5625 [01:47<03:04, 19.50it/s]
 36%|███▌      | 2027/5625 [01:47<03:08, 19.06it/s]
 36%|███▌      | 2029/5625 [01:47<03:10, 18.92it/s]
 36%|███▌      | 2031/5625 [01:47<03:12, 18.66it/s]
 36%|███▌      | 2033/5625 [01:47<03:11, 18.74it/s]
 36%|███▌      | 2036/5625 [01:47<03:01, 19.80it/s]
 36%|███▌      | 2038/5625 [01:47<03:04, 19.48it/s]
 36%|███▋      | 2041/5625 [01:48<03:05, 19.36it/s]
 36%|███▋      | 2043/5625 [01:48<03:08, 18.99it/s]
 36%|███▋      | 2045/5625 [01:48<03:09, 18.86it/s]
 36%|███▋      | 2047/5625 [01:48<03:15, 18.32it/s]
 36%|███▋      | 2049/5625 [01:48<03:13, 18.50it/s]
 36%|███▋      | 2051/5625 [01:48<03:09, 18.84it/s]
 37%|███▋      | 2054/5625 [01:48<03:06, 19.13it/s]
 37%|███▋      | 2057/5625 [01:48<03:02, 19.60it/s]
 37%|███▋      | 2059/5625 [01:49<03:02, 19.54it/s]
 37%|███▋      | 2061/5625 [01:49<03:04, 19.29it/s]
 37%|███▋      | 2064/5625 [01:49<03:04, 19.34it/s]
 37%|███▋      | 2067/5625 [01:49<02:56, 20.20it/s]
 37%|███▋      | 2070/5625 [01:49<03:03, 19.42it/s]
 37%|███▋      | 2072/5625 [01:49<03:03, 19.39it/s]
 37%|███▋      | 2074/5625 [01:49<03:07, 18.95it/s]
 37%|███▋      | 2077/5625 [01:49<03:00, 19.69it/s]
 37%|███▋      | 2080/5625 [01:50<02:58, 19.81it/s]
 37%|███▋      | 2082/5625 [01:50<03:02, 19.37it/s]
 37%|███▋      | 2084/5625 [01:50<03:04, 19.22it/s]
 37%|███▋      | 2086/5625 [01:50<03:07, 18.92it/s]
 37%|███▋      | 2088/5625 [01:50<03:10, 18.56it/s]
 37%|███▋      | 2090/5625 [01:50<03:13, 18.25it/s]
 37%|███▋      | 2092/5625 [01:50<03:10, 18.50it/s]
 37%|███▋      | 2095/5625 [01:50<03:04, 19.08it/s]
 37%|███▋      | 2097/5625 [01:51<03:03, 19.28it/s]
 37%|███▋      | 2100/5625 [01:51<02:57, 19.84it/s]
 37%|███▋      | 2102/5625 [01:51<03:00, 19.55it/s]
 37%|███▋      | 2104/5625 [01:51<03:03, 19.24it/s]
 37%|███▋      | 2107/5625 [01:51<02:56, 19.89it/s]
 38%|███▊      | 2110/5625 [01:51<02:57, 19.75it/s]
 38%|███▊      | 2112/5625 [01:51<03:01, 19.31it/s]
 38%|███▊      | 2115/5625 [01:51<02:56, 19.93it/s]
 38%|███▊      | 2118/5625 [01:52<02:58, 19.67it/s]
 38%|███▊      | 2120/5625 [01:52<03:03, 19.12it/s]
 38%|███▊      | 2122/5625 [01:52<03:05, 18.89it/s]
 38%|███▊      | 2124/5625 [01:52<03:07, 18.66it/s]
 38%|███▊      | 2126/5625 [01:52<03:10, 18.40it/s]
 38%|███▊      | 2128/5625 [01:52<03:09, 18.46it/s]
 38%|███▊      | 2130/5625 [01:52<03:08, 18.53it/s]
 38%|███▊      | 2132/5625 [01:52<03:07, 18.68it/s]
 38%|███▊      | 2134/5625 [01:52<03:06, 18.69it/s]
 38%|███▊      | 2137/5625 [01:53<03:04, 18.92it/s]
 38%|███▊      | 2139/5625 [01:53<03:05, 18.78it/s]
 38%|███▊      | 2141/5625 [01:53<03:05, 18.77it/s]
 38%|███▊      | 2143/5625 [01:53<03:03, 18.98it/s]
 38%|███▊      | 2146/5625 [01:53<03:02, 19.08it/s]
 38%|███▊      | 2148/5625 [01:53<03:06, 18.63it/s]
 38%|███▊      | 2150/5625 [01:53<03:08, 18.44it/s]
 38%|███▊      | 2153/5625 [01:53<02:58, 19.41it/s]
 38%|███▊      | 2155/5625 [01:54<03:02, 19.03it/s]
 38%|███▊      | 2158/5625 [01:54<02:55, 19.73it/s]
 38%|███▊      | 2160/5625 [01:54<02:55, 19.70it/s]
 38%|███▊      | 2162/5625 [01:54<03:00, 19.24it/s]
 38%|███▊      | 2164/5625 [01:54<02:59, 19.24it/s]
 39%|███▊      | 2167/5625 [01:54<02:53, 19.95it/s]
 39%|███▊      | 2169/5625 [01:54<02:57, 19.47it/s]
 39%|███▊      | 2172/5625 [01:54<02:52, 20.05it/s]
 39%|███▊      | 2174/5625 [01:55<02:56, 19.59it/s]
 39%|███▊      | 2176/5625 [01:55<02:57, 19.44it/s]
 39%|███▊      | 2178/5625 [01:55<03:00, 19.14it/s]
 39%|███▉      | 2180/5625 [01:55<02:57, 19.36it/s]
 39%|███▉      | 2182/5625 [01:55<03:03, 18.73it/s]
 39%|███▉      | 2185/5625 [01:55<02:55, 19.64it/s]
 39%|███▉      | 2187/5625 [01:55<02:55, 19.64it/s]
 39%|███▉      | 2190/5625 [01:55<02:52, 19.89it/s]
 39%|███▉      | 2192/5625 [01:55<02:52, 19.85it/s]
 39%|███▉      | 2195/5625 [01:56<02:46, 20.56it/s]
 39%|███▉      | 2198/5625 [01:56<02:50, 20.14it/s]
 39%|███▉      | 2201/5625 [01:56<02:54, 19.67it/s]
 39%|███▉      | 2203/5625 [01:56<02:57, 19.23it/s]
 39%|███▉      | 2205/5625 [01:56<02:56, 19.34it/s]
 39%|███▉      | 2207/5625 [01:56<02:55, 19.45it/s]
 39%|███▉      | 2209/5625 [01:56<02:54, 19.59it/s]
 39%|███▉      | 2211/5625 [01:56<02:56, 19.33it/s]
 39%|███▉      | 2213/5625 [01:57<02:58, 19.10it/s]
 39%|███▉      | 2216/5625 [01:57<02:54, 19.59it/s]
 39%|███▉      | 2218/5625 [01:57<02:55, 19.46it/s]
 39%|███▉      | 2220/5625 [01:57<02:56, 19.29it/s]
 40%|███▉      | 2222/5625 [01:57<03:00, 18.82it/s]
 40%|███▉      | 2224/5625 [01:57<02:58, 19.00it/s]
 40%|███▉      | 2226/5625 [01:57<03:02, 18.58it/s]
 40%|███▉      | 2228/5625 [01:57<03:00, 18.85it/s]
 40%|███▉      | 2230/5625 [01:57<03:03, 18.46it/s]
 40%|███▉      | 2232/5625 [01:58<03:03, 18.51it/s]
 40%|███▉      | 2234/5625 [01:58<03:01, 18.65it/s]
 40%|███▉      | 2236/5625 [01:58<03:00, 18.81it/s]
 40%|███▉      | 2238/5625 [01:58<03:01, 18.66it/s]
 40%|███▉      | 2240/5625 [01:58<03:05, 18.24it/s]
 40%|███▉      | 2242/5625 [01:58<03:03, 18.45it/s]
 40%|███▉      | 2244/5625 [01:58<03:02, 18.53it/s]
 40%|███▉      | 2246/5625 [01:58<03:02, 18.53it/s]
 40%|███▉      | 2248/5625 [01:58<02:59, 18.82it/s]
 40%|████      | 2250/5625 [01:58<02:59, 18.85it/s]
 40%|████      | 2253/5625 [01:59<02:55, 19.25it/s]
 40%|████      | 2256/5625 [01:59<02:53, 19.38it/s]
 40%|████      | 2258/5625 [01:59<02:55, 19.16it/s]
 40%|████      | 2260/5625 [01:59<04:04, 13.77it/s]
 40%|████      | 2263/5625 [01:59<03:32, 15.82it/s]
 40%|████      | 2265/5625 [01:59<03:22, 16.62it/s]
 40%|████      | 2267/5625 [02:00<03:13, 17.34it/s]
 40%|████      | 2269/5625 [02:00<03:09, 17.68it/s]
 40%|████      | 2271/5625 [02:00<03:06, 18.02it/s]
 40%|████      | 2274/5625 [02:00<02:57, 18.85it/s]
 40%|████      | 2277/5625 [02:00<02:54, 19.18it/s]
 41%|████      | 2279/5625 [02:00<02:57, 18.88it/s]
 41%|████      | 2281/5625 [02:00<02:55, 19.01it/s]
 41%|████      | 2283/5625 [02:00<02:54, 19.15it/s]
 41%|████      | 2285/5625 [02:00<02:54, 19.17it/s]
 41%|████      | 2287/5625 [02:01<02:55, 19.05it/s]
 41%|████      | 2289/5625 [02:01<02:58, 18.65it/s]
 41%|████      | 2292/5625 [02:01<02:52, 19.28it/s]
 41%|████      | 2294/5625 [02:01<02:56, 18.82it/s]
 41%|████      | 2296/5625 [02:01<02:57, 18.77it/s]
 41%|████      | 2298/5625 [02:01<02:59, 18.59it/s]
 41%|████      | 2300/5625 [02:01<02:55, 18.92it/s]
 41%|████      | 2302/5625 [02:01<02:58, 18.66it/s]
 41%|████      | 2305/5625 [02:01<02:48, 19.70it/s]
 41%|████      | 2308/5625 [02:02<02:46, 19.89it/s]
 41%|████      | 2310/5625 [02:02<02:47, 19.83it/s]
 41%|████      | 2312/5625 [02:02<02:51, 19.27it/s]
 41%|████      | 2314/5625 [02:02<02:54, 18.99it/s]
 41%|████      | 2317/5625 [02:02<02:45, 19.98it/s]
 41%|████      | 2320/5625 [02:02<02:39, 20.70it/s]
 41%|████▏     | 2323/5625 [02:02<02:45, 19.97it/s]
 41%|████▏     | 2325/5625 [02:03<02:50, 19.36it/s]
 41%|████▏     | 2327/5625 [02:03<02:51, 19.23it/s]
 41%|████▏     | 2330/5625 [02:03<02:48, 19.53it/s]
 41%|████▏     | 2332/5625 [02:03<02:52, 19.07it/s]
 41%|████▏     | 2334/5625 [02:03<02:51, 19.23it/s]
 42%|████▏     | 2336/5625 [02:03<02:55, 18.71it/s]
 42%|████▏     | 2339/5625 [02:03<02:54, 18.87it/s]
 42%|████▏     | 2341/5625 [02:03<02:58, 18.43it/s]
 42%|████▏     | 2343/5625 [02:03<02:57, 18.49it/s]
 42%|████▏     | 2345/5625 [02:04<02:58, 18.42it/s]
 42%|████▏     | 2347/5625 [02:04<02:54, 18.76it/s]
 42%|████▏     | 2349/5625 [02:04<02:53, 18.90it/s]
 42%|████▏     | 2351/5625 [02:04<02:52, 19.00it/s]
 42%|████▏     | 2353/5625 [02:04<02:53, 18.84it/s]
 42%|████▏     | 2355/5625 [02:04<02:50, 19.14it/s]
 42%|████▏     | 2358/5625 [02:04<02:50, 19.17it/s]
 42%|████▏     | 2361/5625 [02:04<02:47, 19.45it/s]
 42%|████▏     | 2363/5625 [02:05<02:48, 19.39it/s]
 42%|████▏     | 2365/5625 [02:05<02:47, 19.47it/s]
 42%|████▏     | 2367/5625 [02:05<02:48, 19.30it/s]
 42%|████▏     | 2369/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2371/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2374/5625 [02:05<02:44, 19.73it/s]
 42%|████▏     | 2376/5625 [02:05<02:45, 19.69it/s]
 42%|████▏     | 2378/5625 [02:05<02:48, 19.25it/s]
 42%|████▏     | 2380/5625 [02:05<02:53, 18.69it/s]
 42%|████▏     | 2382/5625 [02:06<02:54, 18.55it/s]
 42%|████▏     | 2385/5625 [02:06<02:43, 19.85it/s]
 42%|████▏     | 2387/5625 [02:06<02:42, 19.87it/s]
 42%|████▏     | 2389/5625 [02:06<02:43, 19.82it/s]
 43%|████▎     | 2391/5625 [02:06<02:43, 19.83it/s]
 43%|████▎     | 2393/5625 [02:06<02:46, 19.45it/s]
 43%|████▎     | 2395/5625 [02:06<02:46, 19.34it/s]
 43%|████▎     | 2398/5625 [02:06<02:38, 20.41it/s]
 43%|████▎     | 2401/5625 [02:06<02:42, 19.80it/s]
 43%|████▎     | 2403/5625 [02:07<02:44, 19.55it/s]
 43%|████▎     | 2405/5625 [02:07<02:44, 19.59it/s]
 43%|████▎     | 2407/5625 [02:07<02:44, 19.61it/s]
 43%|████▎     | 2410/5625 [02:07<02:43, 19.72it/s]
 43%|████▎     | 2413/5625 [02:07<02:41, 19.88it/s]
 43%|████▎     | 2415/5625 [02:07<02:46, 19.22it/s]
 43%|████▎     | 2418/5625 [02:07<02:40, 19.94it/s]
 43%|████▎     | 2420/5625 [02:07<02:44, 19.46it/s]
 43%|████▎     | 2422/5625 [02:08<02:44, 19.42it/s]
 43%|████▎     | 2425/5625 [02:08<02:43, 19.58it/s]
 43%|████▎     | 2427/5625 [02:08<02:44, 19.49it/s]
 43%|████▎     | 2429/5625 [02:08<02:43, 19.55it/s]
 43%|████▎     | 2432/5625 [02:08<02:35, 20.48it/s]
 43%|████▎     | 2435/5625 [02:08<02:31, 21.02it/s]
 43%|████▎     | 2438/5625 [02:08<02:33, 20.81it/s]
 43%|████▎     | 2441/5625 [02:08<02:36, 20.39it/s]
 43%|████▎     | 2444/5625 [02:09<02:37, 20.19it/s]
 44%|████▎     | 2447/5625 [02:09<02:42, 19.52it/s]
 44%|████▎     | 2450/5625 [02:09<02:38, 19.99it/s]
 44%|████▎     | 2453/5625 [02:09<02:38, 20.05it/s]
 44%|████▎     | 2456/5625 [02:09<02:36, 20.24it/s]
 44%|████▎     | 2459/5625 [02:09<02:39, 19.90it/s]
 44%|████▍     | 2461/5625 [02:09<02:41, 19.61it/s]
 44%|████▍     | 2464/5625 [02:10<02:40, 19.70it/s]
 44%|████▍     | 2467/5625 [02:10<02:41, 19.52it/s]
 44%|████▍     | 2469/5625 [02:10<02:41, 19.60it/s]
 44%|████▍     | 2471/5625 [02:10<02:41, 19.49it/s]
 44%|████▍     | 2474/5625 [02:10<02:39, 19.78it/s]
 44%|████▍     | 2476/5625 [02:10<02:39, 19.77it/s]
 44%|████▍     | 2478/5625 [02:10<02:44, 19.11it/s]
 44%|████▍     | 2480/5625 [02:10<02:43, 19.29it/s]
 44%|████▍     | 2483/5625 [02:11<02:35, 20.16it/s]
 44%|████▍     | 2486/5625 [02:11<02:37, 19.98it/s]
 44%|████▍     | 2488/5625 [02:11<02:42, 19.33it/s]
 44%|████▍     | 2490/5625 [02:11<02:43, 19.15it/s]
 44%|████▍     | 2492/5625 [02:11<02:47, 18.72it/s]
 44%|████▍     | 2495/5625 [02:11<02:43, 19.10it/s]
 44%|████▍     | 2497/5625 [02:11<02:46, 18.73it/s]
 44%|████▍     | 2499/5625 [02:11<02:46, 18.74it/s]
 44%|████▍     | 2502/5625 [02:12<02:38, 19.66it/s]
 45%|████▍     | 2504/5625 [02:12<02:38, 19.68it/s]
 45%|████▍     | 2507/5625 [02:12<02:31, 20.64it/s]
 45%|████▍     | 2510/5625 [02:12<02:36, 19.87it/s]
 45%|████▍     | 2513/5625 [02:12<02:31, 20.52it/s]
 45%|████▍     | 2516/5625 [02:12<02:30, 20.66it/s]
 45%|████▍     | 2519/5625 [02:12<02:30, 20.68it/s]
 45%|████▍     | 2522/5625 [02:13<02:36, 19.84it/s]
 45%|████▍     | 2525/5625 [02:13<02:32, 20.28it/s]
 45%|████▍     | 2528/5625 [02:13<02:38, 19.60it/s]
 45%|████▍     | 2530/5625 [02:13<02:38, 19.48it/s]
 45%|████▌     | 2532/5625 [02:13<02:42, 19.08it/s]
 45%|████▌     | 2534/5625 [02:13<02:45, 18.71it/s]
 45%|████▌     | 2536/5625 [02:13<02:45, 18.68it/s]
 45%|████▌     | 2538/5625 [02:13<02:47, 18.42it/s]
 45%|████▌     | 2540/5625 [02:14<02:50, 18.14it/s]
 45%|████▌     | 2542/5625 [02:14<02:47, 18.44it/s]
 45%|████▌     | 2545/5625 [02:14<02:39, 19.26it/s]
 45%|████▌     | 2547/5625 [02:14<02:43, 18.87it/s]
 45%|████▌     | 2549/5625 [02:14<02:42, 18.87it/s]
 45%|████▌     | 2551/5625 [02:14<02:41, 19.01it/s]
 45%|████▌     | 2553/5625 [02:14<02:39, 19.28it/s]
 45%|████▌     | 2555/5625 [02:14<02:41, 19.07it/s]
 45%|████▌     | 2557/5625 [02:14<02:39, 19.26it/s]
 45%|████▌     | 2559/5625 [02:15<02:40, 19.05it/s]
 46%|████▌     | 2561/5625 [02:15<02:40, 19.12it/s]
 46%|████▌     | 2563/5625 [02:15<02:39, 19.20it/s]
 46%|████▌     | 2565/5625 [02:15<02:43, 18.69it/s]
 46%|████▌     | 2568/5625 [02:15<02:39, 19.14it/s]
 46%|████▌     | 2571/5625 [02:15<02:33, 19.88it/s]
 46%|████▌     | 2574/5625 [02:15<02:33, 19.84it/s]
 46%|████▌     | 2576/5625 [02:15<02:39, 19.13it/s]
 46%|████▌     | 2579/5625 [02:16<02:37, 19.33it/s]
 46%|████▌     | 2581/5625 [02:16<02:40, 18.99it/s]
 46%|████▌     | 2583/5625 [02:16<02:44, 18.52it/s]
 46%|████▌     | 2586/5625 [02:16<02:39, 19.08it/s]
 46%|████▌     | 2589/5625 [02:16<02:33, 19.76it/s]
 46%|████▌     | 2591/5625 [02:16<02:37, 19.24it/s]
 46%|████▌     | 2594/5625 [02:16<02:36, 19.34it/s]
 46%|████▌     | 2596/5625 [02:16<02:39, 18.99it/s]
 46%|████▌     | 2598/5625 [02:17<02:43, 18.55it/s]
 46%|████▌     | 2601/5625 [02:17<02:38, 19.04it/s]
 46%|████▋     | 2603/5625 [02:17<02:41, 18.70it/s]
 46%|████▋     | 2605/5625 [02:17<02:45, 18.29it/s]
 46%|████▋     | 2607/5625 [02:17<02:43, 18.48it/s]
 46%|████▋     | 2609/5625 [02:17<02:42, 18.55it/s]
 46%|████▋     | 2611/5625 [02:17<02:45, 18.21it/s]
 46%|████▋     | 2613/5625 [02:17<02:44, 18.26it/s]
 47%|████▋     | 2616/5625 [02:18<02:39, 18.84it/s]
 47%|████▋     | 2618/5625 [02:18<02:39, 18.86it/s]
 47%|████▋     | 2620/5625 [02:18<02:40, 18.71it/s]
 47%|████▋     | 2623/5625 [02:18<02:36, 19.16it/s]
 47%|████▋     | 2625/5625 [02:18<02:37, 19.04it/s]
 47%|████▋     | 2627/5625 [02:18<02:39, 18.80it/s]
 47%|████▋     | 2629/5625 [02:18<02:40, 18.71it/s]
 47%|████▋     | 2632/5625 [02:18<02:34, 19.33it/s]
 47%|████▋     | 2634/5625 [02:18<02:36, 19.09it/s]
 47%|████▋     | 2636/5625 [02:19<02:37, 19.04it/s]
 47%|████▋     | 2638/5625 [02:19<02:34, 19.27it/s]
 47%|████▋     | 2640/5625 [02:19<02:35, 19.18it/s]
 47%|████▋     | 2643/5625 [02:19<02:29, 19.89it/s]
 47%|████▋     | 2645/5625 [02:19<02:30, 19.75it/s]
 47%|████▋     | 2647/5625 [02:19<02:33, 19.38it/s]
 47%|████▋     | 2649/5625 [02:19<02:34, 19.29it/s]
 47%|████▋     | 2651/5625 [02:19<02:37, 18.93it/s]
 47%|████▋     | 2653/5625 [02:19<02:39, 18.60it/s]
 47%|████▋     | 2655/5625 [02:20<02:40, 18.52it/s]
 47%|████▋     | 2658/5625 [02:20<02:32, 19.47it/s]
 47%|████▋     | 2661/5625 [02:20<02:26, 20.22it/s]
 47%|████▋     | 2664/5625 [02:20<02:27, 20.05it/s]
 47%|████▋     | 2666/5625 [02:20<02:30, 19.65it/s]
 47%|████▋     | 2669/5625 [02:20<02:27, 20.01it/s]
 47%|████▋     | 2671/5625 [02:20<02:29, 19.75it/s]
 48%|████▊     | 2673/5625 [02:20<02:29, 19.70it/s]
 48%|████▊     | 2676/5625 [02:21<02:30, 19.66it/s]
 48%|████▊     | 2678/5625 [02:21<02:32, 19.29it/s]
 48%|████▊     | 2680/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2682/5625 [02:21<02:31, 19.42it/s]
 48%|████▊     | 2684/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2686/5625 [02:21<02:30, 19.47it/s]
 48%|████▊     | 2688/5625 [02:21<02:31, 19.40it/s]
 48%|████▊     | 2691/5625 [02:21<02:30, 19.44it/s]
 48%|████▊     | 2693/5625 [02:22<02:34, 18.96it/s]
 48%|████▊     | 2696/5625 [02:22<02:27, 19.80it/s]
 48%|████▊     | 2699/5625 [02:22<02:24, 20.24it/s]
 48%|████▊     | 2702/5625 [02:22<02:27, 19.82it/s]
 48%|████▊     | 2704/5625 [02:22<02:29, 19.49it/s]
 48%|████▊     | 2706/5625 [02:22<02:33, 18.98it/s]
 48%|████▊     | 2709/5625 [02:22<02:30, 19.35it/s]
 48%|████▊     | 2711/5625 [02:22<02:34, 18.90it/s]
 48%|████▊     | 2713/5625 [02:23<02:34, 18.87it/s]
 48%|████▊     | 2715/5625 [02:23<02:37, 18.46it/s]
 48%|████▊     | 2717/5625 [02:23<02:34, 18.77it/s]
 48%|████▊     | 2719/5625 [02:23<02:38, 18.35it/s]
 48%|████▊     | 2721/5625 [02:23<02:35, 18.69it/s]
 48%|████▊     | 2723/5625 [02:23<02:35, 18.68it/s]
 48%|████▊     | 2725/5625 [02:23<02:33, 18.86it/s]
 48%|████▊     | 2727/5625 [02:23<02:31, 19.15it/s]
 49%|████▊     | 2730/5625 [02:23<02:28, 19.56it/s]
 49%|████▊     | 2732/5625 [02:24<02:29, 19.37it/s]
 49%|████▊     | 2734/5625 [02:24<02:32, 18.96it/s]
 49%|████▊     | 2737/5625 [02:24<02:26, 19.77it/s]
 49%|████▊     | 2739/5625 [02:24<02:26, 19.66it/s]
 49%|████▊     | 2741/5625 [02:24<02:29, 19.30it/s]
 49%|████▉     | 2743/5625 [02:24<02:31, 19.04it/s]
 49%|████▉     | 2746/5625 [02:24<02:29, 19.31it/s]
 49%|████▉     | 2748/5625 [02:24<02:28, 19.38it/s]
 49%|████▉     | 2750/5625 [02:24<02:27, 19.47it/s]
 49%|████▉     | 2752/5625 [02:25<02:27, 19.46it/s]
 49%|████▉     | 2754/5625 [02:25<02:28, 19.32it/s]
 49%|████▉     | 2757/5625 [02:25<02:29, 19.21it/s]
 49%|████▉     | 2760/5625 [02:25<02:25, 19.69it/s]
 49%|████▉     | 2762/5625 [02:25<02:27, 19.42it/s]
 49%|████▉     | 2764/5625 [02:25<02:30, 18.98it/s]
 49%|████▉     | 2767/5625 [02:25<02:25, 19.61it/s]
 49%|████▉     | 2770/5625 [02:25<02:24, 19.77it/s]
 49%|████▉     | 2772/5625 [02:26<02:28, 19.28it/s]
 49%|████▉     | 2774/5625 [02:26<02:27, 19.33it/s]
 49%|████▉     | 2776/5625 [02:26<02:26, 19.44it/s]
 49%|████▉     | 2778/5625 [02:26<02:28, 19.21it/s]
 49%|████▉     | 2780/5625 [02:26<02:29, 19.01it/s]
 49%|████▉     | 2783/5625 [02:26<02:27, 19.22it/s]
 50%|████▉     | 2785/5625 [02:26<02:29, 18.99it/s]
 50%|████▉     | 2788/5625 [02:26<02:23, 19.76it/s]
 50%|████▉     | 2790/5625 [02:27<02:26, 19.33it/s]
 50%|████▉     | 2792/5625 [02:27<02:27, 19.17it/s]
 50%|████▉     | 2794/5625 [02:27<02:26, 19.34it/s]
 50%|████▉     | 2796/5625 [02:27<02:31, 18.73it/s]
 50%|████▉     | 2798/5625 [02:27<02:29, 18.88it/s]
 50%|████▉     | 2800/5625 [02:27<02:27, 19.15it/s]
 50%|████▉     | 2802/5625 [02:27<02:31, 18.58it/s]
 50%|████▉     | 2804/5625 [02:27<02:29, 18.88it/s]
 50%|████▉     | 2806/5625 [02:27<02:28, 18.93it/s]
 50%|████▉     | 2809/5625 [02:28<02:27, 19.13it/s]
 50%|████▉     | 2811/5625 [02:28<02:26, 19.25it/s]
 50%|█████     | 2814/5625 [02:28<02:23, 19.52it/s]
 50%|█████     | 2816/5625 [02:28<02:25, 19.29it/s]
 50%|█████     | 2818/5625 [02:28<02:25, 19.31it/s]
 50%|█████     | 2820/5625 [02:28<02:29, 18.73it/s]
 50%|█████     | 2822/5625 [02:28<02:28, 18.91it/s]
 50%|█████     | 2824/5625 [02:28<02:25, 19.19it/s]
 50%|█████     | 2827/5625 [02:28<02:19, 20.04it/s]
 50%|█████     | 2829/5625 [02:29<02:21, 19.70it/s]
 50%|█████     | 2831/5625 [02:29<02:23, 19.43it/s]
 50%|█████     | 2833/5625 [02:29<02:26, 19.07it/s]
 50%|█████     | 2835/5625 [02:29<02:24, 19.26it/s]
 50%|█████     | 2838/5625 [02:29<02:20, 19.81it/s]
 50%|█████     | 2840/5625 [02:29<02:21, 19.73it/s]
 51%|█████     | 2843/5625 [02:29<02:16, 20.42it/s]
 51%|█████     | 2846/5625 [02:29<02:22, 19.52it/s]
 51%|█████     | 2849/5625 [02:30<02:21, 19.59it/s]
 51%|█████     | 2851/5625 [02:30<02:23, 19.37it/s]
 51%|█████     | 2853/5625 [02:30<02:25, 19.08it/s]
 51%|█████     | 2856/5625 [02:30<02:21, 19.61it/s]
 51%|█████     | 2858/5625 [02:30<02:25, 19.03it/s]
 51%|█████     | 2861/5625 [02:30<02:18, 19.94it/s]
 51%|█████     | 2863/5625 [02:30<02:20, 19.67it/s]
 51%|█████     | 2865/5625 [02:30<02:22, 19.38it/s]
 51%|█████     | 2867/5625 [02:31<02:21, 19.47it/s]
 51%|█████     | 2870/5625 [02:31<02:15, 20.30it/s]
 51%|█████     | 2873/5625 [02:31<02:18, 19.84it/s]
 51%|█████     | 2875/5625 [02:31<02:20, 19.56it/s]
 51%|█████     | 2877/5625 [02:31<02:21, 19.45it/s]
 51%|█████     | 2879/5625 [02:31<02:23, 19.15it/s]
 51%|█████     | 2882/5625 [02:31<02:21, 19.38it/s]
 51%|█████▏    | 2884/5625 [02:31<02:23, 19.13it/s]
 51%|█████▏    | 2887/5625 [02:32<02:16, 20.07it/s]
 51%|█████▏    | 2889/5625 [02:32<02:21, 19.29it/s]
 51%|█████▏    | 2891/5625 [02:32<02:20, 19.41it/s]
 51%|█████▏    | 2894/5625 [02:32<02:16, 19.99it/s]
 51%|█████▏    | 2896/5625 [02:32<02:19, 19.50it/s]
 52%|█████▏    | 2898/5625 [02:32<02:20, 19.34it/s]
 52%|█████▏    | 2900/5625 [02:32<02:26, 18.65it/s]
 52%|█████▏    | 2903/5625 [02:32<02:19, 19.55it/s]
 52%|█████▏    | 2906/5625 [02:32<02:14, 20.14it/s]
 52%|█████▏    | 2908/5625 [02:33<02:16, 19.85it/s]
 52%|█████▏    | 2910/5625 [02:33<02:16, 19.84it/s]
 52%|█████▏    | 2913/5625 [02:33<02:14, 20.10it/s]
 52%|█████▏    | 2915/5625 [02:33<02:17, 19.77it/s]
 52%|█████▏    | 2917/5625 [02:33<02:20, 19.21it/s]
 52%|█████▏    | 2919/5625 [02:33<02:23, 18.80it/s]
 52%|█████▏    | 2921/5625 [02:33<02:26, 18.44it/s]
 52%|█████▏    | 2923/5625 [02:33<02:23, 18.80it/s]
 52%|█████▏    | 2925/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2927/5625 [02:34<02:25, 18.58it/s]
 52%|█████▏    | 2929/5625 [02:34<02:22, 18.91it/s]
 52%|█████▏    | 2931/5625 [02:34<02:21, 19.10it/s]
 52%|█████▏    | 2934/5625 [02:34<02:20, 19.21it/s]
 52%|█████▏    | 2937/5625 [02:34<02:19, 19.22it/s]
 52%|█████▏    | 2940/5625 [02:34<02:13, 20.06it/s]
 52%|█████▏    | 2943/5625 [02:34<02:11, 20.43it/s]
 52%|█████▏    | 2946/5625 [02:35<02:14, 19.87it/s]
 52%|█████▏    | 2948/5625 [02:35<02:15, 19.76it/s]
 52%|█████▏    | 2950/5625 [02:35<02:18, 19.33it/s]
 52%|█████▏    | 2952/5625 [02:35<02:18, 19.35it/s]
 53%|█████▎    | 2954/5625 [02:35<02:20, 18.99it/s]
 53%|█████▎    | 2957/5625 [02:35<02:17, 19.45it/s]
 53%|█████▎    | 2960/5625 [02:35<02:15, 19.61it/s]
 53%|█████▎    | 2963/5625 [02:35<02:15, 19.65it/s]
 53%|█████▎    | 2965/5625 [02:36<02:19, 19.05it/s]
 53%|█████▎    | 2967/5625 [02:36<02:17, 19.27it/s]
 53%|█████▎    | 2970/5625 [02:36<02:16, 19.41it/s]
 53%|█████▎    | 2973/5625 [02:36<02:14, 19.66it/s]
 53%|█████▎    | 2976/5625 [02:36<02:14, 19.69it/s]
 53%|█████▎    | 2978/5625 [02:36<02:15, 19.51it/s]
 53%|█████▎    | 2980/5625 [02:36<02:17, 19.20it/s]
 53%|█████▎    | 2983/5625 [02:36<02:17, 19.25it/s]
 53%|█████▎    | 2985/5625 [02:37<02:19, 18.91it/s]
 53%|█████▎    | 2988/5625 [02:37<02:16, 19.36it/s]
 53%|█████▎    | 2990/5625 [02:37<02:18, 19.08it/s]
 53%|█████▎    | 2992/5625 [02:37<02:16, 19.30it/s]
 53%|█████▎    | 2995/5625 [02:37<02:11, 19.95it/s]
 53%|█████▎    | 2997/5625 [02:37<02:14, 19.61it/s]
 53%|█████▎    | 2999/5625 [02:37<02:16, 19.30it/s]
 53%|█████▎    | 3002/5625 [02:37<02:12, 19.76it/s]
 53%|█████▎    | 3005/5625 [02:38<02:09, 20.24it/s]
 53%|█████▎    | 3008/5625 [02:38<02:11, 19.93it/s]
 54%|█████▎    | 3010/5625 [02:38<02:14, 19.51it/s]
 54%|█████▎    | 3012/5625 [02:38<02:15, 19.33it/s]
 54%|█████▎    | 3014/5625 [02:38<02:17, 18.94it/s]
 54%|█████▎    | 3017/5625 [02:38<02:13, 19.56it/s]
 54%|█████▎    | 3019/5625 [02:38<02:14, 19.33it/s]
 54%|█████▎    | 3022/5625 [02:38<02:13, 19.57it/s]
 54%|█████▍    | 3024/5625 [02:39<02:12, 19.67it/s]
 54%|█████▍    | 3027/5625 [02:39<02:09, 20.04it/s]
 54%|█████▍    | 3029/5625 [02:39<02:11, 19.77it/s]
 54%|█████▍    | 3032/5625 [02:39<02:09, 20.10it/s]
 54%|█████▍    | 3034/5625 [02:39<02:09, 20.00it/s]
 54%|█████▍    | 3037/5625 [02:39<02:07, 20.26it/s]
 54%|█████▍    | 3040/5625 [02:39<02:13, 19.38it/s]
 54%|█████▍    | 3042/5625 [02:39<02:15, 19.06it/s]
 54%|█████▍    | 3044/5625 [02:40<02:16, 18.95it/s]
 54%|█████▍    | 3047/5625 [02:40<02:14, 19.11it/s]
 54%|█████▍    | 3050/5625 [02:40<02:10, 19.77it/s]
 54%|█████▍    | 3053/5625 [02:40<02:09, 19.81it/s]
 54%|█████▍    | 3056/5625 [02:40<02:06, 20.30it/s]
 54%|█████▍    | 3059/5625 [02:40<02:08, 19.91it/s]
 54%|█████▍    | 3061/5625 [02:40<02:09, 19.79it/s]
 54%|█████▍    | 3063/5625 [02:41<02:09, 19.81it/s]
 54%|█████▍    | 3065/5625 [02:41<02:12, 19.27it/s]
 55%|█████▍    | 3068/5625 [02:41<02:10, 19.60it/s]
 55%|█████▍    | 3070/5625 [02:41<02:12, 19.29it/s]
 55%|█████▍    | 3072/5625 [02:41<02:12, 19.20it/s]
 55%|█████▍    | 3074/5625 [02:41<02:14, 18.99it/s]
 55%|█████▍    | 3077/5625 [02:41<02:08, 19.87it/s]
 55%|█████▍    | 3079/5625 [02:41<02:09, 19.60it/s]
 55%|█████▍    | 3081/5625 [02:41<02:11, 19.38it/s]
 55%|█████▍    | 3084/5625 [02:42<02:10, 19.43it/s]
 55%|█████▍    | 3086/5625 [02:42<02:10, 19.53it/s]
 55%|█████▍    | 3088/5625 [02:42<02:09, 19.61it/s]
 55%|█████▍    | 3090/5625 [02:42<02:10, 19.44it/s]
 55%|█████▍    | 3092/5625 [02:42<02:10, 19.43it/s]
 55%|█████▌    | 3095/5625 [02:42<02:10, 19.32it/s]
 55%|█████▌    | 3097/5625 [02:42<02:12, 19.08it/s]
 55%|█████▌    | 3100/5625 [02:42<02:10, 19.38it/s]
 55%|█████▌    | 3103/5625 [02:43<02:05, 20.17it/s]
 55%|█████▌    | 3106/5625 [02:43<02:07, 19.79it/s]
 55%|█████▌    | 3109/5625 [02:43<02:03, 20.42it/s]
 55%|█████▌    | 3112/5625 [02:43<02:08, 19.61it/s]
 55%|█████▌    | 3114/5625 [02:43<02:09, 19.39it/s]
 55%|█████▌    | 3116/5625 [02:43<02:12, 18.95it/s]
 55%|█████▌    | 3118/5625 [02:43<02:14, 18.59it/s]
 55%|█████▌    | 3120/5625 [02:43<02:12, 18.87it/s]
 56%|█████▌    | 3123/5625 [02:44<02:09, 19.26it/s]
 56%|█████▌    | 3125/5625 [02:44<02:09, 19.24it/s]
 56%|█████▌    | 3127/5625 [02:44<02:11, 19.07it/s]
 56%|█████▌    | 3129/5625 [02:44<02:13, 18.69it/s]
 56%|█████▌    | 3132/5625 [02:44<02:10, 19.03it/s]
 56%|█████▌    | 3134/5625 [02:44<02:11, 19.01it/s]
 56%|█████▌    | 3136/5625 [02:44<02:13, 18.69it/s]
 56%|█████▌    | 3138/5625 [02:44<02:13, 18.61it/s]
 56%|█████▌    | 3140/5625 [02:45<02:15, 18.31it/s]
 56%|█████▌    | 3143/5625 [02:45<02:07, 19.41it/s]
 56%|█████▌    | 3146/5625 [02:45<02:02, 20.30it/s]
 56%|█████▌    | 3149/5625 [02:45<02:06, 19.58it/s]
 56%|█████▌    | 3152/5625 [02:45<02:06, 19.59it/s]
 56%|█████▌    | 3155/5625 [02:45<02:03, 20.08it/s]
 56%|█████▌    | 3158/5625 [02:45<02:03, 19.92it/s]
 56%|█████▌    | 3160/5625 [02:46<02:06, 19.55it/s]
 56%|█████▌    | 3162/5625 [02:46<02:10, 18.93it/s]
 56%|█████▌    | 3164/5625 [02:46<02:11, 18.78it/s]
 56%|█████▋    | 3166/5625 [02:46<02:09, 18.99it/s]
 56%|█████▋    | 3168/5625 [02:46<02:10, 18.89it/s]
 56%|█████▋    | 3170/5625 [02:46<02:12, 18.50it/s]
 56%|█████▋    | 3172/5625 [02:46<02:13, 18.41it/s]
 56%|█████▋    | 3174/5625 [02:46<02:14, 18.18it/s]
 56%|█████▋    | 3176/5625 [02:46<02:14, 18.23it/s]
 56%|█████▋    | 3178/5625 [02:47<02:15, 18.12it/s]
 57%|█████▋    | 3180/5625 [02:47<02:12, 18.45it/s]
 57%|█████▋    | 3183/5625 [02:47<02:09, 18.83it/s]
 57%|█████▋    | 3185/5625 [02:47<02:11, 18.58it/s]
 57%|█████▋    | 3187/5625 [02:47<02:11, 18.52it/s]
 57%|█████▋    | 3189/5625 [02:47<02:08, 18.89it/s]
 57%|█████▋    | 3191/5625 [02:47<02:10, 18.69it/s]
 57%|█████▋    | 3194/5625 [02:47<02:09, 18.81it/s]
 57%|█████▋    | 3196/5625 [02:47<02:07, 19.08it/s]
 57%|█████▋    | 3198/5625 [02:48<02:07, 19.06it/s]
 57%|█████▋    | 3200/5625 [02:48<02:07, 19.00it/s]
 57%|█████▋    | 3203/5625 [02:48<02:04, 19.46it/s]
 57%|█████▋    | 3206/5625 [02:48<02:05, 19.32it/s]
 57%|█████▋    | 3209/5625 [02:48<02:03, 19.60it/s]
 57%|█████▋    | 3211/5625 [02:48<02:03, 19.62it/s]
 57%|█████▋    | 3213/5625 [02:48<02:02, 19.65it/s]
 57%|█████▋    | 3216/5625 [02:49<02:00, 19.92it/s]
 57%|█████▋    | 3218/5625 [02:49<02:02, 19.68it/s]
 57%|█████▋    | 3220/5625 [02:49<02:05, 19.24it/s]
 57%|█████▋    | 3223/5625 [02:49<02:00, 19.86it/s]
 57%|█████▋    | 3226/5625 [02:49<01:58, 20.20it/s]
 57%|█████▋    | 3229/5625 [02:49<02:01, 19.72it/s]
 57%|█████▋    | 3231/5625 [02:49<02:03, 19.43it/s]
 57%|█████▋    | 3234/5625 [02:49<02:02, 19.56it/s]
 58%|█████▊    | 3237/5625 [02:50<02:02, 19.43it/s]
 58%|█████▊    | 3239/5625 [02:50<02:02, 19.53it/s]
 58%|█████▊    | 3241/5625 [02:50<02:06, 18.85it/s]
 58%|█████▊    | 3244/5625 [02:50<02:02, 19.39it/s]
 58%|█████▊    | 3246/5625 [02:50<02:03, 19.29it/s]
 58%|█████▊    | 3249/5625 [02:50<02:00, 19.78it/s]
 58%|█████▊    | 3251/5625 [02:50<02:01, 19.54it/s]
 58%|█████▊    | 3254/5625 [02:50<02:00, 19.71it/s]
 58%|█████▊    | 3257/5625 [02:51<01:58, 19.93it/s]
 58%|█████▊    | 3259/5625 [02:51<02:00, 19.65it/s]
 58%|█████▊    | 3262/5625 [02:51<01:59, 19.80it/s]
 58%|█████▊    | 3264/5625 [02:51<02:00, 19.55it/s]
 58%|█████▊    | 3267/5625 [02:51<02:00, 19.62it/s]
 58%|█████▊    | 3269/5625 [02:51<02:01, 19.33it/s]
 58%|█████▊    | 3272/5625 [02:51<02:00, 19.52it/s]
 58%|█████▊    | 3275/5625 [02:52<01:57, 20.01it/s]
 58%|█████▊    | 3277/5625 [02:52<01:57, 19.94it/s]
 58%|█████▊    | 3279/5625 [02:52<01:58, 19.80it/s]
 58%|█████▊    | 3281/5625 [02:52<02:00, 19.43it/s]
 58%|█████▊    | 3283/5625 [02:52<02:03, 19.03it/s]
 58%|█████▊    | 3285/5625 [02:52<02:01, 19.26it/s]
 58%|█████▊    | 3287/5625 [02:52<02:01, 19.17it/s]
 58%|█████▊    | 3289/5625 [02:52<02:03, 18.91it/s]
 59%|█████▊    | 3292/5625 [02:52<01:59, 19.57it/s]
 59%|█████▊    | 3294/5625 [02:53<02:02, 19.06it/s]
 59%|█████▊    | 3296/5625 [02:53<02:01, 19.20it/s]
 59%|█████▊    | 3299/5625 [02:53<01:56, 19.99it/s]
 59%|█████▊    | 3301/5625 [02:53<02:00, 19.26it/s]
 59%|█████▊    | 3303/5625 [02:53<02:00, 19.26it/s]
 59%|█████▉    | 3306/5625 [02:53<01:58, 19.58it/s]
 59%|█████▉    | 3308/5625 [02:53<01:59, 19.39it/s]
 59%|█████▉    | 3310/5625 [02:53<02:03, 18.77it/s]
 59%|█████▉    | 3312/5625 [02:53<02:03, 18.77it/s]
 59%|█████▉    | 3314/5625 [02:54<02:01, 19.01it/s]
 59%|█████▉    | 3316/5625 [02:54<02:04, 18.60it/s]
 59%|█████▉    | 3319/5625 [02:54<02:01, 19.05it/s]
 59%|█████▉    | 3321/5625 [02:54<02:01, 18.96it/s]
 59%|█████▉    | 3323/5625 [02:54<02:03, 18.67it/s]
 59%|█████▉    | 3325/5625 [02:54<02:00, 19.02it/s]
 59%|█████▉    | 3328/5625 [02:54<01:57, 19.60it/s]
 59%|█████▉    | 3330/5625 [02:54<02:00, 19.08it/s]
 59%|█████▉    | 3333/5625 [02:55<01:56, 19.66it/s]
 59%|█████▉    | 3335/5625 [02:55<01:57, 19.57it/s]
 59%|█████▉    | 3338/5625 [02:55<01:52, 20.26it/s]
 59%|█████▉    | 3341/5625 [02:55<01:54, 19.99it/s]
 59%|█████▉    | 3344/5625 [02:55<01:53, 20.15it/s]
 60%|█████▉    | 3347/5625 [02:55<01:53, 20.07it/s]
 60%|█████▉    | 3350/5625 [02:55<01:53, 20.13it/s]
 60%|█████▉    | 3353/5625 [02:56<01:55, 19.75it/s]
 60%|█████▉    | 3355/5625 [02:56<01:56, 19.47it/s]
 60%|█████▉    | 3357/5625 [02:56<01:56, 19.51it/s]
 60%|█████▉    | 3359/5625 [02:56<01:58, 19.05it/s]
 60%|█████▉    | 3362/5625 [02:56<01:56, 19.40it/s]
 60%|█████▉    | 3364/5625 [02:56<01:56, 19.48it/s]
 60%|█████▉    | 3366/5625 [02:56<01:57, 19.25it/s]
 60%|█████▉    | 3368/5625 [02:56<01:58, 18.97it/s]
 60%|█████▉    | 3370/5625 [02:56<01:57, 19.19it/s]
 60%|█████▉    | 3372/5625 [02:57<02:00, 18.65it/s]
 60%|██████    | 3375/5625 [02:57<01:55, 19.42it/s]
 60%|██████    | 3377/5625 [02:57<01:59, 18.87it/s]
 60%|██████    | 3380/5625 [02:57<01:55, 19.36it/s]
 60%|██████    | 3382/5625 [02:57<01:56, 19.23it/s]
 60%|██████    | 3385/5625 [02:57<01:51, 20.04it/s]
 60%|██████    | 3387/5625 [02:57<01:52, 19.86it/s]
 60%|██████    | 3389/5625 [02:57<01:53, 19.72it/s]
 60%|██████    | 3391/5625 [02:58<01:56, 19.18it/s]
 60%|██████    | 3393/5625 [02:58<01:58, 18.87it/s]
 60%|██████    | 3395/5625 [02:58<01:58, 18.87it/s]
 60%|██████    | 3397/5625 [02:58<01:57, 18.91it/s]
 60%|██████    | 3399/5625 [02:58<01:58, 18.86it/s]
 60%|██████    | 3402/5625 [02:58<01:56, 19.04it/s]
 61%|██████    | 3404/5625 [02:58<01:57, 18.83it/s]
 61%|██████    | 3406/5625 [02:58<02:00, 18.42it/s]
 61%|██████    | 3409/5625 [02:58<01:58, 18.68it/s]
 61%|██████    | 3411/5625 [02:59<01:57, 18.76it/s]
 61%|██████    | 3414/5625 [02:59<01:50, 19.93it/s]
 61%|██████    | 3416/5625 [02:59<01:52, 19.55it/s]
 61%|██████    | 3418/5625 [02:59<01:53, 19.46it/s]
 61%|██████    | 3420/5625 [02:59<01:54, 19.22it/s]
 61%|██████    | 3423/5625 [02:59<01:53, 19.46it/s]
 61%|██████    | 3426/5625 [02:59<01:50, 19.83it/s]
 61%|██████    | 3428/5625 [02:59<01:53, 19.36it/s]
 61%|██████    | 3431/5625 [03:00<01:51, 19.62it/s]
 61%|██████    | 3433/5625 [03:00<01:53, 19.26it/s]
 61%|██████    | 3436/5625 [03:00<01:51, 19.64it/s]
 61%|██████    | 3438/5625 [03:00<01:53, 19.22it/s]
 61%|██████    | 3440/5625 [03:00<01:56, 18.79it/s]
 61%|██████    | 3442/5625 [03:00<01:58, 18.38it/s]
 61%|██████    | 3444/5625 [03:00<01:59, 18.30it/s]
 61%|██████▏   | 3446/5625 [03:00<01:56, 18.71it/s]
 61%|██████▏   | 3449/5625 [03:01<01:50, 19.71it/s]
 61%|██████▏   | 3451/5625 [03:01<01:52, 19.37it/s]
 61%|██████▏   | 3453/5625 [03:01<01:53, 19.06it/s]
 61%|██████▏   | 3456/5625 [03:01<01:51, 19.51it/s]
 61%|██████▏   | 3459/5625 [03:01<01:48, 20.00it/s]
 62%|██████▏   | 3462/5625 [03:01<01:48, 20.01it/s]
 62%|██████▏   | 3464/5625 [03:01<01:50, 19.57it/s]
 62%|██████▏   | 3466/5625 [03:01<01:51, 19.35it/s]
 62%|██████▏   | 3469/5625 [03:02<01:49, 19.60it/s]
 62%|██████▏   | 3471/5625 [03:02<01:50, 19.58it/s]
 62%|██████▏   | 3473/5625 [03:02<01:49, 19.66it/s]
 62%|██████▏   | 3475/5625 [03:02<01:49, 19.69it/s]
 62%|██████▏   | 3477/5625 [03:02<01:51, 19.31it/s]
 62%|██████▏   | 3479/5625 [03:02<01:50, 19.39it/s]
 62%|██████▏   | 3481/5625 [03:02<01:50, 19.46it/s]
 62%|██████▏   | 3484/5625 [03:02<01:45, 20.37it/s]
 62%|██████▏   | 3487/5625 [03:02<01:49, 19.55it/s]
 62%|██████▏   | 3489/5625 [03:03<01:52, 19.00it/s]
 62%|██████▏   | 3492/5625 [03:03<01:49, 19.50it/s]
 62%|██████▏   | 3494/5625 [03:03<01:51, 19.11it/s]
 62%|██████▏   | 3496/5625 [03:03<01:53, 18.76it/s]
 62%|██████▏   | 3498/5625 [03:03<01:51, 19.00it/s]
 62%|██████▏   | 3501/5625 [03:03<01:47, 19.76it/s]
 62%|██████▏   | 3503/5625 [03:03<01:48, 19.64it/s]
 62%|██████▏   | 3506/5625 [03:03<01:44, 20.21it/s]
 62%|██████▏   | 3509/5625 [03:04<01:47, 19.77it/s]
 62%|██████▏   | 3511/5625 [03:04<01:50, 19.09it/s]
 62%|██████▏   | 3514/5625 [03:04<01:49, 19.24it/s]
 63%|██████▎   | 3516/5625 [03:04<01:53, 18.64it/s]
 63%|██████▎   | 3518/5625 [03:04<01:54, 18.47it/s]
 63%|██████▎   | 3521/5625 [03:04<01:49, 19.26it/s]
 63%|██████▎   | 3524/5625 [03:04<01:47, 19.58it/s]
 63%|██████▎   | 3527/5625 [03:05<01:44, 20.14it/s]
 63%|██████▎   | 3530/5625 [03:05<01:46, 19.70it/s]
 63%|██████▎   | 3532/5625 [03:05<01:48, 19.29it/s]
 63%|██████▎   | 3535/5625 [03:05<01:48, 19.30it/s]
 63%|██████▎   | 3537/5625 [03:05<01:50, 18.94it/s]
 63%|██████▎   | 3540/5625 [03:05<01:45, 19.76it/s]
 63%|██████▎   | 3542/5625 [03:05<01:46, 19.61it/s]
 63%|██████▎   | 3545/5625 [03:05<01:43, 20.07it/s]
 63%|██████▎   | 3547/5625 [03:06<01:44, 19.90it/s]
 63%|██████▎   | 3549/5625 [03:06<01:45, 19.66it/s]
 63%|██████▎   | 3551/5625 [03:06<01:48, 19.14it/s]
 63%|██████▎   | 3554/5625 [03:06<01:44, 19.81it/s]
 63%|██████▎   | 3556/5625 [03:06<01:47, 19.31it/s]
 63%|██████▎   | 3559/5625 [03:06<01:42, 20.11it/s]
 63%|██████▎   | 3562/5625 [03:06<01:41, 20.40it/s]
 63%|██████▎   | 3565/5625 [03:06<01:42, 20.08it/s]
 63%|██████▎   | 3568/5625 [03:07<01:45, 19.53it/s]
 63%|██████▎   | 3570/5625 [03:07<01:46, 19.25it/s]
 64%|██████▎   | 3572/5625 [03:07<01:47, 19.15it/s]
 64%|██████▎   | 3574/5625 [03:07<01:47, 19.03it/s]
 64%|██████▎   | 3576/5625 [03:07<01:47, 19.10it/s]
 64%|██████▎   | 3578/5625 [03:07<01:49, 18.72it/s]
 64%|██████▎   | 3580/5625 [03:07<01:47, 18.96it/s]
 64%|██████▎   | 3582/5625 [03:07<01:47, 18.95it/s]
 64%|██████▎   | 3584/5625 [03:07<01:46, 19.15it/s]
 64%|██████▍   | 3586/5625 [03:08<01:46, 19.17it/s]
 64%|██████▍   | 3588/5625 [03:08<01:45, 19.34it/s]
 64%|██████▍   | 3590/5625 [03:08<01:48, 18.73it/s]
 64%|██████▍   | 3592/5625 [03:08<01:50, 18.47it/s]
 64%|██████▍   | 3594/5625 [03:08<01:52, 18.02it/s]
 64%|██████▍   | 3596/5625 [03:08<01:51, 18.17it/s]
 64%|██████▍   | 3598/5625 [03:08<01:49, 18.48it/s]
 64%|██████▍   | 3600/5625 [03:08<01:50, 18.29it/s]
 64%|██████▍   | 3602/5625 [03:08<01:49, 18.47it/s]
 64%|██████▍   | 3604/5625 [03:09<01:48, 18.68it/s]
 64%|██████▍   | 3606/5625 [03:09<01:47, 18.71it/s]
 64%|██████▍   | 3608/5625 [03:09<01:46, 19.01it/s]
 64%|██████▍   | 3610/5625 [03:09<01:44, 19.28it/s]
 64%|██████▍   | 3613/5625 [03:09<01:42, 19.62it/s]
 64%|██████▍   | 3616/5625 [03:09<01:39, 20.13it/s]
 64%|██████▍   | 3619/5625 [03:09<01:41, 19.75it/s]
 64%|██████▍   | 3621/5625 [03:09<01:41, 19.66it/s]
 64%|██████▍   | 3623/5625 [03:10<01:44, 19.24it/s]
 64%|██████▍   | 3625/5625 [03:10<01:46, 18.85it/s]
 64%|██████▍   | 3628/5625 [03:10<01:42, 19.54it/s]
 65%|██████▍   | 3630/5625 [03:10<01:43, 19.33it/s]
 65%|██████▍   | 3632/5625 [03:10<01:46, 18.74it/s]
 65%|██████▍   | 3635/5625 [03:10<01:44, 18.99it/s]
 65%|██████▍   | 3638/5625 [03:10<01:39, 20.01it/s]
 65%|██████▍   | 3641/5625 [03:10<01:38, 20.20it/s]
 65%|██████▍   | 3644/5625 [03:11<01:40, 19.75it/s]
 65%|██████▍   | 3647/5625 [03:11<01:39, 19.88it/s]
 65%|██████▍   | 3649/5625 [03:11<01:40, 19.60it/s]
 65%|██████▍   | 3651/5625 [03:11<01:40, 19.57it/s]
 65%|██████▍   | 3653/5625 [03:11<01:43, 18.99it/s]
 65%|██████▍   | 3656/5625 [03:11<01:41, 19.34it/s]
 65%|██████▌   | 3658/5625 [03:11<01:43, 19.06it/s]
 65%|██████▌   | 3661/5625 [03:11<01:41, 19.30it/s]
 65%|██████▌   | 3663/5625 [03:12<01:40, 19.47it/s]
 65%|██████▌   | 3665/5625 [03:12<01:42, 19.04it/s]
 65%|██████▌   | 3667/5625 [03:12<01:41, 19.29it/s]
 65%|██████▌   | 3669/5625 [03:12<01:41, 19.18it/s]
 65%|██████▌   | 3671/5625 [03:12<01:44, 18.62it/s]
 65%|██████▌   | 3673/5625 [03:12<01:43, 18.94it/s]
 65%|██████▌   | 3675/5625 [03:12<01:42, 19.02it/s]
 65%|██████▌   | 3677/5625 [03:12<01:41, 19.14it/s]
 65%|██████▌   | 3680/5625 [03:12<01:40, 19.28it/s]
 65%|██████▌   | 3682/5625 [03:13<01:41, 19.19it/s]
 66%|██████▌   | 3685/5625 [03:13<01:41, 19.10it/s]
 66%|██████▌   | 3687/5625 [03:13<01:41, 19.05it/s]
 66%|██████▌   | 3690/5625 [03:13<01:40, 19.19it/s]
 66%|██████▌   | 3692/5625 [03:13<01:40, 19.19it/s]
 66%|██████▌   | 3694/5625 [03:13<01:41, 19.01it/s]
 66%|██████▌   | 3696/5625 [03:13<01:43, 18.56it/s]
 66%|██████▌   | 3698/5625 [03:13<01:43, 18.54it/s]
 66%|██████▌   | 3700/5625 [03:14<01:44, 18.47it/s]
 66%|██████▌   | 3702/5625 [03:14<01:44, 18.46it/s]
 66%|██████▌   | 3704/5625 [03:14<01:42, 18.81it/s]
 66%|██████▌   | 3706/5625 [03:14<01:40, 19.02it/s]
 66%|██████▌   | 3708/5625 [03:14<01:41, 18.83it/s]
 66%|██████▌   | 3710/5625 [03:14<01:40, 19.07it/s]
 66%|██████▌   | 3713/5625 [03:14<01:39, 19.22it/s]
 66%|██████▌   | 3715/5625 [03:14<01:41, 18.77it/s]
 66%|██████▌   | 3717/5625 [03:14<01:40, 19.06it/s]
 66%|██████▌   | 3719/5625 [03:15<01:42, 18.61it/s]
 66%|██████▌   | 3721/5625 [03:15<01:43, 18.42it/s]
 66%|██████▌   | 3724/5625 [03:15<01:35, 19.91it/s]
 66%|██████▌   | 3726/5625 [03:15<01:36, 19.76it/s]
 66%|██████▋   | 3728/5625 [03:15<01:37, 19.36it/s]
 66%|██████▋   | 3731/5625 [03:15<01:36, 19.54it/s]
 66%|██████▋   | 3734/5625 [03:15<01:36, 19.68it/s]
 66%|██████▋   | 3736/5625 [03:15<01:36, 19.67it/s]
 66%|██████▋   | 3738/5625 [03:16<01:37, 19.31it/s]
 66%|██████▋   | 3740/5625 [03:16<01:37, 19.28it/s]
 67%|██████▋   | 3743/5625 [03:16<01:36, 19.59it/s]
 67%|██████▋   | 3745/5625 [03:16<01:37, 19.34it/s]
 67%|██████▋   | 3747/5625 [03:16<01:36, 19.37it/s]
 67%|██████▋   | 3749/5625 [03:16<01:39, 18.92it/s]
                                                   

 67%|██████▋   | 3750/5625 [03:16<01:39, 18.92it/s]{'eval_loss': 0.6898801326751709, 'eval_accuracy': 0.704, 'eval_f1': 0.7034622605515944, 'eval_runtime': 1.7337, 'eval_samples_per_second': 1442.04, 'eval_steps_per_second': 180.543, 'epoch': 1.0}
{'loss': 0.5115, 'learning_rate': 1.4535334529809943e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.82it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.59it/s]

 21%|██        | 66/313 [00:00<00:01, 206.16it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.41it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.72it/s]

 40%|████      | 126/313 [00:00<00:01, 185.41it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.21it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.17it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.28it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.37it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.48it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.18it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.02it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.94it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.93it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.93it/s]
 67%|██████▋   | 3750/5625 [03:18<01:39, 18.92it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 3751/5625 [03:19<13:31,  2.31it/s]
 67%|██████▋   | 3753/5625 [03:19<10:04,  3.10it/s]
 67%|██████▋   | 3755/5625 [03:19<07:36,  4.09it/s]
 67%|██████▋   | 3757/5625 [03:19<05:52,  5.31it/s]
 67%|██████▋   | 3760/5625 [03:19<04:08,  7.50it/s]
 67%|██████▋   | 3762/5625 [03:19<03:28,  8.94it/s]
 67%|██████▋   | 3764/5625 [03:20<02:57, 10.48it/s]
 67%|██████▋   | 3766/5625 [03:20<02:35, 11.98it/s]
 67%|██████▋   | 3769/5625 [03:20<02:10, 14.19it/s]
 67%|██████▋   | 3771/5625 [03:20<02:01, 15.22it/s]
 67%|██████▋   | 3774/5625 [03:20<01:51, 16.57it/s]
 67%|██████▋   | 3776/5625 [03:20<01:47, 17.13it/s]
 67%|██████▋   | 3778/5625 [03:20<01:44, 17.73it/s]
 67%|██████▋   | 3781/5625 [03:20<01:39, 18.56it/s]
 67%|██████▋   | 3784/5625 [03:21<01:36, 19.03it/s]
 67%|██████▋   | 3786/5625 [03:21<01:37, 18.91it/s]
 67%|██████▋   | 3788/5625 [03:21<01:38, 18.58it/s]
 67%|██████▋   | 3790/5625 [03:21<01:38, 18.55it/s]
 67%|██████▋   | 3792/5625 [03:21<01:38, 18.69it/s]
 67%|██████▋   | 3795/5625 [03:21<01:33, 19.68it/s]
 68%|██████▊   | 3797/5625 [03:21<01:36, 19.03it/s]
 68%|██████▊   | 3800/5625 [03:21<01:35, 19.19it/s]
 68%|██████▊   | 3802/5625 [03:22<01:34, 19.25it/s]
 68%|██████▊   | 3804/5625 [03:22<01:35, 19.06it/s]
 68%|██████▊   | 3807/5625 [03:22<01:33, 19.43it/s]
 68%|██████▊   | 3809/5625 [03:22<01:34, 19.18it/s]
 68%|██████▊   | 3811/5625 [03:22<01:36, 18.73it/s]
 68%|██████▊   | 3813/5625 [03:22<01:35, 18.90it/s]
 68%|██████▊   | 3816/5625 [03:22<01:33, 19.45it/s]
 68%|██████▊   | 3818/5625 [03:22<01:34, 19.20it/s]
 68%|██████▊   | 3820/5625 [03:22<01:33, 19.36it/s]
 68%|██████▊   | 3822/5625 [03:23<01:33, 19.31it/s]
 68%|██████▊   | 3824/5625 [03:23<01:35, 18.86it/s]
 68%|██████▊   | 3827/5625 [03:23<01:34, 18.97it/s]
 68%|██████▊   | 3830/5625 [03:23<01:33, 19.23it/s]
 68%|██████▊   | 3832/5625 [03:23<01:33, 19.15it/s]
 68%|██████▊   | 3835/5625 [03:23<01:33, 19.21it/s]
 68%|██████▊   | 3837/5625 [03:23<01:32, 19.35it/s]
 68%|██████▊   | 3840/5625 [03:23<01:31, 19.61it/s]
 68%|██████▊   | 3842/5625 [03:24<01:33, 19.17it/s]
 68%|██████▊   | 3844/5625 [03:24<01:32, 19.16it/s]
 68%|██████▊   | 3846/5625 [03:24<01:33, 19.07it/s]
 68%|██████▊   | 3848/5625 [03:24<01:35, 18.63it/s]
 68%|██████▊   | 3851/5625 [03:24<01:31, 19.32it/s]
 69%|██████▊   | 3854/5625 [03:24<01:28, 20.01it/s]
 69%|██████▊   | 3856/5625 [03:24<01:29, 19.80it/s]
 69%|██████▊   | 3858/5625 [03:24<01:32, 19.16it/s]
 69%|██████▊   | 3860/5625 [03:25<01:34, 18.74it/s]
 69%|██████▊   | 3863/5625 [03:25<01:30, 19.56it/s]
 69%|██████▊   | 3866/5625 [03:25<01:27, 20.01it/s]
 69%|██████▉   | 3869/5625 [03:25<01:27, 20.11it/s]
 69%|██████▉   | 3871/5625 [03:25<01:28, 19.75it/s]
 69%|██████▉   | 3873/5625 [03:25<01:31, 19.13it/s]
 69%|██████▉   | 3876/5625 [03:25<01:30, 19.33it/s]
 69%|██████▉   | 3878/5625 [03:25<01:30, 19.23it/s]
 69%|██████▉   | 3880/5625 [03:26<01:30, 19.31it/s]
 69%|██████▉   | 3882/5625 [03:26<01:29, 19.47it/s]
 69%|██████▉   | 3885/5625 [03:26<01:28, 19.59it/s]
 69%|██████▉   | 3888/5625 [03:26<01:26, 20.04it/s]
 69%|██████▉   | 3890/5625 [03:26<01:26, 19.99it/s]
 69%|██████▉   | 3893/5625 [03:26<01:26, 19.91it/s]
 69%|██████▉   | 3895/5625 [03:26<01:28, 19.64it/s]
 69%|██████▉   | 3897/5625 [03:26<01:27, 19.65it/s]
 69%|██████▉   | 3899/5625 [03:27<01:29, 19.21it/s]
 69%|██████▉   | 3901/5625 [03:27<01:29, 19.24it/s]
 69%|██████▉   | 3903/5625 [03:27<01:30, 19.02it/s]
 69%|██████▉   | 3905/5625 [03:27<01:29, 19.20it/s]
 69%|██████▉   | 3907/5625 [03:27<01:31, 18.71it/s]
 70%|██████▉   | 3910/5625 [03:27<01:27, 19.62it/s]
 70%|██████▉   | 3912/5625 [03:27<01:29, 19.13it/s]
 70%|██████▉   | 3915/5625 [03:27<01:27, 19.47it/s]
 70%|██████▉   | 3918/5625 [03:27<01:25, 20.06it/s]
 70%|██████▉   | 3921/5625 [03:28<01:25, 19.92it/s]
 70%|██████▉   | 3923/5625 [03:28<01:28, 19.19it/s]
 70%|██████▉   | 3926/5625 [03:28<01:24, 20.04it/s]
 70%|██████▉   | 3928/5625 [03:28<01:26, 19.51it/s]
 70%|██████▉   | 3931/5625 [03:28<01:24, 20.15it/s]
 70%|██████▉   | 3933/5625 [03:28<01:24, 19.99it/s]
 70%|██████▉   | 3936/5625 [03:28<01:25, 19.80it/s]
 70%|███████   | 3938/5625 [03:29<01:28, 19.14it/s]
 70%|███████   | 3941/5625 [03:29<01:26, 19.41it/s]
 70%|███████   | 3943/5625 [03:29<01:26, 19.54it/s]
 70%|███████   | 3946/5625 [03:29<01:25, 19.65it/s]
 70%|███████   | 3948/5625 [03:29<01:26, 19.40it/s]
 70%|███████   | 3950/5625 [03:29<01:26, 19.31it/s]
 70%|███████   | 3952/5625 [03:29<01:29, 18.79it/s]
 70%|███████   | 3955/5625 [03:29<01:23, 20.11it/s]
 70%|███████   | 3957/5625 [03:29<01:23, 19.92it/s]
 70%|███████   | 3960/5625 [03:30<01:19, 21.06it/s]
 70%|███████   | 3963/5625 [03:30<01:21, 20.36it/s]
 71%|███████   | 3966/5625 [03:30<01:24, 19.56it/s]
 71%|███████   | 3968/5625 [03:30<01:26, 19.19it/s]
 71%|███████   | 3970/5625 [03:30<01:26, 19.15it/s]
 71%|███████   | 3973/5625 [03:30<01:23, 19.74it/s]
 71%|███████   | 3976/5625 [03:30<01:23, 19.87it/s]
 71%|███████   | 3978/5625 [03:31<01:24, 19.49it/s]
 71%|███████   | 3980/5625 [03:31<01:24, 19.43it/s]
 71%|███████   | 3982/5625 [03:31<01:24, 19.51it/s]
 71%|███████   | 3985/5625 [03:31<01:22, 19.79it/s]
 71%|███████   | 3987/5625 [03:31<01:22, 19.82it/s]
 71%|███████   | 3989/5625 [03:31<01:24, 19.46it/s]
 71%|███████   | 3991/5625 [03:31<01:25, 19.02it/s]
 71%|███████   | 3994/5625 [03:31<01:24, 19.29it/s]
 71%|███████   | 3997/5625 [03:32<01:23, 19.48it/s]
 71%|███████   | 3999/5625 [03:32<01:24, 19.32it/s]
 71%|███████   | 4001/5625 [03:32<01:33, 17.41it/s]
 71%|███████   | 4004/5625 [03:32<01:25, 18.85it/s]
 71%|███████   | 4006/5625 [03:32<01:25, 18.85it/s]
 71%|███████▏  | 4008/5625 [03:32<01:25, 18.94it/s]
 71%|███████▏  | 4011/5625 [03:32<01:21, 19.73it/s]
 71%|███████▏  | 4013/5625 [03:32<01:23, 19.39it/s]
 71%|███████▏  | 4015/5625 [03:32<01:25, 18.89it/s]
 71%|███████▏  | 4017/5625 [03:33<01:26, 18.65it/s]
 71%|███████▏  | 4020/5625 [03:33<01:23, 19.18it/s]
 72%|███████▏  | 4022/5625 [03:33<01:24, 18.88it/s]
 72%|███████▏  | 4024/5625 [03:33<01:25, 18.77it/s]
 72%|███████▏  | 4027/5625 [03:33<01:23, 19.17it/s]
 72%|███████▏  | 4029/5625 [03:33<01:22, 19.37it/s]
 72%|███████▏  | 4031/5625 [03:33<01:23, 19.13it/s]
 72%|███████▏  | 4034/5625 [03:33<01:18, 20.24it/s]
 72%|███████▏  | 4037/5625 [03:34<01:21, 19.46it/s]
 72%|███████▏  | 4040/5625 [03:34<01:18, 20.19it/s]
 72%|███████▏  | 4043/5625 [03:34<01:21, 19.52it/s]
 72%|███████▏  | 4045/5625 [03:34<01:20, 19.55it/s]
 72%|███████▏  | 4047/5625 [03:34<01:20, 19.48it/s]
 72%|███████▏  | 4050/5625 [03:34<01:20, 19.65it/s]
 72%|███████▏  | 4052/5625 [03:34<01:22, 19.10it/s]
 72%|███████▏  | 4054/5625 [03:34<01:22, 19.05it/s]
 72%|███████▏  | 4056/5625 [03:35<01:23, 18.89it/s]
 72%|███████▏  | 4059/5625 [03:35<01:21, 19.18it/s]
 72%|███████▏  | 4061/5625 [03:35<01:21, 19.12it/s]
 72%|███████▏  | 4063/5625 [03:35<01:23, 18.74it/s]
 72%|███████▏  | 4066/5625 [03:35<01:18, 19.79it/s]
 72%|███████▏  | 4068/5625 [03:35<01:19, 19.55it/s]
 72%|███████▏  | 4070/5625 [03:35<01:19, 19.44it/s]
 72%|███████▏  | 4073/5625 [03:35<01:16, 20.38it/s]
 72%|███████▏  | 4076/5625 [03:36<01:14, 20.76it/s]
 73%|███████▎  | 4079/5625 [03:36<01:16, 20.10it/s]
 73%|███████▎  | 4082/5625 [03:36<01:19, 19.31it/s]
 73%|███████▎  | 4085/5625 [03:36<01:16, 20.07it/s]
 73%|███████▎  | 4088/5625 [03:36<01:18, 19.67it/s]
 73%|███████▎  | 4090/5625 [03:36<01:19, 19.26it/s]
 73%|███████▎  | 4092/5625 [03:36<01:21, 18.88it/s]
 73%|███████▎  | 4094/5625 [03:37<01:21, 18.85it/s]
 73%|███████▎  | 4097/5625 [03:37<01:16, 19.92it/s]
 73%|███████▎  | 4099/5625 [03:37<01:39, 15.27it/s]
 73%|███████▎  | 4101/5625 [03:37<01:34, 16.10it/s]
 73%|███████▎  | 4103/5625 [03:37<01:32, 16.50it/s]
 73%|███████▎  | 4106/5625 [03:37<01:22, 18.45it/s]
 73%|███████▎  | 4108/5625 [03:37<01:20, 18.83it/s]
 73%|███████▎  | 4110/5625 [03:37<01:19, 19.12it/s]
 73%|███████▎  | 4113/5625 [03:38<01:18, 19.20it/s]
 73%|███████▎  | 4115/5625 [03:38<01:19, 19.01it/s]
 73%|███████▎  | 4118/5625 [03:38<01:17, 19.45it/s]
 73%|███████▎  | 4120/5625 [03:38<01:19, 19.00it/s]
 73%|███████▎  | 4122/5625 [03:38<01:19, 18.87it/s]
 73%|███████▎  | 4124/5625 [03:38<01:18, 19.10it/s]
 73%|███████▎  | 4126/5625 [03:38<01:18, 19.08it/s]
 73%|███████▎  | 4128/5625 [03:38<01:19, 18.77it/s]
 73%|███████▎  | 4130/5625 [03:39<01:18, 19.06it/s]
 73%|███████▎  | 4132/5625 [03:39<01:19, 18.85it/s]
 73%|███████▎  | 4134/5625 [03:39<01:19, 18.66it/s]
 74%|███████▎  | 4136/5625 [03:39<01:20, 18.39it/s]
 74%|███████▎  | 4138/5625 [03:39<01:21, 18.34it/s]
 74%|███████▎  | 4141/5625 [03:39<01:18, 18.86it/s]
 74%|███████▎  | 4143/5625 [03:39<01:19, 18.72it/s]
 74%|███████▎  | 4145/5625 [03:39<01:19, 18.55it/s]
 74%|███████▎  | 4147/5625 [03:39<01:18, 18.92it/s]
 74%|███████▍  | 4149/5625 [03:40<01:18, 18.87it/s]
 74%|███████▍  | 4151/5625 [03:40<01:17, 18.92it/s]
 74%|███████▍  | 4153/5625 [03:40<01:19, 18.56it/s]
 74%|███████▍  | 4155/5625 [03:40<01:17, 18.88it/s]
 74%|███████▍  | 4158/5625 [03:40<01:15, 19.42it/s]
 74%|███████▍  | 4161/5625 [03:40<01:15, 19.44it/s]
 74%|███████▍  | 4164/5625 [03:40<01:14, 19.57it/s]
 74%|███████▍  | 4167/5625 [03:40<01:11, 20.48it/s]
 74%|███████▍  | 4170/5625 [03:41<01:12, 19.94it/s]
 74%|███████▍  | 4172/5625 [03:41<01:14, 19.42it/s]
 74%|███████▍  | 4174/5625 [03:41<01:14, 19.50it/s]
 74%|███████▍  | 4176/5625 [03:41<01:14, 19.36it/s]
 74%|███████▍  | 4179/5625 [03:41<01:14, 19.38it/s]
 74%|███████▍  | 4181/5625 [03:41<01:14, 19.37it/s]
 74%|███████▍  | 4184/5625 [03:41<01:14, 19.39it/s]
 74%|███████▍  | 4186/5625 [03:41<01:15, 19.05it/s]
 74%|███████▍  | 4188/5625 [03:42<01:15, 18.94it/s]
 75%|███████▍  | 4191/5625 [03:42<01:13, 19.46it/s]
 75%|███████▍  | 4193/5625 [03:42<01:14, 19.25it/s]
 75%|███████▍  | 4195/5625 [03:42<01:33, 15.34it/s]
 75%|███████▍  | 4197/5625 [03:42<01:29, 16.03it/s]
 75%|███████▍  | 4200/5625 [03:42<01:21, 17.57it/s]
 75%|███████▍  | 4202/5625 [03:42<01:20, 17.72it/s]
 75%|███████▍  | 4204/5625 [03:42<01:20, 17.64it/s]
 75%|███████▍  | 4206/5625 [03:43<01:17, 18.19it/s]
 75%|███████▍  | 4208/5625 [03:43<01:18, 18.04it/s]
 75%|███████▍  | 4210/5625 [03:43<01:16, 18.45it/s]
 75%|███████▍  | 4212/5625 [03:43<01:17, 18.18it/s]
 75%|███████▍  | 4214/5625 [03:43<01:18, 17.99it/s]
 75%|███████▍  | 4216/5625 [03:43<01:18, 17.97it/s]
 75%|███████▍  | 4218/5625 [03:43<01:17, 18.07it/s]
 75%|███████▌  | 4221/5625 [03:43<01:13, 19.21it/s]
 75%|███████▌  | 4224/5625 [03:44<01:09, 20.08it/s]
 75%|███████▌  | 4227/5625 [03:44<01:09, 20.20it/s]
 75%|███████▌  | 4230/5625 [03:44<01:10, 19.85it/s]
 75%|███████▌  | 4232/5625 [03:44<01:11, 19.54it/s]
 75%|███████▌  | 4235/5625 [03:44<01:09, 20.11it/s]
 75%|███████▌  | 4238/5625 [03:44<01:11, 19.37it/s]
 75%|███████▌  | 4240/5625 [03:44<01:11, 19.46it/s]
 75%|███████▌  | 4243/5625 [03:44<01:08, 20.25it/s]
 75%|███████▌  | 4246/5625 [03:45<01:11, 19.28it/s]
 76%|███████▌  | 4249/5625 [03:45<01:08, 20.09it/s]
 76%|███████▌  | 4252/5625 [03:45<01:10, 19.56it/s]
 76%|███████▌  | 4254/5625 [03:45<01:11, 19.06it/s]
 76%|███████▌  | 4256/5625 [03:45<01:11, 19.19it/s]
 76%|███████▌  | 4258/5625 [03:45<01:13, 18.71it/s]
 76%|███████▌  | 4260/5625 [03:45<01:12, 18.80it/s]
 76%|███████▌  | 4262/5625 [03:45<01:12, 18.90it/s]
 76%|███████▌  | 4264/5625 [03:46<01:12, 18.66it/s]
 76%|███████▌  | 4266/5625 [03:46<01:13, 18.54it/s]
 76%|███████▌  | 4268/5625 [03:46<01:12, 18.62it/s]
 76%|███████▌  | 4271/5625 [03:46<01:11, 19.01it/s]
 76%|███████▌  | 4273/5625 [03:46<01:10, 19.24it/s]
 76%|███████▌  | 4275/5625 [03:46<01:10, 19.27it/s]
 76%|███████▌  | 4277/5625 [03:46<01:11, 18.74it/s]
 76%|███████▌  | 4279/5625 [03:46<01:11, 18.73it/s]
 76%|███████▌  | 4281/5625 [03:46<01:12, 18.45it/s]
 76%|███████▌  | 4283/5625 [03:47<01:12, 18.60it/s]
 76%|███████▌  | 4286/5625 [03:47<01:10, 19.09it/s]
 76%|███████▌  | 4289/5625 [03:47<01:07, 19.68it/s]
 76%|███████▋  | 4291/5625 [03:47<01:09, 19.20it/s]
 76%|███████▋  | 4293/5625 [03:47<01:11, 18.67it/s]
 76%|███████▋  | 4295/5625 [03:47<01:11, 18.64it/s]
 76%|███████▋  | 4297/5625 [03:47<01:11, 18.61it/s]
 76%|███████▋  | 4300/5625 [03:47<01:09, 19.04it/s]
 76%|███████▋  | 4302/5625 [03:48<01:11, 18.60it/s]
 77%|███████▋  | 4305/5625 [03:48<01:08, 19.38it/s]
 77%|███████▋  | 4307/5625 [03:48<01:09, 18.96it/s]
 77%|███████▋  | 4309/5625 [03:48<01:08, 19.20it/s]
 77%|███████▋  | 4311/5625 [03:48<01:09, 18.94it/s]
 77%|███████▋  | 4313/5625 [03:48<01:08, 19.06it/s]
 77%|███████▋  | 4315/5625 [03:48<01:09, 18.87it/s]
 77%|███████▋  | 4317/5625 [03:48<01:09, 18.76it/s]
 77%|███████▋  | 4319/5625 [03:49<01:10, 18.46it/s]
 77%|███████▋  | 4322/5625 [03:49<01:09, 18.88it/s]
 77%|███████▋  | 4325/5625 [03:49<01:05, 19.79it/s]
 77%|███████▋  | 4327/5625 [03:49<01:05, 19.75it/s]
 77%|███████▋  | 4329/5625 [03:49<01:07, 19.15it/s]
 77%|███████▋  | 4332/5625 [03:49<01:07, 19.29it/s]
 77%|███████▋  | 4335/5625 [03:49<01:05, 19.55it/s]
 77%|███████▋  | 4337/5625 [03:49<01:06, 19.28it/s]
 77%|███████▋  | 4339/5625 [03:50<01:08, 18.91it/s]
 77%|███████▋  | 4342/5625 [03:50<01:05, 19.68it/s]
 77%|███████▋  | 4344/5625 [03:50<01:05, 19.61it/s]
 77%|███████▋  | 4347/5625 [03:50<01:04, 19.77it/s]
 77%|███████▋  | 4349/5625 [03:50<01:05, 19.37it/s]
 77%|███████▋  | 4351/5625 [03:50<01:07, 18.84it/s]
 77%|███████▋  | 4353/5625 [03:50<01:08, 18.49it/s]
 77%|███████▋  | 4356/5625 [03:50<01:02, 20.15it/s]
 77%|███████▋  | 4359/5625 [03:51<01:04, 19.74it/s]
 78%|███████▊  | 4362/5625 [03:51<01:02, 20.23it/s]
 78%|███████▊  | 4365/5625 [03:51<01:03, 19.70it/s]
 78%|███████▊  | 4368/5625 [03:51<01:03, 19.72it/s]
 78%|███████▊  | 4371/5625 [03:51<01:04, 19.53it/s]
 78%|███████▊  | 4373/5625 [03:51<01:04, 19.38it/s]
 78%|███████▊  | 4375/5625 [03:51<01:06, 18.92it/s]
 78%|███████▊  | 4377/5625 [03:51<01:05, 19.18it/s]
 78%|███████▊  | 4379/5625 [03:52<01:05, 18.89it/s]
 78%|███████▊  | 4381/5625 [03:52<01:05, 19.11it/s]
 78%|███████▊  | 4383/5625 [03:52<01:05, 19.00it/s]
 78%|███████▊  | 4386/5625 [03:52<01:02, 19.90it/s]
 78%|███████▊  | 4388/5625 [03:52<01:11, 17.25it/s]
 78%|███████▊  | 4391/5625 [03:52<01:08, 17.97it/s]
 78%|███████▊  | 4394/5625 [03:52<01:06, 18.40it/s]
 78%|███████▊  | 4397/5625 [03:53<01:05, 18.77it/s]
 78%|███████▊  | 4399/5625 [03:53<01:05, 18.79it/s]
 78%|███████▊  | 4401/5625 [03:53<01:05, 18.70it/s]
 78%|███████▊  | 4403/5625 [03:53<01:04, 19.00it/s]
 78%|███████▊  | 4406/5625 [03:53<01:02, 19.49it/s]
 78%|███████▊  | 4408/5625 [03:53<01:02, 19.50it/s]
 78%|███████▊  | 4410/5625 [03:53<01:04, 18.93it/s]
 78%|███████▊  | 4413/5625 [03:53<01:01, 19.58it/s]
 79%|███████▊  | 4416/5625 [03:54<01:01, 19.65it/s]
 79%|███████▊  | 4419/5625 [03:54<01:01, 19.54it/s]
 79%|███████▊  | 4421/5625 [03:54<01:03, 18.89it/s]
 79%|███████▊  | 4424/5625 [03:54<01:02, 19.10it/s]
 79%|███████▊  | 4426/5625 [03:54<01:04, 18.67it/s]
 79%|███████▊  | 4429/5625 [03:54<01:02, 19.21it/s]
 79%|███████▉  | 4431/5625 [03:54<01:03, 18.94it/s]
 79%|███████▉  | 4433/5625 [03:54<01:02, 18.97it/s]
 79%|███████▉  | 4436/5625 [03:55<01:00, 19.72it/s]
 79%|███████▉  | 4439/5625 [03:55<00:59, 19.79it/s]
 79%|███████▉  | 4441/5625 [03:55<00:59, 19.75it/s]
 79%|███████▉  | 4443/5625 [03:55<00:59, 19.76it/s]
 79%|███████▉  | 4445/5625 [03:55<01:01, 19.25it/s]
 79%|███████▉  | 4447/5625 [03:55<01:02, 18.97it/s]
 79%|███████▉  | 4449/5625 [03:55<01:02, 18.90it/s]
 79%|███████▉  | 4452/5625 [03:55<01:00, 19.26it/s]
 79%|███████▉  | 4454/5625 [03:56<01:01, 19.16it/s]
 79%|███████▉  | 4456/5625 [03:56<01:00, 19.33it/s]
 79%|███████▉  | 4459/5625 [03:56<00:59, 19.65it/s]
 79%|███████▉  | 4462/5625 [03:56<00:58, 19.76it/s]
 79%|███████▉  | 4464/5625 [03:56<00:58, 19.77it/s]
 79%|███████▉  | 4466/5625 [03:56<00:58, 19.80it/s]
 79%|███████▉  | 4468/5625 [03:56<00:58, 19.81it/s]
 79%|███████▉  | 4470/5625 [03:56<00:59, 19.26it/s]
 80%|███████▉  | 4472/5625 [03:56<00:59, 19.37it/s]
 80%|███████▉  | 4474/5625 [03:57<01:00, 18.88it/s]
 80%|███████▉  | 4476/5625 [03:57<01:00, 18.95it/s]
 80%|███████▉  | 4478/5625 [03:57<01:01, 18.70it/s]
 80%|███████▉  | 4481/5625 [03:57<00:59, 19.15it/s]
 80%|███████▉  | 4484/5625 [03:57<00:55, 20.48it/s]
 80%|███████▉  | 4487/5625 [03:57<00:56, 20.08it/s]
 80%|███████▉  | 4490/5625 [03:57<00:57, 19.67it/s]
 80%|███████▉  | 4492/5625 [03:57<00:57, 19.73it/s]
 80%|███████▉  | 4494/5625 [03:58<00:57, 19.50it/s]
 80%|███████▉  | 4497/5625 [03:58<00:55, 20.24it/s]
 80%|████████  | 4500/5625 [03:58<00:54, 20.46it/s]
 80%|████████  | 4503/5625 [03:58<00:52, 21.17it/s]
 80%|████████  | 4506/5625 [03:58<00:53, 20.84it/s]
 80%|████████  | 4509/5625 [03:58<00:54, 20.54it/s]
 80%|████████  | 4512/5625 [03:58<00:55, 20.08it/s]
 80%|████████  | 4515/5625 [03:59<00:57, 19.31it/s]
 80%|████████  | 4518/5625 [03:59<00:57, 19.36it/s]
 80%|████████  | 4521/5625 [03:59<00:54, 20.28it/s]
 80%|████████  | 4524/5625 [03:59<00:55, 19.88it/s]
 80%|████████  | 4527/5625 [03:59<00:53, 20.47it/s]
 81%|████████  | 4530/5625 [03:59<00:55, 19.72it/s]
 81%|████████  | 4533/5625 [03:59<00:55, 19.75it/s]
 81%|████████  | 4535/5625 [04:00<00:55, 19.70it/s]
 81%|████████  | 4537/5625 [04:00<00:55, 19.55it/s]
 81%|████████  | 4539/5625 [04:00<00:56, 19.34it/s]
 81%|████████  | 4542/5625 [04:00<00:54, 19.72it/s]
 81%|████████  | 4544/5625 [04:00<00:54, 19.66it/s]
 81%|████████  | 4546/5625 [04:00<00:55, 19.41it/s]
 81%|████████  | 4548/5625 [04:00<00:55, 19.48it/s]
 81%|████████  | 4551/5625 [04:00<00:52, 20.33it/s]
 81%|████████  | 4554/5625 [04:01<00:50, 21.07it/s]
 81%|████████  | 4557/5625 [04:01<00:50, 21.15it/s]
 81%|████████  | 4560/5625 [04:01<00:52, 20.25it/s]
 81%|████████  | 4563/5625 [04:01<00:53, 19.70it/s]
 81%|████████  | 4566/5625 [04:01<00:53, 19.62it/s]
 81%|████████  | 4568/5625 [04:01<00:54, 19.22it/s]
 81%|████████  | 4570/5625 [04:01<00:54, 19.26it/s]
 81%|████████▏ | 4572/5625 [04:01<00:56, 18.80it/s]
 81%|████████▏ | 4575/5625 [04:02<00:54, 19.10it/s]
 81%|████████▏ | 4577/5625 [04:02<00:54, 19.30it/s]
 81%|████████▏ | 4579/5625 [04:02<00:54, 19.18it/s]
 81%|████████▏ | 4581/5625 [04:02<00:54, 19.14it/s]
 81%|████████▏ | 4583/5625 [04:02<00:54, 19.08it/s]
 82%|████████▏ | 4585/5625 [04:02<00:53, 19.32it/s]
 82%|████████▏ | 4587/5625 [04:02<00:54, 19.07it/s]
 82%|████████▏ | 4589/5625 [04:02<00:55, 18.76it/s]
 82%|████████▏ | 4592/5625 [04:03<00:53, 19.30it/s]
 82%|████████▏ | 4594/5625 [04:03<00:54, 19.04it/s]
 82%|████████▏ | 4597/5625 [04:03<00:52, 19.52it/s]
 82%|████████▏ | 4599/5625 [04:03<00:52, 19.61it/s]
 82%|████████▏ | 4601/5625 [04:03<00:52, 19.64it/s]
 82%|████████▏ | 4603/5625 [04:03<00:52, 19.32it/s]
 82%|████████▏ | 4605/5625 [04:03<00:52, 19.28it/s]
 82%|████████▏ | 4607/5625 [04:03<00:53, 18.86it/s]
 82%|████████▏ | 4609/5625 [04:03<00:54, 18.61it/s]
 82%|████████▏ | 4611/5625 [04:04<00:55, 18.20it/s]
 82%|████████▏ | 4613/5625 [04:04<00:54, 18.63it/s]
 82%|████████▏ | 4615/5625 [04:04<00:53, 18.92it/s]
 82%|████████▏ | 4617/5625 [04:04<00:53, 18.89it/s]
 82%|████████▏ | 4619/5625 [04:04<00:52, 19.18it/s]
 82%|████████▏ | 4621/5625 [04:04<00:52, 19.21it/s]
 82%|████████▏ | 4623/5625 [04:04<00:53, 18.74it/s]
 82%|████████▏ | 4625/5625 [04:04<00:53, 18.63it/s]
 82%|████████▏ | 4627/5625 [04:04<00:53, 18.62it/s]
 82%|████████▏ | 4629/5625 [04:04<00:53, 18.68it/s]
 82%|████████▏ | 4631/5625 [04:05<00:54, 18.40it/s]
 82%|████████▏ | 4634/5625 [04:05<00:50, 19.73it/s]
 82%|████████▏ | 4637/5625 [04:05<00:50, 19.59it/s]
 82%|████████▏ | 4639/5625 [04:05<00:50, 19.54it/s]
 83%|████████▎ | 4641/5625 [04:05<00:50, 19.55it/s]
 83%|████████▎ | 4643/5625 [04:05<00:51, 18.99it/s]
 83%|████████▎ | 4645/5625 [04:05<00:51, 19.05it/s]
 83%|████████▎ | 4647/5625 [04:05<00:51, 19.01it/s]
 83%|████████▎ | 4649/5625 [04:06<00:52, 18.70it/s]
 83%|████████▎ | 4651/5625 [04:06<00:52, 18.64it/s]
 83%|████████▎ | 4653/5625 [04:06<00:51, 19.00it/s]
 83%|████████▎ | 4655/5625 [04:06<00:51, 18.92it/s]
 83%|████████▎ | 4657/5625 [04:06<00:50, 19.20it/s]
 83%|████████▎ | 4659/5625 [04:06<00:51, 18.91it/s]
 83%|████████▎ | 4661/5625 [04:06<00:50, 18.95it/s]
 83%|████████▎ | 4663/5625 [04:06<00:52, 18.47it/s]
 83%|████████▎ | 4665/5625 [04:06<00:52, 18.32it/s]
 83%|████████▎ | 4667/5625 [04:06<00:51, 18.74it/s]
 83%|████████▎ | 4670/5625 [04:07<00:49, 19.35it/s]
 83%|████████▎ | 4672/5625 [04:07<00:50, 18.85it/s]
 83%|████████▎ | 4675/5625 [04:07<00:49, 19.28it/s]
 83%|████████▎ | 4677/5625 [04:07<00:50, 18.87it/s]
 83%|████████▎ | 4680/5625 [04:07<00:48, 19.56it/s]
 83%|████████▎ | 4682/5625 [04:07<00:48, 19.61it/s]
 83%|████████▎ | 4684/5625 [04:07<00:48, 19.51it/s]
 83%|████████▎ | 4686/5625 [04:07<00:48, 19.45it/s]
 83%|████████▎ | 4688/5625 [04:08<00:48, 19.38it/s]
 83%|████████▎ | 4691/5625 [04:08<00:47, 19.71it/s]
 83%|████████▎ | 4693/5625 [04:08<00:47, 19.61it/s]
 83%|████████▎ | 4695/5625 [04:08<00:47, 19.58it/s]
 84%|████████▎ | 4697/5625 [04:08<00:48, 19.21it/s]
 84%|████████▎ | 4699/5625 [04:08<00:47, 19.36it/s]
 84%|████████▎ | 4701/5625 [04:08<00:48, 19.01it/s]
 84%|████████▎ | 4703/5625 [04:08<00:49, 18.45it/s]
 84%|████████▎ | 4706/5625 [04:08<00:48, 19.13it/s]
 84%|████████▎ | 4709/5625 [04:09<00:47, 19.47it/s]
 84%|████████▍ | 4711/5625 [04:09<00:47, 19.13it/s]
 84%|████████▍ | 4713/5625 [04:09<00:47, 19.10it/s]
 84%|████████▍ | 4715/5625 [04:09<00:48, 18.59it/s]
 84%|████████▍ | 4717/5625 [04:09<00:49, 18.46it/s]
 84%|████████▍ | 4719/5625 [04:09<00:49, 18.41it/s]
 84%|████████▍ | 4722/5625 [04:09<00:46, 19.44it/s]
 84%|████████▍ | 4724/5625 [04:09<00:47, 18.98it/s]
 84%|████████▍ | 4727/5625 [04:10<00:45, 19.71it/s]
 84%|████████▍ | 4730/5625 [04:10<00:44, 20.20it/s]
 84%|████████▍ | 4733/5625 [04:10<00:43, 20.28it/s]
 84%|████████▍ | 4736/5625 [04:10<00:45, 19.66it/s]
 84%|████████▍ | 4738/5625 [04:10<00:45, 19.68it/s]
 84%|████████▍ | 4740/5625 [04:10<00:45, 19.40it/s]
 84%|████████▍ | 4742/5625 [04:10<00:45, 19.29it/s]
 84%|████████▍ | 4744/5625 [04:10<00:46, 19.12it/s]
 84%|████████▍ | 4746/5625 [04:11<00:46, 18.78it/s]
 84%|████████▍ | 4748/5625 [04:11<00:45, 19.08it/s]
 84%|████████▍ | 4751/5625 [04:11<00:44, 19.85it/s]
 84%|████████▍ | 4753/5625 [04:11<00:45, 19.19it/s]
 85%|████████▍ | 4755/5625 [04:11<00:45, 19.11it/s]
 85%|████████▍ | 4757/5625 [04:11<00:44, 19.31it/s]
 85%|████████▍ | 4759/5625 [04:11<00:46, 18.82it/s]
 85%|████████▍ | 4761/5625 [04:11<00:46, 18.75it/s]
 85%|████████▍ | 4764/5625 [04:11<00:43, 19.70it/s]
 85%|████████▍ | 4766/5625 [04:12<00:43, 19.77it/s]
 85%|████████▍ | 4769/5625 [04:12<00:41, 20.41it/s]
 85%|████████▍ | 4772/5625 [04:12<00:44, 19.24it/s]
 85%|████████▍ | 4775/5625 [04:12<00:42, 19.85it/s]
 85%|████████▍ | 4777/5625 [04:12<00:43, 19.65it/s]
 85%|████████▍ | 4779/5625 [04:12<00:43, 19.56it/s]
 85%|████████▍ | 4781/5625 [04:12<00:43, 19.33it/s]
 85%|████████▌ | 4784/5625 [04:13<00:43, 19.29it/s]
 85%|████████▌ | 4786/5625 [04:13<00:44, 18.82it/s]
 85%|████████▌ | 4788/5625 [04:13<00:44, 18.75it/s]
 85%|████████▌ | 4791/5625 [04:13<00:41, 19.95it/s]
 85%|████████▌ | 4794/5625 [04:13<00:40, 20.35it/s]
 85%|████████▌ | 4797/5625 [04:13<00:40, 20.22it/s]
 85%|████████▌ | 4800/5625 [04:13<00:39, 20.73it/s]
 85%|████████▌ | 4803/5625 [04:13<00:40, 20.24it/s]
 85%|████████▌ | 4806/5625 [04:14<00:41, 19.56it/s]
 85%|████████▌ | 4808/5625 [04:14<00:41, 19.56it/s]
 86%|████████▌ | 4810/5625 [04:14<00:42, 18.99it/s]
 86%|████████▌ | 4813/5625 [04:14<00:40, 19.85it/s]
 86%|████████▌ | 4815/5625 [04:14<00:41, 19.55it/s]
 86%|████████▌ | 4818/5625 [04:14<00:40, 19.97it/s]
 86%|████████▌ | 4820/5625 [04:14<00:41, 19.38it/s]
 86%|████████▌ | 4822/5625 [04:14<00:42, 18.98it/s]
 86%|████████▌ | 4824/5625 [04:15<00:42, 18.94it/s]
 86%|████████▌ | 4826/5625 [04:15<00:41, 19.22it/s]
 86%|████████▌ | 4829/5625 [04:15<00:41, 19.41it/s]
 86%|████████▌ | 4831/5625 [04:15<00:40, 19.56it/s]
 86%|████████▌ | 4834/5625 [04:15<00:39, 20.01it/s]
 86%|████████▌ | 4836/5625 [04:15<00:39, 19.94it/s]
 86%|████████▌ | 4839/5625 [04:15<00:38, 20.20it/s]
 86%|████████▌ | 4842/5625 [04:15<00:38, 20.59it/s]
 86%|████████▌ | 4845/5625 [04:16<00:37, 20.53it/s]
 86%|████████▌ | 4848/5625 [04:16<00:38, 20.13it/s]
 86%|████████▌ | 4851/5625 [04:16<00:38, 20.16it/s]
 86%|████████▋ | 4854/5625 [04:16<00:39, 19.56it/s]
 86%|████████▋ | 4856/5625 [04:16<00:39, 19.58it/s]
 86%|████████▋ | 4858/5625 [04:16<00:39, 19.47it/s]
 86%|████████▋ | 4861/5625 [04:16<00:38, 19.84it/s]
 86%|████████▋ | 4863/5625 [04:17<00:38, 19.63it/s]
 86%|████████▋ | 4865/5625 [04:17<00:39, 19.42it/s]
 87%|████████▋ | 4868/5625 [04:17<00:37, 20.02it/s]
 87%|████████▋ | 4871/5625 [04:17<00:37, 20.18it/s]
 87%|████████▋ | 4874/5625 [04:17<00:36, 20.46it/s]
 87%|████████▋ | 4877/5625 [04:17<00:37, 19.81it/s]
 87%|████████▋ | 4879/5625 [04:17<00:38, 19.58it/s]
 87%|████████▋ | 4881/5625 [04:17<00:38, 19.17it/s]
 87%|████████▋ | 4883/5625 [04:18<00:38, 19.37it/s]
 87%|████████▋ | 4886/5625 [04:18<00:37, 19.81it/s]
 87%|████████▋ | 4888/5625 [04:18<00:37, 19.43it/s]
 87%|████████▋ | 4890/5625 [04:18<00:38, 19.23it/s]
 87%|████████▋ | 4893/5625 [04:18<00:37, 19.33it/s]
 87%|████████▋ | 4896/5625 [04:18<00:37, 19.63it/s]
 87%|████████▋ | 4899/5625 [04:18<00:36, 19.76it/s]
 87%|████████▋ | 4902/5625 [04:18<00:36, 19.98it/s]
 87%|████████▋ | 4904/5625 [04:19<00:36, 19.64it/s]
 87%|████████▋ | 4906/5625 [04:19<00:37, 19.29it/s]
 87%|████████▋ | 4908/5625 [04:19<00:36, 19.47it/s]
 87%|████████▋ | 4910/5625 [04:19<00:37, 19.25it/s]
 87%|████████▋ | 4913/5625 [04:19<00:35, 19.91it/s]
 87%|████████▋ | 4915/5625 [04:19<00:35, 19.80it/s]
 87%|████████▋ | 4917/5625 [04:19<00:35, 19.67it/s]
 87%|████████▋ | 4919/5625 [04:19<00:36, 19.36it/s]
 87%|████████▋ | 4921/5625 [04:19<00:36, 19.44it/s]
 88%|████████▊ | 4924/5625 [04:20<00:35, 19.86it/s]
 88%|████████▊ | 4927/5625 [04:20<00:34, 20.31it/s]
 88%|████████▊ | 4930/5625 [04:20<00:35, 19.46it/s]
 88%|████████▊ | 4932/5625 [04:20<00:35, 19.35it/s]
 88%|████████▊ | 4934/5625 [04:20<00:36, 18.83it/s]
 88%|████████▊ | 4936/5625 [04:20<00:36, 18.82it/s]
 88%|████████▊ | 4939/5625 [04:20<00:35, 19.41it/s]
 88%|████████▊ | 4942/5625 [04:21<00:34, 19.74it/s]
 88%|████████▊ | 4945/5625 [04:21<00:33, 20.29it/s]
 88%|████████▊ | 4948/5625 [04:21<00:34, 19.87it/s]
 88%|████████▊ | 4950/5625 [04:21<00:34, 19.49it/s]
 88%|████████▊ | 4952/5625 [04:21<00:34, 19.36it/s]
 88%|████████▊ | 4955/5625 [04:21<00:32, 20.42it/s]
 88%|████████▊ | 4958/5625 [04:21<00:33, 19.87it/s]
 88%|████████▊ | 4960/5625 [04:21<00:33, 19.88it/s]
 88%|████████▊ | 4962/5625 [04:22<00:34, 19.20it/s]
 88%|████████▊ | 4964/5625 [04:22<00:34, 19.05it/s]
 88%|████████▊ | 4966/5625 [04:22<00:34, 19.24it/s]
 88%|████████▊ | 4968/5625 [04:22<00:34, 18.84it/s]
 88%|████████▊ | 4970/5625 [04:22<00:34, 19.11it/s]
 88%|████████▊ | 4972/5625 [04:22<00:34, 18.74it/s]
 88%|████████▊ | 4974/5625 [04:22<00:34, 18.62it/s]
 88%|████████▊ | 4976/5625 [04:22<00:35, 18.44it/s]
 89%|████████▊ | 4979/5625 [04:22<00:33, 19.22it/s]
 89%|████████▊ | 4981/5625 [04:23<00:33, 19.29it/s]
 89%|████████▊ | 4984/5625 [04:23<00:32, 19.75it/s]
 89%|████████▊ | 4987/5625 [04:23<00:31, 19.99it/s]
 89%|████████▊ | 4989/5625 [04:23<00:32, 19.38it/s]
 89%|████████▊ | 4992/5625 [04:23<00:30, 20.63it/s]
 89%|████████▉ | 4995/5625 [04:23<00:31, 19.90it/s]
 89%|████████▉ | 4997/5625 [04:23<00:31, 19.64it/s]
 89%|████████▉ | 5000/5625 [04:23<00:30, 20.35it/s]
 89%|████████▉ | 5003/5625 [04:24<00:31, 19.71it/s]
 89%|████████▉ | 5005/5625 [04:24<00:32, 19.20it/s]
 89%|████████▉ | 5007/5625 [04:24<00:32, 19.26it/s]
 89%|████████▉ | 5009/5625 [04:24<00:32, 19.12it/s]
 89%|████████▉ | 5011/5625 [04:24<00:32, 18.70it/s]
 89%|████████▉ | 5013/5625 [04:24<00:32, 18.89it/s]
 89%|████████▉ | 5015/5625 [04:24<00:32, 18.80it/s]
 89%|████████▉ | 5018/5625 [04:24<00:30, 19.70it/s]
 89%|████████▉ | 5021/5625 [04:25<00:31, 19.48it/s]
 89%|████████▉ | 5024/5625 [04:25<00:30, 19.82it/s]
 89%|████████▉ | 5027/5625 [04:25<00:29, 20.19it/s]
 89%|████████▉ | 5030/5625 [04:25<00:29, 19.96it/s]
 89%|████████▉ | 5032/5625 [04:25<00:30, 19.56it/s]
 90%|████████▉ | 5035/5625 [04:25<00:30, 19.61it/s]
 90%|████████▉ | 5037/5625 [04:25<00:30, 19.48it/s]
 90%|████████▉ | 5040/5625 [04:26<00:29, 19.83it/s]
 90%|████████▉ | 5042/5625 [04:26<00:29, 19.83it/s]
 90%|████████▉ | 5044/5625 [04:26<00:29, 19.86it/s]
 90%|████████▉ | 5046/5625 [04:26<00:29, 19.69it/s]
 90%|████████▉ | 5048/5625 [04:26<00:30, 19.17it/s]
 90%|████████▉ | 5050/5625 [04:26<00:29, 19.33it/s]
 90%|████████▉ | 5052/5625 [04:26<00:29, 19.48it/s]
 90%|████████▉ | 5054/5625 [04:26<00:29, 19.55it/s]
 90%|████████▉ | 5056/5625 [04:26<00:29, 19.25it/s]
 90%|████████▉ | 5058/5625 [04:26<00:29, 19.11it/s]
 90%|████████▉ | 5060/5625 [04:27<00:29, 19.05it/s]
 90%|█████████ | 5063/5625 [04:27<00:28, 20.04it/s]
 90%|█████████ | 5065/5625 [04:27<00:28, 19.80it/s]
 90%|█████████ | 5067/5625 [04:27<00:29, 19.19it/s]
 90%|█████████ | 5070/5625 [04:27<00:28, 19.36it/s]
 90%|█████████ | 5072/5625 [04:27<00:28, 19.18it/s]
 90%|█████████ | 5074/5625 [04:27<00:28, 19.32it/s]
 90%|█████████ | 5076/5625 [04:27<00:28, 19.06it/s]
 90%|█████████ | 5078/5625 [04:28<00:28, 19.03it/s]
 90%|█████████ | 5080/5625 [04:28<00:28, 19.00it/s]
 90%|█████████ | 5082/5625 [04:28<00:28, 19.27it/s]
 90%|█████████ | 5084/5625 [04:28<00:28, 19.05it/s]
 90%|█████████ | 5087/5625 [04:28<00:27, 19.34it/s]
 90%|█████████ | 5089/5625 [04:28<00:28, 19.05it/s]
 91%|█████████ | 5091/5625 [04:28<00:27, 19.23it/s]
 91%|█████████ | 5094/5625 [04:28<00:27, 19.66it/s]
 91%|█████████ | 5096/5625 [04:28<00:27, 19.16it/s]
 91%|█████████ | 5098/5625 [04:29<00:27, 18.95it/s]
 91%|█████████ | 5100/5625 [04:29<00:27, 18.89it/s]
 91%|█████████ | 5102/5625 [04:29<00:27, 19.14it/s]
 91%|█████████ | 5105/5625 [04:29<00:25, 20.47it/s]
 91%|█████████ | 5108/5625 [04:29<00:24, 20.93it/s]
 91%|█████████ | 5111/5625 [04:29<00:24, 20.80it/s]
 91%|█████████ | 5114/5625 [04:29<00:25, 19.82it/s]
 91%|█████████ | 5116/5625 [04:29<00:26, 19.28it/s]
 91%|█████████ | 5119/5625 [04:30<00:25, 19.97it/s]
 91%|█████████ | 5122/5625 [04:30<00:25, 19.83it/s]
 91%|█████████ | 5124/5625 [04:30<00:25, 19.62it/s]
 91%|█████████ | 5127/5625 [04:30<00:24, 20.31it/s]
 91%|█████████ | 5130/5625 [04:30<00:25, 19.71it/s]
 91%|█████████ | 5132/5625 [04:30<00:25, 19.47it/s]
 91%|█████████▏| 5134/5625 [04:30<00:25, 19.36it/s]
 91%|█████████▏| 5137/5625 [04:31<00:24, 19.79it/s]
 91%|█████████▏| 5139/5625 [04:31<00:25, 19.16it/s]
 91%|█████████▏| 5141/5625 [04:31<00:25, 18.94it/s]
 91%|█████████▏| 5143/5625 [04:31<00:25, 18.62it/s]
 91%|█████████▏| 5145/5625 [04:31<00:26, 18.23it/s]
 92%|█████████▏| 5147/5625 [04:31<00:26, 18.15it/s]
 92%|█████████▏| 5150/5625 [04:31<00:25, 18.69it/s]
 92%|█████████▏| 5152/5625 [04:31<00:25, 18.54it/s]
 92%|█████████▏| 5155/5625 [04:31<00:24, 19.04it/s]
 92%|█████████▏| 5158/5625 [04:32<00:24, 19.26it/s]
 92%|█████████▏| 5160/5625 [04:32<00:24, 19.00it/s]
 92%|█████████▏| 5162/5625 [04:32<00:24, 19.15it/s]
 92%|█████████▏| 5164/5625 [04:32<00:24, 19.13it/s]
 92%|█████████▏| 5166/5625 [04:32<00:24, 19.08it/s]
 92%|█████████▏| 5168/5625 [04:32<00:24, 18.62it/s]
 92%|█████████▏| 5170/5625 [04:32<00:24, 18.34it/s]
 92%|█████████▏| 5173/5625 [04:32<00:23, 18.92it/s]
 92%|█████████▏| 5176/5625 [04:33<00:23, 19.43it/s]
 92%|█████████▏| 5179/5625 [04:33<00:22, 19.88it/s]
 92%|█████████▏| 5181/5625 [04:33<00:22, 19.57it/s]
 92%|█████████▏| 5183/5625 [04:33<00:22, 19.53it/s]
 92%|█████████▏| 5186/5625 [04:33<00:22, 19.82it/s]
 92%|█████████▏| 5188/5625 [04:33<00:22, 19.27it/s]
 92%|█████████▏| 5190/5625 [04:33<00:23, 18.76it/s]
 92%|█████████▏| 5192/5625 [04:33<00:22, 18.98it/s]
 92%|█████████▏| 5194/5625 [04:34<00:22, 19.11it/s]
 92%|█████████▏| 5197/5625 [04:34<00:22, 19.34it/s]
 92%|█████████▏| 5199/5625 [04:34<00:21, 19.49it/s]
 92%|█████████▏| 5201/5625 [04:34<00:22, 19.26it/s]
 92%|█████████▏| 5203/5625 [04:34<00:22, 18.83it/s]
 93%|█████████▎| 5205/5625 [04:34<00:22, 18.63it/s]
 93%|█████████▎| 5207/5625 [04:34<00:22, 18.97it/s]
 93%|█████████▎| 5209/5625 [04:34<00:21, 19.25it/s]
 93%|█████████▎| 5211/5625 [04:34<00:21, 19.42it/s]
 93%|█████████▎| 5214/5625 [04:35<00:20, 19.74it/s]
 93%|█████████▎| 5216/5625 [04:35<00:21, 19.40it/s]
 93%|█████████▎| 5219/5625 [04:35<00:20, 20.17it/s]
 93%|█████████▎| 5222/5625 [04:35<00:20, 19.32it/s]
 93%|█████████▎| 5224/5625 [04:35<00:20, 19.10it/s]
 93%|█████████▎| 5226/5625 [04:35<00:21, 18.93it/s]
 93%|█████████▎| 5228/5625 [04:35<00:20, 19.01it/s]
 93%|█████████▎| 5231/5625 [04:35<00:20, 19.59it/s]
 93%|█████████▎| 5233/5625 [04:36<00:20, 19.08it/s]
 93%|█████████▎| 5235/5625 [04:36<00:20, 19.20it/s]
 93%|█████████▎| 5238/5625 [04:36<00:19, 19.82it/s]
 93%|█████████▎| 5240/5625 [04:36<00:19, 19.43it/s]
 93%|█████████▎| 5242/5625 [04:36<00:20, 19.09it/s]
 93%|█████████▎| 5245/5625 [04:36<00:19, 19.32it/s]
 93%|█████████▎| 5247/5625 [04:36<00:19, 19.22it/s]
 93%|█████████▎| 5249/5625 [04:36<00:20, 18.76it/s]
 93%|█████████▎| 5251/5625 [04:36<00:20, 18.62it/s]
 93%|█████████▎| 5254/5625 [04:37<00:19, 19.03it/s]
 93%|█████████▎| 5256/5625 [04:37<00:19, 19.05it/s]
 93%|█████████▎| 5258/5625 [04:37<00:19, 18.86it/s]
 94%|█████████▎| 5260/5625 [04:37<00:19, 18.69it/s]
 94%|█████████▎| 5263/5625 [04:37<00:18, 19.25it/s]
 94%|█████████▎| 5265/5625 [04:37<00:18, 19.23it/s]
 94%|█████████▎| 5267/5625 [04:37<00:18, 19.38it/s]
 94%|█████████▎| 5270/5625 [04:37<00:17, 19.81it/s]
 94%|█████████▎| 5272/5625 [04:38<00:18, 19.46it/s]
 94%|█████████▍| 5274/5625 [04:38<00:18, 18.86it/s]
 94%|█████████▍| 5276/5625 [04:38<00:18, 18.90it/s]
 94%|█████████▍| 5278/5625 [04:38<00:18, 18.82it/s]
 94%|█████████▍| 5280/5625 [04:38<00:18, 18.77it/s]
 94%|█████████▍| 5282/5625 [04:38<00:18, 19.03it/s]
 94%|█████████▍| 5284/5625 [04:38<00:18, 18.65it/s]
 94%|█████████▍| 5286/5625 [04:38<00:18, 18.61it/s]
 94%|█████████▍| 5288/5625 [04:38<00:18, 18.54it/s]
 94%|█████████▍| 5291/5625 [04:39<00:17, 18.91it/s]
 94%|█████████▍| 5293/5625 [04:39<00:17, 18.64it/s]
 94%|█████████▍| 5295/5625 [04:39<00:17, 18.37it/s]
 94%|█████████▍| 5297/5625 [04:39<00:17, 18.55it/s]
 94%|█████████▍| 5299/5625 [04:39<00:17, 18.34it/s]
 94%|█████████▍| 5301/5625 [04:39<00:17, 18.58it/s]
 94%|█████████▍| 5304/5625 [04:39<00:16, 19.06it/s]
 94%|█████████▍| 5306/5625 [04:39<00:16, 19.07it/s]
 94%|█████████▍| 5308/5625 [04:39<00:16, 19.30it/s]
 94%|█████████▍| 5310/5625 [04:40<00:16, 19.36it/s]
 94%|█████████▍| 5312/5625 [04:40<00:16, 18.95it/s]
 94%|█████████▍| 5315/5625 [04:40<00:16, 19.18it/s]
 95%|█████████▍| 5318/5625 [04:40<00:15, 19.53it/s]
 95%|█████████▍| 5320/5625 [04:40<00:15, 19.23it/s]
 95%|█████████▍| 5322/5625 [04:40<00:15, 19.27it/s]
 95%|█████████▍| 5324/5625 [04:40<00:15, 19.14it/s]
 95%|█████████▍| 5327/5625 [04:40<00:15, 19.34it/s]
 95%|█████████▍| 5329/5625 [04:41<00:15, 19.12it/s]
 95%|█████████▍| 5331/5625 [04:41<00:15, 19.18it/s]
 95%|█████████▍| 5334/5625 [04:41<00:15, 19.36it/s]
 95%|█████████▍| 5337/5625 [04:41<00:14, 19.45it/s]
 95%|█████████▍| 5339/5625 [04:41<00:15, 19.00it/s]
 95%|█████████▍| 5341/5625 [04:41<00:15, 18.88it/s]
 95%|█████████▍| 5343/5625 [04:41<00:15, 18.49it/s]
 95%|█████████▌| 5345/5625 [04:41<00:14, 18.76it/s]
 95%|█████████▌| 5348/5625 [04:42<00:14, 19.69it/s]
 95%|█████████▌| 5351/5625 [04:42<00:13, 19.64it/s]
 95%|█████████▌| 5353/5625 [04:42<00:13, 19.46it/s]
 95%|█████████▌| 5356/5625 [04:42<00:13, 19.81it/s]
 95%|█████████▌| 5358/5625 [04:42<00:13, 19.28it/s]
 95%|█████████▌| 5360/5625 [04:42<00:13, 19.23it/s]
 95%|█████████▌| 5362/5625 [04:42<00:14, 18.73it/s]
 95%|█████████▌| 5364/5625 [04:42<00:13, 18.68it/s]
 95%|█████████▌| 5366/5625 [04:43<00:13, 18.81it/s]
 95%|█████████▌| 5369/5625 [04:43<00:12, 20.03it/s]
 95%|█████████▌| 5371/5625 [04:43<00:13, 19.44it/s]
 96%|█████████▌| 5373/5625 [04:43<00:13, 19.33it/s]
 96%|█████████▌| 5375/5625 [04:43<00:13, 19.02it/s]
 96%|█████████▌| 5378/5625 [04:43<00:12, 19.92it/s]
 96%|█████████▌| 5381/5625 [04:43<00:12, 20.27it/s]
 96%|█████████▌| 5384/5625 [04:43<00:11, 20.71it/s]
 96%|█████████▌| 5387/5625 [04:44<00:12, 19.80it/s]
 96%|█████████▌| 5389/5625 [04:44<00:12, 19.17it/s]
 96%|█████████▌| 5391/5625 [04:44<00:12, 18.77it/s]
 96%|█████████▌| 5393/5625 [04:44<00:12, 18.78it/s]
 96%|█████████▌| 5395/5625 [04:44<00:12, 18.76it/s]
 96%|█████████▌| 5398/5625 [04:44<00:11, 19.66it/s]
 96%|█████████▌| 5400/5625 [04:44<00:11, 18.94it/s]
 96%|█████████▌| 5402/5625 [04:44<00:11, 18.69it/s]
 96%|█████████▌| 5404/5625 [04:44<00:11, 19.03it/s]
 96%|█████████▌| 5407/5625 [04:45<00:10, 19.94it/s]
 96%|█████████▌| 5409/5625 [04:45<00:10, 19.87it/s]
 96%|█████████▌| 5411/5625 [04:45<00:11, 19.29it/s]
 96%|█████████▌| 5413/5625 [04:45<00:11, 18.77it/s]
 96%|█████████▋| 5415/5625 [04:45<00:11, 18.37it/s]
 96%|█████████▋| 5418/5625 [04:45<00:10, 19.29it/s]
 96%|█████████▋| 5420/5625 [04:45<00:10, 19.24it/s]
 96%|█████████▋| 5422/5625 [04:45<00:10, 19.32it/s]
 96%|█████████▋| 5424/5625 [04:46<00:10, 18.90it/s]
 96%|█████████▋| 5426/5625 [04:46<00:10, 18.72it/s]
 96%|█████████▋| 5428/5625 [04:46<00:10, 18.96it/s]
 97%|█████████▋| 5430/5625 [04:46<00:10, 19.07it/s]
 97%|█████████▋| 5433/5625 [04:46<00:09, 19.50it/s]
 97%|█████████▋| 5435/5625 [04:46<00:09, 19.55it/s]
 97%|█████████▋| 5437/5625 [04:46<00:09, 19.43it/s]
 97%|█████████▋| 5439/5625 [04:46<00:09, 18.83it/s]
 97%|█████████▋| 5441/5625 [04:46<00:09, 18.76it/s]
 97%|█████████▋| 5443/5625 [04:47<00:09, 18.38it/s]
 97%|█████████▋| 5445/5625 [04:47<00:09, 18.65it/s]
 97%|█████████▋| 5447/5625 [04:47<00:09, 18.69it/s]
 97%|█████████▋| 5449/5625 [04:47<00:09, 18.93it/s]
 97%|█████████▋| 5451/5625 [04:47<00:09, 19.19it/s]
 97%|█████████▋| 5453/5625 [04:47<00:08, 19.13it/s]
 97%|█████████▋| 5455/5625 [04:47<00:08, 19.24it/s]
 97%|█████████▋| 5458/5625 [04:47<00:08, 19.32it/s]
 97%|█████████▋| 5460/5625 [04:47<00:08, 18.96it/s]
 97%|█████████▋| 5462/5625 [04:48<00:08, 18.42it/s]
 97%|█████████▋| 5464/5625 [04:48<00:08, 18.41it/s]
 97%|█████████▋| 5466/5625 [04:48<00:08, 18.48it/s]
 97%|█████████▋| 5468/5625 [04:48<00:08, 18.39it/s]
 97%|█████████▋| 5470/5625 [04:48<00:08, 18.47it/s]
 97%|█████████▋| 5473/5625 [04:48<00:08, 18.75it/s]
 97%|█████████▋| 5475/5625 [04:48<00:08, 18.54it/s]
 97%|█████████▋| 5478/5625 [04:48<00:07, 19.30it/s]
 97%|█████████▋| 5481/5625 [04:49<00:07, 20.33it/s]
 97%|█████████▋| 5484/5625 [04:49<00:07, 19.35it/s]
 98%|█████████▊| 5486/5625 [04:49<00:07, 19.02it/s]
 98%|█████████▊| 5489/5625 [04:49<00:07, 19.37it/s]
 98%|█████████▊| 5491/5625 [04:49<00:07, 19.04it/s]
 98%|█████████▊| 5494/5625 [04:49<00:06, 19.41it/s]
 98%|█████████▊| 5496/5625 [04:49<00:06, 19.08it/s]
 98%|█████████▊| 5498/5625 [04:49<00:06, 18.82it/s]
 98%|█████████▊| 5500/5625 [04:50<00:06, 19.11it/s]
 98%|█████████▊| 5502/5625 [04:50<00:06, 18.58it/s]
 98%|█████████▊| 5505/5625 [04:50<00:06, 18.74it/s]
 98%|█████████▊| 5507/5625 [04:50<00:06, 18.41it/s]
 98%|█████████▊| 5509/5625 [04:50<00:06, 18.23it/s]
 98%|█████████▊| 5511/5625 [04:50<00:06, 18.07it/s]
 98%|█████████▊| 5514/5625 [04:50<00:05, 19.00it/s]
 98%|█████████▊| 5516/5625 [04:50<00:05, 18.81it/s]
 98%|█████████▊| 5518/5625 [04:50<00:05, 19.04it/s]
 98%|█████████▊| 5521/5625 [04:51<00:05, 19.35it/s]
 98%|█████████▊| 5523/5625 [04:51<00:05, 19.24it/s]
 98%|█████████▊| 5526/5625 [04:51<00:05, 19.48it/s]
 98%|█████████▊| 5528/5625 [04:51<00:05, 19.29it/s]
 98%|█████████▊| 5530/5625 [04:51<00:04, 19.24it/s]
 98%|█████████▊| 5533/5625 [04:51<00:04, 19.73it/s]
 98%|█████████▊| 5535/5625 [04:51<00:04, 19.72it/s]
 98%|█████████▊| 5538/5625 [04:51<00:04, 20.27it/s]
 99%|█████████▊| 5541/5625 [04:52<00:04, 20.55it/s]
 99%|█████████▊| 5544/5625 [04:52<00:03, 20.36it/s]
 99%|█████████▊| 5547/5625 [04:52<00:03, 19.73it/s]
 99%|█████████▊| 5549/5625 [04:52<00:03, 19.59it/s]
 99%|█████████▊| 5551/5625 [04:52<00:03, 19.27it/s]
 99%|█████████▊| 5553/5625 [04:52<00:03, 19.11it/s]
 99%|█████████▉| 5556/5625 [04:52<00:03, 19.50it/s]
 99%|█████████▉| 5558/5625 [04:53<00:03, 18.91it/s]
 99%|█████████▉| 5560/5625 [04:53<00:03, 19.11it/s]
 99%|█████████▉| 5562/5625 [04:53<00:03, 18.98it/s]
 99%|█████████▉| 5565/5625 [04:53<00:03, 19.43it/s]
 99%|█████████▉| 5568/5625 [04:53<00:02, 19.66it/s]
 99%|█████████▉| 5570/5625 [04:53<00:02, 19.36it/s]
 99%|█████████▉| 5573/5625 [04:53<00:02, 19.62it/s]
 99%|█████████▉| 5576/5625 [04:53<00:02, 19.72it/s]
 99%|█████████▉| 5578/5625 [04:54<00:02, 19.38it/s]
 99%|█████████▉| 5580/5625 [04:54<00:02, 19.10it/s]
 99%|█████████▉| 5583/5625 [04:54<00:02, 19.87it/s]
 99%|█████████▉| 5586/5625 [04:54<00:01, 20.27it/s]
 99%|█████████▉| 5589/5625 [04:54<00:01, 19.63it/s]
 99%|█████████▉| 5591/5625 [04:54<00:01, 19.09it/s]
 99%|█████████▉| 5593/5625 [04:54<00:01, 19.20it/s]
 99%|█████████▉| 5595/5625 [04:54<00:01, 19.18it/s]
100%|█████████▉| 5597/5625 [04:55<00:01, 19.05it/s]
100%|█████████▉| 5599/5625 [04:55<00:01, 19.16it/s]
100%|█████████▉| 5602/5625 [04:55<00:01, 19.25it/s]
100%|█████████▉| 5604/5625 [04:55<00:01, 18.98it/s]
100%|█████████▉| 5606/5625 [04:55<00:01, 18.96it/s]
100%|█████████▉| 5608/5625 [04:55<00:00, 18.43it/s]
100%|█████████▉| 5610/5625 [04:55<00:00, 18.76it/s]
100%|█████████▉| 5613/5625 [04:55<00:00, 19.41it/s]
100%|█████████▉| 5616/5625 [04:56<00:00, 19.54it/s]
100%|█████████▉| 5618/5625 [04:56<00:00, 19.33it/s]
100%|█████████▉| 5620/5625 [04:56<00:00, 19.24it/s]
100%|█████████▉| 5622/5625 [04:56<00:00, 19.04it/s]
100%|█████████▉| 5624/5625 [04:56<00:00, 18.56it/s]
                                                   

100%|██████████| 5625/5625 [04:56<00:00, 18.56it/s]{'eval_loss': 0.6895633935928345, 'eval_accuracy': 0.7152, 'eval_f1': 0.713872651078523, 'eval_runtime': 1.7295, 'eval_samples_per_second': 1445.474, 'eval_steps_per_second': 180.973, 'epoch': 2.0}
{'loss': 0.2412, 'learning_rate': 7.394124810861369e-11, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.83it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.75it/s]

 21%|██        | 66/313 [00:00<00:01, 206.26it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.49it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.80it/s]

 40%|████      | 126/313 [00:00<00:01, 185.57it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.33it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.35it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.30it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.44it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.52it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.23it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 185.07it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.99it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.80it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.80it/s]
100%|██████████| 5625/5625 [04:58<00:00, 18.56it/s]

                                                  
100%|██████████| 5625/5625 [04:58<00:00, 18.86it/s]
[I 2023-10-26 23:42:37,400] Trial 37 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.9348405003547668, 'eval_accuracy': 0.7076, 'eval_f1': 0.7088317229368951, 'eval_runtime': 1.7295, 'eval_samples_per_second': 1445.484, 'eval_steps_per_second': 180.975, 'epoch': 3.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:04,  1.92it/s]
  1%|          | 2/354 [00:01<03:01,  1.94it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:54,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:55,  1.99it/s]
  2%|▏         | 6/354 [00:03<02:53,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.04it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.02it/s]
  3%|▎         | 9/354 [00:04<02:52,  2.00it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:50,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:51,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:51,  1.99it/s]
  4%|▍         | 14/354 [00:07<02:51,  1.98it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.98it/s]
  5%|▍         | 16/354 [00:08<02:50,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:50,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:46,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:46,  2.00it/s]
  6%|▌         | 22/354 [00:11<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:47,  1.98it/s]
  7%|▋         | 24/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 25/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:46,  1.97it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.01it/s]
  8%|▊         | 28/354 [00:14<02:41,  2.01it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:43,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:16<02:40,  2.01it/s]
  9%|▉         | 33/354 [00:16<02:40,  2.00it/s]
 10%|▉         | 34/354 [00:17<02:41,  1.99it/s]
 10%|▉         | 35/354 [00:17<02:37,  2.03it/s]
 10%|█         | 36/354 [00:17<02:35,  2.05it/s]
 10%|█         | 37/354 [00:18<02:34,  2.05it/s]
 11%|█         | 38/354 [00:18<02:35,  2.03it/s]
 11%|█         | 39/354 [00:19<02:36,  2.02it/s]
 11%|█▏        | 40/354 [00:19<02:37,  2.00it/s]
 12%|█▏        | 41/354 [00:20<02:37,  1.99it/s]
 12%|█▏        | 42/354 [00:20<02:34,  2.02it/s]
 12%|█▏        | 43/354 [00:21<02:35,  2.00it/s]
 12%|█▏        | 44/354 [00:21<02:34,  2.00it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:22<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:23<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:25<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:26<02:32,  1.98it/s]
 15%|█▍        | 53/354 [00:26<02:28,  2.03it/s]
 15%|█▌        | 54/354 [00:26<02:28,  2.02it/s]
 16%|█▌        | 55/354 [00:27<02:28,  2.02it/s]
 16%|█▌        | 56/354 [00:27<02:28,  2.01it/s]
 16%|█▌        | 57/354 [00:28<02:26,  2.03it/s]
 16%|█▋        | 58/354 [00:28<02:27,  2.01it/s]
 17%|█▋        | 59/354 [00:29<02:24,  2.04it/s]
 17%|█▋        | 60/354 [00:29<02:25,  2.01it/s]
 17%|█▋        | 61/354 [00:30<02:25,  2.01it/s]
 18%|█▊        | 62/354 [00:30<02:23,  2.04it/s]
 18%|█▊        | 63/354 [00:31<02:21,  2.06it/s]
 18%|█▊        | 64/354 [00:31<02:19,  2.07it/s]
 18%|█▊        | 65/354 [00:32<02:20,  2.05it/s]
 19%|█▊        | 66/354 [00:32<02:20,  2.05it/s]
 19%|█▉        | 67/354 [00:33<02:21,  2.03it/s]
 19%|█▉        | 68/354 [00:33<02:20,  2.03it/s]
 19%|█▉        | 69/354 [00:34<02:18,  2.05it/s]
 20%|█▉        | 70/354 [00:34<02:20,  2.02it/s]
 20%|██        | 71/354 [00:35<02:21,  2.01it/s]
 20%|██        | 72/354 [00:35<02:21,  1.99it/s]
 21%|██        | 73/354 [00:36<02:21,  1.98it/s]
 21%|██        | 74/354 [00:36<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.01it/s]
 21%|██▏       | 76/354 [00:37<02:15,  2.05it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:38<02:17,  2.01it/s]
 22%|██▏       | 79/354 [00:39<02:16,  2.01it/s]
 23%|██▎       | 80/354 [00:39<02:17,  1.99it/s]
 23%|██▎       | 81/354 [00:40<02:17,  1.99it/s]
 23%|██▎       | 82/354 [00:40<02:16,  1.99it/s]
 23%|██▎       | 83/354 [00:41<02:15,  2.01it/s]
 24%|██▎       | 84/354 [00:41<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:13,  2.02it/s]
 24%|██▍       | 86/354 [00:42<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  1.99it/s]
 25%|██▍       | 88/354 [00:43<02:13,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:44<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.97it/s]
 26%|██▌       | 92/354 [00:45<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.01it/s]
 27%|██▋       | 94/354 [00:46<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 96/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:48<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.09it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:03,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  1.99it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  1.99it/s]
 31%|███       | 109/354 [00:54<02:03,  1.98it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:59,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.8645, 'learning_rate': 2.3762336562079696e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.69it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.62it/s]

 21%|██        | 65/313 [00:00<00:01, 204.73it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.00it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.17it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.85it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.50it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.16it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.72it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.65it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.80it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.95it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.09it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.54it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.63it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.63it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  
 33%|███▎      | 118/354 [01:00<02:00,  1.96it/s]
[I 2023-10-26 23:43:38,194] Trial 38 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7836872935295105, 'eval_accuracy': 0.6452, 'eval_f1': 0.640150152497887, 'eval_runtime': 1.734, 'eval_samples_per_second': 1441.744, 'eval_steps_per_second': 180.506, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:11,  3.67it/s]
  0%|          | 2/705 [00:00<03:10,  3.69it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:44,  3.82it/s]
 11%|█         | 78/705 [00:20<02:42,  3.86it/s]
 11%|█         | 79/705 [00:20<02:44,  3.80it/s]
 11%|█▏        | 80/705 [00:21<02:44,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:42,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.77it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.848, 'learning_rate': 1.5759052062872798e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.09it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.36it/s]

 21%|██        | 66/313 [00:00<00:01, 205.83it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.04it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.43it/s]

 40%|████      | 126/313 [00:00<00:01, 185.11it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.90it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.79it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.75it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.96it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.10it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.81it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.52it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.41it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.26it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.26it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 23:44:42,290] Trial 39 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7101575136184692, 'eval_accuracy': 0.6896, 'eval_f1': 0.6869841192642184, 'eval_runtime': 1.7345, 'eval_samples_per_second': 1441.326, 'eval_steps_per_second': 180.454, 'epoch': 1.0}

  0%|          | 0/1407 [00:00<?, ?it/s]
  0%|          | 1/1407 [00:00<03:31,  6.63it/s]
  0%|          | 2/1407 [00:00<03:25,  6.83it/s]
  0%|          | 3/1407 [00:00<03:25,  6.82it/s]
  0%|          | 4/1407 [00:00<03:31,  6.64it/s]
  0%|          | 5/1407 [00:00<03:33,  6.56it/s]
  0%|          | 6/1407 [00:00<03:35,  6.50it/s]
  0%|          | 7/1407 [00:01<03:36,  6.45it/s]
  1%|          | 8/1407 [00:01<03:30,  6.66it/s]
  1%|          | 9/1407 [00:01<03:26,  6.78it/s]
  1%|          | 10/1407 [00:01<03:26,  6.76it/s]
  1%|          | 11/1407 [00:01<03:24,  6.83it/s]
  1%|          | 12/1407 [00:01<03:06,  7.46it/s]
  1%|          | 13/1407 [00:01<03:12,  7.22it/s]
  1%|          | 14/1407 [00:02<03:16,  7.09it/s]
  1%|          | 15/1407 [00:02<03:17,  7.05it/s]
  1%|          | 16/1407 [00:02<03:16,  7.08it/s]
  1%|          | 17/1407 [00:02<03:18,  7.00it/s]
  1%|▏         | 18/1407 [00:02<03:24,  6.80it/s]
  1%|▏         | 19/1407 [00:02<03:27,  6.70it/s]
  1%|▏         | 20/1407 [00:02<03:29,  6.61it/s]
  1%|▏         | 21/1407 [00:03<03:27,  6.67it/s]
  2%|▏         | 22/1407 [00:03<03:27,  6.69it/s]
  2%|▏         | 23/1407 [00:03<03:25,  6.75it/s]
  2%|▏         | 24/1407 [00:03<03:24,  6.78it/s]
  2%|▏         | 25/1407 [00:03<03:21,  6.86it/s]
  2%|▏         | 26/1407 [00:03<03:20,  6.90it/s]
  2%|▏         | 27/1407 [00:03<03:19,  6.92it/s]
  2%|▏         | 28/1407 [00:04<03:20,  6.89it/s]
  2%|▏         | 29/1407 [00:04<03:23,  6.77it/s]
  2%|▏         | 30/1407 [00:04<03:26,  6.67it/s]
  2%|▏         | 32/1407 [00:04<03:04,  7.46it/s]
  2%|▏         | 33/1407 [00:04<03:11,  7.16it/s]
  2%|▏         | 34/1407 [00:04<03:13,  7.08it/s]
  2%|▏         | 35/1407 [00:05<03:19,  6.88it/s]
  3%|▎         | 36/1407 [00:05<03:18,  6.90it/s]
  3%|▎         | 37/1407 [00:05<03:10,  7.18it/s]
  3%|▎         | 38/1407 [00:05<03:12,  7.11it/s]
  3%|▎         | 39/1407 [00:05<03:13,  7.07it/s]
  3%|▎         | 40/1407 [00:05<03:16,  6.97it/s]
  3%|▎         | 41/1407 [00:05<03:19,  6.84it/s]
  3%|▎         | 42/1407 [00:06<03:18,  6.88it/s]
  3%|▎         | 43/1407 [00:06<03:17,  6.90it/s]
  3%|▎         | 44/1407 [00:06<03:15,  6.96it/s]
  3%|▎         | 45/1407 [00:06<03:21,  6.78it/s]
  3%|▎         | 46/1407 [00:06<03:10,  7.15it/s]
  3%|▎         | 47/1407 [00:06<03:16,  6.92it/s]
  3%|▎         | 48/1407 [00:06<03:08,  7.21it/s]
  3%|▎         | 49/1407 [00:07<03:11,  7.09it/s]
  4%|▎         | 50/1407 [00:07<03:13,  7.02it/s]
  4%|▎         | 51/1407 [00:07<03:18,  6.83it/s]
  4%|▎         | 52/1407 [00:07<03:14,  6.96it/s]
  4%|▍         | 53/1407 [00:07<03:16,  6.89it/s]
  4%|▍         | 54/1407 [00:07<03:20,  6.74it/s]
  4%|▍         | 55/1407 [00:07<03:07,  7.23it/s]
  4%|▍         | 56/1407 [00:08<03:14,  6.95it/s]
  4%|▍         | 57/1407 [00:08<03:12,  7.01it/s]
  4%|▍         | 58/1407 [00:08<03:05,  7.29it/s]
  4%|▍         | 59/1407 [00:08<03:12,  7.00it/s]
  4%|▍         | 60/1407 [00:08<03:03,  7.34it/s]
  4%|▍         | 61/1407 [00:08<03:10,  7.07it/s]
  4%|▍         | 62/1407 [00:08<03:09,  7.09it/s]
  4%|▍         | 63/1407 [00:09<03:14,  6.92it/s]
  5%|▍         | 64/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 65/1407 [00:09<03:13,  6.94it/s]
  5%|▍         | 66/1407 [00:09<03:11,  6.99it/s]
  5%|▍         | 67/1407 [00:09<03:17,  6.79it/s]
  5%|▍         | 68/1407 [00:09<03:20,  6.67it/s]
  5%|▍         | 69/1407 [00:09<03:18,  6.75it/s]
  5%|▍         | 70/1407 [00:10<03:16,  6.81it/s]
  5%|▌         | 71/1407 [00:10<03:15,  6.82it/s]
  5%|▌         | 72/1407 [00:10<03:14,  6.85it/s]
  5%|▌         | 73/1407 [00:10<03:11,  6.98it/s]
  5%|▌         | 74/1407 [00:10<03:10,  7.01it/s]
  5%|▌         | 75/1407 [00:10<03:09,  7.03it/s]
  5%|▌         | 76/1407 [00:10<03:13,  6.87it/s]
  5%|▌         | 77/1407 [00:11<03:16,  6.77it/s]
  6%|▌         | 78/1407 [00:11<03:07,  7.09it/s]
  6%|▌         | 79/1407 [00:11<03:08,  7.06it/s]
  6%|▌         | 80/1407 [00:11<03:13,  6.86it/s]
  6%|▌         | 81/1407 [00:11<03:13,  6.86it/s]
  6%|▌         | 82/1407 [00:11<03:16,  6.74it/s]
  6%|▌         | 83/1407 [00:12<03:14,  6.80it/s]
  6%|▌         | 84/1407 [00:12<03:15,  6.78it/s]
  6%|▌         | 85/1407 [00:12<03:18,  6.66it/s]
  6%|▌         | 86/1407 [00:12<03:17,  6.68it/s]
  6%|▌         | 87/1407 [00:12<03:15,  6.75it/s]
  6%|▋         | 88/1407 [00:12<03:04,  7.14it/s]
  6%|▋         | 89/1407 [00:12<03:06,  7.08it/s]
  6%|▋         | 90/1407 [00:13<03:12,  6.85it/s]
  6%|▋         | 91/1407 [00:13<03:16,  6.70it/s]
  7%|▋         | 92/1407 [00:13<03:19,  6.60it/s]
  7%|▋         | 93/1407 [00:13<03:17,  6.64it/s]
  7%|▋         | 94/1407 [00:13<03:15,  6.73it/s]
  7%|▋         | 95/1407 [00:13<03:16,  6.66it/s]
  7%|▋         | 96/1407 [00:13<03:17,  6.63it/s]
  7%|▋         | 97/1407 [00:14<03:16,  6.66it/s]
  7%|▋         | 98/1407 [00:14<03:15,  6.68it/s]
  7%|▋         | 99/1407 [00:14<03:18,  6.59it/s]
  7%|▋         | 100/1407 [00:14<03:16,  6.63it/s]
  7%|▋         | 101/1407 [00:14<03:14,  6.72it/s]
  7%|▋         | 102/1407 [00:14<03:13,  6.75it/s]
  7%|▋         | 103/1407 [00:14<03:16,  6.64it/s]
  7%|▋         | 104/1407 [00:15<03:04,  7.07it/s]
  7%|▋         | 105/1407 [00:15<03:04,  7.07it/s]
  8%|▊         | 106/1407 [00:15<03:03,  7.11it/s]
  8%|▊         | 107/1407 [00:15<03:03,  7.10it/s]
  8%|▊         | 108/1407 [00:15<03:04,  7.02it/s]
  8%|▊         | 109/1407 [00:15<02:55,  7.41it/s]
  8%|▊         | 110/1407 [00:15<03:01,  7.13it/s]
  8%|▊         | 111/1407 [00:16<03:03,  7.08it/s]
  8%|▊         | 112/1407 [00:16<03:06,  6.96it/s]
  8%|▊         | 113/1407 [00:16<03:07,  6.90it/s]
  8%|▊         | 114/1407 [00:16<03:05,  6.98it/s]
  8%|▊         | 115/1407 [00:16<03:09,  6.83it/s]
  8%|▊         | 116/1407 [00:16<03:13,  6.69it/s]
  8%|▊         | 117/1407 [00:16<03:09,  6.81it/s]
  8%|▊         | 118/1407 [00:17<03:13,  6.67it/s]
  8%|▊         | 119/1407 [00:17<03:14,  6.63it/s]
  9%|▊         | 120/1407 [00:17<03:12,  6.70it/s]
  9%|▊         | 121/1407 [00:17<03:10,  6.75it/s]
  9%|▊         | 122/1407 [00:17<03:09,  6.80it/s]
  9%|▊         | 123/1407 [00:17<03:00,  7.11it/s]
  9%|▉         | 124/1407 [00:17<02:59,  7.13it/s]
  9%|▉         | 125/1407 [00:18<03:05,  6.90it/s]
  9%|▉         | 126/1407 [00:18<03:08,  6.79it/s]
  9%|▉         | 127/1407 [00:18<02:57,  7.23it/s]
  9%|▉         | 128/1407 [00:18<02:59,  7.12it/s]
  9%|▉         | 129/1407 [00:18<03:02,  7.00it/s]
  9%|▉         | 130/1407 [00:18<03:07,  6.79it/s]
  9%|▉         | 131/1407 [00:19<03:11,  6.67it/s]
  9%|▉         | 132/1407 [00:19<03:09,  6.72it/s]
  9%|▉         | 133/1407 [00:19<03:12,  6.61it/s]
 10%|▉         | 134/1407 [00:19<03:14,  6.54it/s]
 10%|▉         | 135/1407 [00:19<03:09,  6.72it/s]
 10%|▉         | 136/1407 [00:19<03:07,  6.78it/s]
 10%|▉         | 137/1407 [00:19<03:05,  6.83it/s]
 10%|▉         | 138/1407 [00:20<03:03,  6.90it/s]
 10%|▉         | 139/1407 [00:20<03:03,  6.89it/s]
 10%|▉         | 140/1407 [00:20<03:01,  6.98it/s]
 10%|█         | 141/1407 [00:20<03:03,  6.91it/s]
 10%|█         | 142/1407 [00:20<03:02,  6.93it/s]
 10%|█         | 143/1407 [00:20<02:55,  7.21it/s]
 10%|█         | 144/1407 [00:20<02:55,  7.20it/s]
 10%|█         | 145/1407 [00:21<02:57,  7.13it/s]
 10%|█         | 146/1407 [00:21<02:59,  7.01it/s]
 10%|█         | 147/1407 [00:21<03:02,  6.92it/s]
 11%|█         | 148/1407 [00:21<03:01,  6.93it/s]
 11%|█         | 149/1407 [00:21<03:05,  6.80it/s]
 11%|█         | 150/1407 [00:21<03:02,  6.89it/s]
 11%|█         | 151/1407 [00:21<03:06,  6.74it/s]
 11%|█         | 152/1407 [00:22<03:05,  6.77it/s]
 11%|█         | 153/1407 [00:22<03:05,  6.76it/s]
 11%|█         | 154/1407 [00:22<03:07,  6.68it/s]
 11%|█         | 155/1407 [00:22<03:05,  6.76it/s]
 11%|█         | 156/1407 [00:22<03:02,  6.86it/s]
 11%|█         | 157/1407 [00:22<03:00,  6.93it/s]
 11%|█         | 158/1407 [00:22<03:05,  6.75it/s]
 11%|█▏        | 159/1407 [00:23<03:06,  6.69it/s]
 11%|█▏        | 160/1407 [00:23<03:01,  6.86it/s]
 11%|█▏        | 161/1407 [00:23<02:54,  7.16it/s]
 12%|█▏        | 162/1407 [00:23<03:00,  6.90it/s]
 12%|█▏        | 163/1407 [00:23<03:04,  6.74it/s]
 12%|█▏        | 164/1407 [00:23<02:54,  7.12it/s]
 12%|█▏        | 165/1407 [00:23<02:56,  7.03it/s]
 12%|█▏        | 166/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 167/1407 [00:24<02:57,  6.98it/s]
 12%|█▏        | 168/1407 [00:24<02:55,  7.07it/s]
 12%|█▏        | 169/1407 [00:24<02:59,  6.90it/s]
 12%|█▏        | 170/1407 [00:24<03:00,  6.84it/s]
 12%|█▏        | 171/1407 [00:24<03:04,  6.70it/s]
 12%|█▏        | 172/1407 [00:24<02:59,  6.87it/s]
 12%|█▏        | 173/1407 [00:25<02:59,  6.86it/s]
 12%|█▏        | 174/1407 [00:25<03:02,  6.75it/s]
 12%|█▏        | 175/1407 [00:25<03:04,  6.68it/s]
 13%|█▎        | 176/1407 [00:25<03:03,  6.72it/s]
 13%|█▎        | 177/1407 [00:25<03:02,  6.73it/s]
 13%|█▎        | 178/1407 [00:25<02:53,  7.07it/s]
 13%|█▎        | 179/1407 [00:25<02:56,  6.97it/s]
 13%|█▎        | 180/1407 [00:26<03:00,  6.79it/s]
 13%|█▎        | 181/1407 [00:26<02:57,  6.90it/s]
 13%|█▎        | 182/1407 [00:26<02:57,  6.92it/s]
 13%|█▎        | 183/1407 [00:26<03:00,  6.79it/s]
 13%|█▎        | 184/1407 [00:26<02:58,  6.84it/s]
 13%|█▎        | 185/1407 [00:26<03:01,  6.72it/s]
 13%|█▎        | 186/1407 [00:27<02:50,  7.17it/s]
 13%|█▎        | 187/1407 [00:27<02:55,  6.95it/s]
 13%|█▎        | 188/1407 [00:27<02:59,  6.81it/s]
 13%|█▎        | 189/1407 [00:27<02:58,  6.83it/s]
 14%|█▎        | 190/1407 [00:27<03:00,  6.73it/s]
 14%|█▎        | 191/1407 [00:27<03:02,  6.67it/s]
 14%|█▎        | 192/1407 [00:27<03:00,  6.74it/s]
 14%|█▎        | 193/1407 [00:28<03:02,  6.65it/s]
 14%|█▍        | 194/1407 [00:28<03:04,  6.57it/s]
 14%|█▍        | 195/1407 [00:28<03:03,  6.62it/s]
 14%|█▍        | 196/1407 [00:28<02:49,  7.14it/s]
 14%|█▍        | 197/1407 [00:28<02:55,  6.88it/s]
 14%|█▍        | 198/1407 [00:28<02:56,  6.87it/s]
 14%|█▍        | 199/1407 [00:28<02:55,  6.90it/s]
 14%|█▍        | 200/1407 [00:29<02:58,  6.78it/s]
 14%|█▍        | 201/1407 [00:29<03:01,  6.66it/s]
 14%|█▍        | 202/1407 [00:29<03:00,  6.68it/s]
 14%|█▍        | 203/1407 [00:29<03:02,  6.59it/s]
 14%|█▍        | 204/1407 [00:29<02:57,  6.79it/s]
 15%|█▍        | 205/1407 [00:29<02:57,  6.77it/s]
 15%|█▍        | 206/1407 [00:29<02:56,  6.79it/s]
 15%|█▍        | 207/1407 [00:30<02:58,  6.71it/s]
 15%|█▍        | 208/1407 [00:30<02:47,  7.16it/s]
 15%|█▍        | 209/1407 [00:30<02:48,  7.10it/s]
 15%|█▍        | 210/1407 [00:30<02:49,  7.05it/s]
 15%|█▍        | 211/1407 [00:30<02:43,  7.32it/s]
 15%|█▌        | 212/1407 [00:30<02:46,  7.19it/s]
 15%|█▌        | 213/1407 [00:30<02:45,  7.22it/s]
 15%|█▌        | 214/1407 [00:31<02:51,  6.95it/s]
 15%|█▌        | 215/1407 [00:31<02:49,  7.02it/s]
 15%|█▌        | 216/1407 [00:31<02:51,  6.93it/s]
 15%|█▌        | 217/1407 [00:31<02:43,  7.26it/s]
 15%|█▌        | 218/1407 [00:31<02:47,  7.09it/s]
 16%|█▌        | 219/1407 [00:31<02:47,  7.09it/s]
 16%|█▌        | 220/1407 [00:31<02:51,  6.90it/s]
 16%|█▌        | 221/1407 [00:32<02:52,  6.89it/s]
 16%|█▌        | 222/1407 [00:32<02:44,  7.19it/s]
 16%|█▌        | 223/1407 [00:32<02:45,  7.16it/s]
 16%|█▌        | 224/1407 [00:32<02:50,  6.92it/s]
 16%|█▌        | 225/1407 [00:32<02:37,  7.53it/s]
 16%|█▌        | 226/1407 [00:32<02:40,  7.35it/s]
 16%|█▌        | 227/1407 [00:32<02:44,  7.15it/s]
 16%|█▌        | 228/1407 [00:33<02:39,  7.40it/s]
 16%|█▋        | 229/1407 [00:33<02:40,  7.35it/s]
 16%|█▋        | 230/1407 [00:33<02:47,  7.03it/s]
 16%|█▋        | 231/1407 [00:33<02:51,  6.88it/s]
 16%|█▋        | 232/1407 [00:33<02:51,  6.87it/s]
 17%|█▋        | 233/1407 [00:33<02:48,  6.96it/s]
 17%|█▋        | 234/1407 [00:33<02:49,  6.92it/s]
 17%|█▋        | 235/1407 [00:34<02:50,  6.89it/s]
 17%|█▋        | 236/1407 [00:34<02:45,  7.08it/s]
 17%|█▋        | 237/1407 [00:34<02:47,  6.97it/s]
 17%|█▋        | 238/1407 [00:34<02:52,  6.78it/s]
 17%|█▋        | 239/1407 [00:34<02:51,  6.80it/s]
 17%|█▋        | 240/1407 [00:34<02:49,  6.89it/s]
 17%|█▋        | 241/1407 [00:34<02:47,  6.97it/s]
 17%|█▋        | 242/1407 [00:35<02:47,  6.96it/s]
 17%|█▋        | 243/1407 [00:35<02:50,  6.82it/s]
 17%|█▋        | 244/1407 [00:35<02:49,  6.86it/s]
 17%|█▋        | 245/1407 [00:35<02:47,  6.96it/s]
 17%|█▋        | 246/1407 [00:35<02:47,  6.92it/s]
 18%|█▊        | 247/1407 [00:35<02:46,  6.97it/s]
 18%|█▊        | 248/1407 [00:35<02:38,  7.33it/s]
 18%|█▊        | 249/1407 [00:36<02:41,  7.18it/s]
 18%|█▊        | 250/1407 [00:36<02:43,  7.07it/s]
 18%|█▊        | 251/1407 [00:36<02:37,  7.33it/s]
 18%|█▊        | 252/1407 [00:36<02:41,  7.17it/s]
 18%|█▊        | 253/1407 [00:36<02:42,  7.10it/s]
 18%|█▊        | 254/1407 [00:36<02:44,  7.02it/s]
 18%|█▊        | 255/1407 [00:36<02:36,  7.34it/s]
 18%|█▊        | 256/1407 [00:37<02:40,  7.19it/s]
 18%|█▊        | 257/1407 [00:37<02:37,  7.30it/s]
 18%|█▊        | 258/1407 [00:37<02:40,  7.16it/s]
 18%|█▊        | 259/1407 [00:37<02:44,  6.96it/s]
 18%|█▊        | 260/1407 [00:37<02:45,  6.93it/s]
 19%|█▊        | 261/1407 [00:37<02:46,  6.87it/s]
 19%|█▊        | 262/1407 [00:37<02:45,  6.90it/s]
 19%|█▊        | 263/1407 [00:38<02:37,  7.26it/s]
 19%|█▉        | 264/1407 [00:38<02:40,  7.13it/s]
 19%|█▉        | 265/1407 [00:38<02:41,  7.06it/s]
 19%|█▉        | 266/1407 [00:38<02:45,  6.88it/s]
 19%|█▉        | 267/1407 [00:38<02:45,  6.89it/s]
 19%|█▉        | 268/1407 [00:38<02:48,  6.77it/s]
 19%|█▉        | 269/1407 [00:38<02:46,  6.82it/s]
 19%|█▉        | 270/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 271/1407 [00:39<02:48,  6.73it/s]
 19%|█▉        | 272/1407 [00:39<02:45,  6.86it/s]
 19%|█▉        | 273/1407 [00:39<02:44,  6.88it/s]
 19%|█▉        | 274/1407 [00:39<02:44,  6.87it/s]
 20%|█▉        | 275/1407 [00:39<02:42,  6.96it/s]
 20%|█▉        | 276/1407 [00:39<02:43,  6.93it/s]
 20%|█▉        | 277/1407 [00:40<02:47,  6.76it/s]
 20%|█▉        | 278/1407 [00:40<02:36,  7.21it/s]
 20%|█▉        | 279/1407 [00:40<02:42,  6.96it/s]
 20%|█▉        | 280/1407 [00:40<02:43,  6.89it/s]
 20%|█▉        | 281/1407 [00:40<02:47,  6.73it/s]
 20%|██        | 282/1407 [00:40<02:45,  6.80it/s]
 20%|██        | 283/1407 [00:40<02:38,  7.11it/s]
 20%|██        | 284/1407 [00:41<02:35,  7.24it/s]
 20%|██        | 285/1407 [00:41<02:41,  6.96it/s]
 20%|██        | 286/1407 [00:41<02:44,  6.83it/s]
 20%|██        | 287/1407 [00:41<02:43,  6.85it/s]
 20%|██        | 288/1407 [00:41<02:34,  7.26it/s]
 21%|██        | 289/1407 [00:41<02:37,  7.09it/s]
 21%|██        | 290/1407 [00:41<02:42,  6.86it/s]
 21%|██        | 291/1407 [00:42<02:43,  6.83it/s]
 21%|██        | 292/1407 [00:42<02:46,  6.69it/s]
 21%|██        | 293/1407 [00:42<02:43,  6.82it/s]
 21%|██        | 294/1407 [00:42<02:38,  7.04it/s]
 21%|██        | 295/1407 [00:42<02:38,  7.02it/s]
 21%|██        | 296/1407 [00:42<02:32,  7.29it/s]
 21%|██        | 297/1407 [00:42<02:37,  7.05it/s]
 21%|██        | 298/1407 [00:43<02:38,  6.99it/s]
 21%|██▏       | 299/1407 [00:43<02:42,  6.80it/s]
 21%|██▏       | 300/1407 [00:43<02:27,  7.52it/s]
 21%|██▏       | 301/1407 [00:43<02:22,  7.73it/s]
 21%|██▏       | 302/1407 [00:43<02:28,  7.45it/s]
 22%|██▏       | 303/1407 [00:43<02:31,  7.30it/s]
 22%|██▏       | 304/1407 [00:43<02:33,  7.20it/s]
 22%|██▏       | 305/1407 [00:44<02:25,  7.55it/s]
 22%|██▏       | 306/1407 [00:44<02:33,  7.15it/s]
 22%|██▏       | 307/1407 [00:44<02:38,  6.94it/s]
 22%|██▏       | 308/1407 [00:44<02:39,  6.87it/s]
 22%|██▏       | 309/1407 [00:44<02:32,  7.18it/s]
 22%|██▏       | 310/1407 [00:44<02:37,  6.97it/s]
 22%|██▏       | 311/1407 [00:44<02:37,  6.96it/s]
 22%|██▏       | 312/1407 [00:45<02:35,  7.05it/s]
 22%|██▏       | 313/1407 [00:45<02:33,  7.12it/s]
 22%|██▏       | 314/1407 [00:45<02:28,  7.37it/s]
 22%|██▏       | 315/1407 [00:45<02:29,  7.29it/s]
 22%|██▏       | 316/1407 [00:45<02:35,  7.04it/s]
 23%|██▎       | 317/1407 [00:45<02:39,  6.83it/s]
 23%|██▎       | 318/1407 [00:45<02:41,  6.72it/s]
 23%|██▎       | 319/1407 [00:46<02:43,  6.63it/s]
 23%|██▎       | 320/1407 [00:46<02:42,  6.70it/s]
 23%|██▎       | 321/1407 [00:46<02:41,  6.72it/s]
 23%|██▎       | 322/1407 [00:46<02:32,  7.12it/s]
 23%|██▎       | 323/1407 [00:46<02:37,  6.89it/s]
 23%|██▎       | 324/1407 [00:46<02:36,  6.90it/s]
 23%|██▎       | 325/1407 [00:46<02:39,  6.79it/s]
 23%|██▎       | 326/1407 [00:47<02:41,  6.70it/s]
 23%|██▎       | 327/1407 [00:47<02:39,  6.78it/s]
 23%|██▎       | 328/1407 [00:47<02:31,  7.12it/s]
 23%|██▎       | 329/1407 [00:47<02:33,  7.04it/s]
 23%|██▎       | 330/1407 [00:47<02:33,  7.01it/s]
 24%|██▎       | 331/1407 [00:47<02:35,  6.92it/s]
 24%|██▎       | 332/1407 [00:47<02:35,  6.92it/s]
 24%|██▎       | 333/1407 [00:48<02:31,  7.11it/s]
 24%|██▎       | 334/1407 [00:48<02:31,  7.07it/s]
 24%|██▍       | 335/1407 [00:48<02:35,  6.90it/s]
 24%|██▍       | 336/1407 [00:48<02:34,  6.93it/s]
 24%|██▍       | 337/1407 [00:48<02:33,  6.95it/s]
 24%|██▍       | 338/1407 [00:48<02:32,  7.01it/s]
 24%|██▍       | 339/1407 [00:48<02:33,  6.96it/s]
 24%|██▍       | 340/1407 [00:49<02:35,  6.88it/s]
 24%|██▍       | 341/1407 [00:49<02:33,  6.95it/s]
 24%|██▍       | 342/1407 [00:49<02:36,  6.79it/s]
 24%|██▍       | 343/1407 [00:49<02:37,  6.77it/s]
 24%|██▍       | 344/1407 [00:49<02:39,  6.66it/s]
 25%|██▍       | 345/1407 [00:49<02:37,  6.75it/s]
 25%|██▍       | 346/1407 [00:49<02:39,  6.64it/s]
 25%|██▍       | 347/1407 [00:50<02:29,  7.09it/s]
 25%|██▍       | 348/1407 [00:50<02:31,  6.98it/s]
 25%|██▍       | 349/1407 [00:50<02:30,  7.05it/s]
 25%|██▍       | 350/1407 [00:50<02:28,  7.12it/s]
 25%|██▍       | 351/1407 [00:50<02:28,  7.12it/s]
 25%|██▌       | 352/1407 [00:50<02:32,  6.93it/s]
 25%|██▌       | 353/1407 [00:50<02:35,  6.76it/s]
 25%|██▌       | 354/1407 [00:51<02:32,  6.89it/s]
 25%|██▌       | 355/1407 [00:51<02:36,  6.73it/s]
 25%|██▌       | 356/1407 [00:51<02:35,  6.77it/s]
 25%|██▌       | 357/1407 [00:51<02:33,  6.86it/s]
 25%|██▌       | 358/1407 [00:51<02:31,  6.94it/s]
 26%|██▌       | 359/1407 [00:51<02:30,  6.98it/s]
 26%|██▌       | 360/1407 [00:51<02:34,  6.79it/s]
 26%|██▌       | 361/1407 [00:52<02:33,  6.83it/s]
 26%|██▌       | 362/1407 [00:52<02:35,  6.73it/s]
 26%|██▌       | 363/1407 [00:52<02:27,  7.06it/s]
 26%|██▌       | 364/1407 [00:52<02:32,  6.84it/s]
 26%|██▌       | 365/1407 [00:52<02:30,  6.91it/s]
 26%|██▌       | 366/1407 [00:52<02:34,  6.76it/s]
 26%|██▌       | 367/1407 [00:53<02:34,  6.75it/s]
 26%|██▌       | 368/1407 [00:53<02:31,  6.87it/s]
 26%|██▌       | 369/1407 [00:53<02:30,  6.89it/s]
 26%|██▋       | 370/1407 [00:53<02:30,  6.87it/s]
 26%|██▋       | 371/1407 [00:53<02:30,  6.90it/s]
 26%|██▋       | 372/1407 [00:53<02:29,  6.91it/s]
 27%|██▋       | 373/1407 [00:53<02:33,  6.75it/s]
 27%|██▋       | 374/1407 [00:54<02:31,  6.80it/s]
 27%|██▋       | 375/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 376/1407 [00:54<02:36,  6.61it/s]
 27%|██▋       | 377/1407 [00:54<02:33,  6.71it/s]
 27%|██▋       | 378/1407 [00:54<02:31,  6.77it/s]
 27%|██▋       | 379/1407 [00:54<02:30,  6.83it/s]
 27%|██▋       | 380/1407 [00:54<02:29,  6.86it/s]
 27%|██▋       | 381/1407 [00:55<02:30,  6.83it/s]
 27%|██▋       | 382/1407 [00:55<02:22,  7.19it/s]
 27%|██▋       | 383/1407 [00:55<02:22,  7.18it/s]
 27%|██▋       | 384/1407 [00:55<02:25,  7.03it/s]
 27%|██▋       | 385/1407 [00:55<02:26,  6.97it/s]
 27%|██▋       | 386/1407 [00:55<02:29,  6.83it/s]
 28%|██▊       | 387/1407 [00:55<02:21,  7.20it/s]
 28%|██▊       | 388/1407 [00:56<02:24,  7.05it/s]
 28%|██▊       | 389/1407 [00:56<02:24,  7.06it/s]
 28%|██▊       | 390/1407 [00:56<02:20,  7.21it/s]
 28%|██▊       | 391/1407 [00:56<02:21,  7.18it/s]
 28%|██▊       | 392/1407 [00:56<02:23,  7.08it/s]
 28%|██▊       | 393/1407 [00:56<02:23,  7.05it/s]
 28%|██▊       | 394/1407 [00:56<02:25,  6.95it/s]
 28%|██▊       | 395/1407 [00:57<02:25,  6.96it/s]
 28%|██▊       | 396/1407 [00:57<02:25,  6.93it/s]
 28%|██▊       | 397/1407 [00:57<02:25,  6.93it/s]
 28%|██▊       | 398/1407 [00:57<02:19,  7.23it/s]
 28%|██▊       | 399/1407 [00:57<02:20,  7.19it/s]
 28%|██▊       | 400/1407 [00:57<02:20,  7.16it/s]
 29%|██▊       | 401/1407 [00:57<02:21,  7.09it/s]
 29%|██▊       | 402/1407 [00:58<02:23,  7.01it/s]
 29%|██▊       | 403/1407 [00:58<02:24,  6.96it/s]
 29%|██▊       | 404/1407 [00:58<02:25,  6.89it/s]
 29%|██▉       | 405/1407 [00:58<02:19,  7.19it/s]
 29%|██▉       | 406/1407 [00:58<02:15,  7.40it/s]
 29%|██▉       | 407/1407 [00:58<02:20,  7.12it/s]
 29%|██▉       | 408/1407 [00:58<02:15,  7.36it/s]
 29%|██▉       | 409/1407 [00:58<02:12,  7.56it/s]
 29%|██▉       | 410/1407 [00:59<02:18,  7.22it/s]
 29%|██▉       | 411/1407 [00:59<02:21,  7.06it/s]
 29%|██▉       | 412/1407 [00:59<02:22,  6.96it/s]
 29%|██▉       | 413/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 414/1407 [00:59<02:23,  6.92it/s]
 29%|██▉       | 415/1407 [00:59<02:26,  6.76it/s]
 30%|██▉       | 416/1407 [01:00<02:28,  6.65it/s]
 30%|██▉       | 417/1407 [01:00<02:30,  6.58it/s]
 30%|██▉       | 418/1407 [01:00<02:20,  7.03it/s]
 30%|██▉       | 419/1407 [01:00<02:20,  7.01it/s]
 30%|██▉       | 420/1407 [01:00<02:23,  6.86it/s]
 30%|██▉       | 421/1407 [01:00<02:26,  6.71it/s]
 30%|██▉       | 422/1407 [01:00<02:26,  6.74it/s]
 30%|███       | 423/1407 [01:01<02:18,  7.10it/s]
 30%|███       | 424/1407 [01:01<02:18,  7.12it/s]
 30%|███       | 425/1407 [01:01<02:19,  7.03it/s]
 30%|███       | 426/1407 [01:01<02:22,  6.87it/s]
 30%|███       | 427/1407 [01:01<02:22,  6.87it/s]
 30%|███       | 428/1407 [01:01<02:23,  6.83it/s]
 30%|███       | 429/1407 [01:01<02:23,  6.79it/s]
 31%|███       | 430/1407 [01:02<02:26,  6.68it/s]
 31%|███       | 431/1407 [01:02<02:24,  6.76it/s]
 31%|███       | 432/1407 [01:02<02:22,  6.83it/s]
 31%|███       | 433/1407 [01:02<02:15,  7.21it/s]
 31%|███       | 434/1407 [01:02<02:20,  6.94it/s]
 31%|███       | 435/1407 [01:02<02:23,  6.76it/s]
 31%|███       | 436/1407 [01:02<02:26,  6.64it/s]
 31%|███       | 437/1407 [01:03<02:25,  6.67it/s]
 31%|███       | 438/1407 [01:03<02:24,  6.69it/s]
 31%|███       | 439/1407 [01:03<02:21,  6.85it/s]
 31%|███▏      | 440/1407 [01:03<02:20,  6.87it/s]
 31%|███▏      | 441/1407 [01:03<02:20,  6.88it/s]
 31%|███▏      | 442/1407 [01:03<02:20,  6.89it/s]
 31%|███▏      | 443/1407 [01:03<02:19,  6.91it/s]
 32%|███▏      | 444/1407 [01:04<02:21,  6.80it/s]
 32%|███▏      | 445/1407 [01:04<02:19,  6.88it/s]
 32%|███▏      | 446/1407 [01:04<02:22,  6.73it/s]
 32%|███▏      | 447/1407 [01:04<02:22,  6.72it/s]
 32%|███▏      | 448/1407 [01:04<02:21,  6.78it/s]
 32%|███▏      | 449/1407 [01:04<02:12,  7.22it/s]
 32%|███▏      | 450/1407 [01:04<02:14,  7.12it/s]
 32%|███▏      | 451/1407 [01:05<02:18,  6.88it/s]
 32%|███▏      | 452/1407 [01:05<02:21,  6.77it/s]
 32%|███▏      | 453/1407 [01:05<02:12,  7.18it/s]
 32%|███▏      | 454/1407 [01:05<02:14,  7.07it/s]
 32%|███▏      | 455/1407 [01:05<02:15,  7.04it/s]
 32%|███▏      | 456/1407 [01:05<02:16,  6.98it/s]
 32%|███▏      | 457/1407 [01:05<02:17,  6.91it/s]
 33%|███▎      | 458/1407 [01:06<02:20,  6.76it/s]
 33%|███▎      | 459/1407 [01:06<02:19,  6.81it/s]
 33%|███▎      | 460/1407 [01:06<02:17,  6.89it/s]
 33%|███▎      | 461/1407 [01:06<02:16,  6.95it/s]
 33%|███▎      | 462/1407 [01:06<02:19,  6.77it/s]
 33%|███▎      | 463/1407 [01:06<02:07,  7.41it/s]
 33%|███▎      | 464/1407 [01:06<02:08,  7.35it/s]
 33%|███▎      | 465/1407 [01:07<02:11,  7.18it/s]
 33%|███▎      | 466/1407 [01:07<02:13,  7.07it/s]
 33%|███▎      | 467/1407 [01:07<02:13,  7.04it/s]
 33%|███▎      | 468/1407 [01:07<02:15,  6.95it/s]
 33%|███▎      | 469/1407 [01:07<02:07,  7.34it/s]
                                                  

 33%|███▎      | 469/1407 [01:07<02:07,  7.34it/s]{'loss': 0.752, 'learning_rate': 3.662193232456209e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.86it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.59it/s]

 21%|██        | 65/313 [00:00<00:01, 204.58it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.00it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.24it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.85it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.57it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.31it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.93it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.95it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.74it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.86it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.03it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.53it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.68it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.68it/s]
 33%|███▎      | 469/1407 [01:09<02:07,  7.34it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 470/1407 [01:10<14:45,  1.06it/s]
 33%|███▎      | 471/1407 [01:10<10:59,  1.42it/s]
 34%|███▎      | 472/1407 [01:10<08:21,  1.86it/s]
 34%|███▎      | 473/1407 [01:10<06:31,  2.38it/s]
 34%|███▎      | 474/1407 [01:11<05:13,  2.98it/s]
 34%|███▍      | 475/1407 [01:11<04:22,  3.55it/s]
 34%|███▍      | 476/1407 [01:11<03:44,  4.15it/s]
 34%|███▍      | 477/1407 [01:11<03:17,  4.70it/s]
 34%|███▍      | 478/1407 [01:11<03:01,  5.11it/s]
 34%|███▍      | 479/1407 [01:11<02:49,  5.47it/s]
 34%|███▍      | 480/1407 [01:11<02:39,  5.82it/s]
 34%|███▍      | 481/1407 [01:12<02:31,  6.12it/s]
 34%|███▍      | 482/1407 [01:12<02:29,  6.20it/s]
 34%|███▍      | 483/1407 [01:12<02:24,  6.41it/s]
 34%|███▍      | 484/1407 [01:12<02:21,  6.51it/s]
 34%|███▍      | 485/1407 [01:12<02:19,  6.62it/s]
 35%|███▍      | 486/1407 [01:12<02:16,  6.76it/s]
 35%|███▍      | 487/1407 [01:12<02:14,  6.82it/s]
 35%|███▍      | 488/1407 [01:13<02:12,  6.95it/s]
 35%|███▍      | 489/1407 [01:13<02:14,  6.81it/s]
 35%|███▍      | 490/1407 [01:13<02:17,  6.67it/s]
 35%|███▍      | 491/1407 [01:13<02:16,  6.69it/s]
 35%|███▍      | 492/1407 [01:13<02:15,  6.76it/s]
 35%|███▌      | 493/1407 [01:13<02:17,  6.65it/s]
 35%|███▌      | 494/1407 [01:14<02:06,  7.23it/s]
 35%|███▌      | 495/1407 [01:14<02:06,  7.19it/s]
 35%|███▌      | 496/1407 [01:14<02:09,  7.05it/s]
 35%|███▌      | 497/1407 [01:14<02:09,  7.03it/s]
 35%|███▌      | 498/1407 [01:14<02:11,  6.94it/s]
 35%|███▌      | 499/1407 [01:14<02:14,  6.76it/s]
 36%|███▌      | 500/1407 [01:14<02:08,  7.08it/s]
 36%|███▌      | 501/1407 [01:14<02:03,  7.32it/s]
 36%|███▌      | 502/1407 [01:15<02:04,  7.25it/s]
 36%|███▌      | 503/1407 [01:15<02:06,  7.14it/s]
 36%|███▌      | 504/1407 [01:15<02:02,  7.37it/s]
 36%|███▌      | 505/1407 [01:15<01:59,  7.55it/s]
 36%|███▌      | 506/1407 [01:15<02:02,  7.35it/s]
 36%|███▌      | 507/1407 [01:15<02:07,  7.03it/s]
 36%|███▌      | 508/1407 [01:15<02:08,  7.00it/s]
 36%|███▌      | 509/1407 [01:16<02:08,  6.98it/s]
 36%|███▌      | 510/1407 [01:16<02:07,  7.01it/s]
 36%|███▋      | 511/1407 [01:16<02:11,  6.81it/s]
 36%|███▋      | 512/1407 [01:16<02:14,  6.68it/s]
 36%|███▋      | 513/1407 [01:16<02:11,  6.80it/s]
 37%|███▋      | 514/1407 [01:16<02:10,  6.85it/s]
 37%|███▋      | 515/1407 [01:16<02:04,  7.15it/s]
 37%|███▋      | 516/1407 [01:17<02:00,  7.38it/s]
 37%|███▋      | 517/1407 [01:17<02:05,  7.10it/s]
 37%|███▋      | 518/1407 [01:17<02:09,  6.88it/s]
 37%|███▋      | 519/1407 [01:17<02:08,  6.89it/s]
 37%|███▋      | 520/1407 [01:17<02:08,  6.91it/s]
 37%|███▋      | 521/1407 [01:17<02:07,  6.96it/s]
 37%|███▋      | 522/1407 [01:18<02:10,  6.78it/s]
 37%|███▋      | 523/1407 [01:18<02:12,  6.69it/s]
 37%|███▋      | 524/1407 [01:18<02:08,  6.86it/s]
 37%|███▋      | 525/1407 [01:18<01:58,  7.42it/s]
 37%|███▋      | 526/1407 [01:18<02:03,  7.13it/s]
 37%|███▋      | 527/1407 [01:18<01:57,  7.49it/s]
 38%|███▊      | 528/1407 [01:18<01:59,  7.33it/s]
 38%|███▊      | 529/1407 [01:18<02:00,  7.28it/s]
 38%|███▊      | 530/1407 [01:19<02:04,  7.04it/s]
 38%|███▊      | 531/1407 [01:19<02:06,  6.95it/s]
 38%|███▊      | 532/1407 [01:19<02:06,  6.92it/s]
 38%|███▊      | 533/1407 [01:19<02:09,  6.76it/s]
 38%|███▊      | 534/1407 [01:19<02:08,  6.81it/s]
 38%|███▊      | 535/1407 [01:19<02:10,  6.67it/s]
 38%|███▊      | 536/1407 [01:20<02:09,  6.72it/s]
 38%|███▊      | 537/1407 [01:20<02:11,  6.62it/s]
 38%|███▊      | 538/1407 [01:20<02:10,  6.65it/s]
 38%|███▊      | 539/1407 [01:20<02:08,  6.74it/s]
 38%|███▊      | 540/1407 [01:20<02:07,  6.80it/s]
 38%|███▊      | 541/1407 [01:20<02:05,  6.88it/s]
 39%|███▊      | 542/1407 [01:20<02:04,  6.95it/s]
 39%|███▊      | 543/1407 [01:21<02:04,  6.96it/s]
 39%|███▊      | 544/1407 [01:21<02:03,  7.01it/s]
 39%|███▊      | 545/1407 [01:21<02:03,  6.95it/s]
 39%|███▉      | 546/1407 [01:21<02:06,  6.79it/s]
 39%|███▉      | 547/1407 [01:21<02:05,  6.84it/s]
 39%|███▉      | 548/1407 [01:21<01:58,  7.22it/s]
 39%|███▉      | 549/1407 [01:21<01:52,  7.62it/s]
 39%|███▉      | 550/1407 [01:21<01:54,  7.48it/s]
 39%|███▉      | 551/1407 [01:22<01:57,  7.31it/s]
 39%|███▉      | 552/1407 [01:22<01:58,  7.21it/s]
 39%|███▉      | 553/1407 [01:22<01:59,  7.13it/s]
 39%|███▉      | 554/1407 [01:22<01:57,  7.26it/s]
 39%|███▉      | 555/1407 [01:22<02:01,  6.99it/s]
 40%|███▉      | 556/1407 [01:22<02:02,  6.94it/s]
 40%|███▉      | 557/1407 [01:23<02:05,  6.76it/s]
 40%|███▉      | 558/1407 [01:23<02:05,  6.76it/s]
 40%|███▉      | 559/1407 [01:23<02:05,  6.78it/s]
 40%|███▉      | 560/1407 [01:23<02:06,  6.70it/s]
 40%|███▉      | 561/1407 [01:23<02:07,  6.65it/s]
 40%|███▉      | 562/1407 [01:23<02:05,  6.74it/s]
 40%|████      | 563/1407 [01:23<02:01,  6.97it/s]
 40%|████      | 564/1407 [01:24<02:01,  6.93it/s]
 40%|████      | 565/1407 [01:24<02:03,  6.80it/s]
 40%|████      | 566/1407 [01:24<02:01,  6.94it/s]
 40%|████      | 567/1407 [01:24<02:00,  6.95it/s]
 40%|████      | 568/1407 [01:24<02:03,  6.81it/s]
 40%|████      | 569/1407 [01:24<02:01,  6.91it/s]
 41%|████      | 570/1407 [01:24<02:01,  6.89it/s]
 41%|████      | 571/1407 [01:25<02:04,  6.74it/s]
 41%|████      | 572/1407 [01:25<02:02,  6.84it/s]
 41%|████      | 573/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 574/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 575/1407 [01:25<02:04,  6.70it/s]
 41%|████      | 576/1407 [01:25<02:02,  6.78it/s]
 41%|████      | 577/1407 [01:25<02:01,  6.84it/s]
 41%|████      | 578/1407 [01:26<02:01,  6.85it/s]
 41%|████      | 579/1407 [01:26<02:10,  6.36it/s]
 41%|████      | 580/1407 [01:26<02:01,  6.83it/s]
 41%|████▏     | 581/1407 [01:26<02:02,  6.74it/s]
 41%|████▏     | 582/1407 [01:26<02:00,  6.84it/s]
 41%|████▏     | 583/1407 [01:26<01:56,  7.05it/s]
 42%|████▏     | 584/1407 [01:26<01:56,  7.06it/s]
 42%|████▏     | 585/1407 [01:27<01:58,  6.96it/s]
 42%|████▏     | 586/1407 [01:27<02:00,  6.81it/s]
 42%|████▏     | 587/1407 [01:27<02:01,  6.73it/s]
 42%|████▏     | 588/1407 [01:27<02:03,  6.63it/s]
 42%|████▏     | 589/1407 [01:27<02:03,  6.61it/s]
 42%|████▏     | 590/1407 [01:27<02:02,  6.70it/s]
 42%|████▏     | 591/1407 [01:27<01:55,  7.04it/s]
 42%|████▏     | 592/1407 [01:28<01:54,  7.09it/s]
 42%|████▏     | 593/1407 [01:28<01:50,  7.36it/s]
 42%|████▏     | 594/1407 [01:28<01:50,  7.33it/s]
 42%|████▏     | 595/1407 [01:28<01:54,  7.07it/s]
 42%|████▏     | 596/1407 [01:28<01:56,  6.97it/s]
 42%|████▏     | 597/1407 [01:28<01:50,  7.34it/s]
 43%|████▎     | 598/1407 [01:28<01:46,  7.59it/s]
 43%|████▎     | 599/1407 [01:29<01:49,  7.35it/s]
 43%|████▎     | 600/1407 [01:29<01:50,  7.32it/s]
 43%|████▎     | 601/1407 [01:29<01:52,  7.17it/s]
 43%|████▎     | 602/1407 [01:29<01:54,  7.03it/s]
 43%|████▎     | 603/1407 [01:29<01:53,  7.05it/s]
 43%|████▎     | 604/1407 [01:29<01:56,  6.89it/s]
 43%|████▎     | 605/1407 [01:29<01:56,  6.89it/s]
 43%|████▎     | 606/1407 [01:30<01:51,  7.21it/s]
 43%|████▎     | 607/1407 [01:30<01:51,  7.20it/s]
 43%|████▎     | 608/1407 [01:30<01:51,  7.18it/s]
 43%|████▎     | 609/1407 [01:30<01:45,  7.59it/s]
 43%|████▎     | 610/1407 [01:30<01:48,  7.35it/s]
 43%|████▎     | 611/1407 [01:30<01:51,  7.15it/s]
 43%|████▎     | 612/1407 [01:30<01:55,  6.90it/s]
 44%|████▎     | 613/1407 [01:31<01:48,  7.29it/s]
 44%|████▎     | 614/1407 [01:31<02:14,  5.88it/s]
 44%|████▎     | 615/1407 [01:31<02:08,  6.14it/s]
 44%|████▍     | 616/1407 [01:31<02:04,  6.34it/s]
 44%|████▍     | 617/1407 [01:31<02:01,  6.48it/s]
 44%|████▍     | 618/1407 [01:31<02:02,  6.45it/s]
 44%|████▍     | 619/1407 [01:32<01:59,  6.58it/s]
 44%|████▍     | 620/1407 [01:32<01:58,  6.63it/s]
 44%|████▍     | 621/1407 [01:32<01:51,  7.07it/s]
 44%|████▍     | 622/1407 [01:32<01:53,  6.90it/s]
 44%|████▍     | 623/1407 [01:32<01:53,  6.90it/s]
 44%|████▍     | 624/1407 [01:32<01:55,  6.78it/s]
 44%|████▍     | 625/1407 [01:32<01:55,  6.77it/s]
 44%|████▍     | 626/1407 [01:33<01:49,  7.14it/s]
 45%|████▍     | 627/1407 [01:33<01:42,  7.62it/s]
 45%|████▍     | 628/1407 [01:33<01:44,  7.46it/s]
 45%|████▍     | 629/1407 [01:33<01:49,  7.11it/s]
 45%|████▍     | 630/1407 [01:33<01:48,  7.17it/s]
 45%|████▍     | 631/1407 [01:33<01:51,  6.97it/s]
 45%|████▍     | 632/1407 [01:33<01:49,  7.06it/s]
 45%|████▍     | 633/1407 [01:33<01:50,  7.03it/s]
 45%|████▌     | 634/1407 [01:34<01:53,  6.83it/s]
 45%|████▌     | 635/1407 [01:34<01:53,  6.83it/s]
 45%|████▌     | 636/1407 [01:34<01:55,  6.69it/s]
 45%|████▌     | 637/1407 [01:34<01:54,  6.71it/s]
 45%|████▌     | 638/1407 [01:34<01:56,  6.61it/s]
 45%|████▌     | 639/1407 [01:34<01:54,  6.70it/s]
 45%|████▌     | 640/1407 [01:35<01:53,  6.77it/s]
 46%|████▌     | 641/1407 [01:35<01:52,  6.79it/s]
 46%|████▌     | 642/1407 [01:35<01:52,  6.77it/s]
 46%|████▌     | 643/1407 [01:35<01:50,  6.91it/s]
 46%|████▌     | 644/1407 [01:35<01:53,  6.74it/s]
 46%|████▌     | 645/1407 [01:35<01:54,  6.68it/s]
 46%|████▌     | 646/1407 [01:35<01:55,  6.60it/s]
 46%|████▌     | 647/1407 [01:36<01:55,  6.58it/s]
 46%|████▌     | 648/1407 [01:36<01:56,  6.50it/s]
 46%|████▌     | 649/1407 [01:36<01:52,  6.71it/s]
 46%|████▌     | 650/1407 [01:36<01:52,  6.75it/s]
 46%|████▋     | 651/1407 [01:36<01:51,  6.81it/s]
 46%|████▋     | 652/1407 [01:36<01:53,  6.67it/s]
 46%|████▋     | 653/1407 [01:36<01:53,  6.63it/s]
 46%|████▋     | 654/1407 [01:37<01:53,  6.66it/s]
 47%|████▋     | 655/1407 [01:37<01:54,  6.57it/s]
 47%|████▋     | 656/1407 [01:37<01:51,  6.71it/s]
 47%|████▋     | 657/1407 [01:37<01:50,  6.79it/s]
 47%|████▋     | 658/1407 [01:37<01:50,  6.80it/s]
 47%|████▋     | 659/1407 [01:37<01:51,  6.69it/s]
 47%|████▋     | 660/1407 [01:38<01:52,  6.64it/s]
 47%|████▋     | 661/1407 [01:38<01:43,  7.24it/s]
 47%|████▋     | 662/1407 [01:38<01:47,  6.96it/s]
 47%|████▋     | 663/1407 [01:38<01:46,  6.96it/s]
 47%|████▋     | 664/1407 [01:38<01:48,  6.82it/s]
 47%|████▋     | 665/1407 [01:38<01:43,  7.19it/s]
 47%|████▋     | 666/1407 [01:38<01:42,  7.22it/s]
 47%|████▋     | 667/1407 [01:39<01:46,  6.96it/s]
 47%|████▋     | 668/1407 [01:39<01:45,  7.00it/s]
 48%|████▊     | 669/1407 [01:39<01:46,  6.96it/s]
 48%|████▊     | 670/1407 [01:39<01:46,  6.89it/s]
 48%|████▊     | 671/1407 [01:39<01:46,  6.92it/s]
 48%|████▊     | 672/1407 [01:39<01:48,  6.77it/s]
 48%|████▊     | 673/1407 [01:39<01:48,  6.78it/s]
 48%|████▊     | 674/1407 [01:40<01:47,  6.80it/s]
 48%|████▊     | 675/1407 [01:40<01:41,  7.18it/s]
 48%|████▊     | 676/1407 [01:40<01:41,  7.21it/s]
 48%|████▊     | 677/1407 [01:40<01:45,  6.94it/s]
 48%|████▊     | 678/1407 [01:40<01:46,  6.87it/s]
 48%|████▊     | 679/1407 [01:40<01:48,  6.73it/s]
 48%|████▊     | 680/1407 [01:40<01:48,  6.73it/s]
 48%|████▊     | 681/1407 [01:41<01:49,  6.63it/s]
 48%|████▊     | 682/1407 [01:41<01:45,  6.89it/s]
 49%|████▊     | 683/1407 [01:41<01:54,  6.32it/s]
 49%|████▊     | 684/1407 [01:41<01:51,  6.46it/s]
 49%|████▊     | 685/1407 [01:41<01:50,  6.54it/s]
 49%|████▉     | 686/1407 [01:41<01:51,  6.49it/s]
 49%|████▉     | 687/1407 [01:41<01:51,  6.46it/s]
 49%|████▉     | 688/1407 [01:42<01:48,  6.63it/s]
 49%|████▉     | 689/1407 [01:42<01:46,  6.73it/s]
 49%|████▉     | 690/1407 [01:42<01:46,  6.76it/s]
 49%|████▉     | 691/1407 [01:42<01:45,  6.81it/s]
 49%|████▉     | 692/1407 [01:42<01:44,  6.87it/s]
 49%|████▉     | 693/1407 [01:42<01:44,  6.85it/s]
 49%|████▉     | 694/1407 [01:43<01:45,  6.74it/s]
 49%|████▉     | 695/1407 [01:43<01:45,  6.74it/s]
 49%|████▉     | 696/1407 [01:43<01:44,  6.81it/s]
 50%|████▉     | 697/1407 [01:43<01:42,  6.90it/s]
 50%|████▉     | 698/1407 [01:43<01:45,  6.74it/s]
 50%|████▉     | 699/1407 [01:43<01:44,  6.81it/s]
 50%|████▉     | 700/1407 [01:43<01:45,  6.73it/s]
 50%|████▉     | 701/1407 [01:44<01:46,  6.62it/s]
 50%|████▉     | 702/1407 [01:44<01:45,  6.71it/s]
 50%|████▉     | 703/1407 [01:44<01:43,  6.83it/s]
 50%|█████     | 704/1407 [01:44<01:43,  6.81it/s]
 50%|█████     | 705/1407 [01:44<01:42,  6.85it/s]
 50%|█████     | 706/1407 [01:44<01:44,  6.71it/s]
 50%|█████     | 707/1407 [01:44<01:42,  6.82it/s]
 50%|█████     | 708/1407 [01:45<01:41,  6.86it/s]
 50%|█████     | 709/1407 [01:45<01:43,  6.71it/s]
 50%|█████     | 710/1407 [01:45<01:42,  6.82it/s]
 51%|█████     | 711/1407 [01:45<01:42,  6.80it/s]
 51%|█████     | 712/1407 [01:45<01:43,  6.70it/s]
 51%|█████     | 713/1407 [01:45<01:45,  6.61it/s]
 51%|█████     | 714/1407 [01:45<01:40,  6.87it/s]
 51%|█████     | 715/1407 [01:46<01:43,  6.72it/s]
 51%|█████     | 716/1407 [01:46<01:42,  6.72it/s]
 51%|█████     | 717/1407 [01:46<01:50,  6.23it/s]
 51%|█████     | 718/1407 [01:46<01:41,  6.77it/s]
 51%|█████     | 719/1407 [01:46<01:41,  6.77it/s]
 51%|█████     | 720/1407 [01:46<01:43,  6.66it/s]
 51%|█████     | 721/1407 [01:47<01:42,  6.68it/s]
 51%|█████▏    | 722/1407 [01:47<01:36,  7.09it/s]
 51%|█████▏    | 723/1407 [01:47<01:39,  6.90it/s]
 51%|█████▏    | 724/1407 [01:47<01:41,  6.75it/s]
 52%|█████▏    | 725/1407 [01:47<01:42,  6.64it/s]
 52%|█████▏    | 726/1407 [01:47<01:43,  6.56it/s]
 52%|█████▏    | 727/1407 [01:47<01:42,  6.62it/s]
 52%|█████▏    | 728/1407 [01:48<01:43,  6.55it/s]
 52%|█████▏    | 729/1407 [01:48<01:40,  6.72it/s]
 52%|█████▏    | 730/1407 [01:48<01:39,  6.78it/s]
 52%|█████▏    | 731/1407 [01:48<01:39,  6.77it/s]
 52%|█████▏    | 732/1407 [01:48<01:38,  6.87it/s]
 52%|█████▏    | 733/1407 [01:48<01:37,  6.89it/s]
 52%|█████▏    | 734/1407 [01:48<01:36,  6.95it/s]
 52%|█████▏    | 735/1407 [01:49<01:37,  6.89it/s]
 52%|█████▏    | 736/1407 [01:49<01:33,  7.21it/s]
 52%|█████▏    | 737/1407 [01:49<01:34,  7.06it/s]
 52%|█████▏    | 738/1407 [01:49<01:34,  7.07it/s]
 53%|█████▎    | 739/1407 [01:49<01:35,  7.00it/s]
 53%|█████▎    | 740/1407 [01:49<01:31,  7.29it/s]
 53%|█████▎    | 741/1407 [01:49<01:32,  7.18it/s]
 53%|█████▎    | 742/1407 [01:50<01:35,  6.93it/s]
 53%|█████▎    | 743/1407 [01:50<01:35,  6.98it/s]
 53%|█████▎    | 744/1407 [01:50<01:36,  6.90it/s]
 53%|█████▎    | 745/1407 [01:50<01:35,  6.92it/s]
 53%|█████▎    | 746/1407 [01:50<01:37,  6.75it/s]
 53%|█████▎    | 747/1407 [01:50<01:37,  6.78it/s]
 53%|█████▎    | 748/1407 [01:50<01:32,  7.09it/s]
 53%|█████▎    | 749/1407 [01:51<01:34,  6.98it/s]
 53%|█████▎    | 750/1407 [01:51<01:36,  6.79it/s]
 53%|█████▎    | 751/1407 [01:51<01:35,  6.84it/s]
 53%|█████▎    | 752/1407 [01:51<01:31,  7.15it/s]
 54%|█████▎    | 753/1407 [01:51<01:31,  7.13it/s]
 54%|█████▎    | 754/1407 [01:51<01:33,  7.00it/s]
 54%|█████▎    | 755/1407 [01:51<01:32,  7.05it/s]
 54%|█████▎    | 756/1407 [01:52<01:33,  7.00it/s]
 54%|█████▍    | 757/1407 [01:52<01:29,  7.28it/s]
 54%|█████▍    | 758/1407 [01:52<01:29,  7.28it/s]
 54%|█████▍    | 759/1407 [01:52<01:30,  7.14it/s]
 54%|█████▍    | 760/1407 [01:52<01:32,  7.03it/s]
 54%|█████▍    | 761/1407 [01:52<01:33,  6.94it/s]
 54%|█████▍    | 762/1407 [01:52<01:33,  6.87it/s]
 54%|█████▍    | 763/1407 [01:53<01:28,  7.30it/s]
 54%|█████▍    | 764/1407 [01:53<01:25,  7.51it/s]
 54%|█████▍    | 765/1407 [01:53<01:27,  7.33it/s]
 54%|█████▍    | 766/1407 [01:53<01:31,  7.02it/s]
 55%|█████▍    | 767/1407 [01:53<01:31,  6.96it/s]
 55%|█████▍    | 768/1407 [01:53<01:33,  6.82it/s]
 55%|█████▍    | 769/1407 [01:53<01:35,  6.69it/s]
 55%|█████▍    | 770/1407 [01:54<01:33,  6.83it/s]
 55%|█████▍    | 771/1407 [01:54<01:32,  6.86it/s]
 55%|█████▍    | 772/1407 [01:54<01:34,  6.75it/s]
 55%|█████▍    | 773/1407 [01:54<01:32,  6.84it/s]
 55%|█████▌    | 774/1407 [01:54<01:34,  6.70it/s]
 55%|█████▌    | 775/1407 [01:54<01:32,  6.86it/s]
 55%|█████▌    | 776/1407 [01:54<01:31,  6.88it/s]
 55%|█████▌    | 777/1407 [01:55<01:30,  6.97it/s]
 55%|█████▌    | 778/1407 [01:55<01:29,  7.06it/s]
 55%|█████▌    | 779/1407 [01:55<01:30,  6.96it/s]
 55%|█████▌    | 780/1407 [01:55<01:29,  6.99it/s]
 56%|█████▌    | 781/1407 [01:55<01:32,  6.80it/s]
 56%|█████▌    | 782/1407 [01:55<01:30,  6.94it/s]
 56%|█████▌    | 783/1407 [01:55<01:29,  6.94it/s]
 56%|█████▌    | 784/1407 [01:56<01:29,  6.93it/s]
 56%|█████▌    | 785/1407 [01:56<01:31,  6.80it/s]
 56%|█████▌    | 786/1407 [01:56<01:30,  6.84it/s]
 56%|█████▌    | 787/1407 [01:56<01:29,  6.91it/s]
 56%|█████▌    | 788/1407 [01:56<01:30,  6.85it/s]
 56%|█████▌    | 789/1407 [01:56<01:31,  6.74it/s]
 56%|█████▌    | 790/1407 [01:56<01:30,  6.80it/s]
 56%|█████▌    | 791/1407 [01:57<01:32,  6.67it/s]
 56%|█████▋    | 792/1407 [01:57<01:32,  6.68it/s]
 56%|█████▋    | 793/1407 [01:57<01:33,  6.60it/s]
 56%|█████▋    | 794/1407 [01:57<01:33,  6.57it/s]
 57%|█████▋    | 795/1407 [01:57<01:31,  6.68it/s]
 57%|█████▋    | 796/1407 [01:57<01:29,  6.81it/s]
 57%|█████▋    | 797/1407 [01:58<01:29,  6.78it/s]
 57%|█████▋    | 798/1407 [01:58<01:29,  6.77it/s]
 57%|█████▋    | 799/1407 [01:58<01:30,  6.69it/s]
 57%|█████▋    | 800/1407 [01:58<01:26,  7.04it/s]
 57%|█████▋    | 801/1407 [01:58<01:25,  7.05it/s]
 57%|█████▋    | 802/1407 [01:58<01:28,  6.84it/s]
 57%|█████▋    | 803/1407 [01:58<01:28,  6.84it/s]
 57%|█████▋    | 804/1407 [01:59<01:23,  7.20it/s]
 57%|█████▋    | 805/1407 [01:59<01:26,  6.93it/s]
 57%|█████▋    | 806/1407 [01:59<01:24,  7.12it/s]
 57%|█████▋    | 807/1407 [01:59<01:20,  7.43it/s]
 57%|█████▋    | 808/1407 [01:59<01:22,  7.27it/s]
 57%|█████▋    | 809/1407 [01:59<01:24,  7.10it/s]
 58%|█████▊    | 810/1407 [01:59<01:22,  7.23it/s]
 58%|█████▊    | 811/1407 [02:00<01:25,  6.95it/s]
 58%|█████▊    | 812/1407 [02:00<01:23,  7.12it/s]
 58%|█████▊    | 813/1407 [02:00<01:23,  7.14it/s]
 58%|█████▊    | 814/1407 [02:00<01:23,  7.07it/s]
 58%|█████▊    | 815/1407 [02:00<01:24,  7.01it/s]
 58%|█████▊    | 816/1407 [02:00<01:25,  6.92it/s]
 58%|█████▊    | 817/1407 [02:00<01:25,  6.89it/s]
 58%|█████▊    | 818/1407 [02:01<01:27,  6.74it/s]
 58%|█████▊    | 819/1407 [02:01<01:26,  6.79it/s]
 58%|█████▊    | 820/1407 [02:01<01:27,  6.70it/s]
 58%|█████▊    | 821/1407 [02:01<01:26,  6.74it/s]
 58%|█████▊    | 822/1407 [02:01<01:24,  6.89it/s]
 58%|█████▊    | 823/1407 [02:01<01:24,  6.88it/s]
 59%|█████▊    | 824/1407 [02:01<01:24,  6.90it/s]
 59%|█████▊    | 825/1407 [02:02<01:20,  7.19it/s]
 59%|█████▊    | 826/1407 [02:02<01:22,  7.04it/s]
 59%|█████▉    | 827/1407 [02:02<01:22,  7.01it/s]
 59%|█████▉    | 828/1407 [02:02<01:24,  6.85it/s]
 59%|█████▉    | 829/1407 [02:02<01:24,  6.81it/s]
 59%|█████▉    | 830/1407 [02:02<01:24,  6.82it/s]
 59%|█████▉    | 831/1407 [02:02<01:23,  6.87it/s]
 59%|█████▉    | 832/1407 [02:03<01:19,  7.21it/s]
 59%|█████▉    | 833/1407 [02:03<01:20,  7.10it/s]
 59%|█████▉    | 834/1407 [02:03<01:19,  7.24it/s]
 59%|█████▉    | 835/1407 [02:03<01:19,  7.20it/s]
 59%|█████▉    | 836/1407 [02:03<01:18,  7.31it/s]
 59%|█████▉    | 837/1407 [02:03<01:19,  7.16it/s]
 60%|█████▉    | 838/1407 [02:03<01:19,  7.15it/s]
 60%|█████▉    | 839/1407 [02:04<01:20,  7.06it/s]
 60%|█████▉    | 840/1407 [02:04<01:20,  7.03it/s]
 60%|█████▉    | 841/1407 [02:04<01:22,  6.87it/s]
 60%|█████▉    | 842/1407 [02:04<01:21,  6.93it/s]
 60%|█████▉    | 843/1407 [02:04<01:22,  6.87it/s]
 60%|█████▉    | 844/1407 [02:04<01:22,  6.82it/s]
 60%|██████    | 845/1407 [02:04<01:24,  6.69it/s]
 60%|██████    | 846/1407 [02:05<01:19,  7.05it/s]
 60%|██████    | 847/1407 [02:05<01:21,  6.88it/s]
 60%|██████    | 848/1407 [02:05<01:21,  6.87it/s]
 60%|██████    | 849/1407 [02:05<01:21,  6.88it/s]
 60%|██████    | 850/1407 [02:05<01:21,  6.87it/s]
 60%|██████    | 851/1407 [02:05<01:20,  6.93it/s]
 61%|██████    | 852/1407 [02:05<01:21,  6.80it/s]
 61%|██████    | 853/1407 [02:06<01:20,  6.91it/s]
 61%|██████    | 854/1407 [02:06<01:13,  7.53it/s]
 61%|██████    | 855/1407 [02:06<01:17,  7.14it/s]
 61%|██████    | 856/1407 [02:06<01:17,  7.08it/s]
 61%|██████    | 857/1407 [02:06<01:17,  7.10it/s]
 61%|██████    | 858/1407 [02:06<01:17,  7.05it/s]
 61%|██████    | 859/1407 [02:06<01:18,  6.95it/s]
 61%|██████    | 860/1407 [02:07<01:19,  6.88it/s]
 61%|██████    | 861/1407 [02:07<01:21,  6.73it/s]
 61%|██████▏   | 862/1407 [02:07<01:19,  6.83it/s]
 61%|██████▏   | 863/1407 [02:07<01:19,  6.83it/s]
 61%|██████▏   | 864/1407 [02:07<01:18,  6.91it/s]
 61%|██████▏   | 865/1407 [02:07<01:19,  6.79it/s]
 62%|██████▏   | 866/1407 [02:07<01:20,  6.71it/s]
 62%|██████▏   | 867/1407 [02:08<01:19,  6.77it/s]
 62%|██████▏   | 868/1407 [02:08<01:15,  7.09it/s]
 62%|██████▏   | 869/1407 [02:08<01:15,  7.10it/s]
 62%|██████▏   | 870/1407 [02:08<01:16,  7.02it/s]
 62%|██████▏   | 871/1407 [02:08<01:16,  7.00it/s]
 62%|██████▏   | 872/1407 [02:08<01:18,  6.83it/s]
 62%|██████▏   | 873/1407 [02:08<01:18,  6.84it/s]
 62%|██████▏   | 874/1407 [02:09<01:18,  6.80it/s]
 62%|██████▏   | 875/1407 [02:09<01:16,  6.95it/s]
 62%|██████▏   | 876/1407 [02:09<01:17,  6.82it/s]
 62%|██████▏   | 877/1407 [02:09<01:13,  7.24it/s]
 62%|██████▏   | 878/1407 [02:09<01:15,  6.97it/s]
 62%|██████▏   | 879/1407 [02:09<01:17,  6.78it/s]
 63%|██████▎   | 880/1407 [02:09<01:19,  6.66it/s]
 63%|██████▎   | 881/1407 [02:10<01:18,  6.70it/s]
 63%|██████▎   | 882/1407 [02:10<01:18,  6.72it/s]
 63%|██████▎   | 883/1407 [02:10<01:16,  6.82it/s]
 63%|██████▎   | 884/1407 [02:10<01:15,  6.90it/s]
 63%|██████▎   | 885/1407 [02:10<01:15,  6.91it/s]
 63%|██████▎   | 886/1407 [02:10<01:17,  6.75it/s]
 63%|██████▎   | 887/1407 [02:10<01:16,  6.83it/s]
 63%|██████▎   | 888/1407 [02:11<01:15,  6.88it/s]
 63%|██████▎   | 889/1407 [02:11<01:15,  6.85it/s]
 63%|██████▎   | 890/1407 [02:11<01:12,  7.17it/s]
 63%|██████▎   | 891/1407 [02:11<01:12,  7.17it/s]
 63%|██████▎   | 892/1407 [02:11<01:12,  7.06it/s]
 63%|██████▎   | 893/1407 [02:11<01:12,  7.09it/s]
 64%|██████▎   | 894/1407 [02:11<01:13,  6.98it/s]
 64%|██████▎   | 895/1407 [02:12<01:13,  6.97it/s]
 64%|██████▎   | 896/1407 [02:12<01:12,  7.07it/s]
 64%|██████▍   | 897/1407 [02:12<01:12,  7.03it/s]
 64%|██████▍   | 898/1407 [02:12<01:14,  6.86it/s]
 64%|██████▍   | 899/1407 [02:12<01:15,  6.71it/s]
 64%|██████▍   | 900/1407 [02:12<01:15,  6.72it/s]
 64%|██████▍   | 901/1407 [02:12<01:15,  6.73it/s]
 64%|██████▍   | 902/1407 [02:13<01:14,  6.79it/s]
 64%|██████▍   | 903/1407 [02:13<01:12,  6.93it/s]
 64%|██████▍   | 904/1407 [02:13<01:10,  7.12it/s]
 64%|██████▍   | 905/1407 [02:13<01:11,  7.06it/s]
 64%|██████▍   | 906/1407 [02:13<01:11,  7.01it/s]
 64%|██████▍   | 907/1407 [02:13<01:11,  6.99it/s]
 65%|██████▍   | 908/1407 [02:13<01:11,  7.02it/s]
 65%|██████▍   | 909/1407 [02:14<01:12,  6.87it/s]
 65%|██████▍   | 910/1407 [02:14<01:06,  7.52it/s]
 65%|██████▍   | 911/1407 [02:14<01:07,  7.30it/s]
 65%|██████▍   | 912/1407 [02:14<01:09,  7.12it/s]
 65%|██████▍   | 913/1407 [02:14<01:10,  7.00it/s]
 65%|██████▍   | 914/1407 [02:14<01:11,  6.86it/s]
 65%|██████▌   | 915/1407 [02:14<01:12,  6.83it/s]
 65%|██████▌   | 916/1407 [02:15<01:12,  6.80it/s]
 65%|██████▌   | 917/1407 [02:15<01:12,  6.80it/s]
 65%|██████▌   | 918/1407 [02:15<01:12,  6.71it/s]
 65%|██████▌   | 919/1407 [02:15<01:13,  6.66it/s]
 65%|██████▌   | 920/1407 [02:15<01:13,  6.61it/s]
 65%|██████▌   | 921/1407 [02:15<01:12,  6.75it/s]
 66%|██████▌   | 922/1407 [02:16<01:12,  6.67it/s]
 66%|██████▌   | 923/1407 [02:16<01:11,  6.75it/s]
 66%|██████▌   | 924/1407 [02:16<01:10,  6.85it/s]
 66%|██████▌   | 925/1407 [02:16<01:11,  6.70it/s]
 66%|██████▌   | 926/1407 [02:16<01:12,  6.61it/s]
 66%|██████▌   | 927/1407 [02:16<01:11,  6.67it/s]
 66%|██████▌   | 928/1407 [02:16<01:10,  6.79it/s]
 66%|██████▌   | 929/1407 [02:17<01:10,  6.80it/s]
 66%|██████▌   | 930/1407 [02:17<01:11,  6.67it/s]
 66%|██████▌   | 931/1407 [02:17<01:12,  6.58it/s]
 66%|██████▌   | 932/1407 [02:17<01:11,  6.66it/s]
 66%|██████▋   | 933/1407 [02:17<01:09,  6.83it/s]
 66%|██████▋   | 934/1407 [02:17<01:10,  6.69it/s]
 66%|██████▋   | 935/1407 [02:17<01:11,  6.60it/s]
 67%|██████▋   | 936/1407 [02:18<01:10,  6.67it/s]
 67%|██████▋   | 937/1407 [02:18<01:09,  6.79it/s]
 67%|██████▋   | 938/1407 [02:18<01:05,  7.20it/s]
                                                  

 67%|██████▋   | 938/1407 [02:18<01:05,  7.20it/s]{'eval_loss': 0.6943790316581726, 'eval_accuracy': 0.6896, 'eval_f1': 0.6904848388428485, 'eval_runtime': 1.7338, 'eval_samples_per_second': 1441.9, 'eval_steps_per_second': 180.526, 'epoch': 1.0}
{'loss': 0.5296, 'learning_rate': 3.662193232456209e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.70it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.69it/s]

 21%|██        | 65/313 [00:00<00:01, 204.60it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.03it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.21it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.90it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.52it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.16it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.79it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.82it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.66it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.77it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.89it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.50it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.66it/s]

                                                  

                                                  

100%|██████████| 313/313 [00:01<00:00, 178.66it/s]
 67%|██████▋   | 938/1407 [02:20<01:05,  7.20it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 939/1407 [02:21<07:24,  1.05it/s]
 67%|██████▋   | 940/1407 [02:21<05:32,  1.41it/s]
 67%|██████▋   | 941/1407 [02:21<04:12,  1.84it/s]
 67%|██████▋   | 942/1407 [02:21<03:16,  2.36it/s]
 67%|██████▋   | 943/1407 [02:21<02:38,  2.93it/s]
 67%|██████▋   | 944/1407 [02:21<02:10,  3.54it/s]
 67%|██████▋   | 945/1407 [02:22<01:51,  4.14it/s]
 67%|██████▋   | 946/1407 [02:22<01:37,  4.73it/s]
 67%|██████▋   | 947/1407 [02:22<01:28,  5.19it/s]
 67%|██████▋   | 948/1407 [02:22<01:23,  5.53it/s]
 67%|██████▋   | 949/1407 [02:22<01:17,  5.94it/s]
 68%|██████▊   | 950/1407 [02:22<01:15,  6.07it/s]
 68%|██████▊   | 951/1407 [02:23<01:13,  6.17it/s]
 68%|██████▊   | 952/1407 [02:23<01:11,  6.35it/s]
 68%|██████▊   | 953/1407 [02:23<01:11,  6.36it/s]
 68%|██████▊   | 954/1407 [02:23<01:09,  6.47it/s]
 68%|██████▊   | 955/1407 [02:23<01:08,  6.61it/s]
 68%|██████▊   | 956/1407 [02:23<01:07,  6.65it/s]
 68%|██████▊   | 957/1407 [02:23<01:08,  6.61it/s]
 68%|██████▊   | 958/1407 [02:24<01:08,  6.59it/s]
 68%|██████▊   | 959/1407 [02:24<01:06,  6.70it/s]
 68%|██████▊   | 960/1407 [02:24<01:06,  6.77it/s]
 68%|██████▊   | 961/1407 [02:24<01:05,  6.82it/s]
 68%|██████▊   | 962/1407 [02:24<01:06,  6.69it/s]
 68%|██████▊   | 963/1407 [02:24<01:06,  6.63it/s]
 69%|██████▊   | 964/1407 [02:24<01:05,  6.72it/s]
 69%|██████▊   | 965/1407 [02:25<01:06,  6.61it/s]
 69%|██████▊   | 966/1407 [02:25<01:07,  6.56it/s]
 69%|██████▊   | 967/1407 [02:25<01:03,  6.95it/s]
 69%|██████▉   | 968/1407 [02:25<01:02,  7.00it/s]
 69%|██████▉   | 969/1407 [02:25<01:04,  6.84it/s]
 69%|██████▉   | 970/1407 [02:25<01:04,  6.75it/s]
 69%|██████▉   | 971/1407 [02:25<01:05,  6.67it/s]
 69%|██████▉   | 972/1407 [02:26<01:04,  6.76it/s]
 69%|██████▉   | 973/1407 [02:26<01:03,  6.83it/s]
 69%|██████▉   | 974/1407 [02:26<01:01,  7.04it/s]
 69%|██████▉   | 975/1407 [02:26<01:03,  6.83it/s]
 69%|██████▉   | 976/1407 [02:26<01:04,  6.69it/s]
 69%|██████▉   | 977/1407 [02:26<01:04,  6.65it/s]
 70%|██████▉   | 978/1407 [02:27<01:03,  6.78it/s]
 70%|██████▉   | 979/1407 [02:27<01:02,  6.83it/s]
 70%|██████▉   | 980/1407 [02:27<00:59,  7.23it/s]
 70%|██████▉   | 981/1407 [02:27<01:00,  7.08it/s]
 70%|██████▉   | 982/1407 [02:27<01:02,  6.85it/s]
 70%|██████▉   | 983/1407 [02:27<01:01,  6.87it/s]
 70%|██████▉   | 984/1407 [02:27<01:02,  6.77it/s]
 70%|███████   | 985/1407 [02:28<01:03,  6.66it/s]
 70%|███████   | 986/1407 [02:28<01:02,  6.75it/s]
 70%|███████   | 987/1407 [02:28<00:59,  7.10it/s]
 70%|███████   | 988/1407 [02:28<00:59,  7.10it/s]
 70%|███████   | 989/1407 [02:28<00:59,  7.02it/s]
 70%|███████   | 990/1407 [02:28<00:59,  6.96it/s]
 70%|███████   | 991/1407 [02:28<00:59,  7.00it/s]
 71%|███████   | 992/1407 [02:29<01:00,  6.81it/s]
 71%|███████   | 993/1407 [02:29<01:00,  6.89it/s]
 71%|███████   | 994/1407 [02:29<00:57,  7.18it/s]
 71%|███████   | 995/1407 [02:29<00:58,  7.04it/s]
 71%|███████   | 996/1407 [02:29<00:58,  7.02it/s]
 71%|███████   | 997/1407 [02:29<00:58,  6.99it/s]
 71%|███████   | 998/1407 [02:29<00:58,  7.02it/s]
 71%|███████   | 999/1407 [02:30<00:57,  7.05it/s]
 71%|███████   | 1000/1407 [02:30<00:58,  6.96it/s]
 71%|███████   | 1001/1407 [02:30<00:58,  6.89it/s]
 71%|███████   | 1002/1407 [02:30<00:57,  7.00it/s]
 71%|███████▏  | 1003/1407 [02:30<00:57,  7.08it/s]
 71%|███████▏  | 1004/1407 [02:30<00:57,  6.97it/s]
 71%|███████▏  | 1005/1407 [02:30<00:57,  6.97it/s]
 71%|███████▏  | 1006/1407 [02:31<00:59,  6.79it/s]
 72%|███████▏  | 1007/1407 [02:31<00:58,  6.81it/s]
 72%|███████▏  | 1008/1407 [02:31<00:59,  6.72it/s]
 72%|███████▏  | 1009/1407 [02:31<00:55,  7.11it/s]
 72%|███████▏  | 1010/1407 [02:31<00:56,  7.00it/s]
 72%|███████▏  | 1011/1407 [02:31<00:56,  6.96it/s]
 72%|███████▏  | 1012/1407 [02:31<00:57,  6.92it/s]
 72%|███████▏  | 1013/1407 [02:32<00:57,  6.79it/s]
 72%|███████▏  | 1014/1407 [02:32<00:59,  6.66it/s]
 72%|███████▏  | 1015/1407 [02:32<00:58,  6.73it/s]
 72%|███████▏  | 1016/1407 [02:32<00:57,  6.86it/s]
 72%|███████▏  | 1017/1407 [02:32<00:57,  6.81it/s]
 72%|███████▏  | 1018/1407 [02:32<00:58,  6.68it/s]
 72%|███████▏  | 1019/1407 [02:32<00:54,  7.11it/s]
 72%|███████▏  | 1020/1407 [02:33<00:55,  7.04it/s]
 73%|███████▎  | 1021/1407 [02:33<00:55,  6.95it/s]
 73%|███████▎  | 1022/1407 [02:33<00:53,  7.23it/s]
 73%|███████▎  | 1023/1407 [02:33<00:54,  7.07it/s]
 73%|███████▎  | 1024/1407 [02:33<00:54,  7.00it/s]
 73%|███████▎  | 1025/1407 [02:33<00:54,  7.07it/s]
 73%|███████▎  | 1026/1407 [02:33<00:55,  6.85it/s]
 73%|███████▎  | 1027/1407 [02:34<00:54,  6.97it/s]
 73%|███████▎  | 1028/1407 [02:34<00:54,  6.90it/s]
 73%|███████▎  | 1029/1407 [02:34<00:55,  6.85it/s]
 73%|███████▎  | 1030/1407 [02:34<00:55,  6.74it/s]
 73%|███████▎  | 1031/1407 [02:34<00:56,  6.67it/s]
 73%|███████▎  | 1032/1407 [02:34<00:54,  6.82it/s]
 73%|███████▎  | 1033/1407 [02:34<00:54,  6.87it/s]
 73%|███████▎  | 1034/1407 [02:35<00:55,  6.76it/s]
 74%|███████▎  | 1035/1407 [02:35<00:54,  6.79it/s]
 74%|███████▎  | 1036/1407 [02:35<00:52,  7.01it/s]
 74%|███████▎  | 1037/1407 [02:35<00:52,  6.99it/s]
 74%|███████▍  | 1038/1407 [02:35<00:52,  7.02it/s]
 74%|███████▍  | 1039/1407 [02:35<00:52,  6.97it/s]
 74%|███████▍  | 1040/1407 [02:35<00:52,  6.93it/s]
 74%|███████▍  | 1041/1407 [02:36<00:52,  6.91it/s]
 74%|███████▍  | 1042/1407 [02:36<00:49,  7.33it/s]
 74%|███████▍  | 1043/1407 [02:36<00:50,  7.14it/s]
 74%|███████▍  | 1044/1407 [02:36<00:51,  7.07it/s]
 74%|███████▍  | 1045/1407 [02:36<00:51,  7.04it/s]
 74%|███████▍  | 1046/1407 [02:36<00:51,  7.01it/s]
 74%|███████▍  | 1047/1407 [02:36<00:51,  6.92it/s]
 74%|███████▍  | 1048/1407 [02:37<00:51,  6.93it/s]
 75%|███████▍  | 1049/1407 [02:37<00:52,  6.88it/s]
 75%|███████▍  | 1050/1407 [02:37<00:53,  6.72it/s]
 75%|███████▍  | 1051/1407 [02:37<00:53,  6.63it/s]
 75%|███████▍  | 1052/1407 [02:37<00:54,  6.56it/s]
 75%|███████▍  | 1053/1407 [02:37<00:53,  6.64it/s]
 75%|███████▍  | 1054/1407 [02:38<00:53,  6.58it/s]
 75%|███████▍  | 1055/1407 [02:38<00:53,  6.63it/s]
 75%|███████▌  | 1056/1407 [02:38<00:49,  7.04it/s]
 75%|███████▌  | 1057/1407 [02:38<00:51,  6.75it/s]
 75%|███████▌  | 1058/1407 [02:38<00:51,  6.81it/s]
 75%|███████▌  | 1059/1407 [02:38<00:50,  6.84it/s]
 75%|███████▌  | 1060/1407 [02:38<00:50,  6.84it/s]
 75%|███████▌  | 1061/1407 [02:38<00:48,  7.20it/s]
 75%|███████▌  | 1062/1407 [02:39<00:49,  6.94it/s]
 76%|███████▌  | 1063/1407 [02:39<00:49,  6.90it/s]
 76%|███████▌  | 1064/1407 [02:39<00:49,  6.91it/s]
 76%|███████▌  | 1065/1407 [02:39<00:50,  6.75it/s]
 76%|███████▌  | 1066/1407 [02:39<00:50,  6.79it/s]
 76%|███████▌  | 1067/1407 [02:39<00:49,  6.85it/s]
 76%|███████▌  | 1068/1407 [02:40<00:48,  6.95it/s]
 76%|███████▌  | 1069/1407 [02:40<00:49,  6.89it/s]
 76%|███████▌  | 1070/1407 [02:40<00:50,  6.73it/s]
 76%|███████▌  | 1071/1407 [02:40<00:50,  6.66it/s]
 76%|███████▌  | 1072/1407 [02:40<00:49,  6.71it/s]
 76%|███████▋  | 1073/1407 [02:40<00:48,  6.85it/s]
 76%|███████▋  | 1074/1407 [02:40<00:49,  6.70it/s]
 76%|███████▋  | 1075/1407 [02:41<00:49,  6.71it/s]
 76%|███████▋  | 1076/1407 [02:41<00:50,  6.61it/s]
 77%|███████▋  | 1077/1407 [02:41<00:49,  6.70it/s]
 77%|███████▋  | 1078/1407 [02:41<00:48,  6.77it/s]
 77%|███████▋  | 1079/1407 [02:41<00:48,  6.70it/s]
 77%|███████▋  | 1080/1407 [02:41<00:49,  6.65it/s]
 77%|███████▋  | 1081/1407 [02:41<00:48,  6.75it/s]
 77%|███████▋  | 1082/1407 [02:42<00:44,  7.32it/s]
 77%|███████▋  | 1083/1407 [02:42<00:46,  7.02it/s]
 77%|███████▋  | 1084/1407 [02:42<00:46,  7.02it/s]
 77%|███████▋  | 1085/1407 [02:42<00:46,  6.96it/s]
 77%|███████▋  | 1086/1407 [02:42<00:47,  6.83it/s]
 77%|███████▋  | 1087/1407 [02:42<00:44,  7.13it/s]
 77%|███████▋  | 1088/1407 [02:42<00:46,  6.89it/s]
 77%|███████▋  | 1089/1407 [02:43<00:46,  6.90it/s]
 77%|███████▋  | 1090/1407 [02:43<00:43,  7.24it/s]
 78%|███████▊  | 1091/1407 [02:43<00:44,  7.12it/s]
 78%|███████▊  | 1092/1407 [02:43<00:57,  5.52it/s]
 78%|███████▊  | 1093/1407 [02:43<00:53,  5.86it/s]
 78%|███████▊  | 1094/1407 [02:43<00:51,  6.13it/s]
 78%|███████▊  | 1095/1407 [02:44<00:49,  6.35it/s]
 78%|███████▊  | 1096/1407 [02:44<00:47,  6.55it/s]
 78%|███████▊  | 1097/1407 [02:44<00:44,  6.93it/s]
 78%|███████▊  | 1098/1407 [02:44<00:44,  6.91it/s]
 78%|███████▊  | 1099/1407 [02:44<00:44,  6.86it/s]
 78%|███████▊  | 1100/1407 [02:44<00:44,  6.92it/s]
 78%|███████▊  | 1101/1407 [02:44<00:45,  6.80it/s]
 78%|███████▊  | 1102/1407 [02:45<00:45,  6.78it/s]
 78%|███████▊  | 1103/1407 [02:45<00:45,  6.66it/s]
 78%|███████▊  | 1104/1407 [02:45<00:42,  7.08it/s]
 79%|███████▊  | 1105/1407 [02:45<00:43,  7.00it/s]
 79%|███████▊  | 1106/1407 [02:45<00:44,  6.81it/s]
 79%|███████▊  | 1107/1407 [02:45<00:44,  6.68it/s]
 79%|███████▊  | 1108/1407 [02:45<00:44,  6.69it/s]
 79%|███████▉  | 1109/1407 [02:46<00:43,  6.83it/s]
 79%|███████▉  | 1110/1407 [02:46<00:40,  7.31it/s]
 79%|███████▉  | 1111/1407 [02:46<00:40,  7.31it/s]
 79%|███████▉  | 1112/1407 [02:46<00:41,  7.13it/s]
 79%|███████▉  | 1113/1407 [02:46<00:41,  7.05it/s]
 79%|███████▉  | 1114/1407 [02:46<00:41,  7.02it/s]
 79%|███████▉  | 1115/1407 [02:46<00:42,  6.86it/s]
 79%|███████▉  | 1116/1407 [02:47<00:41,  6.94it/s]
 79%|███████▉  | 1117/1407 [02:47<00:41,  6.93it/s]
 79%|███████▉  | 1118/1407 [02:47<00:41,  6.93it/s]
 80%|███████▉  | 1119/1407 [02:47<00:41,  6.92it/s]
 80%|███████▉  | 1120/1407 [02:47<00:41,  6.98it/s]
 80%|███████▉  | 1121/1407 [02:47<00:39,  7.26it/s]
 80%|███████▉  | 1122/1407 [02:47<00:38,  7.48it/s]
 80%|███████▉  | 1123/1407 [02:48<00:39,  7.26it/s]
 80%|███████▉  | 1124/1407 [02:48<00:39,  7.24it/s]
 80%|███████▉  | 1125/1407 [02:48<00:36,  7.63it/s]
 80%|████████  | 1126/1407 [02:48<00:36,  7.79it/s]
 80%|████████  | 1127/1407 [02:48<00:36,  7.72it/s]
 80%|████████  | 1128/1407 [02:48<00:43,  6.34it/s]
 80%|████████  | 1129/1407 [02:48<00:43,  6.36it/s]
 80%|████████  | 1130/1407 [02:49<00:42,  6.53it/s]
 80%|████████  | 1131/1407 [02:49<00:41,  6.64it/s]
 80%|████████  | 1132/1407 [02:49<00:41,  6.60it/s]
 81%|████████  | 1133/1407 [02:49<00:41,  6.66it/s]
 81%|████████  | 1134/1407 [02:49<00:40,  6.73it/s]
 81%|████████  | 1135/1407 [02:49<00:39,  6.84it/s]
 81%|████████  | 1136/1407 [02:49<00:39,  6.92it/s]
 81%|████████  | 1137/1407 [02:50<00:38,  6.93it/s]
 81%|████████  | 1138/1407 [02:50<00:38,  6.94it/s]
 81%|████████  | 1139/1407 [02:50<00:36,  7.28it/s]
 81%|████████  | 1140/1407 [02:50<00:37,  7.16it/s]
 81%|████████  | 1141/1407 [02:50<00:38,  6.91it/s]
 81%|████████  | 1142/1407 [02:50<00:36,  7.19it/s]
 81%|████████  | 1143/1407 [02:50<00:38,  6.93it/s]
 81%|████████▏ | 1144/1407 [02:51<00:38,  6.89it/s]
 81%|████████▏ | 1145/1407 [02:51<00:38,  6.78it/s]
 81%|████████▏ | 1146/1407 [02:51<00:36,  7.10it/s]
 82%|████████▏ | 1147/1407 [02:51<00:37,  6.99it/s]
 82%|████████▏ | 1148/1407 [02:51<00:37,  6.98it/s]
 82%|████████▏ | 1149/1407 [02:51<00:37,  6.97it/s]
 82%|████████▏ | 1150/1407 [02:51<00:36,  6.97it/s]
 82%|████████▏ | 1151/1407 [02:52<00:37,  6.90it/s]
 82%|████████▏ | 1152/1407 [02:52<00:37,  6.79it/s]
 82%|████████▏ | 1153/1407 [02:52<00:37,  6.70it/s]
 82%|████████▏ | 1154/1407 [02:52<00:37,  6.70it/s]
 82%|████████▏ | 1155/1407 [02:52<00:38,  6.61it/s]
 82%|████████▏ | 1156/1407 [02:52<00:36,  6.97it/s]
 82%|████████▏ | 1157/1407 [02:52<00:35,  6.95it/s]
 82%|████████▏ | 1158/1407 [02:53<00:36,  6.77it/s]
 82%|████████▏ | 1159/1407 [02:53<00:36,  6.82it/s]
 82%|████████▏ | 1160/1407 [02:53<00:35,  6.90it/s]
 83%|████████▎ | 1161/1407 [02:53<00:36,  6.78it/s]
 83%|████████▎ | 1162/1407 [02:53<00:36,  6.66it/s]
 83%|████████▎ | 1163/1407 [02:53<00:43,  5.57it/s]
 83%|████████▎ | 1164/1407 [02:54<00:39,  6.15it/s]
 83%|████████▎ | 1165/1407 [02:54<00:37,  6.40it/s]
 83%|████████▎ | 1166/1407 [02:54<00:36,  6.56it/s]
 83%|████████▎ | 1167/1407 [02:54<00:36,  6.61it/s]
 83%|████████▎ | 1168/1407 [02:54<00:35,  6.69it/s]
 83%|████████▎ | 1169/1407 [02:54<00:35,  6.70it/s]
 83%|████████▎ | 1170/1407 [02:54<00:35,  6.71it/s]
 83%|████████▎ | 1171/1407 [02:55<00:34,  6.78it/s]
 83%|████████▎ | 1172/1407 [02:55<00:34,  6.76it/s]
 83%|████████▎ | 1173/1407 [02:55<00:35,  6.69it/s]
 83%|████████▎ | 1174/1407 [02:55<00:33,  6.86it/s]
 84%|████████▎ | 1175/1407 [02:55<00:32,  7.15it/s]
 84%|████████▎ | 1176/1407 [02:55<00:33,  6.92it/s]
 84%|████████▎ | 1177/1407 [02:56<00:34,  6.75it/s]
 84%|████████▎ | 1178/1407 [02:56<00:33,  6.84it/s]
 84%|████████▍ | 1179/1407 [02:56<00:33,  6.87it/s]
 84%|████████▍ | 1180/1407 [02:56<00:33,  6.72it/s]
 84%|████████▍ | 1181/1407 [02:56<00:32,  6.86it/s]
 84%|████████▍ | 1182/1407 [02:56<00:32,  6.88it/s]
 84%|████████▍ | 1183/1407 [02:56<00:30,  7.26it/s]
 84%|████████▍ | 1184/1407 [02:57<00:31,  6.99it/s]
 84%|████████▍ | 1185/1407 [02:57<00:32,  6.79it/s]
 84%|████████▍ | 1186/1407 [02:57<00:32,  6.80it/s]
 84%|████████▍ | 1187/1407 [02:57<00:32,  6.85it/s]
 84%|████████▍ | 1188/1407 [02:57<00:30,  7.16it/s]
 85%|████████▍ | 1189/1407 [02:57<00:31,  6.96it/s]
 85%|████████▍ | 1190/1407 [02:57<00:31,  6.96it/s]
 85%|████████▍ | 1191/1407 [02:58<00:31,  6.90it/s]
 85%|████████▍ | 1192/1407 [02:58<00:30,  6.96it/s]
 85%|████████▍ | 1193/1407 [02:58<00:30,  6.91it/s]
 85%|████████▍ | 1194/1407 [02:58<00:31,  6.76it/s]
 85%|████████▍ | 1195/1407 [02:58<00:30,  6.85it/s]
 85%|████████▌ | 1196/1407 [02:58<00:30,  6.98it/s]
 85%|████████▌ | 1197/1407 [02:58<00:30,  6.96it/s]
 85%|████████▌ | 1198/1407 [02:59<00:30,  6.83it/s]
 85%|████████▌ | 1199/1407 [02:59<00:28,  7.20it/s]
 85%|████████▌ | 1200/1407 [02:59<00:27,  7.53it/s]
 85%|████████▌ | 1201/1407 [02:59<00:27,  7.39it/s]
 85%|████████▌ | 1202/1407 [02:59<00:29,  7.05it/s]
 86%|████████▌ | 1203/1407 [02:59<00:29,  6.95it/s]
 86%|████████▌ | 1204/1407 [02:59<00:29,  7.00it/s]
 86%|████████▌ | 1205/1407 [03:00<00:28,  7.03it/s]
 86%|████████▌ | 1206/1407 [03:00<00:28,  6.94it/s]
 86%|████████▌ | 1207/1407 [03:00<00:28,  6.95it/s]
 86%|████████▌ | 1208/1407 [03:00<00:28,  6.92it/s]
 86%|████████▌ | 1209/1407 [03:00<00:29,  6.75it/s]
 86%|████████▌ | 1210/1407 [03:00<00:28,  6.82it/s]
 86%|████████▌ | 1211/1407 [03:00<00:26,  7.35it/s]
 86%|████████▌ | 1212/1407 [03:00<00:25,  7.54it/s]
 86%|████████▌ | 1213/1407 [03:01<00:26,  7.34it/s]
 86%|████████▋ | 1214/1407 [03:01<00:26,  7.15it/s]
 86%|████████▋ | 1215/1407 [03:01<00:27,  6.95it/s]
 86%|████████▋ | 1216/1407 [03:01<00:28,  6.77it/s]
 86%|████████▋ | 1217/1407 [03:01<00:27,  6.87it/s]
 87%|████████▋ | 1218/1407 [03:01<00:27,  6.96it/s]
 87%|████████▋ | 1219/1407 [03:01<00:25,  7.32it/s]
 87%|████████▋ | 1220/1407 [03:02<00:25,  7.27it/s]
 87%|████████▋ | 1221/1407 [03:02<00:26,  7.14it/s]
 87%|████████▋ | 1222/1407 [03:02<00:25,  7.12it/s]
 87%|████████▋ | 1223/1407 [03:02<00:26,  6.88it/s]
 87%|████████▋ | 1224/1407 [03:02<00:26,  6.84it/s]
 87%|████████▋ | 1225/1407 [03:02<00:25,  7.16it/s]
 87%|████████▋ | 1226/1407 [03:02<00:25,  7.09it/s]
 87%|████████▋ | 1227/1407 [03:03<00:25,  7.00it/s]
 87%|████████▋ | 1228/1407 [03:03<00:25,  6.96it/s]
 87%|████████▋ | 1229/1407 [03:03<00:25,  7.00it/s]
 87%|████████▋ | 1230/1407 [03:03<00:25,  6.98it/s]
 87%|████████▋ | 1231/1407 [03:03<00:24,  7.27it/s]
 88%|████████▊ | 1232/1407 [03:03<00:24,  7.22it/s]
 88%|████████▊ | 1233/1407 [03:03<00:24,  7.11it/s]
 88%|████████▊ | 1234/1407 [03:04<00:24,  6.93it/s]
 88%|████████▊ | 1235/1407 [03:04<00:24,  7.01it/s]
 88%|████████▊ | 1236/1407 [03:04<00:22,  7.45it/s]
 88%|████████▊ | 1237/1407 [03:04<00:22,  7.63it/s]
 88%|████████▊ | 1238/1407 [03:04<00:23,  7.34it/s]
 88%|████████▊ | 1239/1407 [03:04<00:22,  7.32it/s]
 88%|████████▊ | 1240/1407 [03:04<00:23,  7.21it/s]
 88%|████████▊ | 1241/1407 [03:05<00:23,  6.95it/s]
 88%|████████▊ | 1242/1407 [03:05<00:23,  6.95it/s]
 88%|████████▊ | 1243/1407 [03:05<00:23,  7.05it/s]
 88%|████████▊ | 1244/1407 [03:05<00:23,  6.96it/s]
 88%|████████▊ | 1245/1407 [03:05<00:23,  6.93it/s]
 89%|████████▊ | 1246/1407 [03:05<00:22,  7.21it/s]
 89%|████████▊ | 1247/1407 [03:05<00:22,  7.07it/s]
 89%|████████▊ | 1248/1407 [03:06<00:22,  7.00it/s]
 89%|████████▉ | 1249/1407 [03:06<00:22,  6.91it/s]
 89%|████████▉ | 1250/1407 [03:06<00:22,  6.92it/s]
 89%|████████▉ | 1251/1407 [03:06<00:22,  6.93it/s]
 89%|████████▉ | 1252/1407 [03:06<00:22,  6.76it/s]
 89%|████████▉ | 1253/1407 [03:06<00:22,  6.86it/s]
 89%|████████▉ | 1254/1407 [03:06<00:22,  6.88it/s]
 89%|████████▉ | 1255/1407 [03:07<00:20,  7.25it/s]
 89%|████████▉ | 1256/1407 [03:07<00:21,  7.09it/s]
 89%|████████▉ | 1257/1407 [03:07<00:21,  7.02it/s]
 89%|████████▉ | 1258/1407 [03:07<00:21,  6.86it/s]
 89%|████████▉ | 1259/1407 [03:07<00:21,  6.85it/s]
 90%|████████▉ | 1260/1407 [03:07<00:21,  6.70it/s]
 90%|████████▉ | 1261/1407 [03:08<00:22,  6.61it/s]
 90%|████████▉ | 1262/1407 [03:08<00:21,  6.65it/s]
 90%|████████▉ | 1263/1407 [03:08<00:21,  6.73it/s]
 90%|████████▉ | 1264/1407 [03:08<00:21,  6.78it/s]
 90%|████████▉ | 1265/1407 [03:08<00:20,  6.84it/s]
 90%|████████▉ | 1266/1407 [03:08<00:20,  6.94it/s]
 90%|█████████ | 1267/1407 [03:08<00:19,  7.04it/s]
 90%|█████████ | 1268/1407 [03:09<00:20,  6.83it/s]
 90%|█████████ | 1269/1407 [03:09<00:20,  6.86it/s]
 90%|█████████ | 1270/1407 [03:09<00:20,  6.82it/s]
 90%|█████████ | 1271/1407 [03:09<00:20,  6.74it/s]
 90%|█████████ | 1272/1407 [03:09<00:19,  6.78it/s]
 90%|█████████ | 1273/1407 [03:09<00:19,  6.87it/s]
 91%|█████████ | 1274/1407 [03:09<00:19,  6.76it/s]
 91%|█████████ | 1275/1407 [03:10<00:19,  6.78it/s]
 91%|█████████ | 1276/1407 [03:10<00:19,  6.88it/s]
 91%|█████████ | 1278/1407 [03:10<00:16,  7.75it/s]
 91%|█████████ | 1279/1407 [03:10<00:17,  7.47it/s]
 91%|█████████ | 1280/1407 [03:10<00:17,  7.39it/s]
 91%|█████████ | 1281/1407 [03:10<00:17,  7.30it/s]
 91%|█████████ | 1282/1407 [03:10<00:17,  7.25it/s]
 91%|█████████ | 1283/1407 [03:11<00:17,  7.00it/s]
 91%|█████████▏| 1284/1407 [03:11<00:17,  6.97it/s]
 91%|█████████▏| 1285/1407 [03:11<00:17,  6.81it/s]
 91%|█████████▏| 1286/1407 [03:11<00:18,  6.72it/s]
 91%|█████████▏| 1287/1407 [03:11<00:18,  6.65it/s]
 92%|█████████▏| 1288/1407 [03:11<00:17,  6.78it/s]
 92%|█████████▏| 1289/1407 [03:12<00:17,  6.77it/s]
 92%|█████████▏| 1290/1407 [03:12<00:16,  6.92it/s]
 92%|█████████▏| 1291/1407 [03:12<00:16,  7.11it/s]
 92%|█████████▏| 1292/1407 [03:12<00:16,  6.88it/s]
 92%|█████████▏| 1293/1407 [03:12<00:16,  6.87it/s]
 92%|█████████▏| 1294/1407 [03:12<00:16,  6.99it/s]
 92%|█████████▏| 1295/1407 [03:12<00:16,  6.92it/s]
 92%|█████████▏| 1296/1407 [03:13<00:15,  7.20it/s]
 92%|█████████▏| 1297/1407 [03:13<00:15,  7.08it/s]
 92%|█████████▏| 1298/1407 [03:13<00:15,  7.02it/s]
 92%|█████████▏| 1299/1407 [03:13<00:15,  6.96it/s]
 92%|█████████▏| 1300/1407 [03:13<00:15,  6.88it/s]
 92%|█████████▏| 1301/1407 [03:13<00:15,  6.92it/s]
 93%|█████████▎| 1302/1407 [03:13<00:15,  6.75it/s]
 93%|█████████▎| 1303/1407 [03:14<00:15,  6.87it/s]
 93%|█████████▎| 1304/1407 [03:14<00:14,  7.20it/s]
 93%|█████████▎| 1305/1407 [03:14<00:14,  7.13it/s]
 93%|█████████▎| 1306/1407 [03:14<00:14,  7.01it/s]
 93%|█████████▎| 1307/1407 [03:14<00:14,  6.81it/s]
 93%|█████████▎| 1308/1407 [03:14<00:13,  7.20it/s]
 93%|█████████▎| 1309/1407 [03:14<00:13,  7.09it/s]
 93%|█████████▎| 1310/1407 [03:15<00:13,  6.99it/s]
 93%|█████████▎| 1311/1407 [03:15<00:13,  7.02it/s]
 93%|█████████▎| 1312/1407 [03:15<00:13,  6.97it/s]
 93%|█████████▎| 1313/1407 [03:15<00:13,  6.95it/s]
 93%|█████████▎| 1314/1407 [03:15<00:13,  7.00it/s]
 93%|█████████▎| 1315/1407 [03:15<00:13,  6.86it/s]
 94%|█████████▎| 1316/1407 [03:15<00:13,  6.95it/s]
 94%|█████████▎| 1317/1407 [03:16<00:12,  6.95it/s]
 94%|█████████▎| 1318/1407 [03:16<00:12,  7.31it/s]
 94%|█████████▎| 1319/1407 [03:16<00:12,  7.12it/s]
 94%|█████████▍| 1320/1407 [03:16<00:12,  7.11it/s]
 94%|█████████▍| 1321/1407 [03:16<00:11,  7.35it/s]
 94%|█████████▍| 1322/1407 [03:16<00:12,  7.03it/s]
 94%|█████████▍| 1323/1407 [03:16<00:11,  7.08it/s]
 94%|█████████▍| 1324/1407 [03:17<00:11,  6.97it/s]
 94%|█████████▍| 1325/1407 [03:17<00:11,  6.96it/s]
 94%|█████████▍| 1326/1407 [03:17<00:11,  6.80it/s]
 94%|█████████▍| 1327/1407 [03:17<00:11,  6.94it/s]
 94%|█████████▍| 1328/1407 [03:17<00:10,  7.25it/s]
 94%|█████████▍| 1329/1407 [03:17<00:10,  7.15it/s]
 95%|█████████▍| 1330/1407 [03:17<00:10,  7.02it/s]
 95%|█████████▍| 1331/1407 [03:18<00:11,  6.86it/s]
 95%|█████████▍| 1332/1407 [03:18<00:11,  6.76it/s]
 95%|█████████▍| 1333/1407 [03:18<00:10,  6.78it/s]
 95%|█████████▍| 1334/1407 [03:18<00:10,  6.90it/s]
 95%|█████████▍| 1335/1407 [03:18<00:10,  6.75it/s]
 95%|█████████▍| 1336/1407 [03:18<00:10,  6.78it/s]
 95%|█████████▌| 1337/1407 [03:18<00:10,  6.77it/s]
 95%|█████████▌| 1338/1407 [03:19<00:09,  6.92it/s]
 95%|█████████▌| 1339/1407 [03:19<00:09,  6.86it/s]
 95%|█████████▌| 1340/1407 [03:19<00:09,  6.85it/s]
 95%|█████████▌| 1341/1407 [03:19<00:09,  6.81it/s]
 95%|█████████▌| 1342/1407 [03:19<00:09,  6.71it/s]
 95%|█████████▌| 1343/1407 [03:19<00:09,  6.79it/s]
 96%|█████████▌| 1344/1407 [03:19<00:09,  6.84it/s]
 96%|█████████▌| 1345/1407 [03:20<00:08,  6.91it/s]
 96%|█████████▌| 1346/1407 [03:20<00:08,  7.25it/s]
 96%|█████████▌| 1347/1407 [03:20<00:08,  7.33it/s]
 96%|█████████▌| 1348/1407 [03:20<00:08,  7.01it/s]
 96%|█████████▌| 1349/1407 [03:20<00:08,  6.98it/s]
 96%|█████████▌| 1350/1407 [03:20<00:07,  7.42it/s]
 96%|█████████▌| 1351/1407 [03:20<00:07,  7.09it/s]
 96%|█████████▌| 1352/1407 [03:21<00:07,  7.04it/s]
 96%|█████████▌| 1353/1407 [03:21<00:07,  7.19it/s]
 96%|█████████▌| 1354/1407 [03:21<00:07,  6.93it/s]
 96%|█████████▋| 1355/1407 [03:21<00:07,  6.97it/s]
 96%|█████████▋| 1356/1407 [03:21<00:07,  6.82it/s]
 96%|█████████▋| 1357/1407 [03:21<00:07,  6.72it/s]
 97%|█████████▋| 1358/1407 [03:21<00:07,  6.73it/s]
 97%|█████████▋| 1359/1407 [03:22<00:07,  6.80it/s]
 97%|█████████▋| 1360/1407 [03:22<00:07,  6.68it/s]
 97%|█████████▋| 1361/1407 [03:22<00:06,  6.62it/s]
 97%|█████████▋| 1362/1407 [03:22<00:06,  6.59it/s]
 97%|█████████▋| 1363/1407 [03:22<00:06,  6.70it/s]
 97%|█████████▋| 1364/1407 [03:22<00:06,  6.71it/s]
 97%|█████████▋| 1365/1407 [03:22<00:06,  6.77it/s]
 97%|█████████▋| 1366/1407 [03:23<00:06,  6.65it/s]
 97%|█████████▋| 1367/1407 [03:23<00:06,  6.56it/s]
 97%|█████████▋| 1368/1407 [03:23<00:05,  6.54it/s]
 97%|█████████▋| 1369/1407 [03:23<00:05,  6.54it/s]
 97%|█████████▋| 1370/1407 [03:23<00:05,  6.63it/s]
 97%|█████████▋| 1371/1407 [03:23<00:05,  6.72it/s]
 98%|█████████▊| 1372/1407 [03:24<00:05,  6.75it/s]
 98%|█████████▊| 1373/1407 [03:24<00:04,  6.82it/s]
 98%|█████████▊| 1374/1407 [03:24<00:04,  6.86it/s]
 98%|█████████▊| 1375/1407 [03:24<00:04,  6.72it/s]
 98%|█████████▊| 1376/1407 [03:24<00:04,  6.63it/s]
 98%|█████████▊| 1377/1407 [03:24<00:04,  6.59it/s]
 98%|█████████▊| 1378/1407 [03:24<00:04,  6.57it/s]
 98%|█████████▊| 1379/1407 [03:25<00:04,  6.75it/s]
 98%|█████████▊| 1380/1407 [03:25<00:03,  6.82it/s]
 98%|█████████▊| 1381/1407 [03:25<00:03,  7.03it/s]
 98%|█████████▊| 1382/1407 [03:25<00:03,  6.96it/s]
 98%|█████████▊| 1383/1407 [03:25<00:03,  6.78it/s]
 98%|█████████▊| 1384/1407 [03:25<00:03,  6.71it/s]
 98%|█████████▊| 1385/1407 [03:25<00:03,  6.77it/s]
 99%|█████████▊| 1386/1407 [03:26<00:03,  6.86it/s]
 99%|█████████▊| 1387/1407 [03:26<00:02,  6.75it/s]
 99%|█████████▊| 1388/1407 [03:26<00:02,  6.63it/s]
 99%|█████████▊| 1389/1407 [03:26<00:02,  6.56it/s]
 99%|█████████▉| 1390/1407 [03:26<00:02,  6.56it/s]
 99%|█████████▉| 1391/1407 [03:26<00:02,  6.71it/s]
 99%|█████████▉| 1392/1407 [03:26<00:02,  7.06it/s]
 99%|█████████▉| 1393/1407 [03:27<00:01,  7.02it/s]
 99%|█████████▉| 1394/1407 [03:27<00:01,  7.01it/s]
 99%|█████████▉| 1395/1407 [03:27<00:01,  6.86it/s]
 99%|█████████▉| 1396/1407 [03:27<00:01,  6.83it/s]
 99%|█████████▉| 1397/1407 [03:27<00:01,  7.36it/s]
 99%|█████████▉| 1398/1407 [03:27<00:01,  7.20it/s]
 99%|█████████▉| 1399/1407 [03:27<00:01,  6.93it/s]
100%|█████████▉| 1400/1407 [03:28<00:01,  7.00it/s]
100%|█████████▉| 1401/1407 [03:28<00:00,  7.00it/s]
100%|█████████▉| 1402/1407 [03:28<00:00,  6.81it/s]
100%|█████████▉| 1403/1407 [03:28<00:00,  6.69it/s]
100%|█████████▉| 1404/1407 [03:28<00:00,  7.15it/s]
100%|█████████▉| 1405/1407 [03:28<00:00,  7.10it/s]
100%|█████████▉| 1406/1407 [03:28<00:00,  7.04it/s]
100%|██████████| 1407/1407 [03:29<00:00,  7.39it/s]
                                                   

100%|██████████| 1407/1407 [03:29<00:00,  7.39it/s]{'eval_loss': 0.6862090826034546, 'eval_accuracy': 0.716, 'eval_f1': 0.7094126336755631, 'eval_runtime': 1.7342, 'eval_samples_per_second': 1441.615, 'eval_steps_per_second': 180.49, 'epoch': 2.0}
{'loss': 0.3443, 'learning_rate': 3.662193232456209e-05, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.57it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.81it/s]

 21%|██        | 65/313 [00:00<00:01, 204.85it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.25it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.47it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.17it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.72it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.63it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.18it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.05it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.94it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.09it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.22it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.81it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.90it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.90it/s]
100%|██████████| 1407/1407 [03:30<00:00,  7.39it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 1407/1407 [03:31<00:00,  7.39it/s]
100%|██████████| 1407/1407 [03:31<00:00,  6.64it/s]
[I 2023-10-26 23:48:14,913] Trial 40 finished with value: 0.7088697639382067 and parameters: {'lr_scheduler_type': 'constant', 'learning_rate': 3.662193232456209e-05, 'per_device_train_batch_size': 64, 'weight_decay': 0.0004358195049791615}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7876779437065125, 'eval_accuracy': 0.7092, 'eval_f1': 0.7088697639382067, 'eval_runtime': 1.7316, 'eval_samples_per_second': 1443.759, 'eval_steps_per_second': 180.759, 'epoch': 3.0}
{'train_runtime': 211.8914, 'train_samples_per_second': 424.746, 'train_steps_per_second': 6.64, 'train_loss': 0.5419676780022876, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:12,  3.66it/s]
  0%|          | 2/705 [00:00<03:10,  3.68it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.81it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.76it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.81it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:52,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 42/705 [00:11<02:52,  3.84it/s]
  6%|▌         | 43/705 [00:11<02:54,  3.80it/s]
  6%|▌         | 44/705 [00:11<02:52,  3.83it/s]
  6%|▋         | 45/705 [00:11<02:54,  3.78it/s]
  7%|▋         | 46/705 [00:12<02:55,  3.76it/s]
  7%|▋         | 47/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 48/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.77it/s]
  7%|▋         | 50/705 [00:13<02:54,  3.75it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.87it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:19<02:46,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:59,  3.42it/s]
 13%|█▎        | 91/705 [00:24<02:52,  3.56it/s]
 13%|█▎        | 92/705 [00:24<02:49,  3.61it/s]
 13%|█▎        | 93/705 [00:24<02:47,  3.65it/s]
 13%|█▎        | 94/705 [00:24<02:46,  3.68it/s]
 13%|█▎        | 95/705 [00:25<02:45,  3.70it/s]
 14%|█▎        | 96/705 [00:25<02:43,  3.72it/s]
 14%|█▍        | 97/705 [00:25<02:43,  3.71it/s]
 14%|█▍        | 98/705 [00:25<02:42,  3.73it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.72it/s]
 14%|█▍        | 100/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 101/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:28<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.80it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.89it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:39<02:22,  3.91it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.82it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.83it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.80it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.77it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.86it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.81it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:13,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:14,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.87it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7952, 'learning_rate': 5.7928239491712626e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.58it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.53it/s]

 21%|██        | 65/313 [00:00<00:01, 204.53it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.04it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.10it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.68it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.22it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 183.90it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.50it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.72it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.91it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.11it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.21it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 185.14it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 178.38it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.38it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:08,  1.04s/it]
 34%|███▎      | 237/705 [01:04<06:17,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:07,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:03,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.03it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.79it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.84it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.80it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.81it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:14<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:46,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:19<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:20<01:45,  3.84it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.83it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.81it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:43,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.78it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.01it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.88it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:25<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.79it/s]
 46%|████▌     | 322/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.76it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.78it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.80it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.76it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.75it/s]
 48%|████▊     | 335/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:30<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:36,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:47,  3.36it/s]
 49%|████▊     | 343/705 [01:32<01:44,  3.48it/s]
 49%|████▉     | 344/705 [01:32<01:41,  3.54it/s]
 49%|████▉     | 345/705 [01:33<01:38,  3.66it/s]
 49%|████▉     | 346/705 [01:33<01:36,  3.71it/s]
 49%|████▉     | 347/705 [01:33<01:35,  3.74it/s]
 49%|████▉     | 348/705 [01:33<01:35,  3.74it/s]
 50%|████▉     | 349/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.78it/s]
 50%|████▉     | 351/705 [01:34<01:34,  3.75it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.79it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.76it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:31,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:47,  3.19it/s]
 51%|█████▏    | 362/705 [01:37<01:42,  3.34it/s]
 51%|█████▏    | 363/705 [01:38<01:39,  3.44it/s]
 52%|█████▏    | 364/705 [01:38<01:36,  3.52it/s]
 52%|█████▏    | 365/705 [01:38<01:35,  3.58it/s]
 52%|█████▏    | 366/705 [01:38<01:33,  3.64it/s]
 52%|█████▏    | 367/705 [01:39<01:30,  3.71it/s]
 52%|█████▏    | 368/705 [01:39<01:30,  3.74it/s]
 52%|█████▏    | 369/705 [01:39<01:29,  3.75it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.78it/s]
 53%|█████▎    | 371/705 [01:40<01:27,  3.83it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.79it/s]
 53%|█████▎    | 373/705 [01:40<01:27,  3.78it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:28,  3.74it/s]
 53%|█████▎    | 377/705 [01:41<01:25,  3.84it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.82it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:38,  3.29it/s]
 54%|█████▍    | 381/705 [01:43<01:34,  3.42it/s]
 54%|█████▍    | 382/705 [01:43<01:31,  3.52it/s]
 54%|█████▍    | 383/705 [01:43<01:28,  3.63it/s]
 54%|█████▍    | 384/705 [01:43<01:27,  3.65it/s]
 55%|█████▍    | 385/705 [01:44<01:27,  3.66it/s]
 55%|█████▍    | 386/705 [01:44<01:25,  3.73it/s]
 55%|█████▍    | 387/705 [01:44<01:25,  3.74it/s]
 55%|█████▌    | 388/705 [01:44<01:25,  3.72it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.77it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.78it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.80it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.77it/s]
 62%|██████▏   | 435/705 [01:57<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:59<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:04,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.75it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6774970889091492, 'eval_accuracy': 0.7028, 'eval_f1': 0.7011236082565487, 'eval_runtime': 1.7339, 'eval_samples_per_second': 1441.868, 'eval_steps_per_second': 180.522, 'epoch': 1.0}
{'loss': 0.5295, 'learning_rate': 2.0871298514749473e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.63it/s]

 13%|█▎        | 42/313 [00:00<00:01, 197.93it/s]

 20%|██        | 63/313 [00:00<00:01, 202.36it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.70it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.07it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.57it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.18it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.25it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 178.99it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.08it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 167.78it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.82it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.19it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.55it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 178.97it/s]

100%|██████████| 313/313 [00:01<00:00, 175.84it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.84it/s]
 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:04,  1.05s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.23it/s]
 67%|██████▋   | 473/705 [02:09<02:30,  1.55it/s]
 67%|██████▋   | 474/705 [02:10<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:31,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:11<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:04,  3.50it/s]
 68%|██████▊   | 482/705 [02:12<01:02,  3.55it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.82it/s]
 69%|██████▉   | 489/705 [02:14<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.83it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:15<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:16<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:17<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.80it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.76it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:20<00:54,  3.57it/s]
 73%|███████▎  | 513/705 [02:20<00:52,  3.63it/s]
 73%|███████▎  | 514/705 [02:20<00:52,  3.65it/s]
 73%|███████▎  | 515/705 [02:20<00:51,  3.69it/s]
 73%|███████▎  | 516/705 [02:21<00:51,  3.70it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.72it/s]
 73%|███████▎  | 518/705 [02:21<00:50,  3.72it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.76it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.82it/s]
 74%|███████▍  | 521/705 [02:22<00:48,  3.83it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.83it/s]
 74%|███████▍  | 523/705 [02:23<00:47,  3.81it/s]
 74%|███████▍  | 524/705 [02:23<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.82it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:24<00:47,  3.75it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:25<00:49,  3.53it/s]
 75%|███████▌  | 532/705 [02:25<00:48,  3.57it/s]
 76%|███████▌  | 533/705 [02:25<00:47,  3.64it/s]
 76%|███████▌  | 534/705 [02:25<00:46,  3.67it/s]
 76%|███████▌  | 535/705 [02:26<00:45,  3.76it/s]
 76%|███████▌  | 536/705 [02:26<00:45,  3.74it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.74it/s]
 76%|███████▋  | 538/705 [02:27<00:44,  3.72it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.71it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.77it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.77it/s]
 77%|███████▋  | 542/705 [02:28<00:42,  3.83it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.79it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:29<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:30<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.83it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.81it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.74it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.84it/s]
 79%|███████▉  | 557/705 [02:32<00:38,  3.82it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.80it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:33<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:34<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.94it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.91it/s]
 81%|████████  | 569/705 [02:35<00:34,  3.97it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.94it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:36<00:34,  3.81it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.81it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.79it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:39<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:40<00:30,  3.75it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:41<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.77it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.75it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.81it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:42<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.82it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.93it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:28,  3.33it/s]
 87%|████████▋ | 610/705 [02:45<00:26,  3.52it/s]
 87%|████████▋ | 611/705 [02:46<00:25,  3.69it/s]
 87%|████████▋ | 612/705 [02:46<00:24,  3.73it/s]
 87%|████████▋ | 613/705 [02:46<00:24,  3.72it/s]
 87%|████████▋ | 614/705 [02:46<00:24,  3.77it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.79it/s]
 87%|████████▋ | 616/705 [02:47<00:23,  3.82it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.89it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.85it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.95it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.90it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.92it/s]
 88%|████████▊ | 622/705 [02:49<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:49<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.81it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 629/705 [02:50<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:51<00:18,  3.79it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.84it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.83it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.85it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.78it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.78it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.72it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.85it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6903568506240845, 'eval_accuracy': 0.7224, 'eval_f1': 0.7200454635504288, 'eval_runtime': 1.7357, 'eval_samples_per_second': 1440.333, 'eval_steps_per_second': 180.33, 'epoch': 2.0}
{'loss': 0.3174, 'learning_rate': 4.205277893850638e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.77it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.12it/s]

 20%|██        | 63/313 [00:00<00:01, 202.56it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.83it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.10it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.53it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.31it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.50it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.35it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.41it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 167.97it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.90it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.26it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.49it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 178.92it/s]

100%|██████████| 313/313 [00:01<00:00, 175.79it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.79it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  
100%|██████████| 705/705 [03:12<00:00,  3.66it/s]
[I 2023-10-26 23:51:28,076] Trial 41 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.755027711391449, 'eval_accuracy': 0.7156, 'eval_f1': 0.7150970537360714, 'eval_runtime': 1.7348, 'eval_samples_per_second': 1441.086, 'eval_steps_per_second': 180.424, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:10,  3.70it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:52,  3.81it/s]
  7%|▋         | 50/705 [00:13<02:53,  3.78it/s]
  7%|▋         | 51/705 [00:13<02:52,  3.79it/s]
  7%|▋         | 52/705 [00:13<02:53,  3.76it/s]
  8%|▊         | 53/705 [00:13<02:48,  3.86it/s]
  8%|▊         | 54/705 [00:14<02:48,  3.86it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 56/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:49,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.77it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:45,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.84it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:41,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.77it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.75it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 102/705 [00:26<02:41,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:35,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.80it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.79it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.78it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:36,  3.78it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:34,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.81it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.85it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.82it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.89it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.77it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.87it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:39<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:23,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.84it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.87it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:17,  3.89it/s]
 24%|██▍       | 170/705 [00:44<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.84it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.83it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.91it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.87it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.77it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.85it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:06,  3.85it/s]
 31%|███       | 217/705 [00:56<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:05,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.82it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:01,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7913, 'learning_rate': 8.304588104989721e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.41it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.46it/s]

 21%|██        | 66/313 [00:00<00:01, 205.78it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.11it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.33it/s]

 40%|████      | 126/313 [00:00<00:01, 184.95it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.65it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.75it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.90it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.23it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.52it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.23it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.69it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.42it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.47it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.47it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 23:52:32,449] Trial 42 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7044159173965454, 'eval_accuracy': 0.6808, 'eval_f1': 0.6812636956351527, 'eval_runtime': 1.7328, 'eval_samples_per_second': 1442.773, 'eval_steps_per_second': 180.635, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:09,  3.71it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:08,  3.72it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.74it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.81it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:01,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<02:59,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.83it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:52,  3.86it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.76it/s]
  6%|▌         | 44/705 [00:11<02:51,  3.85it/s]
  6%|▋         | 45/705 [00:11<02:53,  3.81it/s]
  7%|▋         | 46/705 [00:12<02:54,  3.77it/s]
  7%|▋         | 47/705 [00:12<02:54,  3.77it/s]
  7%|▋         | 48/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 49/705 [00:12<02:53,  3.77it/s]
  7%|▋         | 50/705 [00:13<02:54,  3.75it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.81it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.84it/s]
 10%|█         | 72/705 [00:18<02:41,  3.93it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:43,  3.85it/s]
 11%|█         | 75/705 [00:19<02:44,  3.82it/s]
 11%|█         | 76/705 [00:19<02:45,  3.79it/s]
 11%|█         | 77/705 [00:20<02:46,  3.78it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.74it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.79it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.87it/s]
 18%|█▊        | 126/705 [00:33<02:30,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.84it/s]
 18%|█▊        | 128/705 [00:33<02:30,  3.84it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.84it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:31,  3.80it/s]
 19%|█▊        | 132/705 [00:34<02:30,  3.81it/s]
 19%|█▉        | 133/705 [00:35<02:31,  3.79it/s]
 19%|█▉        | 134/705 [00:35<02:31,  3.78it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.79it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:31,  3.74it/s]
 20%|█▉        | 140/705 [00:36<02:31,  3.73it/s]
 20%|██        | 141/705 [00:37<02:31,  3.72it/s]
 20%|██        | 142/705 [00:37<02:25,  3.87it/s]
 20%|██        | 143/705 [00:37<02:27,  3.81it/s]
 20%|██        | 144/705 [00:37<02:26,  3.84it/s]
 21%|██        | 145/705 [00:38<02:27,  3.79it/s]
 21%|██        | 146/705 [00:38<02:28,  3.75it/s]
 21%|██        | 147/705 [00:38<02:24,  3.85it/s]
 21%|██        | 148/705 [00:38<02:24,  3.86it/s]
 21%|██        | 149/705 [00:39<02:25,  3.83it/s]
 21%|██▏       | 150/705 [00:39<02:26,  3.78it/s]
 21%|██▏       | 151/705 [00:39<02:25,  3.80it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.84it/s]
 22%|██▏       | 153/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 154/705 [00:40<02:26,  3.77it/s]
 22%|██▏       | 155/705 [00:40<02:26,  3.76it/s]
 22%|██▏       | 156/705 [00:41<02:24,  3.80it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.92it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.87it/s]
 23%|██▎       | 159/705 [00:41<02:23,  3.81it/s]
 23%|██▎       | 160/705 [00:42<02:24,  3.78it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.78it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:21,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:20,  3.83it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:19,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.76it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.84it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.84it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.95it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.77it/s]
 30%|██▉       | 210/705 [00:55<02:13,  3.72it/s]
 30%|██▉       | 211/705 [00:55<02:13,  3.70it/s]
 30%|███       | 212/705 [00:55<02:08,  3.83it/s]
 30%|███       | 213/705 [00:56<02:09,  3.81it/s]
 30%|███       | 214/705 [00:56<02:09,  3.80it/s]
 30%|███       | 215/705 [00:56<02:09,  3.78it/s]
 31%|███       | 216/705 [00:56<02:07,  3.84it/s]
 31%|███       | 217/705 [00:57<02:08,  3.79it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:09,  3.76it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.77it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.81it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.77it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:02,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]{'loss': 0.7977, 'learning_rate': 6.31844716415873e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.59it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.43it/s]

 21%|██        | 65/313 [00:00<00:01, 204.23it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.78it/s]

 34%|███▍      | 106/313 [00:00<00:01, 187.68it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.40it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.02it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 183.88it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.68it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.61it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.59it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.74it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.84it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.47it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.73it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.73it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.60it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-26 23:53:36,571] Trial 43 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.673241913318634, 'eval_accuracy': 0.698, 'eval_f1': 0.694116128499879, 'eval_runtime': 1.7357, 'eval_samples_per_second': 1440.351, 'eval_steps_per_second': 180.332, 'epoch': 1.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:09,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.71it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.78it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.76it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:56,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.80it/s]
  4%|▍         | 31/705 [00:08<02:58,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:58,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:54,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.84it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.84it/s]
  8%|▊         | 55/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:48,  3.85it/s]
  8%|▊         | 58/705 [00:15<02:49,  3.81it/s]
  8%|▊         | 59/705 [00:15<02:51,  3.78it/s]
  9%|▊         | 60/705 [00:15<02:50,  3.77it/s]
  9%|▊         | 61/705 [00:16<02:49,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.91it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:42,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.84it/s]
 11%|█         | 75/705 [00:19<02:45,  3.81it/s]
 11%|█         | 76/705 [00:20<02:46,  3.78it/s]
 11%|█         | 77/705 [00:20<02:46,  3.77it/s]
 11%|█         | 78/705 [00:20<02:43,  3.83it/s]
 11%|█         | 79/705 [00:20<02:45,  3.79it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.78it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.73it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 87/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:42,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.84it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.78it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.79it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:35,  3.81it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.77it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.83it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.82it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:30,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.78it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.79it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.81it/s]
 20%|█▉        | 139/705 [00:36<02:30,  3.77it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.79it/s]
 21%|██        | 146/705 [00:38<02:28,  3.76it/s]
 21%|██        | 147/705 [00:38<02:24,  3.87it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:24,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.80it/s]
 21%|██▏       | 151/705 [00:39<02:25,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.81it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:19,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:20,  3.76it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.84it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.75it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.74it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.75it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.77it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.78it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.75it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.80it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.80it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.77it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.77it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.88it/s]
 30%|███       | 213/705 [00:55<02:07,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.80it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:02,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:42,  4.60it/s]{'loss': 0.8006, 'learning_rate': 4.647549941071595e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.98it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.29it/s]

 20%|██        | 63/313 [00:00<00:01, 202.77it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.96it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.26it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.77it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.29it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.26it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 178.99it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 171.71it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 166.92it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.22it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 179.80it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.21it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 178.87it/s]

100%|██████████| 313/313 [00:01<00:00, 175.92it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.92it/s]
 33%|███▎      | 235/705 [01:03<01:42,  4.60it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:10,  1.05s/it]
 34%|███▎      | 237/705 [01:04<06:18,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:02,  1.54it/s]
 34%|███▍      | 239/705 [01:05<04:07,  1.88it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:05<03:03,  2.53it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.79it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.03it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.26it/s]
 35%|███▍      | 245/705 [01:06<02:15,  3.39it/s]
 35%|███▍      | 246/705 [01:07<02:12,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.69it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.71it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:08<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.06it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.94it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.92it/s]
 36%|███▋      | 256/705 [01:09<01:56,  3.85it/s]
 36%|███▋      | 257/705 [01:10<01:58,  3.79it/s]
 37%|███▋      | 258/705 [01:10<01:56,  3.84it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.82it/s]
 37%|███▋      | 260/705 [01:10<01:57,  3.79it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.84it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.79it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.92it/s]
 37%|███▋      | 264/705 [01:11<01:53,  3.87it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.90it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.86it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:12<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:13<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:13<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.84it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.80it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.03it/s]
 39%|███▉      | 276/705 [01:14<01:47,  4.01it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.98it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:15<01:51,  3.83it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.81it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.80it/s]
 40%|████      | 282/705 [01:16<01:49,  3.85it/s]
 40%|████      | 283/705 [01:16<01:50,  3.82it/s]
 40%|████      | 284/705 [01:17<01:48,  3.86it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:17<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.77it/s]
 41%|████      | 289/705 [01:18<01:48,  3.83it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:18<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.88it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:52,  3.66it/s]
 42%|████▏     | 295/705 [01:20<01:51,  3.68it/s]
 42%|████▏     | 296/705 [01:20<01:49,  3.74it/s]
 42%|████▏     | 297/705 [01:20<01:45,  3.86it/s]
 42%|████▏     | 298/705 [01:20<01:46,  3.83it/s]
 42%|████▏     | 299/705 [01:21<01:46,  3.81it/s]
 43%|████▎     | 300/705 [01:21<01:46,  3.82it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.80it/s]
 43%|████▎     | 303/705 [01:22<01:46,  3.79it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.90it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.94it/s]
 43%|████▎     | 306/705 [01:22<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:23<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:24<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.91it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:25<01:41,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.75it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:27<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:28<01:38,  3.80it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.77it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:30<01:37,  3.77it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:31<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:31<01:37,  3.73it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.72it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.85it/s]
 49%|████▉     | 344/705 [01:32<01:35,  3.80it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:33<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:34<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:34<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.77it/s]
 50%|█████     | 355/705 [01:35<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:32,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:36<01:33,  3.72it/s]
 51%|█████     | 359/705 [01:36<01:32,  3.74it/s]
 51%|█████     | 360/705 [01:37<01:32,  3.75it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.74it/s]
 51%|█████▏    | 362/705 [01:37<01:31,  3.74it/s]
 51%|█████▏    | 363/705 [01:37<01:31,  3.73it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 366/705 [01:38<01:30,  3.74it/s]
 52%|█████▏    | 367/705 [01:38<01:29,  3.79it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.79it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:39<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:39,  3.34it/s]
 53%|█████▎    | 373/705 [01:40<01:36,  3.46it/s]
 53%|█████▎    | 374/705 [01:40<01:33,  3.52it/s]
 53%|█████▎    | 375/705 [01:41<01:31,  3.59it/s]
 53%|█████▎    | 376/705 [01:41<01:30,  3.63it/s]
 53%|█████▎    | 377/705 [01:41<01:27,  3.76it/s]
 54%|█████▎    | 378/705 [01:41<01:26,  3.76it/s]
 54%|█████▍    | 379/705 [01:42<01:26,  3.79it/s]
 54%|█████▍    | 380/705 [01:42<01:25,  3.80it/s]
 54%|█████▍    | 381/705 [01:42<01:25,  3.79it/s]
 54%|█████▍    | 382/705 [01:43<01:25,  3.79it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.82it/s]
 54%|█████▍    | 384/705 [01:43<01:24,  3.78it/s]
 55%|█████▍    | 385/705 [01:43<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.78it/s]
 55%|█████▌    | 388/705 [01:44<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:44<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:45<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:45<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:46<01:21,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.81it/s]
 57%|█████▋    | 403/705 [01:48<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:48<01:16,  3.92it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:49<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:49<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:50<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:50<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.81it/s]
 59%|█████▉    | 415/705 [01:51<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:51<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.82it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:52<01:13,  3.87it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.86it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.81it/s]
 60%|██████    | 423/705 [01:53<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.77it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:54<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:54<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.75it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:55<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:55<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:56<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:57<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:58<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [01:59<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [01:59<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:00<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:00<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:01<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:01<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:02<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:02<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:03<01:04,  3.77it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.76it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:04<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:04<01:03,  3.75it/s]
 66%|██████▌   | 466/705 [02:05<01:04,  3.73it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:05<01:03,  3.74it/s]
 67%|██████▋   | 469/705 [02:05<01:02,  3.78it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.52it/s]{'eval_loss': 0.6651185750961304, 'eval_accuracy': 0.704, 'eval_f1': 0.7024814249021423, 'eval_runtime': 1.7374, 'eval_samples_per_second': 1438.921, 'eval_steps_per_second': 180.153, 'epoch': 1.0}
{'loss': 0.541, 'learning_rate': 1.6744924933579025e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 21/313 [00:00<00:01, 209.88it/s]

 13%|█▎        | 42/313 [00:00<00:01, 198.11it/s]

 20%|██        | 63/313 [00:00<00:01, 202.56it/s]

 27%|██▋       | 84/313 [00:00<00:01, 194.80it/s]

 33%|███▎      | 104/313 [00:00<00:01, 189.09it/s]

 39%|███▉      | 123/313 [00:00<00:01, 184.56it/s]

 45%|████▌     | 142/313 [00:00<00:00, 184.13it/s]

 51%|█████▏    | 161/313 [00:00<00:00, 184.28it/s]

 58%|█████▊    | 180/313 [00:00<00:00, 179.20it/s]

 63%|██████▎   | 198/313 [00:01<00:00, 173.20it/s]

 69%|██████▉   | 216/313 [00:01<00:00, 167.90it/s]

 74%|███████▍  | 233/313 [00:01<00:00, 164.89it/s]

 81%|████████▏ | 255/313 [00:01<00:00, 180.14it/s]

 88%|████████▊ | 275/313 [00:01<00:00, 185.33it/s]

 94%|█████████▍| 294/313 [00:01<00:00, 178.80it/s]

100%|█████████▉| 312/313 [00:01<00:00, 175.12it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 175.12it/s]
 67%|██████▋   | 470/705 [02:07<00:51,  4.52it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:04,  1.05s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.23it/s]
 67%|██████▋   | 473/705 [02:09<02:30,  1.55it/s]
 67%|██████▋   | 474/705 [02:09<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:31,  2.52it/s]
 68%|██████▊   | 477/705 [02:10<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:10<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:11<01:04,  3.50it/s]
 68%|██████▊   | 482/705 [02:11<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:12<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:12<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.82it/s]
 69%|██████▉   | 489/705 [02:13<00:57,  3.78it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:56,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:14<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 496/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:15<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:16<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:16<00:53,  3.83it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:17<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.77it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.79it/s]
 72%|███████▏  | 508/705 [02:18<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.77it/s]
 72%|███████▏  | 511/705 [02:19<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:19<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.75it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:21<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:21<00:48,  3.84it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:22<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:22<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.78it/s]
 75%|███████▍  | 527/705 [02:23<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:24<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.80it/s]
 76%|███████▌  | 534/705 [02:25<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:25<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:26<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:26<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:27<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.81it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 545/705 [02:28<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:28<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 549/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 550/705 [02:29<00:40,  3.85it/s]
 78%|███████▊  | 551/705 [02:30<00:40,  3.82it/s]
 78%|███████▊  | 552/705 [02:30<00:40,  3.80it/s]
 78%|███████▊  | 553/705 [02:30<00:40,  3.77it/s]
 79%|███████▊  | 554/705 [02:30<00:40,  3.74it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.73it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.85it/s]
 79%|███████▉  | 557/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 558/705 [02:31<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 560/705 [02:32<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:32<00:37,  3.86it/s]
 80%|███████▉  | 562/705 [02:32<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:33<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:33<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:34<00:35,  3.90it/s]
 81%|████████  | 569/705 [02:34<00:34,  3.96it/s]
 81%|████████  | 570/705 [02:34<00:34,  3.95it/s]
 81%|████████  | 571/705 [02:35<00:34,  3.93it/s]
 81%|████████  | 572/705 [02:35<00:34,  3.86it/s]
 81%|████████▏ | 573/705 [02:35<00:34,  3.80it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.79it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:36<00:33,  3.84it/s]
 82%|████████▏ | 577/705 [02:36<00:33,  3.82it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.80it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:37<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:37<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:38<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:38<00:33,  3.59it/s]
 83%|████████▎ | 585/705 [02:38<00:32,  3.64it/s]
 83%|████████▎ | 586/705 [02:39<00:32,  3.68it/s]
 83%|████████▎ | 587/705 [02:39<00:31,  3.71it/s]
 83%|████████▎ | 588/705 [02:39<00:31,  3.72it/s]
 84%|████████▎ | 589/705 [02:40<00:31,  3.72it/s]
 84%|████████▎ | 590/705 [02:40<00:30,  3.71it/s]
 84%|████████▍ | 591/705 [02:40<00:30,  3.71it/s]
 84%|████████▍ | 592/705 [02:40<00:29,  3.77it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.76it/s]
 84%|████████▍ | 594/705 [02:41<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:41<00:28,  3.80it/s]
 85%|████████▍ | 596/705 [02:41<00:28,  3.79it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:42<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:42<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:42<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:43<00:26,  3.94it/s]
 86%|████████▌ | 603/705 [02:43<00:26,  3.89it/s]
 86%|████████▌ | 604/705 [02:43<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:44<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:44<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:44<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.86it/s]
 87%|████████▋ | 610/705 [02:45<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:45<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:45<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:46<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:47<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:47<00:21,  3.96it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:48<00:21,  3.86it/s]
 88%|████████▊ | 623/705 [02:48<00:24,  3.39it/s]
 89%|████████▊ | 624/705 [02:49<00:23,  3.52it/s]
 89%|████████▊ | 625/705 [02:49<00:22,  3.59it/s]
 89%|████████▉ | 626/705 [02:49<00:21,  3.64it/s]
 89%|████████▉ | 627/705 [02:50<00:21,  3.67it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.74it/s]
 89%|████████▉ | 629/705 [02:50<00:20,  3.76it/s]
 89%|████████▉ | 630/705 [02:50<00:19,  3.75it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.74it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.73it/s]
 90%|████████▉ | 633/705 [02:51<00:19,  3.78it/s]
 90%|████████▉ | 634/705 [02:51<00:18,  3.83it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.78it/s]
 90%|█████████ | 637/705 [02:52<00:17,  3.78it/s]
 90%|█████████ | 638/705 [02:52<00:17,  3.77it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:53<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.86it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:54<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:54<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:55<00:15,  3.78it/s]
 92%|█████████▏| 649/705 [02:55<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:56<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:56<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:57<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:57<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:58<00:11,  3.85it/s]
 94%|█████████▍| 661/705 [02:58<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [02:59<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [02:59<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:00<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:01<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:01<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:02<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:02<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.78it/s]
 96%|█████████▋| 679/705 [03:03<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:03<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:04<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:04<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:05<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:06<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:06<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:07<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:07<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.75it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:08<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:08<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:09<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:09<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6779348850250244, 'eval_accuracy': 0.7256, 'eval_f1': 0.7234661527588284, 'eval_runtime': 1.7354, 'eval_samples_per_second': 1440.611, 'eval_steps_per_second': 180.364, 'epoch': 2.0}
{'loss': 0.3536, 'learning_rate': 3.373870706108938e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.73it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.70it/s]

 21%|██        | 65/313 [00:00<00:01, 204.70it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.93it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.26it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.96it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.57it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.39it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.97it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.01it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.89it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.02it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.01it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.59it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.73it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.73it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.65it/s]
[I 2023-10-26 23:56:50,472] Trial 44 finished with value: 0.7155751028819379 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 5.496270340077909e-05, 'per_device_train_batch_size': 128, 'weight_decay': 2.4619909546244164e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7235382199287415, 'eval_accuracy': 0.716, 'eval_f1': 0.7155751028819379, 'eval_runtime': 1.7331, 'eval_samples_per_second': 1442.493, 'eval_steps_per_second': 180.6, 'epoch': 3.0}
{'train_runtime': 193.1681, 'train_samples_per_second': 465.916, 'train_steps_per_second': 3.65, 'train_loss': 0.5650573297595302, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.69it/s]
  0%|          | 2/705 [00:00<03:10,  3.70it/s]
  0%|          | 3/705 [00:00<03:09,  3.71it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.82it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.80it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.77it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:02,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:00,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.85it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:54,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:54,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.79it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.76it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.77it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.75it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:45,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:47,  3.84it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.84it/s]
  9%|▉         | 65/705 [00:17<03:10,  3.36it/s]
  9%|▉         | 66/705 [00:17<03:04,  3.46it/s]
 10%|▉         | 67/705 [00:17<03:00,  3.53it/s]
 10%|▉         | 68/705 [00:18<02:55,  3.64it/s]
 10%|▉         | 69/705 [00:18<02:50,  3.73it/s]
 10%|▉         | 70/705 [00:18<02:48,  3.77it/s]
 10%|█         | 71/705 [00:18<02:48,  3.77it/s]
 10%|█         | 72/705 [00:19<02:43,  3.88it/s]
 10%|█         | 73/705 [00:19<02:44,  3.85it/s]
 10%|█         | 74/705 [00:19<02:44,  3.83it/s]
 11%|█         | 75/705 [00:19<02:45,  3.80it/s]
 11%|█         | 76/705 [00:20<02:44,  3.83it/s]
 11%|█         | 77/705 [00:20<02:44,  3.81it/s]
 11%|█         | 78/705 [00:20<02:42,  3.86it/s]
 11%|█         | 79/705 [00:20<02:44,  3.80it/s]
 11%|█▏        | 80/705 [00:21<02:44,  3.79it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.76it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.74it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.77it/s]
 12%|█▏        | 84/705 [00:22<02:54,  3.56it/s]
 12%|█▏        | 85/705 [00:22<02:51,  3.62it/s]
 12%|█▏        | 86/705 [00:22<02:49,  3.64it/s]
 12%|█▏        | 87/705 [00:23<02:48,  3.68it/s]
 12%|█▏        | 88/705 [00:23<02:46,  3.70it/s]
 13%|█▎        | 89/705 [00:23<02:45,  3.72it/s]
 13%|█▎        | 90/705 [00:23<02:45,  3.72it/s]
 13%|█▎        | 91/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 93/705 [00:24<02:43,  3.75it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.75it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.75it/s]
 14%|█▎        | 96/705 [00:25<02:42,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:26<02:41,  3.75it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:27<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<03:00,  3.34it/s]
 15%|█▍        | 104/705 [00:27<02:53,  3.46it/s]
 15%|█▍        | 105/705 [00:27<02:47,  3.59it/s]
 15%|█▌        | 106/705 [00:28<02:42,  3.68it/s]
 15%|█▌        | 107/705 [00:28<02:42,  3.69it/s]
 15%|█▌        | 108/705 [00:28<02:40,  3.71it/s]
 15%|█▌        | 109/705 [00:29<02:39,  3.73it/s]
 16%|█▌        | 110/705 [00:29<02:39,  3.74it/s]
 16%|█▌        | 111/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.76it/s]
 16%|█▌        | 113/705 [00:30<02:35,  3.82it/s]
 16%|█▌        | 114/705 [00:30<02:35,  3.80it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.77it/s]
 16%|█▋        | 116/705 [00:30<02:36,  3.77it/s]
 17%|█▋        | 117/705 [00:31<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:32<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:34<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:35<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:36<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.90it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:39<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:40<02:24,  3.82it/s]
 22%|██▏       | 152/705 [00:40<02:23,  3.86it/s]
 22%|██▏       | 153/705 [00:40<02:25,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.79it/s]
 22%|██▏       | 155/705 [00:41<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:42<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:45<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:46<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.81it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:52<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:54<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:57<02:06,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.84it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.82it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.88it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8123, 'learning_rate': 3.4809757470418174e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.20it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.41it/s]

 21%|██        | 66/313 [00:00<00:01, 205.69it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.05it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.39it/s]

 40%|████      | 126/313 [00:00<00:01, 185.20it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.01it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.94it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.96it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.16it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.43it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.12it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.71it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.44it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.50it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.50it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:08,  1.04s/it]
 34%|███▎      | 237/705 [01:05<06:17,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:01,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:06<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:06<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:12,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:07<02:03,  3.69it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:09<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:10<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.80it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:11<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<01:55,  3.85it/s]
 37%|███▋      | 262/705 [01:11<01:56,  3.81it/s]
 37%|███▋      | 263/705 [01:11<01:52,  3.93it/s]
 37%|███▋      | 264/705 [01:12<01:53,  3.88it/s]
 38%|███▊      | 265/705 [01:12<01:52,  3.91it/s]
 38%|███▊      | 266/705 [01:12<01:53,  3.87it/s]
 38%|███▊      | 267/705 [01:12<01:54,  3.82it/s]
 38%|███▊      | 268/705 [01:13<01:55,  3.78it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.76it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.77it/s]
 38%|███▊      | 271/705 [01:13<01:53,  3.81it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.86it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:14<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.91it/s]
 40%|███▉      | 279/705 [01:15<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<01:51,  3.81it/s]
 40%|████      | 282/705 [01:16<01:49,  3.86it/s]
 40%|████      | 283/705 [01:17<01:50,  3.83it/s]
 40%|████      | 284/705 [01:17<01:48,  3.87it/s]
 40%|████      | 285/705 [01:17<01:49,  3.83it/s]
 41%|████      | 286/705 [01:17<01:50,  3.80it/s]
 41%|████      | 287/705 [01:18<01:49,  3.81it/s]
 41%|████      | 288/705 [01:18<01:50,  3.78it/s]
 41%|████      | 289/705 [01:18<01:48,  3.84it/s]
 41%|████      | 290/705 [01:18<01:48,  3.84it/s]
 41%|████▏     | 291/705 [01:19<01:48,  3.82it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.89it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.85it/s]
 42%|████▏     | 294/705 [01:19<01:47,  3.82it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:46,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:43,  3.93it/s]
 42%|████▏     | 298/705 [01:20<01:45,  3.88it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:21<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:23<01:42,  3.89it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:23<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:24<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:25<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:25<01:39,  3.88it/s]
 45%|████▌     | 318/705 [01:26<01:40,  3.83it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:42,  3.76it/s]
 46%|████▌     | 321/705 [01:26<01:41,  3.78it/s]
 46%|████▌     | 322/705 [01:27<01:41,  3.78it/s]
 46%|████▌     | 323/705 [01:27<01:41,  3.75it/s]
 46%|████▌     | 324/705 [01:27<01:41,  3.74it/s]
 46%|████▌     | 325/705 [01:28<01:40,  3.77it/s]
 46%|████▌     | 326/705 [01:28<01:39,  3.79it/s]
 46%|████▋     | 327/705 [01:28<01:40,  3.76it/s]
 47%|████▋     | 328/705 [01:28<01:40,  3.74it/s]
 47%|████▋     | 329/705 [01:29<01:38,  3.81it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.78it/s]
 47%|████▋     | 331/705 [01:29<01:38,  3.78it/s]
 47%|████▋     | 332/705 [01:29<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:30<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:54,  3.23it/s]
 48%|████▊     | 335/705 [01:30<01:49,  3.39it/s]
 48%|████▊     | 336/705 [01:31<01:45,  3.50it/s]
 48%|████▊     | 337/705 [01:31<01:43,  3.57it/s]
 48%|████▊     | 338/705 [01:31<01:40,  3.64it/s]
 48%|████▊     | 339/705 [01:31<01:40,  3.66it/s]
 48%|████▊     | 340/705 [01:32<01:39,  3.68it/s]
 48%|████▊     | 341/705 [01:32<01:38,  3.68it/s]
 49%|████▊     | 342/705 [01:32<01:34,  3.85it/s]
 49%|████▊     | 343/705 [01:32<01:34,  3.83it/s]
 49%|████▉     | 344/705 [01:33<01:35,  3.79it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.84it/s]
 49%|████▉     | 347/705 [01:33<01:33,  3.83it/s]
 49%|████▉     | 348/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:35<01:33,  3.77it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:48,  3.24it/s]
 50%|█████     | 354/705 [01:35<01:44,  3.37it/s]
 50%|█████     | 355/705 [01:36<01:41,  3.46it/s]
 50%|█████     | 356/705 [01:36<01:38,  3.55it/s]
 51%|█████     | 357/705 [01:36<01:36,  3.59it/s]
 51%|█████     | 358/705 [01:37<01:35,  3.62it/s]
 51%|█████     | 359/705 [01:37<01:34,  3.67it/s]
 51%|█████     | 360/705 [01:37<01:33,  3.70it/s]
 51%|█████     | 361/705 [01:37<01:32,  3.71it/s]
 51%|█████▏    | 362/705 [01:38<01:32,  3.72it/s]
 51%|█████▏    | 363/705 [01:38<01:31,  3.72it/s]
 52%|█████▏    | 364/705 [01:38<01:31,  3.71it/s]
 52%|█████▏    | 365/705 [01:38<01:31,  3.71it/s]
 52%|█████▏    | 366/705 [01:39<01:30,  3.73it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.78it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.78it/s]
 52%|█████▏    | 369/705 [01:39<01:28,  3.78it/s]
 52%|█████▏    | 370/705 [01:40<01:28,  3.80it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.85it/s]
 53%|█████▎    | 372/705 [01:40<01:45,  3.16it/s]
 53%|█████▎    | 373/705 [01:41<01:40,  3.32it/s]
 53%|█████▎    | 374/705 [01:41<01:36,  3.43it/s]
 53%|█████▎    | 375/705 [01:41<01:33,  3.52it/s]
 53%|█████▎    | 376/705 [01:41<01:32,  3.57it/s]
 53%|█████▎    | 377/705 [01:42<01:28,  3.72it/s]
 54%|█████▎    | 378/705 [01:42<01:27,  3.73it/s]
 54%|█████▍    | 379/705 [01:42<01:26,  3.77it/s]
 54%|█████▍    | 380/705 [01:43<01:25,  3.78it/s]
 54%|█████▍    | 381/705 [01:43<01:25,  3.78it/s]
 54%|█████▍    | 382/705 [01:43<01:25,  3.78it/s]
 54%|█████▍    | 383/705 [01:43<01:24,  3.82it/s]
 54%|█████▍    | 384/705 [01:44<01:24,  3.78it/s]
 55%|█████▍    | 385/705 [01:44<01:25,  3.75it/s]
 55%|█████▍    | 386/705 [01:44<01:24,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.78it/s]
 55%|█████▌    | 388/705 [01:45<01:24,  3.75it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:46<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.82it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:47<01:22,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:48<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:49<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.81it/s]
 58%|█████▊    | 407/705 [01:50<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.85it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.81it/s]
 58%|█████▊    | 411/705 [01:51<01:17,  3.79it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.83it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.81it/s]
 59%|█████▉    | 415/705 [01:52<01:16,  3.79it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:53<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.84it/s]
 60%|█████▉    | 422/705 [01:54<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:55<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.78it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:56<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.76it/s]
 61%|██████▏   | 432/705 [01:56<01:12,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:12,  3.78it/s]
 62%|██████▏   | 434/705 [01:57<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:10,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.81it/s]
 62%|██████▏   | 438/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:59<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:59<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [02:00<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:01<01:06,  3.87it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:02<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:03<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:04<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.74it/s]
 66%|██████▌   | 464/705 [02:05<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:06<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6701952219009399, 'eval_accuracy': 0.7012, 'eval_f1': 0.699699268777878, 'eval_runtime': 1.7326, 'eval_samples_per_second': 1442.925, 'eval_steps_per_second': 180.654, 'epoch': 1.0}
{'loss': 0.5652, 'learning_rate': 1.2541807687683429e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.73it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.81it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.04it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.32it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.96it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.59it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.46it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.08it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.93it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.87it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.97it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.12it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.67it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.84it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.84it/s]
 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:04,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.23it/s]
 67%|██████▋   | 473/705 [02:10<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:10<02:02,  1.88it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.21it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:11<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:11<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.20it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:12<01:04,  3.50it/s]
 68%|██████▊   | 482/705 [02:12<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:13<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:14<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:15<00:56,  3.78it/s]
 70%|██████▉   | 493/705 [02:15<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.85it/s]
 70%|███████   | 496/705 [02:16<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:16<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:17<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:17<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.80it/s]
 71%|███████▏  | 504/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.71it/s]
 72%|███████▏  | 506/705 [02:18<00:53,  3.73it/s]
 72%|███████▏  | 507/705 [02:19<00:52,  3.76it/s]
 72%|███████▏  | 508/705 [02:19<00:52,  3.74it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.79it/s]
 72%|███████▏  | 510/705 [02:19<00:51,  3.76it/s]
 72%|███████▏  | 511/705 [02:20<00:51,  3.79it/s]
 73%|███████▎  | 512/705 [02:20<00:50,  3.79it/s]
 73%|███████▎  | 513/705 [02:20<00:50,  3.78it/s]
 73%|███████▎  | 514/705 [02:20<00:50,  3.76it/s]
 73%|███████▎  | 515/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 516/705 [02:21<00:50,  3.76it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.75it/s]
 73%|███████▎  | 518/705 [02:21<00:49,  3.75it/s]
 74%|███████▎  | 519/705 [02:22<00:49,  3.78it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.83it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:23<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:47,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:47,  3.83it/s]
 75%|███████▍  | 526/705 [02:24<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:24<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.75it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.76it/s]
 75%|███████▌  | 530/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:26<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:26<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.77it/s]
 76%|███████▋  | 538/705 [02:27<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:28<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:29<00:53,  3.00it/s]
 77%|███████▋  | 545/705 [02:29<00:50,  3.18it/s]
 77%|███████▋  | 546/705 [02:29<00:47,  3.37it/s]
 78%|███████▊  | 547/705 [02:29<00:45,  3.50it/s]
 78%|███████▊  | 548/705 [02:30<00:43,  3.59it/s]
 78%|███████▊  | 549/705 [02:30<00:42,  3.69it/s]
 78%|███████▊  | 550/705 [02:30<00:41,  3.73it/s]
 78%|███████▊  | 551/705 [02:30<00:41,  3.74it/s]
 78%|███████▊  | 552/705 [02:31<00:40,  3.75it/s]
 78%|███████▊  | 553/705 [02:31<00:40,  3.73it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.72it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.71it/s]
 79%|███████▉  | 556/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 557/705 [02:32<00:38,  3.82it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.83it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.80it/s]
 79%|███████▉  | 560/705 [02:33<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:33<00:37,  3.85it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:34<00:40,  3.53it/s]
 80%|████████  | 564/705 [02:34<00:36,  3.82it/s]
 80%|████████  | 565/705 [02:34<00:35,  3.93it/s]
 80%|████████  | 566/705 [02:34<00:36,  3.86it/s]
 80%|████████  | 567/705 [02:35<00:36,  3.82it/s]
 81%|████████  | 568/705 [02:35<00:35,  3.83it/s]
 81%|████████  | 569/705 [02:35<00:34,  3.91it/s]
 81%|████████  | 570/705 [02:35<00:34,  3.92it/s]
 81%|████████  | 571/705 [02:36<00:34,  3.91it/s]
 81%|████████  | 572/705 [02:36<00:34,  3.84it/s]
 81%|████████▏ | 573/705 [02:36<00:34,  3.80it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.78it/s]
 82%|████████▏ | 575/705 [02:37<00:34,  3.78it/s]
 82%|████████▏ | 576/705 [02:37<00:33,  3.83it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.81it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.79it/s]
 82%|████████▏ | 579/705 [02:38<00:33,  3.76it/s]
 82%|████████▏ | 580/705 [02:38<00:33,  3.74it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.79it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:39<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:39<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:40<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:40<00:31,  3.78it/s]
 83%|████████▎ | 588/705 [02:40<00:31,  3.77it/s]
 84%|████████▎ | 589/705 [02:40<00:30,  3.76it/s]
 84%|████████▎ | 590/705 [02:41<00:30,  3.74it/s]
 84%|████████▍ | 591/705 [02:41<00:30,  3.72it/s]
 84%|████████▍ | 592/705 [02:41<00:29,  3.78it/s]
 84%|████████▍ | 593/705 [02:41<00:29,  3.76it/s]
 84%|████████▍ | 594/705 [02:42<00:29,  3.74it/s]
 84%|████████▍ | 595/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.80it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:43<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:44<00:26,  3.94it/s]
 86%|████████▌ | 603/705 [02:44<00:26,  3.89it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:45<00:25,  3.82it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  4.00it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:46<00:24,  3.86it/s]
 87%|████████▋ | 610/705 [02:46<00:24,  3.92it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:47<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:47<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:48<00:22,  3.93it/s]
 88%|████████▊ | 618/705 [02:48<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:49<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:49<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.83it/s]
 89%|████████▊ | 624/705 [02:49<00:21,  3.84it/s]
 89%|████████▊ | 625/705 [02:50<00:20,  3.82it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.80it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.78it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.82it/s]
 89%|████████▉ | 629/705 [02:51<00:19,  3.81it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.79it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:52<00:18,  3.80it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.85it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:53<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:53<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:54<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:55<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:56<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.80it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:57<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.83it/s]
 93%|█████████▎| 655/705 [02:58<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:58<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.81it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.84it/s]
 93%|█████████▎| 659/705 [02:59<00:12,  3.82it/s]
 94%|█████████▎| 660/705 [02:59<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [03:00<00:11,  3.78it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:02<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:03<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:04<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:04<00:06,  3.77it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:05<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:06<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.83it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.79it/s]
 98%|█████████▊| 690/705 [03:07<00:03,  3.78it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:08<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:08<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:09<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:09<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:10<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:11<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:11<00:00,  4.54it/s]{'eval_loss': 0.6747229695320129, 'eval_accuracy': 0.7224, 'eval_f1': 0.7198357062170154, 'eval_runtime': 1.7325, 'eval_samples_per_second': 1443.022, 'eval_steps_per_second': 180.666, 'epoch': 2.0}
{'loss': 0.4108, 'learning_rate': 2.5270007316827547e-10, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.53it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.65it/s]

 21%|██        | 65/313 [00:00<00:01, 204.65it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.94it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.19it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.95it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.62it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.45it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.02it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.03it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.93it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.02it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.07it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.72it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.06it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.06it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                 

100%|██████████| 705/705 [03:13<00:00,  4.54it/s]
100%|██████████| 705/705 [03:13<00:00,  3.64it/s]
[I 2023-10-27 00:00:05,044] Trial 45 finished with value: 0.7247245830321328 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 4.116660174841519e-05, 'per_device_train_batch_size': 128, 'weight_decay': 4.2461411766251764e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.699777364730835, 'eval_accuracy': 0.7248, 'eval_f1': 0.7247245830321328, 'eval_runtime': 1.7319, 'eval_samples_per_second': 1443.534, 'eval_steps_per_second': 180.73, 'epoch': 3.0}
{'train_runtime': 193.8259, 'train_samples_per_second': 464.334, 'train_steps_per_second': 3.637, 'train_loss': 0.5960881226451684, 'epoch': 3.0}

  0%|          | 0/354 [00:00<?, ?it/s]
  0%|          | 1/354 [00:00<03:03,  1.92it/s]
  1%|          | 2/354 [00:01<03:01,  1.94it/s]
  1%|          | 3/354 [00:01<02:56,  1.99it/s]
  1%|          | 4/354 [00:02<02:53,  2.01it/s]
  1%|▏         | 5/354 [00:02<02:54,  1.99it/s]
  2%|▏         | 6/354 [00:03<02:53,  2.01it/s]
  2%|▏         | 7/354 [00:03<02:49,  2.05it/s]
  2%|▏         | 8/354 [00:03<02:50,  2.03it/s]
  3%|▎         | 9/354 [00:04<02:52,  2.01it/s]
  3%|▎         | 10/354 [00:04<02:50,  2.02it/s]
  3%|▎         | 11/354 [00:05<02:49,  2.02it/s]
  3%|▎         | 12/354 [00:05<02:50,  2.00it/s]
  4%|▎         | 13/354 [00:06<02:50,  1.99it/s]
  4%|▍         | 14/354 [00:06<02:51,  1.98it/s]
  4%|▍         | 15/354 [00:07<02:50,  1.98it/s]
  5%|▍         | 16/354 [00:08<02:50,  1.99it/s]
  5%|▍         | 17/354 [00:08<02:50,  1.98it/s]
  5%|▌         | 18/354 [00:08<02:46,  2.02it/s]
  5%|▌         | 19/354 [00:09<02:46,  2.02it/s]
  6%|▌         | 20/354 [00:09<02:46,  2.01it/s]
  6%|▌         | 21/354 [00:10<02:46,  2.00it/s]
  6%|▌         | 22/354 [00:10<02:46,  1.99it/s]
  6%|▋         | 23/354 [00:11<02:47,  1.98it/s]
  7%|▋         | 24/354 [00:12<02:46,  1.99it/s]
  7%|▋         | 25/354 [00:12<02:46,  1.98it/s]
  7%|▋         | 26/354 [00:13<02:46,  1.97it/s]
  8%|▊         | 27/354 [00:13<02:42,  2.02it/s]
  8%|▊         | 28/354 [00:13<02:41,  2.02it/s]
  8%|▊         | 29/354 [00:14<02:42,  2.00it/s]
  8%|▊         | 30/354 [00:15<02:42,  1.99it/s]
  9%|▉         | 31/354 [00:15<02:39,  2.03it/s]
  9%|▉         | 32/354 [00:15<02:39,  2.01it/s]
  9%|▉         | 33/354 [00:16<02:40,  2.00it/s]
 10%|▉         | 34/354 [00:17<02:40,  1.99it/s]
 10%|▉         | 35/354 [00:17<02:37,  2.03it/s]
 10%|█         | 36/354 [00:17<02:35,  2.05it/s]
 10%|█         | 37/354 [00:18<02:34,  2.05it/s]
 11%|█         | 38/354 [00:18<02:35,  2.03it/s]
 11%|█         | 39/354 [00:19<02:35,  2.03it/s]
 11%|█▏        | 40/354 [00:19<02:36,  2.01it/s]
 12%|█▏        | 41/354 [00:20<02:36,  2.00it/s]
 12%|█▏        | 42/354 [00:20<02:33,  2.03it/s]
 12%|█▏        | 43/354 [00:21<02:34,  2.01it/s]
 12%|█▏        | 44/354 [00:21<02:34,  2.01it/s]
 13%|█▎        | 45/354 [00:22<02:35,  1.99it/s]
 13%|█▎        | 46/354 [00:22<02:34,  1.99it/s]
 13%|█▎        | 47/354 [00:23<02:34,  1.99it/s]
 14%|█▎        | 48/354 [00:23<02:33,  1.99it/s]
 14%|█▍        | 49/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 50/354 [00:24<02:33,  1.98it/s]
 14%|█▍        | 51/354 [00:25<02:33,  1.97it/s]
 15%|█▍        | 52/354 [00:25<02:32,  1.98it/s]
 15%|█▍        | 53/354 [00:26<02:28,  2.03it/s]
 15%|█▌        | 54/354 [00:26<02:29,  2.01it/s]
 16%|█▌        | 55/354 [00:27<02:28,  2.01it/s]
 16%|█▌        | 56/354 [00:27<02:28,  2.00it/s]
 16%|█▌        | 57/354 [00:28<02:26,  2.03it/s]
 16%|█▋        | 58/354 [00:28<02:27,  2.01it/s]
 17%|█▋        | 59/354 [00:29<02:24,  2.04it/s]
 17%|█▋        | 60/354 [00:29<02:26,  2.01it/s]
 17%|█▋        | 61/354 [00:30<02:25,  2.01it/s]
 18%|█▊        | 62/354 [00:30<02:23,  2.04it/s]
 18%|█▊        | 63/354 [00:31<02:21,  2.06it/s]
 18%|█▊        | 64/354 [00:31<02:19,  2.07it/s]
 18%|█▊        | 65/354 [00:32<02:20,  2.06it/s]
 19%|█▊        | 66/354 [00:32<02:20,  2.05it/s]
 19%|█▉        | 67/354 [00:33<02:20,  2.04it/s]
 19%|█▉        | 68/354 [00:33<02:20,  2.03it/s]
 19%|█▉        | 69/354 [00:34<02:18,  2.05it/s]
 20%|█▉        | 70/354 [00:34<02:20,  2.03it/s]
 20%|██        | 71/354 [00:35<02:21,  2.01it/s]
 20%|██        | 72/354 [00:35<02:21,  1.99it/s]
 21%|██        | 73/354 [00:36<02:21,  1.98it/s]
 21%|██        | 74/354 [00:36<02:17,  2.04it/s]
 21%|██        | 75/354 [00:37<02:18,  2.02it/s]
 21%|██▏       | 76/354 [00:37<02:15,  2.05it/s]
 22%|██▏       | 77/354 [00:38<02:17,  2.02it/s]
 22%|██▏       | 78/354 [00:38<02:17,  2.01it/s]
 22%|██▏       | 79/354 [00:39<02:16,  2.01it/s]
 23%|██▎       | 80/354 [00:39<02:17,  1.99it/s]
 23%|██▎       | 81/354 [00:40<02:17,  1.99it/s]
 23%|██▎       | 82/354 [00:40<02:16,  1.99it/s]
 23%|██▎       | 83/354 [00:41<02:14,  2.01it/s]
 24%|██▎       | 84/354 [00:41<02:14,  2.01it/s]
 24%|██▍       | 85/354 [00:42<02:13,  2.02it/s]
 24%|██▍       | 86/354 [00:42<02:13,  2.01it/s]
 25%|██▍       | 87/354 [00:43<02:13,  1.99it/s]
 25%|██▍       | 88/354 [00:43<02:12,  2.00it/s]
 25%|██▌       | 89/354 [00:44<02:13,  1.99it/s]
 25%|██▌       | 90/354 [00:44<02:13,  1.98it/s]
 26%|██▌       | 91/354 [00:45<02:13,  1.97it/s]
 26%|██▌       | 92/354 [00:45<02:12,  1.98it/s]
 26%|██▋       | 93/354 [00:46<02:09,  2.01it/s]
 27%|██▋       | 94/354 [00:46<02:10,  2.00it/s]
 27%|██▋       | 95/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 96/354 [00:47<02:06,  2.04it/s]
 27%|██▋       | 97/354 [00:48<02:06,  2.03it/s]
 28%|██▊       | 98/354 [00:48<02:04,  2.06it/s]
 28%|██▊       | 99/354 [00:49<02:03,  2.07it/s]
 28%|██▊       | 100/354 [00:49<02:01,  2.09it/s]
 29%|██▊       | 101/354 [00:50<02:01,  2.08it/s]
 29%|██▉       | 102/354 [00:50<02:02,  2.06it/s]
 29%|██▉       | 103/354 [00:51<02:02,  2.05it/s]
 29%|██▉       | 104/354 [00:51<02:03,  2.02it/s]
 30%|██▉       | 105/354 [00:52<02:03,  2.01it/s]
 30%|██▉       | 106/354 [00:52<02:04,  1.99it/s]
 30%|███       | 107/354 [00:53<02:03,  2.00it/s]
 31%|███       | 108/354 [00:53<02:03,  2.00it/s]
 31%|███       | 109/354 [00:54<02:03,  1.98it/s]
 31%|███       | 110/354 [00:54<02:01,  2.00it/s]
 31%|███▏      | 111/354 [00:55<02:01,  2.01it/s]
 32%|███▏      | 112/354 [00:55<02:01,  1.99it/s]
 32%|███▏      | 113/354 [00:56<02:01,  1.98it/s]
 32%|███▏      | 114/354 [00:56<01:58,  2.02it/s]
 32%|███▏      | 115/354 [00:57<01:59,  2.01it/s]
 33%|███▎      | 116/354 [00:57<01:59,  1.99it/s]
 33%|███▎      | 117/354 [00:58<01:57,  2.02it/s]
 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]
                                                 

 33%|███▎      | 118/354 [00:58<01:30,  2.62it/s]{'loss': 0.8462, 'learning_rate': 3.465319762153528e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.52it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.72it/s]

 21%|██        | 66/313 [00:00<00:01, 205.92it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.17it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.55it/s]

 40%|████      | 126/313 [00:00<00:01, 185.33it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.13it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.08it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.97it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.13it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.33it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.01it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.72it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.62it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.55it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.55it/s]
 33%|███▎      | 118/354 [01:00<01:30,  2.62it/s]

                                                  
 33%|███▎      | 118/354 [01:00<02:00,  1.97it/s]
[I 2023-10-27 00:01:05,822] Trial 46 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7438437342643738, 'eval_accuracy': 0.658, 'eval_f1': 0.6551946056445461, 'eval_runtime': 1.7321, 'eval_samples_per_second': 1443.304, 'eval_steps_per_second': 180.702, 'epoch': 1.0}

  0%|          | 0/5625 [00:00<?, ?it/s]
  0%|          | 2/5625 [00:00<04:51, 19.29it/s]
  0%|          | 4/5625 [00:00<04:56, 18.94it/s]
  0%|          | 6/5625 [00:00<04:52, 19.22it/s]
  0%|          | 8/5625 [00:00<04:55, 19.00it/s]
  0%|          | 10/5625 [00:00<04:58, 18.83it/s]
  0%|          | 12/5625 [00:00<04:53, 19.15it/s]
  0%|          | 14/5625 [00:00<05:03, 18.52it/s]
  0%|          | 17/5625 [00:00<04:48, 19.44it/s]
  0%|          | 20/5625 [00:01<04:47, 19.52it/s]
  0%|          | 22/5625 [00:01<04:53, 19.11it/s]
  0%|          | 24/5625 [00:01<04:57, 18.83it/s]
  0%|          | 26/5625 [00:01<05:05, 18.35it/s]
  0%|          | 28/5625 [00:01<05:05, 18.30it/s]
  1%|          | 30/5625 [00:01<04:59, 18.67it/s]
  1%|          | 33/5625 [00:01<04:51, 19.21it/s]
  1%|          | 36/5625 [00:01<04:46, 19.48it/s]
  1%|          | 39/5625 [00:02<04:35, 20.27it/s]
  1%|          | 42/5625 [00:02<04:43, 19.66it/s]
  1%|          | 45/5625 [00:02<04:35, 20.26it/s]
  1%|          | 48/5625 [00:02<04:32, 20.48it/s]
  1%|          | 51/5625 [00:02<04:35, 20.23it/s]
  1%|          | 54/5625 [00:02<04:39, 19.96it/s]
  1%|          | 56/5625 [00:02<04:45, 19.50it/s]
  1%|          | 58/5625 [00:02<04:47, 19.35it/s]
  1%|          | 60/5625 [00:03<04:46, 19.41it/s]
  1%|          | 63/5625 [00:03<04:38, 19.98it/s]
  1%|          | 65/5625 [00:03<04:41, 19.73it/s]
  1%|          | 68/5625 [00:03<04:35, 20.17it/s]
  1%|▏         | 71/5625 [00:03<04:34, 20.20it/s]
  1%|▏         | 74/5625 [00:03<04:41, 19.72it/s]
  1%|▏         | 76/5625 [00:03<04:45, 19.42it/s]
  1%|▏         | 78/5625 [00:04<04:55, 18.77it/s]
  1%|▏         | 80/5625 [00:04<04:57, 18.66it/s]
  1%|▏         | 83/5625 [00:04<04:50, 19.07it/s]
  2%|▏         | 86/5625 [00:04<04:43, 19.52it/s]
  2%|▏         | 88/5625 [00:04<04:44, 19.46it/s]
  2%|▏         | 90/5625 [00:04<04:46, 19.29it/s]
  2%|▏         | 92/5625 [00:04<04:50, 19.06it/s]
  2%|▏         | 94/5625 [00:04<04:50, 19.05it/s]
  2%|▏         | 96/5625 [00:04<04:57, 18.59it/s]
  2%|▏         | 99/5625 [00:05<04:49, 19.06it/s]
  2%|▏         | 101/5625 [00:05<04:46, 19.25it/s]
  2%|▏         | 103/5625 [00:05<04:44, 19.43it/s]
  2%|▏         | 105/5625 [00:05<04:47, 19.22it/s]
  2%|▏         | 107/5625 [00:05<04:47, 19.16it/s]
  2%|▏         | 109/5625 [00:05<04:50, 18.98it/s]
  2%|▏         | 112/5625 [00:05<04:40, 19.67it/s]
  2%|▏         | 114/5625 [00:05<04:48, 19.10it/s]
  2%|▏         | 117/5625 [00:06<04:44, 19.35it/s]
  2%|▏         | 119/5625 [00:06<04:43, 19.43it/s]
  2%|▏         | 122/5625 [00:06<04:35, 19.99it/s]
  2%|▏         | 125/5625 [00:06<04:27, 20.55it/s]
  2%|▏         | 128/5625 [00:06<04:39, 19.63it/s]
  2%|▏         | 130/5625 [00:06<04:40, 19.58it/s]
  2%|▏         | 132/5625 [00:06<04:40, 19.59it/s]
  2%|▏         | 134/5625 [00:06<04:46, 19.14it/s]
  2%|▏         | 136/5625 [00:07<04:52, 18.74it/s]
  2%|▏         | 139/5625 [00:07<04:48, 18.99it/s]
  3%|▎         | 141/5625 [00:07<04:55, 18.56it/s]
  3%|▎         | 143/5625 [00:07<04:55, 18.58it/s]
  3%|▎         | 145/5625 [00:07<05:00, 18.26it/s]
  3%|▎         | 147/5625 [00:07<04:54, 18.63it/s]
  3%|▎         | 149/5625 [00:07<04:54, 18.59it/s]
  3%|▎         | 151/5625 [00:07<04:50, 18.87it/s]
  3%|▎         | 154/5625 [00:07<04:45, 19.19it/s]
  3%|▎         | 156/5625 [00:08<04:46, 19.10it/s]
  3%|▎         | 158/5625 [00:08<04:53, 18.65it/s]
  3%|▎         | 161/5625 [00:08<04:36, 19.76it/s]
  3%|▎         | 163/5625 [00:08<04:37, 19.68it/s]
  3%|▎         | 165/5625 [00:08<04:46, 19.03it/s]
  3%|▎         | 167/5625 [00:08<04:47, 19.01it/s]
  3%|▎         | 169/5625 [00:08<04:46, 19.04it/s]
  3%|▎         | 171/5625 [00:08<04:43, 19.25it/s]
  3%|▎         | 173/5625 [00:08<04:44, 19.15it/s]
  3%|▎         | 176/5625 [00:09<04:35, 19.80it/s]
  3%|▎         | 179/5625 [00:09<04:28, 20.25it/s]
  3%|▎         | 182/5625 [00:09<04:30, 20.14it/s]
  3%|▎         | 185/5625 [00:09<04:36, 19.71it/s]
  3%|▎         | 187/5625 [00:09<04:39, 19.43it/s]
  3%|▎         | 190/5625 [00:09<04:39, 19.43it/s]
  3%|▎         | 193/5625 [00:09<04:37, 19.59it/s]
  3%|▎         | 195/5625 [00:10<04:41, 19.29it/s]
  4%|▎         | 197/5625 [00:10<04:42, 19.21it/s]
  4%|▎         | 199/5625 [00:10<04:40, 19.32it/s]
  4%|▎         | 201/5625 [00:10<04:49, 18.74it/s]
  4%|▎         | 204/5625 [00:10<04:32, 19.89it/s]
  4%|▎         | 207/5625 [00:10<04:25, 20.44it/s]
  4%|▎         | 210/5625 [00:10<04:34, 19.73it/s]
  4%|▍         | 212/5625 [00:10<04:34, 19.69it/s]
  4%|▍         | 215/5625 [00:11<04:38, 19.43it/s]
  4%|▍         | 217/5625 [00:11<04:42, 19.14it/s]
  4%|▍         | 220/5625 [00:11<04:36, 19.55it/s]
  4%|▍         | 222/5625 [00:11<04:37, 19.49it/s]
  4%|▍         | 224/5625 [00:11<04:41, 19.17it/s]
  4%|▍         | 227/5625 [00:11<04:41, 19.21it/s]
  4%|▍         | 230/5625 [00:11<04:30, 19.93it/s]
  4%|▍         | 233/5625 [00:12<04:26, 20.24it/s]
  4%|▍         | 236/5625 [00:12<04:36, 19.51it/s]
  4%|▍         | 238/5625 [00:12<04:34, 19.59it/s]
  4%|▍         | 240/5625 [00:12<04:36, 19.50it/s]
  4%|▍         | 242/5625 [00:12<04:44, 18.94it/s]
  4%|▍         | 244/5625 [00:12<04:48, 18.68it/s]
  4%|▍         | 247/5625 [00:12<04:36, 19.44it/s]
  4%|▍         | 249/5625 [00:12<04:34, 19.55it/s]
  4%|▍         | 251/5625 [00:12<04:42, 19.01it/s]
  4%|▍         | 253/5625 [00:13<04:46, 18.77it/s]
  5%|▍         | 255/5625 [00:13<04:42, 19.03it/s]
  5%|▍         | 257/5625 [00:13<04:47, 18.68it/s]
  5%|▍         | 260/5625 [00:13<04:43, 18.95it/s]
  5%|▍         | 263/5625 [00:13<04:32, 19.69it/s]
  5%|▍         | 266/5625 [00:13<04:27, 20.04it/s]
  5%|▍         | 268/5625 [00:13<04:33, 19.56it/s]
  5%|▍         | 271/5625 [00:13<04:33, 19.56it/s]
  5%|▍         | 273/5625 [00:14<04:37, 19.27it/s]
  5%|▍         | 275/5625 [00:14<04:40, 19.06it/s]
  5%|▍         | 277/5625 [00:14<04:42, 18.94it/s]
  5%|▍         | 280/5625 [00:14<04:32, 19.64it/s]
  5%|▌         | 283/5625 [00:14<04:24, 20.18it/s]
  5%|▌         | 286/5625 [00:14<04:32, 19.58it/s]
  5%|▌         | 288/5625 [00:14<04:35, 19.37it/s]
  5%|▌         | 291/5625 [00:15<04:36, 19.27it/s]
  5%|▌         | 294/5625 [00:15<04:35, 19.38it/s]
  5%|▌         | 296/5625 [00:15<04:37, 19.23it/s]
  5%|▌         | 299/5625 [00:15<04:30, 19.70it/s]
  5%|▌         | 301/5625 [00:15<04:34, 19.39it/s]
  5%|▌         | 303/5625 [00:15<04:40, 18.96it/s]
  5%|▌         | 305/5625 [00:15<04:43, 18.77it/s]
  5%|▌         | 308/5625 [00:15<04:35, 19.32it/s]
  6%|▌         | 311/5625 [00:16<04:30, 19.66it/s]
  6%|▌         | 313/5625 [00:16<04:30, 19.62it/s]
  6%|▌         | 315/5625 [00:16<04:30, 19.60it/s]
  6%|▌         | 317/5625 [00:16<04:33, 19.40it/s]
  6%|▌         | 319/5625 [00:16<04:38, 19.04it/s]
  6%|▌         | 321/5625 [00:16<04:36, 19.20it/s]
  6%|▌         | 323/5625 [00:16<04:39, 18.98it/s]
  6%|▌         | 326/5625 [00:16<04:22, 20.19it/s]
  6%|▌         | 329/5625 [00:16<04:22, 20.21it/s]
  6%|▌         | 332/5625 [00:17<04:27, 19.76it/s]
  6%|▌         | 334/5625 [00:17<04:27, 19.78it/s]
  6%|▌         | 337/5625 [00:17<04:23, 20.06it/s]
  6%|▌         | 340/5625 [00:17<04:29, 19.64it/s]
  6%|▌         | 342/5625 [00:17<04:36, 19.12it/s]
  6%|▌         | 344/5625 [00:17<04:40, 18.84it/s]
  6%|▌         | 346/5625 [00:17<04:43, 18.61it/s]
  6%|▌         | 349/5625 [00:18<04:31, 19.42it/s]
  6%|▋         | 352/5625 [00:18<04:29, 19.58it/s]
  6%|▋         | 354/5625 [00:18<04:31, 19.39it/s]
  6%|▋         | 357/5625 [00:18<04:18, 20.38it/s]
  6%|▋         | 360/5625 [00:18<04:31, 19.36it/s]
  6%|▋         | 362/5625 [00:18<04:30, 19.45it/s]
  6%|▋         | 364/5625 [00:18<04:38, 18.86it/s]
  7%|▋         | 366/5625 [00:18<04:39, 18.80it/s]
  7%|▋         | 368/5625 [00:19<04:46, 18.36it/s]
  7%|▋         | 370/5625 [00:19<04:44, 18.45it/s]
  7%|▋         | 372/5625 [00:19<04:39, 18.80it/s]
  7%|▋         | 374/5625 [00:19<04:35, 19.08it/s]
  7%|▋         | 376/5625 [00:19<04:41, 18.64it/s]
  7%|▋         | 378/5625 [00:19<04:37, 18.89it/s]
  7%|▋         | 380/5625 [00:19<04:36, 18.99it/s]
  7%|▋         | 382/5625 [00:19<04:38, 18.80it/s]
  7%|▋         | 385/5625 [00:19<04:25, 19.75it/s]
  7%|▋         | 387/5625 [00:19<04:32, 19.21it/s]
  7%|▋         | 389/5625 [00:20<04:35, 19.03it/s]
  7%|▋         | 391/5625 [00:20<04:31, 19.26it/s]
  7%|▋         | 393/5625 [00:20<04:38, 18.80it/s]
  7%|▋         | 395/5625 [00:20<04:34, 19.07it/s]
  7%|▋         | 397/5625 [00:20<04:31, 19.23it/s]
  7%|▋         | 399/5625 [00:20<04:32, 19.16it/s]
  7%|▋         | 401/5625 [00:20<04:29, 19.39it/s]
  7%|▋         | 403/5625 [00:20<04:30, 19.28it/s]
  7%|▋         | 405/5625 [00:20<04:37, 18.80it/s]
  7%|▋         | 407/5625 [00:21<04:37, 18.80it/s]
  7%|▋         | 409/5625 [00:21<04:33, 19.05it/s]
  7%|▋         | 411/5625 [00:21<04:39, 18.63it/s]
  7%|▋         | 413/5625 [00:21<04:34, 18.96it/s]
  7%|▋         | 416/5625 [00:21<04:23, 19.80it/s]
  7%|▋         | 419/5625 [00:21<04:24, 19.70it/s]
  7%|▋         | 421/5625 [00:21<04:28, 19.40it/s]
  8%|▊         | 423/5625 [00:21<04:26, 19.55it/s]
  8%|▊         | 425/5625 [00:21<04:31, 19.14it/s]
  8%|▊         | 427/5625 [00:22<04:33, 19.03it/s]
  8%|▊         | 429/5625 [00:22<04:30, 19.22it/s]
  8%|▊         | 431/5625 [00:22<04:33, 19.02it/s]
  8%|▊         | 434/5625 [00:22<04:24, 19.65it/s]
  8%|▊         | 437/5625 [00:22<04:15, 20.31it/s]
  8%|▊         | 440/5625 [00:22<04:18, 20.04it/s]
  8%|▊         | 442/5625 [00:22<04:26, 19.48it/s]
  8%|▊         | 445/5625 [00:22<04:21, 19.78it/s]
  8%|▊         | 447/5625 [00:23<04:22, 19.74it/s]
  8%|▊         | 449/5625 [00:23<04:25, 19.46it/s]
  8%|▊         | 451/5625 [00:23<04:30, 19.10it/s]
  8%|▊         | 453/5625 [00:23<04:27, 19.33it/s]
  8%|▊         | 456/5625 [00:23<04:15, 20.25it/s]
  8%|▊         | 459/5625 [00:23<04:29, 19.19it/s]
  8%|▊         | 461/5625 [00:23<04:32, 18.93it/s]
  8%|▊         | 463/5625 [00:23<04:29, 19.13it/s]
  8%|▊         | 465/5625 [00:24<04:35, 18.76it/s]
  8%|▊         | 468/5625 [00:24<04:22, 19.63it/s]
  8%|▊         | 470/5625 [00:24<04:28, 19.23it/s]
  8%|▊         | 473/5625 [00:24<04:23, 19.56it/s]
  8%|▊         | 475/5625 [00:24<04:23, 19.58it/s]
  8%|▊         | 477/5625 [00:24<04:26, 19.29it/s]
  9%|▊         | 480/5625 [00:24<04:20, 19.73it/s]
  9%|▊         | 482/5625 [00:24<04:20, 19.75it/s]
  9%|▊         | 484/5625 [00:25<04:24, 19.45it/s]
  9%|▊         | 486/5625 [00:25<04:30, 18.97it/s]
  9%|▊         | 489/5625 [00:25<04:18, 19.87it/s]
  9%|▊         | 491/5625 [00:25<04:22, 19.53it/s]
  9%|▉         | 494/5625 [00:25<04:09, 20.57it/s]
  9%|▉         | 497/5625 [00:25<04:14, 20.17it/s]
  9%|▉         | 500/5625 [00:25<04:20, 19.69it/s]
  9%|▉         | 502/5625 [00:25<04:27, 19.14it/s]
  9%|▉         | 504/5625 [00:26<04:28, 19.09it/s]
  9%|▉         | 507/5625 [00:26<04:17, 19.86it/s]
  9%|▉         | 510/5625 [00:26<04:14, 20.10it/s]
  9%|▉         | 513/5625 [00:26<04:22, 19.49it/s]
  9%|▉         | 515/5625 [00:26<04:27, 19.08it/s]
  9%|▉         | 517/5625 [00:26<04:32, 18.74it/s]
  9%|▉         | 520/5625 [00:26<04:29, 18.92it/s]
  9%|▉         | 522/5625 [00:26<04:29, 18.96it/s]
  9%|▉         | 524/5625 [00:27<04:31, 18.78it/s]
  9%|▉         | 526/5625 [00:27<04:35, 18.49it/s]
  9%|▉         | 529/5625 [00:27<04:28, 18.98it/s]
  9%|▉         | 531/5625 [00:27<04:33, 18.65it/s]
  9%|▉         | 533/5625 [00:27<04:39, 18.20it/s]
 10%|▉         | 536/5625 [00:27<04:24, 19.22it/s]
 10%|▉         | 539/5625 [00:27<04:20, 19.53it/s]
 10%|▉         | 541/5625 [00:27<04:19, 19.60it/s]
 10%|▉         | 544/5625 [00:28<04:20, 19.47it/s]
 10%|▉         | 546/5625 [00:28<04:21, 19.41it/s]
 10%|▉         | 548/5625 [00:28<04:25, 19.10it/s]
 10%|▉         | 550/5625 [00:28<04:27, 18.99it/s]
 10%|▉         | 553/5625 [00:28<04:21, 19.40it/s]
 10%|▉         | 555/5625 [00:28<04:20, 19.44it/s]
 10%|▉         | 557/5625 [00:28<04:24, 19.16it/s]
 10%|▉         | 559/5625 [00:28<04:24, 19.16it/s]
 10%|▉         | 562/5625 [00:29<04:19, 19.53it/s]
 10%|█         | 564/5625 [00:29<04:25, 19.04it/s]
 10%|█         | 566/5625 [00:29<04:30, 18.70it/s]
 10%|█         | 568/5625 [00:29<04:33, 18.48it/s]
 10%|█         | 570/5625 [00:29<04:33, 18.47it/s]
 10%|█         | 573/5625 [00:29<04:24, 19.07it/s]
 10%|█         | 576/5625 [00:29<04:18, 19.50it/s]
 10%|█         | 578/5625 [00:29<04:22, 19.24it/s]
 10%|█         | 580/5625 [00:30<04:28, 18.81it/s]
 10%|█         | 583/5625 [00:30<04:25, 18.98it/s]
 10%|█         | 585/5625 [00:30<04:30, 18.63it/s]
 10%|█         | 587/5625 [00:30<04:31, 18.58it/s]
 10%|█         | 589/5625 [00:30<04:29, 18.71it/s]
 11%|█         | 592/5625 [00:30<04:20, 19.32it/s]
 11%|█         | 594/5625 [00:30<04:26, 18.90it/s]
 11%|█         | 596/5625 [00:30<04:25, 18.94it/s]
 11%|█         | 598/5625 [00:30<04:23, 19.11it/s]
 11%|█         | 601/5625 [00:31<04:15, 19.66it/s]
 11%|█         | 603/5625 [00:31<04:17, 19.53it/s]
 11%|█         | 605/5625 [00:31<04:24, 18.94it/s]
 11%|█         | 608/5625 [00:31<04:16, 19.59it/s]
 11%|█         | 610/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 612/5625 [00:31<04:18, 19.39it/s]
 11%|█         | 614/5625 [00:31<04:22, 19.06it/s]
 11%|█         | 616/5625 [00:31<04:19, 19.29it/s]
 11%|█         | 618/5625 [00:31<04:24, 18.90it/s]
 11%|█         | 621/5625 [00:32<04:07, 20.18it/s]
 11%|█         | 624/5625 [00:32<04:15, 19.55it/s]
 11%|█         | 626/5625 [00:32<04:21, 19.13it/s]
 11%|█         | 628/5625 [00:32<04:18, 19.33it/s]
 11%|█         | 631/5625 [00:32<04:11, 19.88it/s]
 11%|█▏        | 633/5625 [00:32<04:21, 19.11it/s]
 11%|█▏        | 635/5625 [00:32<04:23, 18.93it/s]
 11%|█▏        | 637/5625 [00:32<04:22, 18.98it/s]
 11%|█▏        | 640/5625 [00:33<04:16, 19.40it/s]
 11%|█▏        | 642/5625 [00:33<04:17, 19.38it/s]
 11%|█▏        | 645/5625 [00:33<04:11, 19.78it/s]
 12%|█▏        | 647/5625 [00:33<04:20, 19.09it/s]
 12%|█▏        | 649/5625 [00:33<04:20, 19.12it/s]
 12%|█▏        | 651/5625 [00:33<04:26, 18.69it/s]
 12%|█▏        | 653/5625 [00:33<04:23, 18.90it/s]
 12%|█▏        | 656/5625 [00:33<04:11, 19.77it/s]
 12%|█▏        | 658/5625 [00:34<04:12, 19.65it/s]
 12%|█▏        | 661/5625 [00:34<04:13, 19.59it/s]
 12%|█▏        | 663/5625 [00:34<04:17, 19.30it/s]
 12%|█▏        | 665/5625 [00:34<04:22, 18.93it/s]
 12%|█▏        | 667/5625 [00:34<04:25, 18.68it/s]
 12%|█▏        | 669/5625 [00:34<04:26, 18.57it/s]
 12%|█▏        | 671/5625 [00:34<04:21, 18.93it/s]
 12%|█▏        | 673/5625 [00:34<04:21, 18.97it/s]
 12%|█▏        | 675/5625 [00:34<04:22, 18.86it/s]
 12%|█▏        | 677/5625 [00:35<04:29, 18.38it/s]
 12%|█▏        | 679/5625 [00:35<04:28, 18.42it/s]
 12%|█▏        | 681/5625 [00:35<04:27, 18.47it/s]
 12%|█▏        | 683/5625 [00:35<04:32, 18.12it/s]
 12%|█▏        | 685/5625 [00:35<04:28, 18.39it/s]
 12%|█▏        | 687/5625 [00:35<04:25, 18.60it/s]
 12%|█▏        | 689/5625 [00:35<04:21, 18.85it/s]
 12%|█▏        | 691/5625 [00:35<04:18, 19.11it/s]
 12%|█▏        | 693/5625 [00:35<04:21, 18.84it/s]
 12%|█▏        | 696/5625 [00:36<04:15, 19.32it/s]
 12%|█▏        | 699/5625 [00:36<04:14, 19.37it/s]
 12%|█▏        | 701/5625 [00:36<04:19, 18.95it/s]
 12%|█▏        | 703/5625 [00:36<04:23, 18.68it/s]
 13%|█▎        | 705/5625 [00:36<04:19, 18.94it/s]
 13%|█▎        | 707/5625 [00:36<04:20, 18.88it/s]
 13%|█▎        | 709/5625 [00:36<04:21, 18.79it/s]
 13%|█▎        | 711/5625 [00:36<04:24, 18.57it/s]
 13%|█▎        | 714/5625 [00:37<04:18, 19.01it/s]
 13%|█▎        | 716/5625 [00:37<04:16, 19.15it/s]
 13%|█▎        | 718/5625 [00:37<04:15, 19.19it/s]
 13%|█▎        | 720/5625 [00:37<04:16, 19.16it/s]
 13%|█▎        | 722/5625 [00:37<04:17, 19.05it/s]
 13%|█▎        | 725/5625 [00:37<04:13, 19.30it/s]
 13%|█▎        | 728/5625 [00:37<04:04, 20.01it/s]
 13%|█▎        | 730/5625 [00:37<04:12, 19.38it/s]
 13%|█▎        | 733/5625 [00:38<04:11, 19.43it/s]
 13%|█▎        | 735/5625 [00:38<04:13, 19.30it/s]
 13%|█▎        | 737/5625 [00:38<04:11, 19.47it/s]
 13%|█▎        | 739/5625 [00:38<04:18, 18.90it/s]
 13%|█▎        | 742/5625 [00:38<04:10, 19.53it/s]
 13%|█▎        | 745/5625 [00:38<04:09, 19.59it/s]
 13%|█▎        | 747/5625 [00:38<04:16, 19.05it/s]
 13%|█▎        | 750/5625 [00:38<04:08, 19.60it/s]
 13%|█▎        | 752/5625 [00:38<04:10, 19.49it/s]
 13%|█▎        | 754/5625 [00:39<04:12, 19.26it/s]
 13%|█▎        | 756/5625 [00:39<04:18, 18.86it/s]
 13%|█▎        | 758/5625 [00:39<04:16, 18.98it/s]
 14%|█▎        | 761/5625 [00:39<04:12, 19.30it/s]
 14%|█▎        | 763/5625 [00:39<04:12, 19.26it/s]
 14%|█▎        | 765/5625 [00:39<04:14, 19.13it/s]
 14%|█▎        | 767/5625 [00:39<04:16, 18.97it/s]
 14%|█▎        | 769/5625 [00:39<04:13, 19.19it/s]
 14%|█▎        | 771/5625 [00:39<04:14, 19.08it/s]
 14%|█▍        | 774/5625 [00:40<04:10, 19.34it/s]
 14%|█▍        | 776/5625 [00:40<04:15, 18.98it/s]
 14%|█▍        | 778/5625 [00:40<04:11, 19.25it/s]
 14%|█▍        | 780/5625 [00:40<04:09, 19.43it/s]
 14%|█▍        | 782/5625 [00:40<04:08, 19.53it/s]
 14%|█▍        | 785/5625 [00:40<04:03, 19.90it/s]
 14%|█▍        | 787/5625 [00:40<04:11, 19.21it/s]
 14%|█▍        | 789/5625 [00:40<04:14, 19.00it/s]
 14%|█▍        | 791/5625 [00:41<04:19, 18.64it/s]
 14%|█▍        | 794/5625 [00:41<04:05, 19.64it/s]
 14%|█▍        | 796/5625 [00:41<04:12, 19.16it/s]
 14%|█▍        | 798/5625 [00:41<04:16, 18.82it/s]
 14%|█▍        | 800/5625 [00:41<04:20, 18.53it/s]
 14%|█▍        | 803/5625 [00:41<04:09, 19.35it/s]
 14%|█▍        | 805/5625 [00:41<04:15, 18.84it/s]
 14%|█▍        | 808/5625 [00:41<04:07, 19.47it/s]
 14%|█▍        | 810/5625 [00:42<04:10, 19.20it/s]
 14%|█▍        | 812/5625 [00:42<04:16, 18.79it/s]
 14%|█▍        | 815/5625 [00:42<04:06, 19.55it/s]
 15%|█▍        | 817/5625 [00:42<04:09, 19.24it/s]
 15%|█▍        | 819/5625 [00:42<04:16, 18.72it/s]
 15%|█▍        | 821/5625 [00:42<04:12, 18.99it/s]
 15%|█▍        | 823/5625 [00:42<04:14, 18.88it/s]
 15%|█▍        | 826/5625 [00:42<04:06, 19.46it/s]
 15%|█▍        | 829/5625 [00:43<04:04, 19.61it/s]
 15%|█▍        | 832/5625 [00:43<03:55, 20.33it/s]
 15%|█▍        | 835/5625 [00:43<03:57, 20.14it/s]
 15%|█▍        | 838/5625 [00:43<04:02, 19.76it/s]
 15%|█▍        | 840/5625 [00:43<04:06, 19.43it/s]
 15%|█▍        | 842/5625 [00:43<04:11, 19.04it/s]
 15%|█▌        | 844/5625 [00:43<04:09, 19.19it/s]
 15%|█▌        | 846/5625 [00:43<04:10, 19.09it/s]
 15%|█▌        | 848/5625 [00:43<04:16, 18.63it/s]
 15%|█▌        | 851/5625 [00:44<04:10, 19.05it/s]
 15%|█▌        | 854/5625 [00:44<04:08, 19.16it/s]
 15%|█▌        | 856/5625 [00:44<04:07, 19.25it/s]
 15%|█▌        | 859/5625 [00:44<04:01, 19.72it/s]
 15%|█▌        | 862/5625 [00:44<04:02, 19.68it/s]
 15%|█▌        | 864/5625 [00:44<04:08, 19.16it/s]
 15%|█▌        | 867/5625 [00:44<03:56, 20.11it/s]
 15%|█▌        | 870/5625 [00:45<03:58, 19.94it/s]
 16%|█▌        | 872/5625 [00:45<03:59, 19.84it/s]
 16%|█▌        | 874/5625 [00:45<04:02, 19.60it/s]
 16%|█▌        | 876/5625 [00:45<04:04, 19.45it/s]
 16%|█▌        | 879/5625 [00:45<04:02, 19.57it/s]
 16%|█▌        | 882/5625 [00:45<03:59, 19.77it/s]
 16%|█▌        | 885/5625 [00:45<03:59, 19.82it/s]
 16%|█▌        | 888/5625 [00:46<03:57, 19.92it/s]
 16%|█▌        | 890/5625 [00:46<04:01, 19.60it/s]
 16%|█▌        | 893/5625 [00:46<04:02, 19.54it/s]
 16%|█▌        | 895/5625 [00:46<04:10, 18.89it/s]
 16%|█▌        | 898/5625 [00:46<03:58, 19.86it/s]
 16%|█▌        | 901/5625 [00:46<03:55, 20.08it/s]
 16%|█▌        | 904/5625 [00:46<03:51, 20.41it/s]
 16%|█▌        | 907/5625 [00:46<03:56, 19.93it/s]
 16%|█▌        | 909/5625 [00:47<04:00, 19.63it/s]
 16%|█▌        | 912/5625 [00:47<03:53, 20.19it/s]
 16%|█▋        | 915/5625 [00:47<03:53, 20.19it/s]
 16%|█▋        | 918/5625 [00:47<03:59, 19.65it/s]
 16%|█▋        | 920/5625 [00:47<04:03, 19.31it/s]
 16%|█▋        | 922/5625 [00:47<04:02, 19.36it/s]
 16%|█▋        | 924/5625 [00:47<04:05, 19.14it/s]
 16%|█▋        | 926/5625 [00:47<04:02, 19.36it/s]
 16%|█▋        | 928/5625 [00:48<04:02, 19.38it/s]
 17%|█▋        | 930/5625 [00:48<04:02, 19.33it/s]
 17%|█▋        | 933/5625 [00:48<03:52, 20.22it/s]
 17%|█▋        | 936/5625 [00:48<03:53, 20.05it/s]
 17%|█▋        | 938/5625 [00:48<03:55, 19.94it/s]
 17%|█▋        | 940/5625 [00:48<03:55, 19.87it/s]
 17%|█▋        | 943/5625 [00:48<03:49, 20.39it/s]
 17%|█▋        | 946/5625 [00:48<03:58, 19.59it/s]
 17%|█▋        | 949/5625 [00:49<03:53, 20.01it/s]
 17%|█▋        | 952/5625 [00:49<03:56, 19.78it/s]
 17%|█▋        | 954/5625 [00:49<03:56, 19.75it/s]
 17%|█▋        | 957/5625 [00:49<03:53, 20.00it/s]
 17%|█▋        | 959/5625 [00:49<03:56, 19.75it/s]
 17%|█▋        | 961/5625 [00:49<04:03, 19.19it/s]
 17%|█▋        | 963/5625 [00:49<04:05, 18.98it/s]
 17%|█▋        | 966/5625 [00:49<03:58, 19.51it/s]
 17%|█▋        | 968/5625 [00:50<03:57, 19.58it/s]
 17%|█▋        | 970/5625 [00:50<03:58, 19.53it/s]
 17%|█▋        | 972/5625 [00:50<04:01, 19.25it/s]
 17%|█▋        | 974/5625 [00:50<03:59, 19.43it/s]
 17%|█▋        | 976/5625 [00:50<04:01, 19.29it/s]
 17%|█▋        | 979/5625 [00:50<03:58, 19.52it/s]
 17%|█▋        | 982/5625 [00:50<03:57, 19.57it/s]
 17%|█▋        | 984/5625 [00:50<04:02, 19.11it/s]
 18%|█▊        | 986/5625 [00:51<04:03, 19.03it/s]
 18%|█▊        | 988/5625 [00:51<04:05, 18.90it/s]
 18%|█▊        | 991/5625 [00:51<03:56, 19.59it/s]
 18%|█▊        | 994/5625 [00:51<03:55, 19.66it/s]
 18%|█▊        | 996/5625 [00:51<03:57, 19.51it/s]
 18%|█▊        | 998/5625 [00:51<03:55, 19.62it/s]
 18%|█▊        | 1000/5625 [00:51<03:55, 19.62it/s]
 18%|█▊        | 1002/5625 [00:51<03:57, 19.49it/s]
 18%|█▊        | 1005/5625 [00:51<03:55, 19.61it/s]
 18%|█▊        | 1008/5625 [00:52<03:48, 20.21it/s]
 18%|█▊        | 1011/5625 [00:52<03:49, 20.07it/s]
 18%|█▊        | 1014/5625 [00:52<03:50, 20.00it/s]
 18%|█▊        | 1016/5625 [00:52<03:56, 19.48it/s]
 18%|█▊        | 1018/5625 [00:52<03:55, 19.54it/s]
 18%|█▊        | 1021/5625 [00:52<03:51, 19.93it/s]
 18%|█▊        | 1023/5625 [00:52<03:55, 19.50it/s]
 18%|█▊        | 1025/5625 [00:52<03:55, 19.54it/s]
 18%|█▊        | 1027/5625 [00:53<03:57, 19.39it/s]
 18%|█▊        | 1030/5625 [00:53<03:57, 19.35it/s]
 18%|█▊        | 1032/5625 [00:53<04:00, 19.12it/s]
 18%|█▊        | 1034/5625 [00:53<04:05, 18.67it/s]
 18%|█▊        | 1037/5625 [00:53<03:57, 19.30it/s]
 18%|█▊        | 1040/5625 [00:53<03:57, 19.28it/s]
 19%|█▊        | 1042/5625 [00:53<03:57, 19.26it/s]
 19%|█▊        | 1044/5625 [00:53<04:03, 18.83it/s]
 19%|█▊        | 1047/5625 [00:54<03:53, 19.62it/s]
 19%|█▊        | 1050/5625 [00:54<03:45, 20.25it/s]
 19%|█▊        | 1053/5625 [00:54<03:48, 20.03it/s]
 19%|█▉        | 1056/5625 [00:54<03:47, 20.07it/s]
 19%|█▉        | 1059/5625 [00:54<03:51, 19.69it/s]
 19%|█▉        | 1061/5625 [00:54<03:51, 19.69it/s]
 19%|█▉        | 1063/5625 [00:54<03:56, 19.33it/s]
 19%|█▉        | 1066/5625 [00:55<03:49, 19.90it/s]
 19%|█▉        | 1068/5625 [00:55<03:52, 19.58it/s]
 19%|█▉        | 1070/5625 [00:55<03:57, 19.15it/s]
 19%|█▉        | 1072/5625 [00:55<03:59, 19.02it/s]
 19%|█▉        | 1074/5625 [00:55<03:58, 19.05it/s]
 19%|█▉        | 1076/5625 [00:55<04:01, 18.86it/s]
 19%|█▉        | 1078/5625 [00:55<04:05, 18.54it/s]
 19%|█▉        | 1081/5625 [00:55<04:00, 18.87it/s]
 19%|█▉        | 1084/5625 [00:56<03:56, 19.23it/s]
 19%|█▉        | 1086/5625 [00:56<03:54, 19.37it/s]
 19%|█▉        | 1089/5625 [00:56<03:45, 20.11it/s]
 19%|█▉        | 1092/5625 [00:56<03:50, 19.70it/s]
 19%|█▉        | 1094/5625 [00:56<03:53, 19.38it/s]
 19%|█▉        | 1096/5625 [00:56<03:52, 19.46it/s]
 20%|█▉        | 1099/5625 [00:56<03:46, 19.96it/s]
 20%|█▉        | 1101/5625 [00:56<03:48, 19.78it/s]
 20%|█▉        | 1104/5625 [00:57<03:50, 19.62it/s]
 20%|█▉        | 1107/5625 [00:57<03:51, 19.50it/s]
 20%|█▉        | 1110/5625 [00:57<03:47, 19.89it/s]
 20%|█▉        | 1113/5625 [00:57<03:42, 20.29it/s]
 20%|█▉        | 1116/5625 [00:57<03:48, 19.69it/s]
 20%|█▉        | 1119/5625 [00:57<03:44, 20.11it/s]
 20%|█▉        | 1122/5625 [00:57<03:54, 19.21it/s]
 20%|█▉        | 1124/5625 [00:58<03:54, 19.23it/s]
 20%|██        | 1126/5625 [00:58<03:53, 19.30it/s]
 20%|██        | 1128/5625 [00:58<03:57, 18.91it/s]
 20%|██        | 1130/5625 [00:58<03:58, 18.86it/s]
 20%|██        | 1133/5625 [00:58<03:47, 19.77it/s]
 20%|██        | 1135/5625 [00:58<03:50, 19.47it/s]
 20%|██        | 1137/5625 [00:58<03:56, 18.98it/s]
 20%|██        | 1139/5625 [00:58<04:00, 18.65it/s]
 20%|██        | 1141/5625 [00:58<03:57, 18.85it/s]
 20%|██        | 1143/5625 [00:59<04:01, 18.53it/s]
 20%|██        | 1146/5625 [00:59<03:48, 19.64it/s]
 20%|██        | 1148/5625 [00:59<03:51, 19.35it/s]
 20%|██        | 1150/5625 [00:59<03:51, 19.34it/s]
 20%|██        | 1153/5625 [00:59<03:42, 20.10it/s]
 21%|██        | 1155/5625 [00:59<03:44, 19.91it/s]
 21%|██        | 1157/5625 [00:59<03:53, 19.12it/s]
 21%|██        | 1159/5625 [00:59<03:59, 18.65it/s]
 21%|██        | 1162/5625 [01:00<03:47, 19.64it/s]
 21%|██        | 1164/5625 [01:00<03:53, 19.08it/s]
 21%|██        | 1166/5625 [01:00<03:56, 18.88it/s]
 21%|██        | 1169/5625 [01:00<03:46, 19.65it/s]
 21%|██        | 1171/5625 [01:00<03:49, 19.39it/s]
 21%|██        | 1173/5625 [01:00<03:52, 19.11it/s]
 21%|██        | 1176/5625 [01:00<03:43, 19.95it/s]
 21%|██        | 1178/5625 [01:00<03:43, 19.93it/s]
 21%|██        | 1180/5625 [01:00<03:45, 19.73it/s]
 21%|██        | 1182/5625 [01:01<03:47, 19.50it/s]
 21%|██        | 1185/5625 [01:01<03:44, 19.80it/s]
 21%|██        | 1188/5625 [01:01<03:44, 19.76it/s]
 21%|██        | 1190/5625 [01:01<03:45, 19.69it/s]
 21%|██        | 1192/5625 [01:01<03:46, 19.59it/s]
 21%|██        | 1194/5625 [01:01<03:49, 19.29it/s]
 21%|██▏       | 1196/5625 [01:01<03:52, 19.01it/s]
 21%|██▏       | 1199/5625 [01:01<03:38, 20.22it/s]
 21%|██▏       | 1202/5625 [01:02<03:32, 20.85it/s]
 21%|██▏       | 1205/5625 [01:02<03:35, 20.54it/s]
 21%|██▏       | 1208/5625 [01:02<03:40, 20.04it/s]
 22%|██▏       | 1211/5625 [01:02<03:40, 20.05it/s]
 22%|██▏       | 1214/5625 [01:02<03:39, 20.13it/s]
 22%|██▏       | 1217/5625 [01:02<03:40, 20.02it/s]
 22%|██▏       | 1220/5625 [01:02<03:35, 20.45it/s]
 22%|██▏       | 1223/5625 [01:03<03:42, 19.77it/s]
 22%|██▏       | 1225/5625 [01:03<03:44, 19.57it/s]
 22%|██▏       | 1227/5625 [01:03<03:51, 18.96it/s]
 22%|██▏       | 1229/5625 [01:03<03:57, 18.50it/s]
 22%|██▏       | 1231/5625 [01:03<03:57, 18.53it/s]
 22%|██▏       | 1233/5625 [01:03<03:58, 18.45it/s]
 22%|██▏       | 1236/5625 [01:03<03:46, 19.39it/s]
 22%|██▏       | 1238/5625 [01:03<03:51, 18.94it/s]
 22%|██▏       | 1241/5625 [01:04<03:44, 19.57it/s]
 22%|██▏       | 1243/5625 [01:04<03:43, 19.63it/s]
 22%|██▏       | 1245/5625 [01:04<03:45, 19.42it/s]
 22%|██▏       | 1248/5625 [01:04<03:43, 19.62it/s]
 22%|██▏       | 1250/5625 [01:04<03:46, 19.29it/s]
 22%|██▏       | 1253/5625 [01:04<03:38, 19.98it/s]
 22%|██▏       | 1256/5625 [01:04<03:34, 20.38it/s]
 22%|██▏       | 1259/5625 [01:04<03:34, 20.34it/s]
 22%|██▏       | 1262/5625 [01:05<03:32, 20.56it/s]
 22%|██▏       | 1265/5625 [01:05<03:36, 20.09it/s]
 23%|██▎       | 1268/5625 [01:05<03:40, 19.75it/s]
 23%|██▎       | 1270/5625 [01:05<03:42, 19.55it/s]
 23%|██▎       | 1272/5625 [01:05<03:41, 19.62it/s]
 23%|██▎       | 1274/5625 [01:05<03:43, 19.45it/s]
 23%|██▎       | 1276/5625 [01:05<03:51, 18.79it/s]
 23%|██▎       | 1278/5625 [01:05<03:56, 18.39it/s]
 23%|██▎       | 1280/5625 [01:06<03:55, 18.48it/s]
 23%|██▎       | 1283/5625 [01:06<03:46, 19.17it/s]
 23%|██▎       | 1286/5625 [01:06<03:38, 19.85it/s]
 23%|██▎       | 1289/5625 [01:06<03:37, 19.96it/s]
 23%|██▎       | 1291/5625 [01:06<03:45, 19.22it/s]
 23%|██▎       | 1293/5625 [01:06<03:48, 18.94it/s]
 23%|██▎       | 1295/5625 [01:06<03:47, 19.04it/s]
 23%|██▎       | 1297/5625 [01:06<03:45, 19.21it/s]
 23%|██▎       | 1299/5625 [01:07<03:44, 19.30it/s]
 23%|██▎       | 1301/5625 [01:07<03:50, 18.73it/s]
 23%|██▎       | 1303/5625 [01:07<03:56, 18.28it/s]
 23%|██▎       | 1305/5625 [01:07<03:56, 18.28it/s]
 23%|██▎       | 1307/5625 [01:07<03:54, 18.40it/s]
 23%|██▎       | 1309/5625 [01:07<03:52, 18.56it/s]
 23%|██▎       | 1312/5625 [01:07<03:41, 19.44it/s]
 23%|██▎       | 1314/5625 [01:07<03:41, 19.47it/s]
 23%|██▎       | 1317/5625 [01:07<03:37, 19.83it/s]
 23%|██▎       | 1319/5625 [01:08<03:40, 19.52it/s]
 23%|██▎       | 1321/5625 [01:08<03:40, 19.52it/s]
 24%|██▎       | 1323/5625 [01:08<03:40, 19.50it/s]
 24%|██▎       | 1325/5625 [01:08<03:43, 19.26it/s]
 24%|██▎       | 1328/5625 [01:08<03:38, 19.63it/s]
 24%|██▎       | 1331/5625 [01:08<03:35, 19.91it/s]
 24%|██▎       | 1333/5625 [01:08<03:40, 19.47it/s]
 24%|██▎       | 1335/5625 [01:08<03:41, 19.33it/s]
 24%|██▍       | 1337/5625 [01:09<03:40, 19.47it/s]
 24%|██▍       | 1340/5625 [01:09<03:41, 19.33it/s]
 24%|██▍       | 1343/5625 [01:09<03:41, 19.31it/s]
 24%|██▍       | 1346/5625 [01:09<03:38, 19.56it/s]
 24%|██▍       | 1348/5625 [01:09<03:38, 19.58it/s]
 24%|██▍       | 1351/5625 [01:09<03:38, 19.59it/s]
 24%|██▍       | 1354/5625 [01:09<03:31, 20.16it/s]
 24%|██▍       | 1357/5625 [01:10<03:30, 20.31it/s]
 24%|██▍       | 1360/5625 [01:10<03:35, 19.81it/s]
 24%|██▍       | 1363/5625 [01:10<03:31, 20.19it/s]
 24%|██▍       | 1366/5625 [01:10<03:35, 19.73it/s]
 24%|██▍       | 1368/5625 [01:10<03:42, 19.17it/s]
 24%|██▍       | 1370/5625 [01:10<03:40, 19.27it/s]
 24%|██▍       | 1372/5625 [01:10<03:46, 18.81it/s]
 24%|██▍       | 1374/5625 [01:10<03:48, 18.63it/s]
 24%|██▍       | 1377/5625 [01:11<03:39, 19.33it/s]
 25%|██▍       | 1379/5625 [01:11<03:42, 19.05it/s]
 25%|██▍       | 1381/5625 [01:11<03:42, 19.07it/s]
 25%|██▍       | 1384/5625 [01:11<03:41, 19.15it/s]
 25%|██▍       | 1386/5625 [01:11<03:39, 19.31it/s]
 25%|██▍       | 1389/5625 [01:11<03:32, 19.91it/s]
 25%|██▍       | 1391/5625 [01:11<03:36, 19.58it/s]
 25%|██▍       | 1393/5625 [01:11<03:35, 19.60it/s]
 25%|██▍       | 1396/5625 [01:12<03:34, 19.75it/s]
 25%|██▍       | 1399/5625 [01:12<03:35, 19.63it/s]
 25%|██▍       | 1402/5625 [01:12<03:28, 20.25it/s]
 25%|██▍       | 1405/5625 [01:12<03:29, 20.10it/s]
 25%|██▌       | 1408/5625 [01:12<03:37, 19.36it/s]
 25%|██▌       | 1410/5625 [01:12<03:37, 19.42it/s]
 25%|██▌       | 1413/5625 [01:12<03:25, 20.47it/s]
 25%|██▌       | 1416/5625 [01:13<03:27, 20.30it/s]
 25%|██▌       | 1419/5625 [01:13<03:35, 19.48it/s]
 25%|██▌       | 1422/5625 [01:13<03:34, 19.56it/s]
 25%|██▌       | 1424/5625 [01:13<03:37, 19.28it/s]
 25%|██▌       | 1427/5625 [01:13<03:34, 19.57it/s]
 25%|██▌       | 1429/5625 [01:13<03:33, 19.62it/s]
 25%|██▌       | 1432/5625 [01:13<03:32, 19.71it/s]
 25%|██▌       | 1434/5625 [01:13<03:35, 19.42it/s]
 26%|██▌       | 1436/5625 [01:14<03:36, 19.33it/s]
 26%|██▌       | 1438/5625 [01:14<03:42, 18.85it/s]
 26%|██▌       | 1440/5625 [01:14<03:46, 18.49it/s]
 26%|██▌       | 1442/5625 [01:14<03:45, 18.55it/s]
 26%|██▌       | 1444/5625 [01:14<03:44, 18.63it/s]
 26%|██▌       | 1446/5625 [01:14<03:42, 18.82it/s]
 26%|██▌       | 1449/5625 [01:14<03:24, 20.39it/s]
 26%|██▌       | 1452/5625 [01:14<03:24, 20.37it/s]
 26%|██▌       | 1455/5625 [01:15<03:33, 19.53it/s]
 26%|██▌       | 1457/5625 [01:15<03:33, 19.56it/s]
 26%|██▌       | 1459/5625 [01:15<03:32, 19.63it/s]
 26%|██▌       | 1461/5625 [01:15<03:34, 19.44it/s]
 26%|██▌       | 1464/5625 [01:15<03:29, 19.83it/s]
 26%|██▌       | 1466/5625 [01:15<03:31, 19.70it/s]
 26%|██▌       | 1468/5625 [01:15<03:32, 19.56it/s]
 26%|██▌       | 1470/5625 [01:15<03:33, 19.42it/s]
 26%|██▌       | 1472/5625 [01:15<03:33, 19.49it/s]
 26%|██▌       | 1474/5625 [01:16<03:33, 19.48it/s]
 26%|██▌       | 1476/5625 [01:16<03:37, 19.05it/s]
 26%|██▋       | 1479/5625 [01:16<03:26, 20.07it/s]
 26%|██▋       | 1481/5625 [01:16<03:31, 19.63it/s]
 26%|██▋       | 1484/5625 [01:16<03:27, 19.95it/s]
 26%|██▋       | 1487/5625 [01:16<03:20, 20.68it/s]
 26%|██▋       | 1490/5625 [01:16<03:28, 19.86it/s]
 27%|██▋       | 1492/5625 [01:16<03:34, 19.23it/s]
 27%|██▋       | 1494/5625 [01:17<03:33, 19.34it/s]
 27%|██▋       | 1496/5625 [01:17<03:35, 19.15it/s]
 27%|██▋       | 1498/5625 [01:17<03:40, 18.74it/s]
 27%|██▋       | 1500/5625 [01:17<03:36, 19.07it/s]
 27%|██▋       | 1502/5625 [01:17<03:33, 19.27it/s]
 27%|██▋       | 1504/5625 [01:17<03:37, 18.95it/s]
 27%|██▋       | 1506/5625 [01:17<03:37, 18.91it/s]
 27%|██▋       | 1508/5625 [01:17<03:40, 18.65it/s]
 27%|██▋       | 1511/5625 [01:17<03:36, 19.04it/s]
 27%|██▋       | 1513/5625 [01:18<03:40, 18.68it/s]
 27%|██▋       | 1515/5625 [01:18<03:40, 18.65it/s]
 27%|██▋       | 1517/5625 [01:18<03:42, 18.47it/s]
 27%|██▋       | 1520/5625 [01:18<03:32, 19.33it/s]
 27%|██▋       | 1523/5625 [01:18<03:30, 19.51it/s]
 27%|██▋       | 1526/5625 [01:18<03:28, 19.66it/s]
 27%|██▋       | 1529/5625 [01:18<03:23, 20.11it/s]
 27%|██▋       | 1532/5625 [01:19<03:28, 19.66it/s]
 27%|██▋       | 1535/5625 [01:19<03:28, 19.57it/s]
 27%|██▋       | 1538/5625 [01:19<03:27, 19.74it/s]
 27%|██▋       | 1540/5625 [01:19<03:27, 19.68it/s]
 27%|██▋       | 1542/5625 [01:19<03:31, 19.35it/s]
 27%|██▋       | 1544/5625 [01:19<03:33, 19.14it/s]
 27%|██▋       | 1546/5625 [01:19<03:31, 19.28it/s]
 28%|██▊       | 1549/5625 [01:19<03:30, 19.35it/s]
 28%|██▊       | 1551/5625 [01:20<03:30, 19.36it/s]
 28%|██▊       | 1554/5625 [01:20<03:26, 19.76it/s]
 28%|██▊       | 1556/5625 [01:20<03:33, 19.10it/s]
 28%|██▊       | 1558/5625 [01:20<03:34, 18.95it/s]
 28%|██▊       | 1560/5625 [01:20<03:33, 19.02it/s]
 28%|██▊       | 1562/5625 [01:20<03:33, 19.00it/s]
 28%|██▊       | 1564/5625 [01:20<03:30, 19.25it/s]
 28%|██▊       | 1566/5625 [01:20<03:35, 18.86it/s]
 28%|██▊       | 1569/5625 [01:20<03:27, 19.51it/s]
 28%|██▊       | 1571/5625 [01:21<03:30, 19.28it/s]
 28%|██▊       | 1573/5625 [01:21<03:28, 19.47it/s]
 28%|██▊       | 1575/5625 [01:21<03:30, 19.25it/s]
 28%|██▊       | 1578/5625 [01:21<03:27, 19.47it/s]
 28%|██▊       | 1581/5625 [01:21<03:19, 20.22it/s]
 28%|██▊       | 1584/5625 [01:21<03:24, 19.73it/s]
 28%|██▊       | 1587/5625 [01:21<03:23, 19.83it/s]
 28%|██▊       | 1589/5625 [01:21<03:26, 19.59it/s]
 28%|██▊       | 1592/5625 [01:22<03:22, 19.90it/s]
 28%|██▊       | 1594/5625 [01:22<03:27, 19.43it/s]
 28%|██▊       | 1596/5625 [01:22<03:29, 19.19it/s]
 28%|██▊       | 1598/5625 [01:22<03:30, 19.14it/s]
 28%|██▊       | 1600/5625 [01:22<03:30, 19.11it/s]
 28%|██▊       | 1602/5625 [01:22<03:34, 18.74it/s]
 29%|██▊       | 1604/5625 [01:22<03:30, 19.06it/s]
 29%|██▊       | 1606/5625 [01:22<03:29, 19.21it/s]
 29%|██▊       | 1608/5625 [01:22<03:27, 19.35it/s]
 29%|██▊       | 1610/5625 [01:23<03:30, 19.06it/s]
 29%|██▊       | 1613/5625 [01:23<03:29, 19.17it/s]
 29%|██▊       | 1616/5625 [01:23<03:22, 19.79it/s]
 29%|██▉       | 1619/5625 [01:23<03:18, 20.17it/s]
 29%|██▉       | 1622/5625 [01:23<03:18, 20.12it/s]
 29%|██▉       | 1625/5625 [01:23<03:23, 19.63it/s]
 29%|██▉       | 1628/5625 [01:23<03:21, 19.87it/s]
 29%|██▉       | 1630/5625 [01:24<03:22, 19.71it/s]
 29%|██▉       | 1633/5625 [01:24<03:17, 20.26it/s]
 29%|██▉       | 1636/5625 [01:24<03:18, 20.06it/s]
 29%|██▉       | 1639/5625 [01:24<03:20, 19.89it/s]
 29%|██▉       | 1641/5625 [01:24<03:21, 19.75it/s]
 29%|██▉       | 1643/5625 [01:24<03:27, 19.23it/s]
 29%|██▉       | 1645/5625 [01:24<03:32, 18.71it/s]
 29%|██▉       | 1648/5625 [01:24<03:24, 19.40it/s]
 29%|██▉       | 1650/5625 [01:25<03:29, 19.00it/s]
 29%|██▉       | 1652/5625 [01:25<03:31, 18.74it/s]
 29%|██▉       | 1654/5625 [01:25<03:33, 18.57it/s]
 29%|██▉       | 1656/5625 [01:25<03:36, 18.37it/s]
 29%|██▉       | 1658/5625 [01:25<03:32, 18.68it/s]
 30%|██▉       | 1660/5625 [01:25<03:33, 18.60it/s]
 30%|██▉       | 1662/5625 [01:25<03:34, 18.48it/s]
 30%|██▉       | 1665/5625 [01:25<03:31, 18.75it/s]
 30%|██▉       | 1667/5625 [01:26<03:32, 18.66it/s]
 30%|██▉       | 1669/5625 [01:26<03:31, 18.70it/s]
 30%|██▉       | 1672/5625 [01:26<03:22, 19.53it/s]
 30%|██▉       | 1674/5625 [01:26<03:26, 19.17it/s]
 30%|██▉       | 1677/5625 [01:26<03:17, 20.00it/s]
 30%|██▉       | 1679/5625 [01:26<03:24, 19.26it/s]
 30%|██▉       | 1681/5625 [01:26<03:23, 19.34it/s]
 30%|██▉       | 1683/5625 [01:26<03:30, 18.70it/s]
 30%|██▉       | 1685/5625 [01:26<03:34, 18.38it/s]
 30%|██▉       | 1687/5625 [01:27<03:32, 18.55it/s]
 30%|███       | 1689/5625 [01:27<03:30, 18.69it/s]
 30%|███       | 1691/5625 [01:27<03:27, 18.97it/s]
 30%|███       | 1694/5625 [01:27<03:18, 19.82it/s]
 30%|███       | 1697/5625 [01:27<03:20, 19.59it/s]
 30%|███       | 1699/5625 [01:27<03:21, 19.46it/s]
 30%|███       | 1701/5625 [01:27<03:27, 18.92it/s]
 30%|███       | 1703/5625 [01:27<03:27, 18.91it/s]
 30%|███       | 1706/5625 [01:28<03:26, 19.02it/s]
 30%|███       | 1708/5625 [01:28<03:27, 18.90it/s]
 30%|███       | 1711/5625 [01:28<03:24, 19.12it/s]
 30%|███       | 1713/5625 [01:28<03:29, 18.70it/s]
 30%|███       | 1715/5625 [01:28<03:32, 18.42it/s]
 31%|███       | 1718/5625 [01:28<03:20, 19.53it/s]
 31%|███       | 1720/5625 [01:28<03:25, 18.97it/s]
 31%|███       | 1722/5625 [01:28<03:25, 18.95it/s]
 31%|███       | 1724/5625 [01:29<03:25, 19.01it/s]
 31%|███       | 1727/5625 [01:29<03:21, 19.37it/s]
 31%|███       | 1729/5625 [01:29<03:20, 19.44it/s]
 31%|███       | 1732/5625 [01:29<03:13, 20.10it/s]
 31%|███       | 1735/5625 [01:29<03:12, 20.24it/s]
 31%|███       | 1738/5625 [01:29<03:16, 19.79it/s]
 31%|███       | 1740/5625 [01:29<03:23, 19.10it/s]
 31%|███       | 1742/5625 [01:29<03:23, 19.07it/s]
 31%|███       | 1745/5625 [01:30<03:20, 19.32it/s]
 31%|███       | 1748/5625 [01:30<03:11, 20.26it/s]
 31%|███       | 1751/5625 [01:30<03:15, 19.77it/s]
 31%|███       | 1753/5625 [01:30<03:18, 19.53it/s]
 31%|███       | 1755/5625 [01:30<03:18, 19.50it/s]
 31%|███       | 1757/5625 [01:30<03:20, 19.31it/s]
 31%|███▏      | 1759/5625 [01:30<03:22, 19.05it/s]
 31%|███▏      | 1761/5625 [01:30<03:23, 18.98it/s]
 31%|███▏      | 1763/5625 [01:31<03:24, 18.89it/s]
 31%|███▏      | 1765/5625 [01:31<03:28, 18.54it/s]
 31%|███▏      | 1767/5625 [01:31<03:26, 18.67it/s]
 31%|███▏      | 1769/5625 [01:31<03:29, 18.42it/s]
 31%|███▏      | 1771/5625 [01:31<03:27, 18.59it/s]
 32%|███▏      | 1774/5625 [01:31<03:19, 19.34it/s]
 32%|███▏      | 1776/5625 [01:31<03:25, 18.76it/s]
 32%|███▏      | 1778/5625 [01:31<03:22, 18.98it/s]
 32%|███▏      | 1780/5625 [01:31<03:20, 19.21it/s]
 32%|███▏      | 1782/5625 [01:32<03:18, 19.35it/s]
 32%|███▏      | 1784/5625 [01:32<03:25, 18.73it/s]
 32%|███▏      | 1786/5625 [01:32<03:24, 18.73it/s]
 32%|███▏      | 1788/5625 [01:32<03:24, 18.76it/s]
 32%|███▏      | 1791/5625 [01:32<03:16, 19.48it/s]
 32%|███▏      | 1794/5625 [01:32<03:15, 19.63it/s]
 32%|███▏      | 1797/5625 [01:32<03:07, 20.39it/s]
 32%|███▏      | 1800/5625 [01:32<03:08, 20.26it/s]
 32%|███▏      | 1803/5625 [01:33<03:07, 20.40it/s]
 32%|███▏      | 1806/5625 [01:33<03:08, 20.24it/s]
 32%|███▏      | 1809/5625 [01:33<03:06, 20.52it/s]
 32%|███▏      | 1812/5625 [01:33<03:06, 20.46it/s]
 32%|███▏      | 1815/5625 [01:33<03:10, 19.99it/s]
 32%|███▏      | 1818/5625 [01:33<03:15, 19.46it/s]
 32%|███▏      | 1820/5625 [01:33<03:14, 19.54it/s]
 32%|███▏      | 1822/5625 [01:34<03:16, 19.33it/s]
 32%|███▏      | 1824/5625 [01:34<03:20, 18.99it/s]
 32%|███▏      | 1827/5625 [01:34<03:15, 19.44it/s]
 33%|███▎      | 1829/5625 [01:34<03:21, 18.88it/s]
 33%|███▎      | 1831/5625 [01:34<03:25, 18.43it/s]
 33%|███▎      | 1834/5625 [01:34<03:21, 18.79it/s]
 33%|███▎      | 1836/5625 [01:34<03:25, 18.41it/s]
 33%|███▎      | 1838/5625 [01:34<03:23, 18.59it/s]
 33%|███▎      | 1841/5625 [01:35<03:20, 18.85it/s]
 33%|███▎      | 1844/5625 [01:35<03:12, 19.65it/s]
 33%|███▎      | 1846/5625 [01:35<03:19, 18.98it/s]
 33%|███▎      | 1848/5625 [01:35<03:20, 18.83it/s]
 33%|███▎      | 1851/5625 [01:35<03:11, 19.69it/s]
 33%|███▎      | 1854/5625 [01:35<03:07, 20.15it/s]
 33%|███▎      | 1857/5625 [01:35<03:07, 20.06it/s]
 33%|███▎      | 1859/5625 [01:35<03:12, 19.54it/s]
 33%|███▎      | 1861/5625 [01:36<03:17, 19.09it/s]
 33%|███▎      | 1863/5625 [01:36<03:16, 19.18it/s]
 33%|███▎      | 1865/5625 [01:36<03:19, 18.82it/s]
 33%|███▎      | 1867/5625 [01:36<03:17, 18.98it/s]
 33%|███▎      | 1869/5625 [01:36<03:21, 18.66it/s]
 33%|███▎      | 1871/5625 [01:36<03:17, 18.99it/s]
 33%|███▎      | 1873/5625 [01:36<03:16, 19.11it/s]
                                                   

 33%|███▎      | 1875/5625 [01:36<03:16, 19.11it/s]{'loss': 0.7816, 'learning_rate': 2.1950423149362004e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.43it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.57it/s]

 21%|██        | 66/313 [00:00<00:01, 205.93it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.21it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.57it/s]

 40%|████      | 126/313 [00:00<00:01, 185.27it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.08it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.11it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.18it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.19it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.28it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.96it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.73it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.61it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.47it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.47it/s]
 33%|███▎      | 1875/5625 [01:38<03:16, 19.11it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 1876/5625 [01:39<24:48,  2.52it/s]
 33%|███▎      | 1878/5625 [01:39<19:00,  3.28it/s]
 33%|███▎      | 1880/5625 [01:39<14:42,  4.24it/s]
 33%|███▎      | 1882/5625 [01:39<11:30,  5.42it/s]
 34%|███▎      | 1885/5625 [01:40<08:23,  7.43it/s]
 34%|███▎      | 1887/5625 [01:40<07:03,  8.83it/s]
 34%|███▎      | 1889/5625 [01:40<06:04, 10.25it/s]
 34%|███▎      | 1891/5625 [01:40<05:17, 11.75it/s]
 34%|███▎      | 1894/5625 [01:40<04:30, 13.80it/s]
 34%|███▎      | 1896/5625 [01:40<04:12, 14.74it/s]
 34%|███▍      | 1899/5625 [01:40<03:45, 16.54it/s]
 34%|███▍      | 1902/5625 [01:40<03:29, 17.74it/s]
 34%|███▍      | 1904/5625 [01:41<03:29, 17.78it/s]
 34%|███▍      | 1906/5625 [01:41<03:24, 18.21it/s]
 34%|███▍      | 1908/5625 [01:41<03:26, 18.04it/s]
 34%|███▍      | 1910/5625 [01:41<03:27, 17.90it/s]
 34%|███▍      | 1912/5625 [01:41<03:21, 18.39it/s]
 34%|███▍      | 1915/5625 [01:41<03:16, 18.86it/s]
 34%|███▍      | 1918/5625 [01:41<03:06, 19.92it/s]
 34%|███▍      | 1921/5625 [01:41<03:13, 19.17it/s]
 34%|███▍      | 1923/5625 [01:42<03:14, 19.07it/s]
 34%|███▍      | 1925/5625 [01:42<03:12, 19.24it/s]
 34%|███▍      | 1927/5625 [01:42<03:14, 19.01it/s]
 34%|███▍      | 1930/5625 [01:42<03:09, 19.51it/s]
 34%|███▍      | 1932/5625 [01:42<03:08, 19.55it/s]
 34%|███▍      | 1934/5625 [01:42<03:10, 19.39it/s]
 34%|███▍      | 1937/5625 [01:42<03:05, 19.93it/s]
 34%|███▍      | 1939/5625 [01:42<03:10, 19.36it/s]
 35%|███▍      | 1942/5625 [01:42<03:06, 19.73it/s]
 35%|███▍      | 1944/5625 [01:43<03:10, 19.30it/s]
 35%|███▍      | 1946/5625 [01:43<03:13, 18.97it/s]
 35%|███▍      | 1949/5625 [01:43<03:12, 19.13it/s]
 35%|███▍      | 1951/5625 [01:43<03:12, 19.06it/s]
 35%|███▍      | 1953/5625 [01:43<03:17, 18.61it/s]
 35%|███▍      | 1955/5625 [01:43<03:16, 18.70it/s]
 35%|███▍      | 1958/5625 [01:43<03:11, 19.20it/s]
 35%|███▍      | 1960/5625 [01:43<03:16, 18.65it/s]
 35%|███▍      | 1963/5625 [01:44<03:12, 19.03it/s]
 35%|███▍      | 1965/5625 [01:44<03:13, 18.90it/s]
 35%|███▍      | 1968/5625 [01:44<03:08, 19.36it/s]
 35%|███▌      | 1970/5625 [01:44<03:10, 19.18it/s]
 35%|███▌      | 1972/5625 [01:44<03:10, 19.13it/s]
 35%|███▌      | 1975/5625 [01:44<03:02, 20.04it/s]
 35%|███▌      | 1977/5625 [01:44<03:02, 19.96it/s]
 35%|███▌      | 1980/5625 [01:44<02:57, 20.50it/s]
 35%|███▌      | 1983/5625 [01:45<03:05, 19.63it/s]
 35%|███▌      | 1986/5625 [01:45<03:04, 19.73it/s]
 35%|███▌      | 1988/5625 [01:45<03:06, 19.55it/s]
 35%|███▌      | 1990/5625 [01:45<03:11, 19.00it/s]
 35%|███▌      | 1992/5625 [01:45<03:11, 18.98it/s]
 35%|███▌      | 1994/5625 [01:45<03:13, 18.75it/s]
 35%|███▌      | 1996/5625 [01:45<03:12, 18.88it/s]
 36%|███▌      | 1999/5625 [01:45<03:04, 19.65it/s]
 36%|███▌      | 2001/5625 [01:46<03:05, 19.56it/s]
 36%|███▌      | 2004/5625 [01:46<03:00, 20.06it/s]
 36%|███▌      | 2006/5625 [01:46<03:00, 20.03it/s]
 36%|███▌      | 2008/5625 [01:46<03:06, 19.42it/s]
 36%|███▌      | 2010/5625 [01:46<03:08, 19.15it/s]
 36%|███▌      | 2012/5625 [01:46<03:08, 19.21it/s]
 36%|███▌      | 2015/5625 [01:46<03:00, 19.99it/s]
 36%|███▌      | 2017/5625 [01:46<03:01, 19.91it/s]
 36%|███▌      | 2019/5625 [01:46<03:03, 19.61it/s]
 36%|███▌      | 2021/5625 [01:47<03:07, 19.21it/s]
 36%|███▌      | 2023/5625 [01:47<03:06, 19.36it/s]
 36%|███▌      | 2025/5625 [01:47<03:04, 19.50it/s]
 36%|███▌      | 2027/5625 [01:47<03:08, 19.07it/s]
 36%|███▌      | 2029/5625 [01:47<03:09, 18.94it/s]
 36%|███▌      | 2031/5625 [01:47<03:12, 18.68it/s]
 36%|███▌      | 2033/5625 [01:47<03:11, 18.78it/s]
 36%|███▌      | 2036/5625 [01:47<03:01, 19.83it/s]
 36%|███▌      | 2038/5625 [01:47<03:03, 19.51it/s]
 36%|███▋      | 2041/5625 [01:48<03:04, 19.39it/s]
 36%|███▋      | 2043/5625 [01:48<03:08, 19.02it/s]
 36%|███▋      | 2045/5625 [01:48<03:09, 18.90it/s]
 36%|███▋      | 2047/5625 [01:48<03:14, 18.37it/s]
 36%|███▋      | 2049/5625 [01:48<03:12, 18.55it/s]
 36%|███▋      | 2051/5625 [01:48<03:09, 18.88it/s]
 37%|███▋      | 2054/5625 [01:48<03:06, 19.16it/s]
 37%|███▋      | 2057/5625 [01:48<03:01, 19.62it/s]
 37%|███▋      | 2059/5625 [01:49<03:02, 19.58it/s]
 37%|███▋      | 2061/5625 [01:49<03:04, 19.32it/s]
 37%|███▋      | 2064/5625 [01:49<03:03, 19.37it/s]
 37%|███▋      | 2067/5625 [01:49<02:56, 20.20it/s]
 37%|███▋      | 2070/5625 [01:49<03:02, 19.44it/s]
 37%|███▋      | 2072/5625 [01:49<03:03, 19.39it/s]
 37%|███▋      | 2074/5625 [01:49<03:07, 18.95it/s]
 37%|███▋      | 2077/5625 [01:49<03:00, 19.70it/s]
 37%|███▋      | 2080/5625 [01:50<02:58, 19.81it/s]
 37%|███▋      | 2082/5625 [01:50<03:02, 19.38it/s]
 37%|███▋      | 2084/5625 [01:50<03:03, 19.25it/s]
 37%|███▋      | 2086/5625 [01:50<03:06, 18.94it/s]
 37%|███▋      | 2088/5625 [01:50<03:10, 18.58it/s]
 37%|███▋      | 2090/5625 [01:50<03:13, 18.28it/s]
 37%|███▋      | 2092/5625 [01:50<03:10, 18.53it/s]
 37%|███▋      | 2095/5625 [01:50<03:04, 19.12it/s]
 37%|███▋      | 2097/5625 [01:51<03:02, 19.30it/s]
 37%|███▋      | 2100/5625 [01:51<02:57, 19.87it/s]
 37%|███▋      | 2102/5625 [01:51<03:00, 19.57it/s]
 37%|███▋      | 2104/5625 [01:51<03:02, 19.26it/s]
 37%|███▋      | 2107/5625 [01:51<02:56, 19.92it/s]
 38%|███▊      | 2110/5625 [01:51<02:57, 19.77it/s]
 38%|███▊      | 2112/5625 [01:51<03:01, 19.32it/s]
 38%|███▊      | 2115/5625 [01:51<02:55, 19.96it/s]
 38%|███▊      | 2118/5625 [01:52<02:58, 19.70it/s]
 38%|███▊      | 2120/5625 [01:52<03:03, 19.14it/s]
 38%|███▊      | 2122/5625 [01:52<03:05, 18.91it/s]
 38%|███▊      | 2124/5625 [01:52<03:07, 18.69it/s]
 38%|███▊      | 2126/5625 [01:52<03:10, 18.41it/s]
 38%|███▊      | 2128/5625 [01:52<03:09, 18.49it/s]
 38%|███▊      | 2130/5625 [01:52<03:08, 18.55it/s]
 38%|███▊      | 2132/5625 [01:52<03:06, 18.69it/s]
 38%|███▊      | 2134/5625 [01:52<03:06, 18.68it/s]
 38%|███▊      | 2136/5625 [01:53<03:17, 17.63it/s]
 38%|███▊      | 2138/5625 [01:53<03:19, 17.49it/s]
 38%|███▊      | 2140/5625 [01:53<03:13, 18.02it/s]
 38%|███▊      | 2142/5625 [01:53<03:07, 18.53it/s]
 38%|███▊      | 2145/5625 [01:53<03:04, 18.90it/s]
 38%|███▊      | 2147/5625 [01:53<03:08, 18.45it/s]
 38%|███▊      | 2149/5625 [01:53<03:11, 18.20it/s]
 38%|███▊      | 2151/5625 [01:53<03:06, 18.67it/s]
 38%|███▊      | 2154/5625 [01:54<03:01, 19.08it/s]
 38%|███▊      | 2156/5625 [01:54<03:04, 18.78it/s]
 38%|███▊      | 2159/5625 [01:54<02:57, 19.56it/s]
 38%|███▊      | 2161/5625 [01:54<02:56, 19.63it/s]
 38%|███▊      | 2164/5625 [01:54<02:53, 20.00it/s]
 39%|███▊      | 2167/5625 [01:54<02:49, 20.40it/s]
 39%|███▊      | 2170/5625 [01:54<02:52, 20.06it/s]
 39%|███▊      | 2173/5625 [01:54<02:51, 20.10it/s]
 39%|███▊      | 2176/5625 [01:55<02:56, 19.56it/s]
 39%|███▊      | 2178/5625 [01:55<02:58, 19.28it/s]
 39%|███▉      | 2180/5625 [01:55<02:57, 19.43it/s]
 39%|███▉      | 2182/5625 [01:55<03:02, 18.85it/s]
 39%|███▉      | 2185/5625 [01:55<02:54, 19.66it/s]
 39%|███▉      | 2187/5625 [01:55<02:54, 19.65it/s]
 39%|███▉      | 2190/5625 [01:55<02:52, 19.89it/s]
 39%|███▉      | 2192/5625 [01:55<02:52, 19.85it/s]
 39%|███▉      | 2195/5625 [01:56<02:47, 20.54it/s]
 39%|███▉      | 2198/5625 [01:56<02:50, 20.11it/s]
 39%|███▉      | 2201/5625 [01:56<02:54, 19.64it/s]
 39%|███▉      | 2203/5625 [01:56<02:58, 19.22it/s]
 39%|███▉      | 2205/5625 [01:56<02:56, 19.33it/s]
 39%|███▉      | 2207/5625 [01:56<02:55, 19.43it/s]
 39%|███▉      | 2209/5625 [01:56<02:54, 19.58it/s]
 39%|███▉      | 2211/5625 [01:56<02:56, 19.34it/s]
 39%|███▉      | 2213/5625 [01:57<02:58, 19.11it/s]
 39%|███▉      | 2216/5625 [01:57<02:54, 19.59it/s]
 39%|███▉      | 2218/5625 [01:57<02:55, 19.47it/s]
 39%|███▉      | 2220/5625 [01:57<02:56, 19.29it/s]
 40%|███▉      | 2222/5625 [01:57<03:00, 18.82it/s]
 40%|███▉      | 2224/5625 [01:57<02:58, 19.01it/s]
 40%|███▉      | 2226/5625 [01:57<03:02, 18.59it/s]
 40%|███▉      | 2228/5625 [01:57<03:00, 18.86it/s]
 40%|███▉      | 2230/5625 [01:57<03:03, 18.47it/s]
 40%|███▉      | 2232/5625 [01:58<04:15, 13.27it/s]
 40%|███▉      | 2234/5625 [01:58<03:52, 14.58it/s]
 40%|███▉      | 2236/5625 [01:58<03:35, 15.71it/s]
 40%|███▉      | 2238/5625 [01:58<03:26, 16.41it/s]
 40%|███▉      | 2240/5625 [01:58<03:23, 16.67it/s]
 40%|███▉      | 2242/5625 [01:58<03:15, 17.31it/s]
 40%|███▉      | 2244/5625 [01:58<03:11, 17.70it/s]
 40%|███▉      | 2246/5625 [01:58<03:08, 17.96it/s]
 40%|███▉      | 2248/5625 [01:59<03:03, 18.38it/s]
 40%|████      | 2250/5625 [01:59<03:01, 18.55it/s]
 40%|████      | 2253/5625 [01:59<02:56, 19.07it/s]
 40%|████      | 2255/5625 [01:59<02:59, 18.81it/s]
 40%|████      | 2257/5625 [01:59<03:02, 18.43it/s]
 40%|████      | 2259/5625 [01:59<03:02, 18.46it/s]
 40%|████      | 2261/5625 [01:59<02:58, 18.88it/s]
 40%|████      | 2264/5625 [01:59<02:48, 19.94it/s]
 40%|████      | 2266/5625 [01:59<02:51, 19.58it/s]
 40%|████      | 2269/5625 [02:00<02:51, 19.55it/s]
 40%|████      | 2271/5625 [02:00<02:53, 19.38it/s]
 40%|████      | 2274/5625 [02:00<02:49, 19.73it/s]
 40%|████      | 2277/5625 [02:00<02:49, 19.77it/s]
 41%|████      | 2279/5625 [02:00<02:53, 19.33it/s]
 41%|████      | 2281/5625 [02:00<02:52, 19.35it/s]
 41%|████      | 2283/5625 [02:00<02:52, 19.39it/s]
 41%|████      | 2285/5625 [02:00<02:52, 19.35it/s]
 41%|████      | 2287/5625 [02:01<02:54, 19.17it/s]
 41%|████      | 2289/5625 [02:01<02:58, 18.74it/s]
 41%|████      | 2292/5625 [02:01<02:52, 19.36it/s]
 41%|████      | 2294/5625 [02:01<02:56, 18.89it/s]
 41%|████      | 2296/5625 [02:01<02:56, 18.83it/s]
 41%|████      | 2298/5625 [02:01<02:58, 18.60it/s]
 41%|████      | 2300/5625 [02:01<02:55, 18.91it/s]
 41%|████      | 2302/5625 [02:01<02:58, 18.65it/s]
 41%|████      | 2305/5625 [02:02<02:48, 19.68it/s]
 41%|████      | 2307/5625 [02:02<02:47, 19.76it/s]
 41%|████      | 2310/5625 [02:02<02:46, 19.86it/s]
 41%|████      | 2312/5625 [02:02<02:51, 19.30it/s]
 41%|████      | 2314/5625 [02:02<02:54, 19.01it/s]
 41%|████      | 2317/5625 [02:02<02:45, 19.98it/s]
 41%|████      | 2320/5625 [02:02<02:39, 20.68it/s]
 41%|████▏     | 2323/5625 [02:02<02:45, 19.96it/s]
 41%|████▏     | 2325/5625 [02:03<02:50, 19.34it/s]
 41%|████▏     | 2327/5625 [02:03<02:51, 19.23it/s]
 41%|████▏     | 2330/5625 [02:03<02:48, 19.52it/s]
 41%|████▏     | 2332/5625 [02:03<02:52, 19.06it/s]
 41%|████▏     | 2334/5625 [02:03<02:51, 19.20it/s]
 42%|████▏     | 2336/5625 [02:03<02:56, 18.69it/s]
 42%|████▏     | 2339/5625 [02:03<02:54, 18.86it/s]
 42%|████▏     | 2341/5625 [02:03<02:58, 18.42it/s]
 42%|████▏     | 2343/5625 [02:03<02:57, 18.48it/s]
 42%|████▏     | 2345/5625 [02:04<02:58, 18.42it/s]
 42%|████▏     | 2347/5625 [02:04<02:54, 18.76it/s]
 42%|████▏     | 2349/5625 [02:04<02:53, 18.90it/s]
 42%|████▏     | 2351/5625 [02:04<02:52, 19.00it/s]
 42%|████▏     | 2353/5625 [02:04<02:53, 18.86it/s]
 42%|████▏     | 2355/5625 [02:04<02:50, 19.15it/s]
 42%|████▏     | 2358/5625 [02:04<02:50, 19.17it/s]
 42%|████▏     | 2361/5625 [02:04<02:47, 19.44it/s]
 42%|████▏     | 2363/5625 [02:05<02:48, 19.39it/s]
 42%|████▏     | 2365/5625 [02:05<02:47, 19.48it/s]
 42%|████▏     | 2367/5625 [02:05<02:48, 19.29it/s]
 42%|████▏     | 2369/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2371/5625 [02:05<02:48, 19.35it/s]
 42%|████▏     | 2374/5625 [02:05<02:44, 19.74it/s]
 42%|████▏     | 2376/5625 [02:05<02:44, 19.70it/s]
 42%|████▏     | 2378/5625 [02:05<02:48, 19.27it/s]
 42%|████▏     | 2380/5625 [02:05<02:53, 18.70it/s]
 42%|████▏     | 2382/5625 [02:06<02:54, 18.55it/s]
 42%|████▏     | 2385/5625 [02:06<02:43, 19.86it/s]
 42%|████▏     | 2387/5625 [02:06<02:42, 19.88it/s]
 42%|████▏     | 2389/5625 [02:06<02:43, 19.82it/s]
 43%|████▎     | 2391/5625 [02:06<02:42, 19.84it/s]
 43%|████▎     | 2393/5625 [02:06<02:46, 19.47it/s]
 43%|████▎     | 2395/5625 [02:06<02:46, 19.35it/s]
 43%|████▎     | 2398/5625 [02:06<02:37, 20.43it/s]
 43%|████▎     | 2401/5625 [02:06<02:42, 19.81it/s]
 43%|████▎     | 2403/5625 [02:07<02:44, 19.56it/s]
 43%|████▎     | 2405/5625 [02:07<02:44, 19.61it/s]
 43%|████▎     | 2407/5625 [02:07<02:44, 19.61it/s]
 43%|████▎     | 2410/5625 [02:07<02:43, 19.72it/s]
 43%|████▎     | 2413/5625 [02:07<02:41, 19.88it/s]
 43%|████▎     | 2415/5625 [02:07<02:47, 19.21it/s]
 43%|████▎     | 2418/5625 [02:07<02:40, 19.93it/s]
 43%|████▎     | 2420/5625 [02:07<02:44, 19.46it/s]
 43%|████▎     | 2422/5625 [02:08<02:44, 19.42it/s]
 43%|████▎     | 2425/5625 [02:08<02:43, 19.59it/s]
 43%|████▎     | 2427/5625 [02:08<03:09, 16.83it/s]
 43%|████▎     | 2429/5625 [02:08<03:02, 17.51it/s]
 43%|████▎     | 2432/5625 [02:08<02:47, 19.02it/s]
 43%|████▎     | 2435/5625 [02:08<02:39, 19.97it/s]
 43%|████▎     | 2438/5625 [02:08<02:38, 20.10it/s]
 43%|████▎     | 2441/5625 [02:09<02:39, 19.93it/s]
 43%|████▎     | 2444/5625 [02:09<02:40, 19.86it/s]
 43%|████▎     | 2446/5625 [02:09<02:42, 19.59it/s]
 44%|████▎     | 2448/5625 [02:09<02:41, 19.63it/s]
 44%|████▎     | 2451/5625 [02:09<02:41, 19.70it/s]
 44%|████▎     | 2454/5625 [02:09<02:36, 20.29it/s]
 44%|████▎     | 2457/5625 [02:09<02:39, 19.82it/s]
 44%|████▎     | 2460/5625 [02:09<02:39, 19.89it/s]
 44%|████▍     | 2462/5625 [02:10<02:41, 19.54it/s]
 44%|████▍     | 2465/5625 [02:10<02:38, 19.91it/s]
 44%|████▍     | 2467/5625 [02:10<02:42, 19.42it/s]
 44%|████▍     | 2469/5625 [02:10<02:41, 19.53it/s]
 44%|████▍     | 2471/5625 [02:10<02:42, 19.43it/s]
 44%|████▍     | 2474/5625 [02:10<02:39, 19.74it/s]
 44%|████▍     | 2476/5625 [02:10<02:39, 19.72it/s]
 44%|████▍     | 2478/5625 [02:10<02:45, 19.05it/s]
 44%|████▍     | 2480/5625 [02:11<02:43, 19.25it/s]
 44%|████▍     | 2483/5625 [02:11<02:35, 20.16it/s]
 44%|████▍     | 2486/5625 [02:11<02:37, 19.98it/s]
 44%|████▍     | 2488/5625 [02:11<02:42, 19.32it/s]
 44%|████▍     | 2490/5625 [02:11<02:43, 19.13it/s]
 44%|████▍     | 2492/5625 [02:11<02:47, 18.70it/s]
 44%|████▍     | 2495/5625 [02:11<02:43, 19.09it/s]
 44%|████▍     | 2497/5625 [02:11<02:46, 18.74it/s]
 44%|████▍     | 2499/5625 [02:12<02:46, 18.75it/s]
 44%|████▍     | 2502/5625 [02:12<02:38, 19.68it/s]
 45%|████▍     | 2504/5625 [02:12<02:38, 19.71it/s]
 45%|████▍     | 2507/5625 [02:12<02:30, 20.65it/s]
 45%|████▍     | 2510/5625 [02:12<02:36, 19.88it/s]
 45%|████▍     | 2513/5625 [02:12<02:31, 20.54it/s]
 45%|████▍     | 2516/5625 [02:12<02:30, 20.67it/s]
 45%|████▍     | 2519/5625 [02:12<02:30, 20.69it/s]
 45%|████▍     | 2522/5625 [02:13<02:36, 19.84it/s]
 45%|████▍     | 2525/5625 [02:13<02:32, 20.27it/s]
 45%|████▍     | 2528/5625 [02:13<02:38, 19.59it/s]
 45%|████▍     | 2530/5625 [02:13<02:38, 19.47it/s]
 45%|████▌     | 2532/5625 [02:13<02:42, 19.08it/s]
 45%|████▌     | 2534/5625 [02:13<02:45, 18.71it/s]
 45%|████▌     | 2536/5625 [02:13<02:45, 18.67it/s]
 45%|████▌     | 2538/5625 [02:14<02:47, 18.41it/s]
 45%|████▌     | 2540/5625 [02:14<02:50, 18.14it/s]
 45%|████▌     | 2542/5625 [02:14<02:47, 18.44it/s]
 45%|████▌     | 2545/5625 [02:14<02:39, 19.28it/s]
 45%|████▌     | 2547/5625 [02:14<02:42, 18.90it/s]
 45%|████▌     | 2549/5625 [02:14<02:42, 18.89it/s]
 45%|████▌     | 2551/5625 [02:14<02:41, 19.03it/s]
 45%|████▌     | 2553/5625 [02:14<02:39, 19.29it/s]
 45%|████▌     | 2555/5625 [02:14<02:40, 19.08it/s]
 45%|████▌     | 2557/5625 [02:14<02:39, 19.27it/s]
 45%|████▌     | 2559/5625 [02:15<02:40, 19.06it/s]
 46%|████▌     | 2561/5625 [02:15<02:40, 19.14it/s]
 46%|████▌     | 2563/5625 [02:15<02:39, 19.21it/s]
 46%|████▌     | 2565/5625 [02:15<02:43, 18.70it/s]
 46%|████▌     | 2568/5625 [02:15<02:39, 19.14it/s]
 46%|████▌     | 2571/5625 [02:15<02:33, 19.86it/s]
 46%|████▌     | 2574/5625 [02:15<02:33, 19.84it/s]
 46%|████▌     | 2576/5625 [02:15<02:39, 19.13it/s]
 46%|████▌     | 2579/5625 [02:16<02:37, 19.34it/s]
 46%|████▌     | 2581/5625 [02:16<02:40, 19.00it/s]
 46%|████▌     | 2583/5625 [02:16<02:44, 18.55it/s]
 46%|████▌     | 2586/5625 [02:16<02:39, 19.10it/s]
 46%|████▌     | 2589/5625 [02:16<02:33, 19.78it/s]
 46%|████▌     | 2591/5625 [02:16<02:37, 19.24it/s]
 46%|████▌     | 2594/5625 [02:16<02:36, 19.33it/s]
 46%|████▌     | 2596/5625 [02:17<02:39, 18.98it/s]
 46%|████▌     | 2598/5625 [02:17<02:43, 18.55it/s]
 46%|████▌     | 2601/5625 [02:17<02:38, 19.03it/s]
 46%|████▋     | 2603/5625 [02:17<02:41, 18.69it/s]
 46%|████▋     | 2605/5625 [02:17<02:45, 18.29it/s]
 46%|████▋     | 2607/5625 [02:17<02:43, 18.50it/s]
 46%|████▋     | 2609/5625 [02:17<02:42, 18.57it/s]
 46%|████▋     | 2611/5625 [02:17<02:45, 18.23it/s]
 46%|████▋     | 2613/5625 [02:17<02:44, 18.27it/s]
 47%|████▋     | 2616/5625 [02:18<02:39, 18.86it/s]
 47%|████▋     | 2618/5625 [02:18<02:39, 18.88it/s]
 47%|████▋     | 2620/5625 [02:18<02:40, 18.73it/s]
 47%|████▋     | 2623/5625 [02:18<02:36, 19.16it/s]
 47%|████▋     | 2625/5625 [02:18<02:37, 19.05it/s]
 47%|████▋     | 2627/5625 [02:18<02:39, 18.80it/s]
 47%|████▋     | 2629/5625 [02:18<02:40, 18.72it/s]
 47%|████▋     | 2632/5625 [02:18<02:34, 19.35it/s]
 47%|████▋     | 2634/5625 [02:19<02:36, 19.12it/s]
 47%|████▋     | 2636/5625 [02:19<02:36, 19.05it/s]
 47%|████▋     | 2638/5625 [02:19<02:34, 19.29it/s]
 47%|████▋     | 2640/5625 [02:19<02:35, 19.21it/s]
 47%|████▋     | 2643/5625 [02:19<02:29, 19.91it/s]
 47%|████▋     | 2645/5625 [02:19<02:30, 19.77it/s]
 47%|████▋     | 2647/5625 [02:19<02:33, 19.39it/s]
 47%|████▋     | 2649/5625 [02:19<02:34, 19.31it/s]
 47%|████▋     | 2651/5625 [02:19<02:36, 18.97it/s]
 47%|████▋     | 2653/5625 [02:20<02:39, 18.63it/s]
 47%|████▋     | 2655/5625 [02:20<02:40, 18.56it/s]
 47%|████▋     | 2658/5625 [02:20<02:31, 19.53it/s]
 47%|████▋     | 2661/5625 [02:20<02:26, 20.24it/s]
 47%|████▋     | 2664/5625 [02:20<02:27, 20.08it/s]
 47%|████▋     | 2666/5625 [02:20<02:30, 19.67it/s]
 47%|████▋     | 2669/5625 [02:20<02:27, 20.03it/s]
 47%|████▋     | 2671/5625 [02:20<02:29, 19.76it/s]
 48%|████▊     | 2673/5625 [02:21<02:29, 19.71it/s]
 48%|████▊     | 2676/5625 [02:21<02:29, 19.67it/s]
 48%|████▊     | 2678/5625 [02:21<02:32, 19.32it/s]
 48%|████▊     | 2680/5625 [02:21<02:32, 19.32it/s]
 48%|████▊     | 2682/5625 [02:21<02:31, 19.42it/s]
 48%|████▊     | 2684/5625 [02:21<02:32, 19.31it/s]
 48%|████▊     | 2686/5625 [02:21<02:30, 19.48it/s]
 48%|████▊     | 2688/5625 [02:21<02:31, 19.41it/s]
 48%|████▊     | 2691/5625 [02:21<02:30, 19.45it/s]
 48%|████▊     | 2693/5625 [02:22<02:34, 18.98it/s]
 48%|████▊     | 2696/5625 [02:22<02:27, 19.81it/s]
 48%|████▊     | 2699/5625 [02:22<02:24, 20.26it/s]
 48%|████▊     | 2702/5625 [02:22<02:27, 19.87it/s]
 48%|████▊     | 2704/5625 [02:22<02:29, 19.52it/s]
 48%|████▊     | 2706/5625 [02:22<02:33, 19.02it/s]
 48%|████▊     | 2709/5625 [02:22<02:30, 19.38it/s]
 48%|████▊     | 2711/5625 [02:23<02:33, 18.93it/s]
 48%|████▊     | 2713/5625 [02:23<02:34, 18.89it/s]
 48%|████▊     | 2715/5625 [02:23<02:37, 18.47it/s]
 48%|████▊     | 2717/5625 [02:23<02:34, 18.78it/s]
 48%|████▊     | 2719/5625 [02:23<02:38, 18.36it/s]
 48%|████▊     | 2721/5625 [02:23<02:35, 18.69it/s]
 48%|████▊     | 2723/5625 [02:23<02:35, 18.68it/s]
 48%|████▊     | 2725/5625 [02:23<02:33, 18.85it/s]
 48%|████▊     | 2727/5625 [02:23<02:31, 19.12it/s]
 49%|████▊     | 2730/5625 [02:24<02:28, 19.54it/s]
 49%|████▊     | 2732/5625 [02:24<02:29, 19.37it/s]
 49%|████▊     | 2734/5625 [02:24<02:32, 18.97it/s]
 49%|████▊     | 2737/5625 [02:24<02:26, 19.76it/s]
 49%|████▊     | 2739/5625 [02:24<02:26, 19.65it/s]
 49%|████▊     | 2741/5625 [02:24<02:29, 19.28it/s]
 49%|████▉     | 2743/5625 [02:24<02:31, 19.02it/s]
 49%|████▉     | 2746/5625 [02:24<02:29, 19.29it/s]
 49%|████▉     | 2748/5625 [02:24<02:28, 19.38it/s]
 49%|████▉     | 2750/5625 [02:25<02:27, 19.47it/s]
 49%|████▉     | 2752/5625 [02:25<02:27, 19.44it/s]
 49%|████▉     | 2754/5625 [02:25<02:28, 19.30it/s]
 49%|████▉     | 2757/5625 [02:25<02:29, 19.22it/s]
 49%|████▉     | 2760/5625 [02:25<02:25, 19.70it/s]
 49%|████▉     | 2762/5625 [02:25<02:27, 19.45it/s]
 49%|████▉     | 2764/5625 [02:25<02:30, 18.99it/s]
 49%|████▉     | 2767/5625 [02:25<02:25, 19.62it/s]
 49%|████▉     | 2770/5625 [02:26<02:24, 19.77it/s]
 49%|████▉     | 2772/5625 [02:26<02:28, 19.27it/s]
 49%|████▉     | 2774/5625 [02:26<02:27, 19.33it/s]
 49%|████▉     | 2776/5625 [02:26<02:26, 19.45it/s]
 49%|████▉     | 2778/5625 [02:26<02:28, 19.22it/s]
 49%|████▉     | 2780/5625 [02:26<02:29, 19.02it/s]
 49%|████▉     | 2783/5625 [02:26<02:27, 19.23it/s]
 50%|████▉     | 2785/5625 [02:26<02:29, 19.02it/s]
 50%|████▉     | 2788/5625 [02:27<02:23, 19.78it/s]
 50%|████▉     | 2790/5625 [02:27<02:26, 19.34it/s]
 50%|████▉     | 2792/5625 [02:27<02:27, 19.17it/s]
 50%|████▉     | 2794/5625 [02:27<02:26, 19.34it/s]
 50%|████▉     | 2796/5625 [02:27<02:31, 18.72it/s]
 50%|████▉     | 2798/5625 [02:27<02:29, 18.89it/s]
 50%|████▉     | 2800/5625 [02:27<02:27, 19.15it/s]
 50%|████▉     | 2802/5625 [02:27<02:31, 18.59it/s]
 50%|████▉     | 2804/5625 [02:27<02:29, 18.89it/s]
 50%|████▉     | 2806/5625 [02:27<02:28, 18.92it/s]
 50%|████▉     | 2809/5625 [02:28<02:27, 19.11it/s]
 50%|████▉     | 2811/5625 [02:28<02:26, 19.25it/s]
 50%|█████     | 2814/5625 [02:28<02:23, 19.53it/s]
 50%|█████     | 2816/5625 [02:28<02:25, 19.30it/s]
 50%|█████     | 2818/5625 [02:28<02:25, 19.32it/s]
 50%|█████     | 2820/5625 [02:28<02:29, 18.73it/s]
 50%|█████     | 2822/5625 [02:28<02:28, 18.90it/s]
 50%|█████     | 2824/5625 [02:28<02:25, 19.19it/s]
 50%|█████     | 2827/5625 [02:29<02:19, 20.03it/s]
 50%|█████     | 2829/5625 [02:29<02:21, 19.71it/s]
 50%|█████     | 2831/5625 [02:29<02:23, 19.44it/s]
 50%|█████     | 2833/5625 [02:29<02:26, 19.08it/s]
 50%|█████     | 2835/5625 [02:29<02:24, 19.27it/s]
 50%|█████     | 2838/5625 [02:29<02:20, 19.81it/s]
 50%|█████     | 2840/5625 [02:29<02:21, 19.72it/s]
 51%|█████     | 2843/5625 [02:29<02:16, 20.41it/s]
 51%|█████     | 2846/5625 [02:30<02:22, 19.50it/s]
 51%|█████     | 2849/5625 [02:30<02:21, 19.59it/s]
 51%|█████     | 2851/5625 [02:30<02:23, 19.37it/s]
 51%|█████     | 2853/5625 [02:30<02:25, 19.08it/s]
 51%|█████     | 2856/5625 [02:30<02:21, 19.60it/s]
 51%|█████     | 2858/5625 [02:30<02:25, 19.03it/s]
 51%|█████     | 2861/5625 [02:30<02:18, 19.94it/s]
 51%|█████     | 2863/5625 [02:30<02:20, 19.67it/s]
 51%|█████     | 2865/5625 [02:30<02:22, 19.39it/s]
 51%|█████     | 2867/5625 [02:31<02:21, 19.47it/s]
 51%|█████     | 2870/5625 [02:31<02:15, 20.30it/s]
 51%|█████     | 2873/5625 [02:31<02:18, 19.85it/s]
 51%|█████     | 2875/5625 [02:31<02:20, 19.56it/s]
 51%|█████     | 2877/5625 [02:31<02:21, 19.46it/s]
 51%|█████     | 2879/5625 [02:31<02:23, 19.16it/s]
 51%|█████     | 2882/5625 [02:31<02:21, 19.39it/s]
 51%|█████▏    | 2884/5625 [02:31<02:23, 19.15it/s]
 51%|█████▏    | 2887/5625 [02:32<02:16, 20.08it/s]
 51%|█████▏    | 2889/5625 [02:32<02:21, 19.29it/s]
 51%|█████▏    | 2891/5625 [02:32<02:20, 19.40it/s]
 51%|█████▏    | 2894/5625 [02:32<02:16, 19.98it/s]
 51%|█████▏    | 2896/5625 [02:32<02:20, 19.49it/s]
 52%|█████▏    | 2898/5625 [02:32<02:21, 19.32it/s]
 52%|█████▏    | 2900/5625 [02:32<02:26, 18.64it/s]
 52%|█████▏    | 2903/5625 [02:32<02:19, 19.54it/s]
 52%|█████▏    | 2906/5625 [02:33<02:15, 20.14it/s]
 52%|█████▏    | 2908/5625 [02:33<02:16, 19.85it/s]
 52%|█████▏    | 2910/5625 [02:33<02:16, 19.83it/s]
 52%|█████▏    | 2913/5625 [02:33<02:14, 20.09it/s]
 52%|█████▏    | 2915/5625 [02:33<02:17, 19.76it/s]
 52%|█████▏    | 2917/5625 [02:33<02:21, 19.20it/s]
 52%|█████▏    | 2919/5625 [02:33<02:24, 18.79it/s]
 52%|█████▏    | 2921/5625 [02:33<02:26, 18.43it/s]
 52%|█████▏    | 2923/5625 [02:33<02:23, 18.80it/s]
 52%|█████▏    | 2925/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2927/5625 [02:34<02:25, 18.59it/s]
 52%|█████▏    | 2929/5625 [02:34<02:22, 18.91it/s]
 52%|█████▏    | 2931/5625 [02:34<02:21, 19.10it/s]
 52%|█████▏    | 2934/5625 [02:34<02:20, 19.22it/s]
 52%|█████▏    | 2937/5625 [02:34<02:19, 19.24it/s]
 52%|█████▏    | 2940/5625 [02:34<02:13, 20.08it/s]
 52%|█████▏    | 2943/5625 [02:34<02:11, 20.43it/s]
 52%|█████▏    | 2946/5625 [02:35<02:14, 19.87it/s]
 52%|█████▏    | 2948/5625 [02:35<02:15, 19.76it/s]
 52%|█████▏    | 2950/5625 [02:35<02:18, 19.33it/s]
 52%|█████▏    | 2952/5625 [02:35<02:18, 19.35it/s]
 53%|█████▎    | 2954/5625 [02:35<02:20, 18.99it/s]
 53%|█████▎    | 2957/5625 [02:35<02:17, 19.44it/s]
 53%|█████▎    | 2960/5625 [02:35<02:16, 19.59it/s]
 53%|█████▎    | 2963/5625 [02:36<02:15, 19.64it/s]
 53%|█████▎    | 2965/5625 [02:36<02:19, 19.04it/s]
 53%|█████▎    | 2967/5625 [02:36<02:18, 19.25it/s]
 53%|█████▎    | 2970/5625 [02:36<02:16, 19.40it/s]
 53%|█████▎    | 2973/5625 [02:36<02:14, 19.66it/s]
 53%|█████▎    | 2976/5625 [02:36<02:11, 20.20it/s]
 53%|█████▎    | 2979/5625 [02:36<02:12, 19.95it/s]
 53%|█████▎    | 2982/5625 [02:36<02:14, 19.67it/s]
 53%|█████▎    | 2984/5625 [02:37<02:17, 19.23it/s]
 53%|█████▎    | 2987/5625 [02:37<02:14, 19.59it/s]
 53%|█████▎    | 2989/5625 [02:37<02:18, 19.04it/s]
 53%|█████▎    | 2992/5625 [02:37<02:16, 19.26it/s]
 53%|█████▎    | 2995/5625 [02:37<02:12, 19.85it/s]
 53%|█████▎    | 2997/5625 [02:37<02:14, 19.56it/s]
 53%|█████▎    | 2999/5625 [02:37<02:16, 19.28it/s]
 53%|█████▎    | 3002/5625 [02:38<02:12, 19.73it/s]
 53%|█████▎    | 3005/5625 [02:38<02:09, 20.22it/s]
 53%|█████▎    | 3008/5625 [02:38<02:11, 19.93it/s]
 54%|█████▎    | 3010/5625 [02:38<02:13, 19.53it/s]
 54%|█████▎    | 3012/5625 [02:38<02:14, 19.36it/s]
 54%|█████▎    | 3014/5625 [02:38<02:17, 18.96it/s]
 54%|█████▎    | 3017/5625 [02:38<02:13, 19.56it/s]
 54%|█████▎    | 3019/5625 [02:38<02:14, 19.32it/s]
 54%|█████▎    | 3022/5625 [02:39<02:13, 19.54it/s]
 54%|█████▍    | 3024/5625 [02:39<02:12, 19.64it/s]
 54%|█████▍    | 3027/5625 [02:39<02:09, 20.01it/s]
 54%|█████▍    | 3029/5625 [02:39<02:11, 19.74it/s]
 54%|█████▍    | 3032/5625 [02:39<02:09, 20.08it/s]
 54%|█████▍    | 3034/5625 [02:39<02:09, 19.99it/s]
 54%|█████▍    | 3037/5625 [02:39<02:07, 20.24it/s]
 54%|█████▍    | 3040/5625 [02:39<02:13, 19.36it/s]
 54%|█████▍    | 3042/5625 [02:40<02:15, 19.05it/s]
 54%|█████▍    | 3044/5625 [02:40<02:16, 18.94it/s]
 54%|█████▍    | 3047/5625 [02:40<02:15, 19.09it/s]
 54%|█████▍    | 3050/5625 [02:40<02:10, 19.77it/s]
 54%|█████▍    | 3053/5625 [02:40<02:09, 19.80it/s]
 54%|█████▍    | 3056/5625 [02:40<02:06, 20.28it/s]
 54%|█████▍    | 3059/5625 [02:40<02:08, 19.90it/s]
 54%|█████▍    | 3061/5625 [02:41<02:09, 19.78it/s]
 54%|█████▍    | 3063/5625 [02:41<02:09, 19.82it/s]
 54%|█████▍    | 3065/5625 [02:41<02:12, 19.28it/s]
 55%|█████▍    | 3068/5625 [02:41<02:10, 19.61it/s]
 55%|█████▍    | 3070/5625 [02:41<02:12, 19.30it/s]
 55%|█████▍    | 3072/5625 [02:41<02:13, 19.19it/s]
 55%|█████▍    | 3074/5625 [02:41<02:14, 18.98it/s]
 55%|█████▍    | 3077/5625 [02:41<02:08, 19.87it/s]
 55%|█████▍    | 3079/5625 [02:41<02:09, 19.60it/s]
 55%|█████▍    | 3081/5625 [02:42<02:11, 19.40it/s]
 55%|█████▍    | 3084/5625 [02:42<02:10, 19.44it/s]
 55%|█████▍    | 3086/5625 [02:42<02:10, 19.53it/s]
 55%|█████▍    | 3088/5625 [02:42<02:09, 19.61it/s]
 55%|█████▍    | 3090/5625 [02:42<02:10, 19.42it/s]
 55%|█████▍    | 3092/5625 [02:42<02:10, 19.42it/s]
 55%|█████▌    | 3095/5625 [02:42<02:10, 19.33it/s]
 55%|█████▌    | 3097/5625 [02:42<02:12, 19.09it/s]
 55%|█████▌    | 3100/5625 [02:43<02:10, 19.41it/s]
 55%|█████▌    | 3103/5625 [02:43<02:04, 20.18it/s]
 55%|█████▌    | 3106/5625 [02:43<02:07, 19.80it/s]
 55%|█████▌    | 3109/5625 [02:43<02:03, 20.43it/s]
 55%|█████▌    | 3112/5625 [02:43<02:07, 19.64it/s]
 55%|█████▌    | 3114/5625 [02:43<02:09, 19.41it/s]
 55%|█████▌    | 3116/5625 [02:43<02:12, 18.96it/s]
 55%|█████▌    | 3118/5625 [02:43<02:14, 18.62it/s]
 55%|█████▌    | 3120/5625 [02:44<02:12, 18.89it/s]
 56%|█████▌    | 3123/5625 [02:44<02:09, 19.28it/s]
 56%|█████▌    | 3125/5625 [02:44<02:09, 19.25it/s]
 56%|█████▌    | 3127/5625 [02:44<02:11, 19.06it/s]
 56%|█████▌    | 3129/5625 [02:44<02:13, 18.67it/s]
 56%|█████▌    | 3132/5625 [02:44<02:11, 19.02it/s]
 56%|█████▌    | 3134/5625 [02:44<02:11, 19.00it/s]
 56%|█████▌    | 3136/5625 [02:44<02:13, 18.69it/s]
 56%|█████▌    | 3138/5625 [02:45<02:13, 18.60it/s]
 56%|█████▌    | 3140/5625 [02:45<02:15, 18.31it/s]
 56%|█████▌    | 3143/5625 [02:45<02:07, 19.42it/s]
 56%|█████▌    | 3146/5625 [02:45<02:02, 20.31it/s]
 56%|█████▌    | 3149/5625 [02:45<02:06, 19.59it/s]
 56%|█████▌    | 3152/5625 [02:45<02:06, 19.61it/s]
 56%|█████▌    | 3155/5625 [02:45<02:02, 20.09it/s]
 56%|█████▌    | 3158/5625 [02:46<02:03, 19.92it/s]
 56%|█████▌    | 3160/5625 [02:46<02:06, 19.55it/s]
 56%|█████▌    | 3162/5625 [02:46<02:10, 18.94it/s]
 56%|█████▌    | 3164/5625 [02:46<02:10, 18.79it/s]
 56%|█████▋    | 3166/5625 [02:46<02:09, 19.01it/s]
 56%|█████▋    | 3168/5625 [02:46<02:09, 18.93it/s]
 56%|█████▋    | 3170/5625 [02:46<02:12, 18.53it/s]
 56%|█████▋    | 3172/5625 [02:46<02:13, 18.44it/s]
 56%|█████▋    | 3174/5625 [02:46<02:14, 18.20it/s]
 56%|█████▋    | 3176/5625 [02:47<02:14, 18.26it/s]
 56%|█████▋    | 3178/5625 [02:47<02:14, 18.14it/s]
 57%|█████▋    | 3180/5625 [02:47<02:12, 18.47it/s]
 57%|█████▋    | 3183/5625 [02:47<02:09, 18.86it/s]
 57%|█████▋    | 3185/5625 [02:47<02:11, 18.60it/s]
 57%|█████▋    | 3187/5625 [02:47<02:11, 18.53it/s]
 57%|█████▋    | 3189/5625 [02:47<02:08, 18.91it/s]
 57%|█████▋    | 3191/5625 [02:47<02:10, 18.71it/s]
 57%|█████▋    | 3194/5625 [02:47<02:09, 18.81it/s]
 57%|█████▋    | 3196/5625 [02:48<02:07, 19.09it/s]
 57%|█████▋    | 3198/5625 [02:48<02:07, 19.07it/s]
 57%|█████▋    | 3200/5625 [02:48<02:07, 18.99it/s]
 57%|█████▋    | 3203/5625 [02:48<02:04, 19.45it/s]
 57%|█████▋    | 3206/5625 [02:48<02:05, 19.32it/s]
 57%|█████▋    | 3209/5625 [02:48<02:03, 19.60it/s]
 57%|█████▋    | 3211/5625 [02:48<02:03, 19.59it/s]
 57%|█████▋    | 3213/5625 [02:48<02:02, 19.63it/s]
 57%|█████▋    | 3216/5625 [02:49<02:01, 19.90it/s]
 57%|█████▋    | 3218/5625 [02:49<02:02, 19.67it/s]
 57%|█████▋    | 3220/5625 [02:49<02:05, 19.22it/s]
 57%|█████▋    | 3223/5625 [02:49<02:00, 19.86it/s]
 57%|█████▋    | 3226/5625 [02:49<01:58, 20.17it/s]
 57%|█████▋    | 3229/5625 [02:49<02:01, 19.69it/s]
 57%|█████▋    | 3231/5625 [02:49<02:03, 19.40it/s]
 57%|█████▋    | 3234/5625 [02:50<02:02, 19.54it/s]
 58%|█████▊    | 3237/5625 [02:50<02:03, 19.40it/s]
 58%|█████▊    | 3239/5625 [02:50<02:02, 19.50it/s]
 58%|█████▊    | 3241/5625 [02:50<02:06, 18.83it/s]
 58%|█████▊    | 3244/5625 [02:50<02:02, 19.37it/s]
 58%|█████▊    | 3246/5625 [02:50<02:03, 19.29it/s]
 58%|█████▊    | 3249/5625 [02:50<02:00, 19.79it/s]
 58%|█████▊    | 3251/5625 [02:50<02:01, 19.55it/s]
 58%|█████▊    | 3254/5625 [02:51<02:00, 19.72it/s]
 58%|█████▊    | 3257/5625 [02:51<01:58, 19.94it/s]
 58%|█████▊    | 3259/5625 [02:51<02:00, 19.67it/s]
 58%|█████▊    | 3262/5625 [02:51<01:59, 19.81it/s]
 58%|█████▊    | 3264/5625 [02:51<02:00, 19.55it/s]
 58%|█████▊    | 3267/5625 [02:51<02:00, 19.62it/s]
 58%|█████▊    | 3269/5625 [02:51<02:01, 19.34it/s]
 58%|█████▊    | 3272/5625 [02:51<02:00, 19.53it/s]
 58%|█████▊    | 3275/5625 [02:52<01:57, 20.02it/s]
 58%|█████▊    | 3277/5625 [02:52<01:57, 19.95it/s]
 58%|█████▊    | 3279/5625 [02:52<01:58, 19.81it/s]
 58%|█████▊    | 3281/5625 [02:52<02:00, 19.44it/s]
 58%|█████▊    | 3283/5625 [02:52<02:03, 19.02it/s]
 58%|█████▊    | 3285/5625 [02:52<02:01, 19.25it/s]
 58%|█████▊    | 3287/5625 [02:52<02:01, 19.17it/s]
 58%|█████▊    | 3289/5625 [02:52<02:03, 18.91it/s]
 59%|█████▊    | 3292/5625 [02:52<01:59, 19.58it/s]
 59%|█████▊    | 3294/5625 [02:53<02:02, 19.08it/s]
 59%|█████▊    | 3296/5625 [02:53<02:01, 19.21it/s]
 59%|█████▊    | 3299/5625 [02:53<01:56, 20.00it/s]
 59%|█████▊    | 3301/5625 [02:53<02:00, 19.25it/s]
 59%|█████▊    | 3303/5625 [02:53<02:00, 19.26it/s]
 59%|█████▉    | 3306/5625 [02:53<01:58, 19.58it/s]
 59%|█████▉    | 3308/5625 [02:53<01:59, 19.40it/s]
 59%|█████▉    | 3310/5625 [02:53<02:03, 18.77it/s]
 59%|█████▉    | 3312/5625 [02:54<02:03, 18.79it/s]
 59%|█████▉    | 3314/5625 [02:54<02:01, 19.02it/s]
 59%|█████▉    | 3316/5625 [02:54<02:04, 18.61it/s]
 59%|█████▉    | 3319/5625 [02:54<02:01, 19.05it/s]
 59%|█████▉    | 3321/5625 [02:54<02:01, 18.96it/s]
 59%|█████▉    | 3323/5625 [02:54<02:03, 18.68it/s]
 59%|█████▉    | 3325/5625 [02:54<02:00, 19.02it/s]
 59%|█████▉    | 3328/5625 [02:54<01:57, 19.62it/s]
 59%|█████▉    | 3330/5625 [02:54<02:00, 19.09it/s]
 59%|█████▉    | 3333/5625 [02:55<01:56, 19.65it/s]
 59%|█████▉    | 3335/5625 [02:55<01:57, 19.56it/s]
 59%|█████▉    | 3338/5625 [02:55<01:52, 20.27it/s]
 59%|█████▉    | 3341/5625 [02:55<01:54, 20.01it/s]
 59%|█████▉    | 3344/5625 [02:55<01:52, 20.19it/s]
 60%|█████▉    | 3347/5625 [02:55<01:53, 20.11it/s]
 60%|█████▉    | 3350/5625 [02:55<01:52, 20.16it/s]
 60%|█████▉    | 3353/5625 [02:56<01:54, 19.76it/s]
 60%|█████▉    | 3355/5625 [02:56<01:56, 19.48it/s]
 60%|█████▉    | 3357/5625 [02:56<01:56, 19.54it/s]
 60%|█████▉    | 3359/5625 [02:56<01:58, 19.06it/s]
 60%|█████▉    | 3362/5625 [02:56<01:56, 19.41it/s]
 60%|█████▉    | 3364/5625 [02:56<01:56, 19.48it/s]
 60%|█████▉    | 3366/5625 [02:56<01:57, 19.24it/s]
 60%|█████▉    | 3368/5625 [02:56<01:58, 18.97it/s]
 60%|█████▉    | 3370/5625 [02:56<01:57, 19.18it/s]
 60%|█████▉    | 3372/5625 [02:57<02:00, 18.66it/s]
 60%|██████    | 3375/5625 [02:57<01:55, 19.44it/s]
 60%|██████    | 3377/5625 [02:57<01:58, 18.90it/s]
 60%|██████    | 3380/5625 [02:57<01:55, 19.37it/s]
 60%|██████    | 3382/5625 [02:57<01:56, 19.24it/s]
 60%|██████    | 3385/5625 [02:57<01:51, 20.05it/s]
 60%|██████    | 3387/5625 [02:57<01:52, 19.87it/s]
 60%|██████    | 3389/5625 [02:57<01:53, 19.72it/s]
 60%|██████    | 3391/5625 [02:58<01:56, 19.18it/s]
 60%|██████    | 3393/5625 [02:58<01:58, 18.87it/s]
 60%|██████    | 3395/5625 [02:58<01:58, 18.88it/s]
 60%|██████    | 3397/5625 [02:58<01:57, 18.91it/s]
 60%|██████    | 3399/5625 [02:58<01:58, 18.86it/s]
 60%|██████    | 3402/5625 [02:58<01:56, 19.07it/s]
 61%|██████    | 3404/5625 [02:58<01:57, 18.83it/s]
 61%|██████    | 3406/5625 [02:58<02:00, 18.43it/s]
 61%|██████    | 3409/5625 [02:59<01:58, 18.70it/s]
 61%|██████    | 3411/5625 [02:59<01:57, 18.77it/s]
 61%|██████    | 3414/5625 [02:59<01:50, 19.94it/s]
 61%|██████    | 3416/5625 [02:59<01:52, 19.57it/s]
 61%|██████    | 3418/5625 [02:59<01:53, 19.48it/s]
 61%|██████    | 3420/5625 [02:59<01:54, 19.23it/s]
 61%|██████    | 3423/5625 [02:59<01:53, 19.47it/s]
 61%|██████    | 3426/5625 [02:59<01:50, 19.82it/s]
 61%|██████    | 3428/5625 [03:00<01:53, 19.37it/s]
 61%|██████    | 3431/5625 [03:00<01:51, 19.63it/s]
 61%|██████    | 3433/5625 [03:00<01:53, 19.27it/s]
 61%|██████    | 3436/5625 [03:00<01:51, 19.66it/s]
 61%|██████    | 3438/5625 [03:00<01:53, 19.23it/s]
 61%|██████    | 3440/5625 [03:00<01:56, 18.82it/s]
 61%|██████    | 3442/5625 [03:00<01:58, 18.40it/s]
 61%|██████    | 3444/5625 [03:00<01:59, 18.32it/s]
 61%|██████▏   | 3446/5625 [03:00<01:56, 18.72it/s]
 61%|██████▏   | 3449/5625 [03:01<01:50, 19.71it/s]
 61%|██████▏   | 3451/5625 [03:01<01:52, 19.35it/s]
 61%|██████▏   | 3453/5625 [03:01<01:54, 19.04it/s]
 61%|██████▏   | 3456/5625 [03:01<01:51, 19.50it/s]
 61%|██████▏   | 3459/5625 [03:01<01:48, 20.00it/s]
 62%|██████▏   | 3462/5625 [03:01<01:48, 20.02it/s]
 62%|██████▏   | 3464/5625 [03:01<01:50, 19.56it/s]
 62%|██████▏   | 3466/5625 [03:01<01:51, 19.34it/s]
 62%|██████▏   | 3469/5625 [03:02<01:50, 19.59it/s]
 62%|██████▏   | 3471/5625 [03:02<01:50, 19.58it/s]
 62%|██████▏   | 3473/5625 [03:02<01:49, 19.66it/s]
 62%|██████▏   | 3475/5625 [03:02<01:49, 19.68it/s]
 62%|██████▏   | 3477/5625 [03:02<01:51, 19.31it/s]
 62%|██████▏   | 3479/5625 [03:02<01:50, 19.38it/s]
 62%|██████▏   | 3481/5625 [03:02<01:50, 19.43it/s]
 62%|██████▏   | 3484/5625 [03:02<01:45, 20.37it/s]
 62%|██████▏   | 3487/5625 [03:03<01:49, 19.53it/s]
 62%|██████▏   | 3489/5625 [03:03<01:52, 18.98it/s]
 62%|██████▏   | 3492/5625 [03:03<01:49, 19.49it/s]
 62%|██████▏   | 3494/5625 [03:03<01:51, 19.09it/s]
 62%|██████▏   | 3496/5625 [03:03<01:53, 18.74it/s]
 62%|██████▏   | 3498/5625 [03:03<01:51, 19.01it/s]
 62%|██████▏   | 3501/5625 [03:03<01:47, 19.77it/s]
 62%|██████▏   | 3503/5625 [03:03<01:48, 19.65it/s]
 62%|██████▏   | 3506/5625 [03:04<01:44, 20.21it/s]
 62%|██████▏   | 3509/5625 [03:04<01:46, 19.78it/s]
 62%|██████▏   | 3511/5625 [03:04<01:50, 19.10it/s]
 62%|██████▏   | 3514/5625 [03:04<01:49, 19.23it/s]
 63%|██████▎   | 3516/5625 [03:04<01:53, 18.64it/s]
 63%|██████▎   | 3518/5625 [03:04<01:54, 18.47it/s]
 63%|██████▎   | 3521/5625 [03:04<01:49, 19.25it/s]
 63%|██████▎   | 3524/5625 [03:04<01:47, 19.55it/s]
 63%|██████▎   | 3527/5625 [03:05<01:44, 20.14it/s]
 63%|██████▎   | 3530/5625 [03:05<01:46, 19.70it/s]
 63%|██████▎   | 3532/5625 [03:05<01:48, 19.30it/s]
 63%|██████▎   | 3535/5625 [03:05<01:48, 19.29it/s]
 63%|██████▎   | 3537/5625 [03:05<01:50, 18.93it/s]
 63%|██████▎   | 3540/5625 [03:05<01:45, 19.76it/s]
 63%|██████▎   | 3542/5625 [03:05<01:46, 19.61it/s]
 63%|██████▎   | 3545/5625 [03:06<01:43, 20.08it/s]
 63%|██████▎   | 3547/5625 [03:06<01:44, 19.92it/s]
 63%|██████▎   | 3549/5625 [03:06<01:45, 19.68it/s]
 63%|██████▎   | 3551/5625 [03:06<01:48, 19.15it/s]
 63%|██████▎   | 3554/5625 [03:06<01:44, 19.81it/s]
 63%|██████▎   | 3556/5625 [03:06<01:47, 19.30it/s]
 63%|██████▎   | 3559/5625 [03:06<01:42, 20.11it/s]
 63%|██████▎   | 3562/5625 [03:06<01:41, 20.42it/s]
 63%|██████▎   | 3565/5625 [03:07<01:42, 20.08it/s]
 63%|██████▎   | 3568/5625 [03:07<01:45, 19.54it/s]
 63%|██████▎   | 3570/5625 [03:07<01:46, 19.26it/s]
 64%|██████▎   | 3572/5625 [03:07<01:47, 19.18it/s]
 64%|██████▎   | 3574/5625 [03:07<01:47, 19.05it/s]
 64%|██████▎   | 3576/5625 [03:07<01:47, 19.12it/s]
 64%|██████▎   | 3578/5625 [03:07<01:49, 18.75it/s]
 64%|██████▎   | 3580/5625 [03:07<01:47, 18.98it/s]
 64%|██████▎   | 3582/5625 [03:07<01:47, 18.97it/s]
 64%|██████▎   | 3584/5625 [03:08<01:46, 19.16it/s]
 64%|██████▍   | 3586/5625 [03:08<01:46, 19.19it/s]
 64%|██████▍   | 3588/5625 [03:08<01:45, 19.35it/s]
 64%|██████▍   | 3590/5625 [03:08<01:48, 18.72it/s]
 64%|██████▍   | 3592/5625 [03:08<01:50, 18.47it/s]
 64%|██████▍   | 3594/5625 [03:08<01:52, 18.01it/s]
 64%|██████▍   | 3596/5625 [03:08<01:51, 18.16it/s]
 64%|██████▍   | 3598/5625 [03:08<01:49, 18.48it/s]
 64%|██████▍   | 3600/5625 [03:08<01:50, 18.29it/s]
 64%|██████▍   | 3602/5625 [03:09<01:49, 18.48it/s]
 64%|██████▍   | 3604/5625 [03:09<01:48, 18.70it/s]
 64%|██████▍   | 3606/5625 [03:09<01:47, 18.73it/s]
 64%|██████▍   | 3608/5625 [03:09<01:46, 19.02it/s]
 64%|██████▍   | 3610/5625 [03:09<01:44, 19.28it/s]
 64%|██████▍   | 3613/5625 [03:09<01:42, 19.61it/s]
 64%|██████▍   | 3616/5625 [03:09<01:39, 20.13it/s]
 64%|██████▍   | 3619/5625 [03:09<01:41, 19.75it/s]
 64%|██████▍   | 3621/5625 [03:09<01:42, 19.64it/s]
 64%|██████▍   | 3623/5625 [03:10<01:44, 19.24it/s]
 64%|██████▍   | 3625/5625 [03:10<01:46, 18.85it/s]
 64%|██████▍   | 3628/5625 [03:10<01:42, 19.55it/s]
 65%|██████▍   | 3630/5625 [03:10<01:43, 19.35it/s]
 65%|██████▍   | 3632/5625 [03:10<01:46, 18.77it/s]
 65%|██████▍   | 3635/5625 [03:10<01:44, 19.01it/s]
 65%|██████▍   | 3638/5625 [03:10<01:39, 20.01it/s]
 65%|██████▍   | 3641/5625 [03:11<01:38, 20.20it/s]
 65%|██████▍   | 3644/5625 [03:11<01:40, 19.75it/s]
 65%|██████▍   | 3647/5625 [03:11<01:39, 19.89it/s]
 65%|██████▍   | 3649/5625 [03:11<01:40, 19.60it/s]
 65%|██████▍   | 3651/5625 [03:11<01:40, 19.59it/s]
 65%|██████▍   | 3653/5625 [03:11<01:43, 19.01it/s]
 65%|██████▍   | 3656/5625 [03:11<01:41, 19.35it/s]
 65%|██████▌   | 3658/5625 [03:11<01:43, 19.07it/s]
 65%|██████▌   | 3661/5625 [03:12<01:41, 19.32it/s]
 65%|██████▌   | 3663/5625 [03:12<01:40, 19.48it/s]
 65%|██████▌   | 3665/5625 [03:12<01:42, 19.06it/s]
 65%|██████▌   | 3668/5625 [03:12<01:41, 19.34it/s]
 65%|██████▌   | 3670/5625 [03:12<01:43, 18.93it/s]
 65%|██████▌   | 3672/5625 [03:12<01:42, 19.07it/s]
 65%|██████▌   | 3674/5625 [03:12<01:44, 18.62it/s]
 65%|██████▌   | 3677/5625 [03:12<01:41, 19.15it/s]
 65%|██████▌   | 3680/5625 [03:13<01:40, 19.26it/s]
 65%|██████▌   | 3682/5625 [03:13<01:41, 19.19it/s]
 66%|██████▌   | 3685/5625 [03:13<01:41, 19.13it/s]
 66%|██████▌   | 3687/5625 [03:13<01:41, 19.07it/s]
 66%|██████▌   | 3690/5625 [03:13<01:40, 19.19it/s]
 66%|██████▌   | 3692/5625 [03:13<01:40, 19.18it/s]
 66%|██████▌   | 3694/5625 [03:13<01:41, 19.01it/s]
 66%|██████▌   | 3696/5625 [03:13<01:43, 18.57it/s]
 66%|██████▌   | 3698/5625 [03:14<01:43, 18.56it/s]
 66%|██████▌   | 3700/5625 [03:14<01:44, 18.48it/s]
 66%|██████▌   | 3702/5625 [03:14<01:44, 18.46it/s]
 66%|██████▌   | 3704/5625 [03:14<01:42, 18.82it/s]
 66%|██████▌   | 3706/5625 [03:14<01:40, 19.03it/s]
 66%|██████▌   | 3708/5625 [03:14<01:41, 18.84it/s]
 66%|██████▌   | 3710/5625 [03:14<01:40, 19.08it/s]
 66%|██████▌   | 3713/5625 [03:14<01:39, 19.23it/s]
 66%|██████▌   | 3715/5625 [03:14<01:41, 18.78it/s]
 66%|██████▌   | 3717/5625 [03:15<01:40, 19.07it/s]
 66%|██████▌   | 3719/5625 [03:15<01:42, 18.61it/s]
 66%|██████▌   | 3721/5625 [03:15<01:43, 18.43it/s]
 66%|██████▌   | 3724/5625 [03:15<01:35, 19.92it/s]
 66%|██████▌   | 3726/5625 [03:15<01:36, 19.78it/s]
 66%|██████▋   | 3728/5625 [03:15<01:37, 19.37it/s]
 66%|██████▋   | 3731/5625 [03:15<01:36, 19.54it/s]
 66%|██████▋   | 3734/5625 [03:15<01:36, 19.66it/s]
 66%|██████▋   | 3736/5625 [03:15<01:36, 19.65it/s]
 66%|██████▋   | 3738/5625 [03:16<01:37, 19.32it/s]
 66%|██████▋   | 3740/5625 [03:16<01:37, 19.29it/s]
 67%|██████▋   | 3743/5625 [03:16<01:36, 19.58it/s]
 67%|██████▋   | 3745/5625 [03:16<01:37, 19.35it/s]
 67%|██████▋   | 3747/5625 [03:16<01:36, 19.38it/s]
 67%|██████▋   | 3749/5625 [03:16<01:39, 18.93it/s]
                                                   

 67%|██████▋   | 3750/5625 [03:16<01:39, 18.93it/s]{'eval_loss': 0.6748814582824707, 'eval_accuracy': 0.6988, 'eval_f1': 0.6978093536187885, 'eval_runtime': 1.7322, 'eval_samples_per_second': 1443.214, 'eval_steps_per_second': 180.69, 'epoch': 1.0}
{'loss': 0.5207, 'learning_rate': 7.880091437261143e-06, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.60it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.55it/s]

 21%|██        | 66/313 [00:00<00:01, 205.81it/s]

 28%|██▊       | 87/313 [00:00<00:01, 194.95it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.38it/s]

 40%|████      | 126/313 [00:00<00:01, 185.08it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.93it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.77it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 178.63it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 172.83it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.03it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.79it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.40it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.34it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.20it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.20it/s]
 67%|██████▋   | 3750/5625 [03:18<01:39, 18.93it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 3751/5625 [03:19<13:32,  2.31it/s]
 67%|██████▋   | 3753/5625 [03:19<10:05,  3.09it/s]
 67%|██████▋   | 3755/5625 [03:19<07:37,  4.09it/s]
 67%|██████▋   | 3757/5625 [03:19<05:52,  5.30it/s]
 67%|██████▋   | 3760/5625 [03:19<04:08,  7.49it/s]
 67%|██████▋   | 3762/5625 [03:20<03:28,  8.94it/s]
 67%|██████▋   | 3764/5625 [03:20<02:57, 10.48it/s]
 67%|██████▋   | 3766/5625 [03:20<02:35, 11.98it/s]
 67%|██████▋   | 3769/5625 [03:20<02:10, 14.20it/s]
 67%|██████▋   | 3771/5625 [03:20<02:01, 15.22it/s]
 67%|██████▋   | 3774/5625 [03:20<01:51, 16.60it/s]
 67%|██████▋   | 3776/5625 [03:20<01:47, 17.16it/s]
 67%|██████▋   | 3778/5625 [03:20<01:44, 17.74it/s]
 67%|██████▋   | 3781/5625 [03:20<01:39, 18.56it/s]
 67%|██████▋   | 3784/5625 [03:21<01:36, 19.04it/s]
 67%|██████▋   | 3786/5625 [03:21<01:37, 18.93it/s]
 67%|██████▋   | 3788/5625 [03:21<01:38, 18.57it/s]
 67%|██████▋   | 3790/5625 [03:21<01:38, 18.54it/s]
 67%|██████▋   | 3792/5625 [03:21<01:38, 18.70it/s]
 67%|██████▋   | 3795/5625 [03:21<01:33, 19.67it/s]
 68%|██████▊   | 3797/5625 [03:21<01:36, 19.04it/s]
 68%|██████▊   | 3800/5625 [03:21<01:35, 19.20it/s]
 68%|██████▊   | 3802/5625 [03:22<01:34, 19.27it/s]
 68%|██████▊   | 3804/5625 [03:22<01:35, 19.08it/s]
 68%|██████▊   | 3807/5625 [03:22<01:33, 19.45it/s]
 68%|██████▊   | 3809/5625 [03:22<01:34, 19.19it/s]
 68%|██████▊   | 3811/5625 [03:22<01:36, 18.72it/s]
 68%|██████▊   | 3813/5625 [03:22<01:35, 18.90it/s]
 68%|██████▊   | 3816/5625 [03:22<01:33, 19.42it/s]
 68%|██████▊   | 3818/5625 [03:22<01:34, 19.20it/s]
 68%|██████▊   | 3820/5625 [03:23<01:33, 19.37it/s]
 68%|██████▊   | 3822/5625 [03:23<01:33, 19.32it/s]
 68%|██████▊   | 3824/5625 [03:23<01:35, 18.86it/s]
 68%|██████▊   | 3827/5625 [03:23<01:34, 18.97it/s]
 68%|██████▊   | 3829/5625 [03:23<01:33, 19.24it/s]
 68%|██████▊   | 3831/5625 [03:23<01:33, 19.09it/s]
 68%|██████▊   | 3834/5625 [03:23<01:32, 19.40it/s]
 68%|██████▊   | 3836/5625 [03:23<01:33, 19.20it/s]
 68%|██████▊   | 3839/5625 [03:23<01:31, 19.57it/s]
 68%|██████▊   | 3841/5625 [03:24<01:32, 19.33it/s]
 68%|██████▊   | 3843/5625 [03:24<01:34, 18.80it/s]
 68%|██████▊   | 3845/5625 [03:24<01:33, 19.06it/s]
 68%|██████▊   | 3847/5625 [03:24<01:33, 18.96it/s]
 68%|██████▊   | 3849/5625 [03:24<01:33, 19.02it/s]
 68%|██████▊   | 3851/5625 [03:24<01:31, 19.29it/s]
 69%|██████▊   | 3854/5625 [03:24<01:28, 20.07it/s]
 69%|██████▊   | 3856/5625 [03:24<01:29, 19.83it/s]
 69%|██████▊   | 3858/5625 [03:24<01:32, 19.13it/s]
 69%|██████▊   | 3860/5625 [03:25<01:34, 18.70it/s]
 69%|██████▊   | 3863/5625 [03:25<01:30, 19.57it/s]
 69%|██████▊   | 3866/5625 [03:25<01:27, 20.04it/s]
 69%|██████▉   | 3869/5625 [03:25<01:27, 20.12it/s]
 69%|██████▉   | 3872/5625 [03:25<01:29, 19.54it/s]
 69%|██████▉   | 3874/5625 [03:25<01:29, 19.57it/s]
 69%|██████▉   | 3876/5625 [03:25<01:30, 19.26it/s]
 69%|██████▉   | 3878/5625 [03:26<01:31, 19.17it/s]
 69%|██████▉   | 3880/5625 [03:26<01:30, 19.26it/s]
 69%|██████▉   | 3882/5625 [03:26<01:29, 19.41it/s]
 69%|██████▉   | 3885/5625 [03:26<01:29, 19.53it/s]
 69%|██████▉   | 3888/5625 [03:26<01:26, 20.02it/s]
 69%|██████▉   | 3890/5625 [03:26<01:26, 19.98it/s]
 69%|██████▉   | 3893/5625 [03:26<01:27, 19.91it/s]
 69%|██████▉   | 3895/5625 [03:26<01:28, 19.62it/s]
 69%|██████▉   | 3897/5625 [03:26<01:28, 19.64it/s]
 69%|██████▉   | 3899/5625 [03:27<01:29, 19.18it/s]
 69%|██████▉   | 3901/5625 [03:27<01:29, 19.24it/s]
 69%|██████▉   | 3903/5625 [03:27<01:30, 19.02it/s]
 69%|██████▉   | 3905/5625 [03:27<01:29, 19.19it/s]
 69%|██████▉   | 3907/5625 [03:27<01:31, 18.70it/s]
 70%|██████▉   | 3910/5625 [03:27<01:27, 19.61it/s]
 70%|██████▉   | 3912/5625 [03:27<01:29, 19.11it/s]
 70%|██████▉   | 3915/5625 [03:27<01:27, 19.46it/s]
 70%|██████▉   | 3918/5625 [03:28<01:25, 20.06it/s]
 70%|██████▉   | 3921/5625 [03:28<01:25, 19.91it/s]
 70%|██████▉   | 3923/5625 [03:28<01:28, 19.19it/s]
 70%|██████▉   | 3926/5625 [03:28<01:24, 20.03it/s]
 70%|██████▉   | 3928/5625 [03:28<01:26, 19.51it/s]
 70%|██████▉   | 3931/5625 [03:28<01:24, 20.15it/s]
 70%|██████▉   | 3933/5625 [03:28<01:24, 19.99it/s]
 70%|██████▉   | 3936/5625 [03:28<01:25, 19.80it/s]
 70%|███████   | 3938/5625 [03:29<01:28, 19.13it/s]
 70%|███████   | 3941/5625 [03:29<01:26, 19.39it/s]
 70%|███████   | 3943/5625 [03:29<01:26, 19.52it/s]
 70%|███████   | 3946/5625 [03:29<01:25, 19.63it/s]
 70%|███████   | 3948/5625 [03:29<01:26, 19.39it/s]
 70%|███████   | 3950/5625 [03:29<01:26, 19.31it/s]
 70%|███████   | 3952/5625 [03:29<01:28, 18.81it/s]
 70%|███████   | 3955/5625 [03:29<01:22, 20.13it/s]
 70%|███████   | 3957/5625 [03:30<01:23, 19.94it/s]
 70%|███████   | 3960/5625 [03:30<01:18, 21.08it/s]
 70%|███████   | 3963/5625 [03:30<01:21, 20.36it/s]
 71%|███████   | 3966/5625 [03:30<01:24, 19.56it/s]
 71%|███████   | 3968/5625 [03:30<01:52, 14.75it/s]
 71%|███████   | 3970/5625 [03:30<01:45, 15.65it/s]
 71%|███████   | 3973/5625 [03:30<01:36, 17.17it/s]
 71%|███████   | 3976/5625 [03:31<01:31, 18.07it/s]
 71%|███████   | 3978/5625 [03:31<01:30, 18.14it/s]
 71%|███████   | 3980/5625 [03:31<01:29, 18.43it/s]
 71%|███████   | 3982/5625 [03:31<01:27, 18.77it/s]
 71%|███████   | 3985/5625 [03:31<01:25, 19.29it/s]
 71%|███████   | 3987/5625 [03:31<01:24, 19.43it/s]
 71%|███████   | 3989/5625 [03:31<01:25, 19.18it/s]
 71%|███████   | 3991/5625 [03:31<01:26, 18.83it/s]
 71%|███████   | 3994/5625 [03:32<01:25, 19.16it/s]
 71%|███████   | 3997/5625 [03:32<01:23, 19.41it/s]
 71%|███████   | 3999/5625 [03:32<01:24, 19.27it/s]
 71%|███████   | 4001/5625 [03:32<01:23, 19.34it/s]
 71%|███████   | 4004/5625 [03:32<01:20, 20.26it/s]
 71%|███████   | 4007/5625 [03:32<01:21, 19.90it/s]
 71%|███████▏  | 4010/5625 [03:32<01:20, 20.11it/s]
 71%|███████▏  | 4013/5625 [03:33<01:21, 19.74it/s]
 71%|███████▏  | 4015/5625 [03:33<01:23, 19.22it/s]
 71%|███████▏  | 4017/5625 [03:33<01:25, 18.92it/s]
 71%|███████▏  | 4020/5625 [03:33<01:23, 19.31it/s]
 72%|███████▏  | 4022/5625 [03:33<01:24, 19.01it/s]
 72%|███████▏  | 4024/5625 [03:33<01:24, 18.87it/s]
 72%|███████▏  | 4027/5625 [03:33<01:23, 19.23it/s]
 72%|███████▏  | 4029/5625 [03:33<01:22, 19.42it/s]
 72%|███████▏  | 4031/5625 [03:33<01:23, 19.17it/s]
 72%|███████▏  | 4034/5625 [03:34<01:18, 20.26it/s]
 72%|███████▏  | 4037/5625 [03:34<01:21, 19.46it/s]
 72%|███████▏  | 4040/5625 [03:34<01:18, 20.18it/s]
 72%|███████▏  | 4043/5625 [03:34<01:21, 19.52it/s]
 72%|███████▏  | 4045/5625 [03:34<01:20, 19.55it/s]
 72%|███████▏  | 4047/5625 [03:34<01:20, 19.48it/s]
 72%|███████▏  | 4050/5625 [03:34<01:20, 19.66it/s]
 72%|███████▏  | 4052/5625 [03:35<01:22, 19.09it/s]
 72%|███████▏  | 4054/5625 [03:35<01:22, 19.06it/s]
 72%|███████▏  | 4056/5625 [03:35<01:22, 18.90it/s]
 72%|███████▏  | 4059/5625 [03:35<01:21, 19.19it/s]
 72%|███████▏  | 4061/5625 [03:35<01:21, 19.13it/s]
 72%|███████▏  | 4063/5625 [03:35<01:23, 18.76it/s]
 72%|███████▏  | 4066/5625 [03:35<01:18, 19.79it/s]
 72%|███████▏  | 4068/5625 [03:35<01:19, 19.55it/s]
 72%|███████▏  | 4070/5625 [03:35<01:19, 19.45it/s]
 72%|███████▏  | 4073/5625 [03:36<01:16, 20.39it/s]
 72%|███████▏  | 4076/5625 [03:36<01:14, 20.79it/s]
 73%|███████▎  | 4079/5625 [03:36<01:16, 20.12it/s]
 73%|███████▎  | 4082/5625 [03:36<01:19, 19.33it/s]
 73%|███████▎  | 4085/5625 [03:36<01:16, 20.08it/s]
 73%|███████▎  | 4088/5625 [03:36<01:18, 19.65it/s]
 73%|███████▎  | 4090/5625 [03:36<01:19, 19.25it/s]
 73%|███████▎  | 4092/5625 [03:37<01:21, 18.87it/s]
 73%|███████▎  | 4094/5625 [03:37<01:21, 18.84it/s]
 73%|███████▎  | 4097/5625 [03:37<01:16, 19.93it/s]
 73%|███████▎  | 4099/5625 [03:37<01:18, 19.32it/s]
 73%|███████▎  | 4101/5625 [03:37<01:19, 19.22it/s]
 73%|███████▎  | 4103/5625 [03:37<01:21, 18.75it/s]
 73%|███████▎  | 4106/5625 [03:37<01:15, 20.16it/s]
 73%|███████▎  | 4109/5625 [03:37<01:16, 19.79it/s]
 73%|███████▎  | 4112/5625 [03:38<01:14, 20.26it/s]
 73%|███████▎  | 4115/5625 [03:38<01:17, 19.53it/s]
 73%|███████▎  | 4118/5625 [03:38<01:16, 19.76it/s]
 73%|███████▎  | 4120/5625 [03:38<01:18, 19.26it/s]
 73%|███████▎  | 4122/5625 [03:38<01:18, 19.07it/s]
 73%|███████▎  | 4124/5625 [03:38<01:17, 19.26it/s]
 73%|███████▎  | 4126/5625 [03:38<01:18, 19.19it/s]
 73%|███████▎  | 4128/5625 [03:38<01:19, 18.86it/s]
 73%|███████▎  | 4130/5625 [03:39<01:18, 19.11it/s]
 73%|███████▎  | 4132/5625 [03:39<01:18, 18.90it/s]
 73%|███████▎  | 4134/5625 [03:39<01:19, 18.69it/s]
 74%|███████▎  | 4136/5625 [03:39<01:20, 18.40it/s]
 74%|███████▎  | 4138/5625 [03:39<01:21, 18.35it/s]
 74%|███████▎  | 4141/5625 [03:39<01:18, 18.87it/s]
 74%|███████▎  | 4143/5625 [03:39<01:19, 18.72it/s]
 74%|███████▎  | 4145/5625 [03:39<01:19, 18.55it/s]
 74%|███████▎  | 4147/5625 [03:39<01:18, 18.92it/s]
 74%|███████▍  | 4149/5625 [03:40<01:18, 18.86it/s]
 74%|███████▍  | 4151/5625 [03:40<01:17, 18.93it/s]
 74%|███████▍  | 4153/5625 [03:40<01:19, 18.57it/s]
 74%|███████▍  | 4155/5625 [03:40<01:17, 18.88it/s]
 74%|███████▍  | 4158/5625 [03:40<01:15, 19.44it/s]
 74%|███████▍  | 4161/5625 [03:40<01:15, 19.48it/s]
 74%|███████▍  | 4164/5625 [03:40<01:14, 19.60it/s]
 74%|███████▍  | 4167/5625 [03:40<01:11, 20.50it/s]
 74%|███████▍  | 4170/5625 [03:41<01:12, 19.95it/s]
 74%|███████▍  | 4172/5625 [03:41<01:14, 19.41it/s]
 74%|███████▍  | 4174/5625 [03:41<01:14, 19.48it/s]
 74%|███████▍  | 4176/5625 [03:41<01:14, 19.34it/s]
 74%|███████▍  | 4179/5625 [03:41<01:14, 19.37it/s]
 74%|███████▍  | 4181/5625 [03:41<01:14, 19.36it/s]
 74%|███████▍  | 4184/5625 [03:41<01:14, 19.38it/s]
 74%|███████▍  | 4186/5625 [03:41<01:15, 19.04it/s]
 74%|███████▍  | 4188/5625 [03:42<01:15, 18.95it/s]
 75%|███████▍  | 4191/5625 [03:42<01:13, 19.45it/s]
 75%|███████▍  | 4193/5625 [03:42<01:14, 19.25it/s]
 75%|███████▍  | 4196/5625 [03:42<01:14, 19.14it/s]
 75%|███████▍  | 4199/5625 [03:42<01:12, 19.72it/s]
 75%|███████▍  | 4201/5625 [03:42<01:13, 19.35it/s]
 75%|███████▍  | 4203/5625 [03:42<01:14, 19.00it/s]
 75%|███████▍  | 4205/5625 [03:42<01:14, 18.95it/s]
 75%|███████▍  | 4207/5625 [03:43<01:15, 18.87it/s]
 75%|███████▍  | 4209/5625 [03:43<01:16, 18.54it/s]
 75%|███████▍  | 4211/5625 [03:43<01:15, 18.80it/s]
 75%|███████▍  | 4213/5625 [03:43<01:17, 18.31it/s]
 75%|███████▍  | 4215/5625 [03:43<01:17, 18.20it/s]
 75%|███████▍  | 4217/5625 [03:43<01:18, 18.03it/s]
 75%|███████▌  | 4220/5625 [03:43<01:14, 18.90it/s]
 75%|███████▌  | 4223/5625 [03:43<01:10, 19.86it/s]
 75%|███████▌  | 4226/5625 [03:44<01:08, 20.30it/s]
 75%|███████▌  | 4229/5625 [03:44<01:09, 20.10it/s]
 75%|███████▌  | 4232/5625 [03:44<01:11, 19.52it/s]
 75%|███████▌  | 4235/5625 [03:44<01:09, 20.04it/s]
 75%|███████▌  | 4238/5625 [03:44<01:11, 19.35it/s]
 75%|███████▌  | 4240/5625 [03:44<01:11, 19.44it/s]
 75%|███████▌  | 4243/5625 [03:44<01:08, 20.21it/s]
 75%|███████▌  | 4246/5625 [03:45<01:11, 19.26it/s]
 76%|███████▌  | 4249/5625 [03:45<01:08, 20.06it/s]
 76%|███████▌  | 4252/5625 [03:45<01:10, 19.54it/s]
 76%|███████▌  | 4254/5625 [03:45<01:11, 19.05it/s]
 76%|███████▌  | 4256/5625 [03:45<01:11, 19.18it/s]
 76%|███████▌  | 4258/5625 [03:45<01:13, 18.70it/s]
 76%|███████▌  | 4260/5625 [03:45<01:12, 18.79it/s]
 76%|███████▌  | 4262/5625 [03:45<01:12, 18.90it/s]
 76%|███████▌  | 4264/5625 [03:46<01:12, 18.66it/s]
 76%|███████▌  | 4266/5625 [03:46<01:13, 18.53it/s]
 76%|███████▌  | 4268/5625 [03:46<01:13, 18.59it/s]
 76%|███████▌  | 4271/5625 [03:46<01:11, 18.98it/s]
 76%|███████▌  | 4273/5625 [03:46<01:10, 19.21it/s]
 76%|███████▌  | 4275/5625 [03:46<01:10, 19.26it/s]
 76%|███████▌  | 4277/5625 [03:46<01:11, 18.73it/s]
 76%|███████▌  | 4279/5625 [03:46<01:11, 18.72it/s]
 76%|███████▌  | 4281/5625 [03:46<01:12, 18.43it/s]
 76%|███████▌  | 4283/5625 [03:47<01:12, 18.58it/s]
 76%|███████▌  | 4286/5625 [03:47<01:10, 19.07it/s]
 76%|███████▌  | 4289/5625 [03:47<01:08, 19.65it/s]
 76%|███████▋  | 4291/5625 [03:47<01:09, 19.17it/s]
 76%|███████▋  | 4293/5625 [03:47<01:11, 18.64it/s]
 76%|███████▋  | 4295/5625 [03:47<01:11, 18.58it/s]
 76%|███████▋  | 4297/5625 [03:47<01:11, 18.59it/s]
 76%|███████▋  | 4300/5625 [03:47<01:09, 19.02it/s]
 76%|███████▋  | 4302/5625 [03:48<01:11, 18.58it/s]
 77%|███████▋  | 4305/5625 [03:48<01:08, 19.38it/s]
 77%|███████▋  | 4307/5625 [03:48<01:09, 18.96it/s]
 77%|███████▋  | 4309/5625 [03:48<01:08, 19.18it/s]
 77%|███████▋  | 4311/5625 [03:48<01:09, 18.94it/s]
 77%|███████▋  | 4313/5625 [03:48<01:08, 19.06it/s]
 77%|███████▋  | 4315/5625 [03:48<01:09, 18.87it/s]
 77%|███████▋  | 4317/5625 [03:48<01:09, 18.76it/s]
 77%|███████▋  | 4319/5625 [03:48<01:10, 18.48it/s]
 77%|███████▋  | 4322/5625 [03:49<01:08, 18.89it/s]
 77%|███████▋  | 4325/5625 [03:49<01:05, 19.78it/s]
 77%|███████▋  | 4327/5625 [03:49<01:05, 19.74it/s]
 77%|███████▋  | 4329/5625 [03:49<01:07, 19.16it/s]
 77%|███████▋  | 4332/5625 [03:49<01:07, 19.28it/s]
 77%|███████▋  | 4335/5625 [03:49<01:05, 19.55it/s]
 77%|███████▋  | 4337/5625 [03:49<01:06, 19.28it/s]
 77%|███████▋  | 4339/5625 [03:49<01:08, 18.91it/s]
 77%|███████▋  | 4342/5625 [03:50<01:05, 19.67it/s]
 77%|███████▋  | 4344/5625 [03:50<01:05, 19.58it/s]
 77%|███████▋  | 4347/5625 [03:50<01:04, 19.75it/s]
 77%|███████▋  | 4349/5625 [03:50<01:05, 19.36it/s]
 77%|███████▋  | 4351/5625 [03:50<01:07, 18.82it/s]
 77%|███████▋  | 4353/5625 [03:50<01:08, 18.47it/s]
 77%|███████▋  | 4356/5625 [03:50<01:05, 19.50it/s]
 77%|███████▋  | 4358/5625 [03:51<01:13, 17.23it/s]
 78%|███████▊  | 4360/5625 [03:51<01:11, 17.79it/s]
 78%|███████▊  | 4363/5625 [03:51<01:07, 18.74it/s]
 78%|███████▊  | 4365/5625 [03:51<01:07, 18.55it/s]
 78%|███████▊  | 4368/5625 [03:51<01:06, 18.97it/s]
 78%|███████▊  | 4371/5625 [03:51<01:05, 19.01it/s]
 78%|███████▊  | 4373/5625 [03:51<01:05, 18.97it/s]
 78%|███████▊  | 4375/5625 [03:51<01:07, 18.61it/s]
 78%|███████▊  | 4377/5625 [03:51<01:05, 18.96it/s]
 78%|███████▊  | 4379/5625 [03:52<01:06, 18.71it/s]
 78%|███████▊  | 4381/5625 [03:52<01:05, 18.97it/s]
 78%|███████▊  | 4383/5625 [03:52<01:05, 18.90it/s]
 78%|███████▊  | 4386/5625 [03:52<01:02, 19.83it/s]
 78%|███████▊  | 4388/5625 [03:52<01:02, 19.86it/s]
 78%|███████▊  | 4391/5625 [03:52<01:02, 19.68it/s]
 78%|███████▊  | 4394/5625 [03:52<01:03, 19.53it/s]
 78%|███████▊  | 4397/5625 [03:53<01:02, 19.56it/s]
 78%|███████▊  | 4399/5625 [03:53<01:03, 19.38it/s]
 78%|███████▊  | 4401/5625 [03:53<01:03, 19.15it/s]
 78%|███████▊  | 4403/5625 [03:53<01:03, 19.33it/s]
 78%|███████▊  | 4406/5625 [03:53<01:01, 19.72it/s]
 78%|███████▊  | 4408/5625 [03:53<01:01, 19.67it/s]
 78%|███████▊  | 4410/5625 [03:53<01:03, 19.04it/s]
 78%|███████▊  | 4413/5625 [03:53<01:01, 19.64it/s]
 79%|███████▊  | 4416/5625 [03:53<01:01, 19.68it/s]
 79%|███████▊  | 4419/5625 [03:54<01:01, 19.55it/s]
 79%|███████▊  | 4421/5625 [03:54<01:03, 18.89it/s]
 79%|███████▊  | 4424/5625 [03:54<01:02, 19.10it/s]
 79%|███████▊  | 4426/5625 [03:54<01:04, 18.67it/s]
 79%|███████▊  | 4429/5625 [03:54<01:02, 19.21it/s]
 79%|███████▉  | 4431/5625 [03:54<01:03, 18.92it/s]
 79%|███████▉  | 4433/5625 [03:54<01:02, 18.96it/s]
 79%|███████▉  | 4436/5625 [03:55<01:00, 19.70it/s]
 79%|███████▉  | 4439/5625 [03:55<00:59, 19.77it/s]
 79%|███████▉  | 4441/5625 [03:55<01:00, 19.73it/s]
 79%|███████▉  | 4443/5625 [03:55<00:59, 19.74it/s]
 79%|███████▉  | 4445/5625 [03:55<01:01, 19.22it/s]
 79%|███████▉  | 4447/5625 [03:55<01:02, 18.96it/s]
 79%|███████▉  | 4449/5625 [03:55<01:02, 18.87it/s]
 79%|███████▉  | 4452/5625 [03:55<01:00, 19.23it/s]
 79%|███████▉  | 4454/5625 [03:56<01:27, 13.43it/s]
 79%|███████▉  | 4456/5625 [03:56<01:19, 14.74it/s]
 79%|███████▉  | 4459/5625 [03:56<01:11, 16.38it/s]
 79%|███████▉  | 4462/5625 [03:56<01:06, 17.47it/s]
 79%|███████▉  | 4464/5625 [03:56<01:04, 17.99it/s]
 79%|███████▉  | 4466/5625 [03:56<01:02, 18.44it/s]
 79%|███████▉  | 4468/5625 [03:56<01:01, 18.81it/s]
 79%|███████▉  | 4470/5625 [03:56<01:02, 18.57it/s]
 80%|███████▉  | 4472/5625 [03:57<01:01, 18.88it/s]
 80%|███████▉  | 4474/5625 [03:57<01:02, 18.54it/s]
 80%|███████▉  | 4476/5625 [03:57<01:01, 18.71it/s]
 80%|███████▉  | 4478/5625 [03:57<01:01, 18.53it/s]
 80%|███████▉  | 4481/5625 [03:57<01:00, 19.03it/s]
 80%|███████▉  | 4484/5625 [03:57<00:55, 20.39it/s]
 80%|███████▉  | 4487/5625 [03:57<00:56, 20.03it/s]
 80%|███████▉  | 4490/5625 [03:57<00:57, 19.64it/s]
 80%|███████▉  | 4492/5625 [03:58<00:57, 19.71it/s]
 80%|███████▉  | 4494/5625 [03:58<00:58, 19.48it/s]
 80%|███████▉  | 4497/5625 [03:58<00:55, 20.22it/s]
 80%|████████  | 4500/5625 [03:58<00:55, 20.44it/s]
 80%|████████  | 4503/5625 [03:58<00:53, 21.15it/s]
 80%|████████  | 4506/5625 [03:58<00:53, 20.84it/s]
 80%|████████  | 4509/5625 [03:58<00:54, 20.54it/s]
 80%|████████  | 4512/5625 [03:59<00:55, 20.09it/s]
 80%|████████  | 4515/5625 [03:59<00:57, 19.30it/s]
 80%|████████  | 4518/5625 [03:59<00:57, 19.36it/s]
 80%|████████  | 4521/5625 [03:59<00:54, 20.28it/s]
 80%|████████  | 4524/5625 [03:59<00:55, 19.88it/s]
 80%|████████  | 4527/5625 [03:59<00:53, 20.46it/s]
 81%|████████  | 4530/5625 [03:59<00:55, 19.70it/s]
 81%|████████  | 4533/5625 [04:00<00:55, 19.73it/s]
 81%|████████  | 4535/5625 [04:00<00:55, 19.68it/s]
 81%|████████  | 4537/5625 [04:00<00:55, 19.53it/s]
 81%|████████  | 4539/5625 [04:00<00:56, 19.31it/s]
 81%|████████  | 4542/5625 [04:00<00:54, 19.71it/s]
 81%|████████  | 4544/5625 [04:00<00:54, 19.66it/s]
 81%|████████  | 4546/5625 [04:00<00:55, 19.41it/s]
 81%|████████  | 4548/5625 [04:00<00:55, 19.49it/s]
 81%|████████  | 4551/5625 [04:01<00:52, 20.34it/s]
 81%|████████  | 4554/5625 [04:01<00:50, 21.10it/s]
 81%|████████  | 4557/5625 [04:01<00:50, 21.16it/s]
 81%|████████  | 4560/5625 [04:01<00:52, 20.27it/s]
 81%|████████  | 4563/5625 [04:01<00:53, 19.72it/s]
 81%|████████  | 4566/5625 [04:01<00:53, 19.61it/s]
 81%|████████  | 4568/5625 [04:01<00:54, 19.22it/s]
 81%|████████  | 4570/5625 [04:01<00:54, 19.25it/s]
 81%|████████▏ | 4572/5625 [04:02<00:56, 18.79it/s]
 81%|████████▏ | 4575/5625 [04:02<00:54, 19.10it/s]
 81%|████████▏ | 4577/5625 [04:02<00:54, 19.29it/s]
 81%|████████▏ | 4579/5625 [04:02<00:54, 19.18it/s]
 81%|████████▏ | 4581/5625 [04:02<00:54, 19.12it/s]
 81%|████████▏ | 4583/5625 [04:02<00:54, 19.07it/s]
 82%|████████▏ | 4585/5625 [04:02<00:53, 19.32it/s]
 82%|████████▏ | 4587/5625 [04:02<00:54, 19.06it/s]
 82%|████████▏ | 4589/5625 [04:02<00:55, 18.75it/s]
 82%|████████▏ | 4592/5625 [04:03<00:53, 19.30it/s]
 82%|████████▏ | 4594/5625 [04:03<00:54, 19.03it/s]
 82%|████████▏ | 4597/5625 [04:03<00:52, 19.51it/s]
 82%|████████▏ | 4599/5625 [04:03<00:52, 19.59it/s]
 82%|████████▏ | 4601/5625 [04:03<00:52, 19.62it/s]
 82%|████████▏ | 4603/5625 [04:03<00:52, 19.31it/s]
 82%|████████▏ | 4605/5625 [04:03<00:52, 19.27it/s]
 82%|████████▏ | 4607/5625 [04:03<00:54, 18.85it/s]
 82%|████████▏ | 4609/5625 [04:04<00:54, 18.60it/s]
 82%|████████▏ | 4611/5625 [04:04<00:55, 18.21it/s]
 82%|████████▏ | 4613/5625 [04:04<00:54, 18.63it/s]
 82%|████████▏ | 4615/5625 [04:04<00:53, 18.92it/s]
 82%|████████▏ | 4617/5625 [04:04<00:53, 18.90it/s]
 82%|████████▏ | 4619/5625 [04:04<00:52, 19.19it/s]
 82%|████████▏ | 4621/5625 [04:04<00:52, 19.21it/s]
 82%|████████▏ | 4623/5625 [04:04<00:53, 18.75it/s]
 82%|████████▏ | 4625/5625 [04:04<00:53, 18.64it/s]
 82%|████████▏ | 4627/5625 [04:04<00:53, 18.62it/s]
 82%|████████▏ | 4629/5625 [04:05<00:53, 18.69it/s]
 82%|████████▏ | 4631/5625 [04:05<00:53, 18.41it/s]
 82%|████████▏ | 4634/5625 [04:05<00:50, 19.73it/s]
 82%|████████▏ | 4637/5625 [04:05<00:50, 19.60it/s]
 82%|████████▏ | 4639/5625 [04:05<00:50, 19.54it/s]
 83%|████████▎ | 4641/5625 [04:05<00:50, 19.54it/s]
 83%|████████▎ | 4643/5625 [04:05<00:51, 18.96it/s]
 83%|████████▎ | 4645/5625 [04:05<00:51, 19.03it/s]
 83%|████████▎ | 4647/5625 [04:06<00:51, 18.99it/s]
 83%|████████▎ | 4649/5625 [04:06<00:52, 18.69it/s]
 83%|████████▎ | 4651/5625 [04:06<00:52, 18.63it/s]
 83%|████████▎ | 4653/5625 [04:06<00:51, 18.99it/s]
 83%|████████▎ | 4655/5625 [04:06<00:51, 18.90it/s]
 83%|████████▎ | 4657/5625 [04:06<00:50, 19.16it/s]
 83%|████████▎ | 4659/5625 [04:06<00:51, 18.89it/s]
 83%|████████▎ | 4661/5625 [04:06<00:50, 18.94it/s]
 83%|████████▎ | 4663/5625 [04:06<00:52, 18.46it/s]
 83%|████████▎ | 4665/5625 [04:06<00:52, 18.32it/s]
 83%|████████▎ | 4667/5625 [04:07<00:51, 18.71it/s]
 83%|████████▎ | 4670/5625 [04:07<00:49, 19.31it/s]
 83%|████████▎ | 4672/5625 [04:07<00:50, 18.82it/s]
 83%|████████▎ | 4675/5625 [04:07<00:49, 19.25it/s]
 83%|████████▎ | 4677/5625 [04:07<00:50, 18.84it/s]
 83%|████████▎ | 4680/5625 [04:07<00:48, 19.53it/s]
 83%|████████▎ | 4682/5625 [04:07<00:48, 19.59it/s]
 83%|████████▎ | 4684/5625 [04:07<00:48, 19.49it/s]
 83%|████████▎ | 4686/5625 [04:08<00:48, 19.43it/s]
 83%|████████▎ | 4688/5625 [04:08<00:48, 19.37it/s]
 83%|████████▎ | 4691/5625 [04:08<00:47, 19.71it/s]
 83%|████████▎ | 4693/5625 [04:08<00:47, 19.61it/s]
 83%|████████▎ | 4695/5625 [04:08<00:47, 19.56it/s]
 84%|████████▎ | 4697/5625 [04:08<00:48, 19.18it/s]
 84%|████████▎ | 4699/5625 [04:08<00:47, 19.34it/s]
 84%|████████▎ | 4701/5625 [04:08<00:48, 19.01it/s]
 84%|████████▎ | 4703/5625 [04:08<00:49, 18.47it/s]
 84%|████████▎ | 4706/5625 [04:09<00:48, 19.14it/s]
 84%|████████▎ | 4709/5625 [04:09<00:47, 19.49it/s]
 84%|████████▍ | 4711/5625 [04:09<00:47, 19.15it/s]
 84%|████████▍ | 4713/5625 [04:09<00:47, 19.08it/s]
 84%|████████▍ | 4715/5625 [04:09<00:48, 18.58it/s]
 84%|████████▍ | 4717/5625 [04:09<00:49, 18.47it/s]
 84%|████████▍ | 4719/5625 [04:09<00:49, 18.41it/s]
 84%|████████▍ | 4722/5625 [04:09<00:46, 19.41it/s]
 84%|████████▍ | 4724/5625 [04:10<00:47, 18.97it/s]
 84%|████████▍ | 4727/5625 [04:10<00:45, 19.70it/s]
 84%|████████▍ | 4730/5625 [04:10<00:44, 20.19it/s]
 84%|████████▍ | 4733/5625 [04:10<00:44, 20.26it/s]
 84%|████████▍ | 4736/5625 [04:10<00:45, 19.65it/s]
 84%|████████▍ | 4738/5625 [04:10<00:45, 19.65it/s]
 84%|████████▍ | 4740/5625 [04:10<00:45, 19.37it/s]
 84%|████████▍ | 4742/5625 [04:10<00:45, 19.25it/s]
 84%|████████▍ | 4744/5625 [04:11<00:46, 19.09it/s]
 84%|████████▍ | 4746/5625 [04:11<00:46, 18.74it/s]
 84%|████████▍ | 4748/5625 [04:11<00:46, 19.04it/s]
 84%|████████▍ | 4751/5625 [04:11<00:44, 19.83it/s]
 84%|████████▍ | 4753/5625 [04:11<00:45, 19.20it/s]
 85%|████████▍ | 4755/5625 [04:11<00:45, 19.11it/s]
 85%|████████▍ | 4757/5625 [04:11<00:44, 19.31it/s]
 85%|████████▍ | 4759/5625 [04:11<00:45, 18.83it/s]
 85%|████████▍ | 4761/5625 [04:11<00:46, 18.75it/s]
 85%|████████▍ | 4764/5625 [04:12<00:43, 19.70it/s]
 85%|████████▍ | 4766/5625 [04:12<00:43, 19.76it/s]
 85%|████████▍ | 4769/5625 [04:12<00:41, 20.38it/s]
 85%|████████▍ | 4772/5625 [04:12<00:44, 19.22it/s]
 85%|████████▍ | 4775/5625 [04:12<00:42, 19.86it/s]
 85%|████████▍ | 4777/5625 [04:12<00:43, 19.66it/s]
 85%|████████▍ | 4779/5625 [04:12<00:43, 19.55it/s]
 85%|████████▍ | 4781/5625 [04:12<00:43, 19.31it/s]
 85%|████████▌ | 4784/5625 [04:13<00:43, 19.29it/s]
 85%|████████▌ | 4786/5625 [04:13<00:44, 18.80it/s]
 85%|████████▌ | 4788/5625 [04:13<00:44, 18.74it/s]
 85%|████████▌ | 4791/5625 [04:13<00:41, 19.95it/s]
 85%|████████▌ | 4794/5625 [04:13<00:40, 20.32it/s]
 85%|████████▌ | 4797/5625 [04:13<00:40, 20.21it/s]
 85%|████████▌ | 4800/5625 [04:13<00:39, 20.72it/s]
 85%|████████▌ | 4803/5625 [04:14<00:40, 20.23it/s]
 85%|████████▌ | 4806/5625 [04:14<00:41, 19.54it/s]
 85%|████████▌ | 4808/5625 [04:14<00:41, 19.55it/s]
 86%|████████▌ | 4810/5625 [04:14<00:42, 19.00it/s]
 86%|████████▌ | 4813/5625 [04:14<00:40, 19.87it/s]
 86%|████████▌ | 4815/5625 [04:14<00:41, 19.58it/s]
 86%|████████▌ | 4818/5625 [04:14<00:40, 19.98it/s]
 86%|████████▌ | 4820/5625 [04:14<00:41, 19.40it/s]
 86%|████████▌ | 4822/5625 [04:15<00:42, 19.00it/s]
 86%|████████▌ | 4824/5625 [04:15<00:42, 18.96it/s]
 86%|████████▌ | 4827/5625 [04:15<00:40, 19.54it/s]
 86%|████████▌ | 4829/5625 [04:15<00:41, 19.32it/s]
 86%|████████▌ | 4831/5625 [04:15<00:40, 19.50it/s]
 86%|████████▌ | 4834/5625 [04:15<00:39, 19.97it/s]
 86%|████████▌ | 4836/5625 [04:15<00:39, 19.90it/s]
 86%|████████▌ | 4839/5625 [04:15<00:38, 20.16it/s]
 86%|████████▌ | 4842/5625 [04:16<00:38, 20.55it/s]
 86%|████████▌ | 4845/5625 [04:16<00:38, 20.50it/s]
 86%|████████▌ | 4848/5625 [04:16<00:38, 20.11it/s]
 86%|████████▌ | 4851/5625 [04:16<00:38, 20.15it/s]
 86%|████████▋ | 4854/5625 [04:16<00:39, 19.55it/s]
 86%|████████▋ | 4856/5625 [04:16<00:39, 19.58it/s]
 86%|████████▋ | 4858/5625 [04:16<00:39, 19.48it/s]
 86%|████████▋ | 4861/5625 [04:17<00:38, 19.83it/s]
 86%|████████▋ | 4863/5625 [04:17<00:38, 19.63it/s]
 86%|████████▋ | 4865/5625 [04:17<00:39, 19.41it/s]
 87%|████████▋ | 4868/5625 [04:17<00:37, 20.00it/s]
 87%|████████▋ | 4871/5625 [04:17<00:37, 20.14it/s]
 87%|████████▋ | 4874/5625 [04:17<00:36, 20.44it/s]
 87%|████████▋ | 4877/5625 [04:17<00:37, 19.81it/s]
 87%|████████▋ | 4879/5625 [04:17<00:38, 19.58it/s]
 87%|████████▋ | 4881/5625 [04:18<00:38, 19.18it/s]
 87%|████████▋ | 4883/5625 [04:18<00:38, 19.37it/s]
 87%|████████▋ | 4886/5625 [04:18<00:37, 19.80it/s]
 87%|████████▋ | 4888/5625 [04:18<00:37, 19.43it/s]
 87%|████████▋ | 4890/5625 [04:18<00:38, 19.22it/s]
 87%|████████▋ | 4893/5625 [04:18<00:37, 19.32it/s]
 87%|████████▋ | 4896/5625 [04:18<00:37, 19.62it/s]
 87%|████████▋ | 4899/5625 [04:18<00:36, 19.77it/s]
 87%|████████▋ | 4902/5625 [04:19<00:36, 19.97it/s]
 87%|████████▋ | 4904/5625 [04:19<00:36, 19.64it/s]
 87%|████████▋ | 4906/5625 [04:19<00:37, 19.30it/s]
 87%|████████▋ | 4909/5625 [04:19<00:36, 19.54it/s]
 87%|████████▋ | 4911/5625 [04:19<00:37, 19.06it/s]
 87%|████████▋ | 4914/5625 [04:19<00:35, 19.91it/s]
 87%|████████▋ | 4916/5625 [04:19<00:36, 19.69it/s]
 87%|████████▋ | 4918/5625 [04:19<00:36, 19.45it/s]
 87%|████████▋ | 4920/5625 [04:20<00:36, 19.55it/s]
 88%|████████▊ | 4922/5625 [04:20<00:35, 19.59it/s]
 88%|████████▊ | 4925/5625 [04:20<00:35, 19.65it/s]
 88%|████████▊ | 4928/5625 [04:20<00:34, 20.19it/s]
 88%|████████▊ | 4931/5625 [04:20<00:35, 19.58it/s]
 88%|████████▊ | 4933/5625 [04:20<00:36, 19.05it/s]
 88%|████████▊ | 4935/5625 [04:20<00:36, 18.92it/s]
 88%|████████▊ | 4938/5625 [04:20<00:35, 19.22it/s]
 88%|████████▊ | 4941/5625 [04:21<00:34, 19.63it/s]
 88%|████████▊ | 4944/5625 [04:21<00:33, 20.17it/s]
 88%|████████▊ | 4947/5625 [04:21<00:33, 20.07it/s]
 88%|████████▊ | 4950/5625 [04:21<00:34, 19.41it/s]
 88%|████████▊ | 4952/5625 [04:21<00:34, 19.31it/s]
 88%|████████▊ | 4955/5625 [04:21<00:32, 20.33it/s]
 88%|████████▊ | 4958/5625 [04:21<00:33, 19.83it/s]
 88%|████████▊ | 4960/5625 [04:22<00:33, 19.84it/s]
 88%|████████▊ | 4962/5625 [04:22<00:34, 19.18it/s]
 88%|████████▊ | 4964/5625 [04:22<00:34, 19.03it/s]
 88%|████████▊ | 4966/5625 [04:22<00:34, 19.21it/s]
 88%|████████▊ | 4968/5625 [04:22<00:34, 18.83it/s]
 88%|████████▊ | 4970/5625 [04:22<00:34, 19.09it/s]
 88%|████████▊ | 4972/5625 [04:22<00:34, 18.74it/s]
 88%|████████▊ | 4974/5625 [04:22<00:34, 18.61it/s]
 88%|████████▊ | 4976/5625 [04:22<00:35, 18.44it/s]
 89%|████████▊ | 4979/5625 [04:23<00:33, 19.22it/s]
 89%|████████▊ | 4981/5625 [04:23<00:33, 19.27it/s]
 89%|████████▊ | 4984/5625 [04:23<00:32, 19.74it/s]
 89%|████████▊ | 4986/5625 [04:23<00:32, 19.80it/s]
 89%|████████▊ | 4988/5625 [04:23<00:32, 19.66it/s]
 89%|████████▊ | 4991/5625 [04:23<00:31, 20.20it/s]
 89%|████████▉ | 4994/5625 [04:23<00:31, 19.92it/s]
 89%|████████▉ | 4996/5625 [04:23<00:32, 19.65it/s]
 89%|████████▉ | 4999/5625 [04:24<00:31, 20.17it/s]
 89%|████████▉ | 5002/5625 [04:24<00:31, 20.06it/s]
 89%|████████▉ | 5005/5625 [04:24<00:32, 19.26it/s]
 89%|████████▉ | 5007/5625 [04:24<00:31, 19.31it/s]
 89%|████████▉ | 5009/5625 [04:24<00:32, 19.17it/s]
 89%|████████▉ | 5011/5625 [04:24<00:32, 18.76it/s]
 89%|████████▉ | 5013/5625 [04:24<00:32, 18.92it/s]
 89%|████████▉ | 5015/5625 [04:24<00:32, 18.82it/s]
 89%|████████▉ | 5018/5625 [04:25<00:30, 19.70it/s]
 89%|████████▉ | 5021/5625 [04:25<00:30, 19.49it/s]
 89%|████████▉ | 5024/5625 [04:25<00:30, 19.83it/s]
 89%|████████▉ | 5027/5625 [04:25<00:29, 20.19it/s]
 89%|████████▉ | 5030/5625 [04:25<00:29, 19.96it/s]
 89%|████████▉ | 5032/5625 [04:25<00:30, 19.56it/s]
 90%|████████▉ | 5035/5625 [04:25<00:30, 19.60it/s]
 90%|████████▉ | 5037/5625 [04:26<00:30, 19.46it/s]
 90%|████████▉ | 5039/5625 [04:26<00:29, 19.60it/s]
 90%|████████▉ | 5041/5625 [04:26<00:29, 19.48it/s]
 90%|████████▉ | 5044/5625 [04:26<00:29, 19.98it/s]
 90%|████████▉ | 5046/5625 [04:26<00:29, 19.79it/s]
 90%|████████▉ | 5048/5625 [04:26<00:29, 19.25it/s]
 90%|████████▉ | 5050/5625 [04:26<00:29, 19.38it/s]
 90%|████████▉ | 5052/5625 [04:26<00:29, 19.51it/s]
 90%|████████▉ | 5054/5625 [04:26<00:29, 19.57it/s]
 90%|████████▉ | 5056/5625 [04:27<00:29, 19.27it/s]
 90%|████████▉ | 5058/5625 [04:27<00:29, 19.12it/s]
 90%|████████▉ | 5060/5625 [04:27<00:29, 19.06it/s]
 90%|█████████ | 5063/5625 [04:27<00:28, 20.06it/s]
 90%|█████████ | 5065/5625 [04:27<00:28, 19.82it/s]
 90%|█████████ | 5067/5625 [04:27<00:29, 19.19it/s]
 90%|█████████ | 5070/5625 [04:27<00:28, 19.36it/s]
 90%|█████████ | 5072/5625 [04:27<00:28, 19.18it/s]
 90%|█████████ | 5074/5625 [04:27<00:28, 19.33it/s]
 90%|█████████ | 5076/5625 [04:28<00:28, 19.06it/s]
 90%|█████████ | 5078/5625 [04:28<00:28, 19.04it/s]
 90%|█████████ | 5080/5625 [04:28<00:28, 19.01it/s]
 90%|█████████ | 5082/5625 [04:28<00:28, 19.26it/s]
 90%|█████████ | 5084/5625 [04:28<00:28, 19.04it/s]
 90%|█████████ | 5086/5625 [04:28<00:27, 19.31it/s]
 90%|█████████ | 5088/5625 [04:28<00:27, 19.21it/s]
 90%|█████████ | 5090/5625 [04:28<00:27, 19.39it/s]
 91%|█████████ | 5092/5625 [04:28<00:27, 19.47it/s]
 91%|█████████ | 5094/5625 [04:28<00:27, 19.53it/s]
 91%|█████████ | 5096/5625 [04:29<00:27, 19.01it/s]
 91%|█████████ | 5098/5625 [04:29<00:27, 18.83it/s]
 91%|█████████ | 5100/5625 [04:29<00:27, 18.80it/s]
 91%|█████████ | 5102/5625 [04:29<00:27, 19.10it/s]
 91%|█████████ | 5105/5625 [04:29<00:25, 20.47it/s]
 91%|█████████ | 5108/5625 [04:29<00:24, 20.95it/s]
 91%|█████████ | 5111/5625 [04:29<00:24, 20.81it/s]
 91%|█████████ | 5114/5625 [04:29<00:25, 19.82it/s]
 91%|█████████ | 5116/5625 [04:30<00:26, 19.29it/s]
 91%|█████████ | 5119/5625 [04:30<00:25, 19.98it/s]
 91%|█████████ | 5122/5625 [04:30<00:25, 19.84it/s]
 91%|█████████ | 5124/5625 [04:30<00:25, 19.64it/s]
 91%|█████████ | 5127/5625 [04:30<00:24, 20.30it/s]
 91%|█████████ | 5130/5625 [04:30<00:25, 19.71it/s]
 91%|█████████ | 5132/5625 [04:30<00:25, 19.49it/s]
 91%|█████████▏| 5134/5625 [04:31<00:25, 19.39it/s]
 91%|█████████▏| 5137/5625 [04:31<00:24, 19.81it/s]
 91%|█████████▏| 5139/5625 [04:31<00:25, 19.17it/s]
 91%|█████████▏| 5141/5625 [04:31<00:25, 18.95it/s]
 91%|█████████▏| 5143/5625 [04:31<00:25, 18.62it/s]
 91%|█████████▏| 5145/5625 [04:31<00:26, 18.23it/s]
 92%|█████████▏| 5147/5625 [04:31<00:26, 18.16it/s]
 92%|█████████▏| 5150/5625 [04:31<00:25, 18.70it/s]
 92%|█████████▏| 5152/5625 [04:31<00:25, 18.54it/s]
 92%|█████████▏| 5155/5625 [04:32<00:24, 19.05it/s]
 92%|█████████▏| 5158/5625 [04:32<00:24, 19.27it/s]
 92%|█████████▏| 5160/5625 [04:32<00:24, 19.03it/s]
 92%|█████████▏| 5162/5625 [04:32<00:24, 19.18it/s]
 92%|█████████▏| 5164/5625 [04:32<00:24, 19.16it/s]
 92%|█████████▏| 5166/5625 [04:32<00:24, 19.11it/s]
 92%|█████████▏| 5168/5625 [04:32<00:24, 18.63it/s]
 92%|█████████▏| 5170/5625 [04:32<00:24, 18.34it/s]
 92%|█████████▏| 5173/5625 [04:33<00:23, 18.92it/s]
 92%|█████████▏| 5176/5625 [04:33<00:23, 19.42it/s]
 92%|█████████▏| 5179/5625 [04:33<00:22, 19.90it/s]
 92%|█████████▏| 5181/5625 [04:33<00:22, 19.58it/s]
 92%|█████████▏| 5183/5625 [04:33<00:22, 19.53it/s]
 92%|█████████▏| 5186/5625 [04:33<00:22, 19.82it/s]
 92%|█████████▏| 5188/5625 [04:33<00:22, 19.27it/s]
 92%|█████████▏| 5190/5625 [04:33<00:23, 18.76it/s]
 92%|█████████▏| 5192/5625 [04:34<00:22, 18.97it/s]
 92%|█████████▏| 5194/5625 [04:34<00:22, 19.08it/s]
 92%|█████████▏| 5197/5625 [04:34<00:22, 19.33it/s]
 92%|█████████▏| 5199/5625 [04:34<00:21, 19.47it/s]
 92%|█████████▏| 5201/5625 [04:34<00:22, 19.24it/s]
 92%|█████████▏| 5203/5625 [04:34<00:22, 18.81it/s]
 93%|█████████▎| 5205/5625 [04:34<00:22, 18.63it/s]
 93%|█████████▎| 5207/5625 [04:34<00:22, 18.97it/s]
 93%|█████████▎| 5209/5625 [04:34<00:21, 19.25it/s]
 93%|█████████▎| 5211/5625 [04:35<00:21, 19.41it/s]
 93%|█████████▎| 5214/5625 [04:35<00:20, 19.72it/s]
 93%|█████████▎| 5216/5625 [04:35<00:21, 19.37it/s]
 93%|█████████▎| 5219/5625 [04:35<00:20, 20.14it/s]
 93%|█████████▎| 5222/5625 [04:35<00:20, 19.29it/s]
 93%|█████████▎| 5224/5625 [04:35<00:21, 19.08it/s]
 93%|█████████▎| 5226/5625 [04:35<00:21, 18.91it/s]
 93%|█████████▎| 5228/5625 [04:35<00:20, 18.99it/s]
 93%|█████████▎| 5231/5625 [04:36<00:20, 19.57it/s]
 93%|█████████▎| 5233/5625 [04:36<00:20, 19.05it/s]
 93%|█████████▎| 5235/5625 [04:36<00:20, 19.17it/s]
 93%|█████████▎| 5238/5625 [04:36<00:19, 19.79it/s]
 93%|█████████▎| 5240/5625 [04:36<00:19, 19.40it/s]
 93%|█████████▎| 5242/5625 [04:36<00:20, 19.07it/s]
 93%|█████████▎| 5245/5625 [04:36<00:19, 19.30it/s]
 93%|█████████▎| 5247/5625 [04:36<00:19, 19.20it/s]
 93%|█████████▎| 5249/5625 [04:37<00:20, 18.73it/s]
 93%|█████████▎| 5251/5625 [04:37<00:20, 18.61it/s]
 93%|█████████▎| 5254/5625 [04:37<00:19, 19.02it/s]
 93%|█████████▎| 5256/5625 [04:37<00:19, 19.04it/s]
 93%|█████████▎| 5258/5625 [04:37<00:19, 18.88it/s]
 94%|█████████▎| 5260/5625 [04:37<00:19, 18.71it/s]
 94%|█████████▎| 5263/5625 [04:37<00:18, 19.26it/s]
 94%|█████████▎| 5265/5625 [04:37<00:18, 19.22it/s]
 94%|█████████▎| 5267/5625 [04:37<00:18, 19.37it/s]
 94%|█████████▎| 5270/5625 [04:38<00:17, 19.80it/s]
 94%|█████████▎| 5272/5625 [04:38<00:18, 19.46it/s]
 94%|█████████▍| 5274/5625 [04:38<00:18, 18.86it/s]
 94%|█████████▍| 5276/5625 [04:38<00:18, 18.91it/s]
 94%|█████████▍| 5278/5625 [04:38<00:18, 18.82it/s]
 94%|█████████▍| 5280/5625 [04:38<00:18, 18.75it/s]
 94%|█████████▍| 5282/5625 [04:38<00:18, 19.02it/s]
 94%|█████████▍| 5284/5625 [04:38<00:18, 18.62it/s]
 94%|█████████▍| 5286/5625 [04:38<00:18, 18.58it/s]
 94%|█████████▍| 5288/5625 [04:39<00:18, 18.50it/s]
 94%|█████████▍| 5291/5625 [04:39<00:17, 18.87it/s]
 94%|█████████▍| 5293/5625 [04:39<00:17, 18.61it/s]
 94%|█████████▍| 5295/5625 [04:39<00:17, 18.36it/s]
 94%|█████████▍| 5297/5625 [04:39<00:17, 18.52it/s]
 94%|█████████▍| 5299/5625 [04:39<00:17, 18.31it/s]
 94%|█████████▍| 5301/5625 [04:39<00:17, 18.55it/s]
 94%|█████████▍| 5304/5625 [04:39<00:16, 19.04it/s]
 94%|█████████▍| 5306/5625 [04:40<00:16, 19.07it/s]
 94%|█████████▍| 5308/5625 [04:40<00:16, 19.30it/s]
 94%|█████████▍| 5310/5625 [04:40<00:16, 19.37it/s]
 94%|█████████▍| 5312/5625 [04:40<00:16, 18.95it/s]
 94%|█████████▍| 5315/5625 [04:40<00:16, 19.20it/s]
 95%|█████████▍| 5318/5625 [04:40<00:15, 19.54it/s]
 95%|█████████▍| 5320/5625 [04:40<00:15, 19.24it/s]
 95%|█████████▍| 5322/5625 [04:40<00:15, 19.28it/s]
 95%|█████████▍| 5324/5625 [04:40<00:15, 19.15it/s]
 95%|█████████▍| 5327/5625 [04:41<00:15, 19.35it/s]
 95%|█████████▍| 5329/5625 [04:41<00:15, 19.13it/s]
 95%|█████████▍| 5331/5625 [04:41<00:15, 19.19it/s]
 95%|█████████▍| 5334/5625 [04:41<00:15, 19.37it/s]
 95%|█████████▍| 5337/5625 [04:41<00:14, 19.45it/s]
 95%|█████████▍| 5339/5625 [04:41<00:15, 18.99it/s]
 95%|█████████▍| 5341/5625 [04:41<00:15, 18.87it/s]
 95%|█████████▍| 5343/5625 [04:41<00:15, 18.48it/s]
 95%|█████████▌| 5345/5625 [04:42<00:14, 18.74it/s]
 95%|█████████▌| 5348/5625 [04:42<00:14, 19.67it/s]
 95%|█████████▌| 5351/5625 [04:42<00:13, 19.64it/s]
 95%|█████████▌| 5353/5625 [04:42<00:13, 19.48it/s]
 95%|█████████▌| 5356/5625 [04:42<00:13, 19.81it/s]
 95%|█████████▌| 5358/5625 [04:42<00:13, 19.27it/s]
 95%|█████████▌| 5360/5625 [04:42<00:13, 19.23it/s]
 95%|█████████▌| 5362/5625 [04:42<00:14, 18.71it/s]
 95%|█████████▌| 5364/5625 [04:43<00:13, 18.67it/s]
 95%|█████████▌| 5366/5625 [04:43<00:13, 18.78it/s]
 95%|█████████▌| 5369/5625 [04:43<00:12, 20.02it/s]
 95%|█████████▌| 5371/5625 [04:43<00:13, 19.44it/s]
 96%|█████████▌| 5373/5625 [04:43<00:13, 19.34it/s]
 96%|█████████▌| 5375/5625 [04:43<00:13, 19.02it/s]
 96%|█████████▌| 5378/5625 [04:43<00:12, 19.91it/s]
 96%|█████████▌| 5381/5625 [04:43<00:12, 20.29it/s]
 96%|█████████▌| 5384/5625 [04:44<00:11, 20.72it/s]
 96%|█████████▌| 5387/5625 [04:44<00:12, 19.81it/s]
 96%|█████████▌| 5389/5625 [04:44<00:12, 19.18it/s]
 96%|█████████▌| 5391/5625 [04:44<00:12, 18.77it/s]
 96%|█████████▌| 5393/5625 [04:44<00:12, 18.78it/s]
 96%|█████████▌| 5395/5625 [04:44<00:12, 18.76it/s]
 96%|█████████▌| 5398/5625 [04:44<00:11, 19.66it/s]
 96%|█████████▌| 5400/5625 [04:44<00:11, 18.96it/s]
 96%|█████████▌| 5402/5625 [04:45<00:11, 18.71it/s]
 96%|█████████▌| 5405/5625 [04:45<00:11, 18.98it/s]
 96%|█████████▌| 5408/5625 [04:45<00:10, 20.01it/s]
 96%|█████████▌| 5410/5625 [04:45<00:10, 19.76it/s]
 96%|█████████▌| 5412/5625 [04:45<00:11, 19.16it/s]
 96%|█████████▌| 5414/5625 [04:45<00:11, 18.56it/s]
 96%|█████████▋| 5416/5625 [04:45<00:11, 18.62it/s]
 96%|█████████▋| 5419/5625 [04:45<00:10, 19.14it/s]
 96%|█████████▋| 5422/5625 [04:46<00:10, 19.48it/s]
 96%|█████████▋| 5424/5625 [04:46<00:10, 19.07it/s]
 96%|█████████▋| 5426/5625 [04:46<00:10, 18.87it/s]
 96%|█████████▋| 5428/5625 [04:46<00:10, 19.05it/s]
 97%|█████████▋| 5430/5625 [04:46<00:10, 19.13it/s]
 97%|█████████▋| 5433/5625 [04:46<00:09, 19.53it/s]
 97%|█████████▋| 5435/5625 [04:46<00:09, 19.57it/s]
 97%|█████████▋| 5437/5625 [04:46<00:09, 19.45it/s]
 97%|█████████▋| 5439/5625 [04:46<00:09, 18.85it/s]
 97%|█████████▋| 5441/5625 [04:47<00:09, 18.77it/s]
 97%|█████████▋| 5443/5625 [04:47<00:09, 18.38it/s]
 97%|█████████▋| 5445/5625 [04:47<00:09, 18.66it/s]
 97%|█████████▋| 5447/5625 [04:47<00:09, 18.69it/s]
 97%|█████████▋| 5449/5625 [04:47<00:09, 18.94it/s]
 97%|█████████▋| 5451/5625 [04:47<00:09, 19.22it/s]
 97%|█████████▋| 5453/5625 [04:47<00:08, 19.15it/s]
 97%|█████████▋| 5455/5625 [04:47<00:08, 19.27it/s]
 97%|█████████▋| 5458/5625 [04:47<00:08, 19.33it/s]
 97%|█████████▋| 5460/5625 [04:48<00:08, 18.98it/s]
 97%|█████████▋| 5462/5625 [04:48<00:08, 18.43it/s]
 97%|█████████▋| 5464/5625 [04:48<00:08, 18.42it/s]
 97%|█████████▋| 5466/5625 [04:48<00:08, 18.49it/s]
 97%|█████████▋| 5468/5625 [04:48<00:08, 18.40it/s]
 97%|█████████▋| 5470/5625 [04:48<00:08, 18.47it/s]
 97%|█████████▋| 5473/5625 [04:48<00:08, 18.74it/s]
 97%|█████████▋| 5475/5625 [04:48<00:08, 18.53it/s]
 97%|█████████▋| 5478/5625 [04:49<00:07, 19.29it/s]
 97%|█████████▋| 5481/5625 [04:49<00:07, 20.32it/s]
 97%|█████████▋| 5484/5625 [04:49<00:07, 19.34it/s]
 98%|█████████▊| 5486/5625 [04:49<00:07, 19.02it/s]
 98%|█████████▊| 5489/5625 [04:49<00:07, 19.36it/s]
 98%|█████████▊| 5491/5625 [04:49<00:07, 19.04it/s]
 98%|█████████▊| 5494/5625 [04:49<00:06, 19.39it/s]
 98%|█████████▊| 5496/5625 [04:49<00:06, 19.09it/s]
 98%|█████████▊| 5498/5625 [04:50<00:06, 18.83it/s]
 98%|█████████▊| 5500/5625 [04:50<00:06, 19.13it/s]
 98%|█████████▊| 5502/5625 [04:50<00:06, 18.60it/s]
 98%|█████████▊| 5505/5625 [04:50<00:06, 18.76it/s]
 98%|█████████▊| 5507/5625 [04:50<00:06, 18.42it/s]
 98%|█████████▊| 5509/5625 [04:50<00:06, 18.24it/s]
 98%|█████████▊| 5511/5625 [04:50<00:06, 18.08it/s]
 98%|█████████▊| 5513/5625 [04:50<00:06, 18.59it/s]
 98%|█████████▊| 5515/5625 [04:50<00:05, 18.98it/s]
 98%|█████████▊| 5517/5625 [04:51<00:05, 18.79it/s]
 98%|█████████▊| 5520/5625 [04:51<00:05, 19.41it/s]
 98%|█████████▊| 5522/5625 [04:51<00:05, 19.52it/s]
 98%|█████████▊| 5524/5625 [04:51<00:05, 19.01it/s]
 98%|█████████▊| 5527/5625 [04:51<00:05, 19.40it/s]
 98%|█████████▊| 5530/5625 [04:51<00:04, 19.34it/s]
 98%|█████████▊| 5533/5625 [04:51<00:04, 19.75it/s]
 98%|█████████▊| 5535/5625 [04:51<00:04, 19.72it/s]
 98%|█████████▊| 5538/5625 [04:52<00:04, 20.22it/s]
 99%|█████████▊| 5541/5625 [04:52<00:04, 20.50it/s]
 99%|█████████▊| 5544/5625 [04:52<00:03, 20.32it/s]
 99%|█████████▊| 5547/5625 [04:52<00:03, 19.70it/s]
 99%|█████████▊| 5549/5625 [04:52<00:03, 19.57it/s]
 99%|█████████▊| 5551/5625 [04:52<00:03, 19.26it/s]
 99%|█████████▊| 5553/5625 [04:52<00:03, 19.10it/s]
 99%|█████████▉| 5556/5625 [04:53<00:03, 19.49it/s]
 99%|█████████▉| 5558/5625 [04:53<00:03, 18.90it/s]
 99%|█████████▉| 5560/5625 [04:53<00:03, 19.10it/s]
 99%|█████████▉| 5562/5625 [04:53<00:03, 18.97it/s]
 99%|█████████▉| 5565/5625 [04:53<00:03, 19.44it/s]
 99%|█████████▉| 5568/5625 [04:53<00:02, 19.66it/s]
 99%|█████████▉| 5570/5625 [04:53<00:02, 19.35it/s]
 99%|█████████▉| 5573/5625 [04:53<00:02, 19.61it/s]
 99%|█████████▉| 5576/5625 [04:54<00:02, 19.71it/s]
 99%|█████████▉| 5578/5625 [04:54<00:02, 19.36it/s]
 99%|█████████▉| 5580/5625 [04:54<00:02, 19.08it/s]
 99%|█████████▉| 5583/5625 [04:54<00:02, 19.85it/s]
 99%|█████████▉| 5586/5625 [04:54<00:01, 20.24it/s]
 99%|█████████▉| 5589/5625 [04:54<00:01, 19.61it/s]
 99%|█████████▉| 5591/5625 [04:54<00:01, 19.07it/s]
 99%|█████████▉| 5593/5625 [04:54<00:01, 19.18it/s]
 99%|█████████▉| 5595/5625 [04:55<00:01, 19.15it/s]
100%|█████████▉| 5597/5625 [04:55<00:01, 19.04it/s]
100%|█████████▉| 5599/5625 [04:55<00:01, 19.15it/s]
100%|█████████▉| 5602/5625 [04:55<00:01, 19.25it/s]
100%|█████████▉| 5604/5625 [04:55<00:01, 18.98it/s]
100%|█████████▉| 5606/5625 [04:55<00:01, 18.96it/s]
100%|█████████▉| 5608/5625 [04:55<00:00, 18.45it/s]
100%|█████████▉| 5610/5625 [04:55<00:00, 18.80it/s]
100%|█████████▉| 5613/5625 [04:56<00:00, 19.43it/s]
100%|█████████▉| 5616/5625 [04:56<00:00, 19.55it/s]
100%|█████████▉| 5618/5625 [04:56<00:00, 19.34it/s]
100%|█████████▉| 5620/5625 [04:56<00:00, 19.24it/s]
100%|█████████▉| 5622/5625 [04:56<00:00, 19.04it/s]
100%|█████████▉| 5624/5625 [04:56<00:00, 18.56it/s]
                                                   

100%|██████████| 5625/5625 [04:56<00:00, 18.56it/s]{'eval_loss': 0.6903769373893738, 'eval_accuracy': 0.7152, 'eval_f1': 0.712613963825246, 'eval_runtime': 1.7347, 'eval_samples_per_second': 1441.192, 'eval_steps_per_second': 180.437, 'epoch': 2.0}
{'loss': 0.3136, 'learning_rate': 2.2548394621518748e-11, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.35it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.43it/s]

 21%|██        | 66/313 [00:00<00:01, 206.00it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.35it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.69it/s]

 40%|████      | 126/313 [00:00<00:01, 185.30it/s]

 46%|████▋     | 145/313 [00:00<00:00, 183.13it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 184.11it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.28it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.46it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.53it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 165.24it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.93it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.87it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.66it/s]

                                                  

                                                   

100%|██████████| 313/313 [00:01<00:00, 178.66it/s]
100%|██████████| 5625/5625 [04:58<00:00, 18.56it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                   

100%|██████████| 5625/5625 [04:59<00:00, 18.56it/s]
100%|██████████| 5625/5625 [04:59<00:00, 18.78it/s]
[I 2023-10-27 00:06:05,993] Trial 47 finished with value: 0.7161629062675927 and parameters: {'lr_scheduler_type': 'cosine', 'learning_rate': 2.60182313140073e-05, 'per_device_train_batch_size': 16, 'weight_decay': 1.992115813871039e-05}. Best is trial 22 with value: 0.7303298984454403.
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7993480563163757, 'eval_accuracy': 0.7156, 'eval_f1': 0.7161629062675927, 'eval_runtime': 1.7307, 'eval_samples_per_second': 1444.499, 'eval_steps_per_second': 180.851, 'epoch': 3.0}
{'train_runtime': 299.4441, 'train_samples_per_second': 300.557, 'train_steps_per_second': 18.785, 'train_loss': 0.5386502278645834, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:12,  3.66it/s]
  0%|          | 2/705 [00:00<03:10,  3.69it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:07,  3.73it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.81it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.82it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.78it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.83it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.79it/s]
  3%|▎         | 24/705 [00:06<03:00,  3.77it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.79it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.75it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.83it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.79it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.83it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.82it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.75it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.76it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.79it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:50,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.80it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<03:02,  3.48it/s]
 10%|█         | 72/705 [00:19<02:53,  3.66it/s]
 10%|█         | 73/705 [00:19<02:51,  3.70it/s]
 10%|█         | 74/705 [00:19<02:49,  3.72it/s]
 11%|█         | 75/705 [00:19<02:49,  3.73it/s]
 11%|█         | 76/705 [00:20<02:48,  3.73it/s]
 11%|█         | 77/705 [00:20<02:48,  3.73it/s]
 11%|█         | 78/705 [00:20<02:45,  3.80it/s]
 11%|█         | 79/705 [00:20<02:46,  3.76it/s]
 11%|█▏        | 80/705 [00:21<02:45,  3.77it/s]
 11%|█▏        | 81/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 82/705 [00:21<02:47,  3.73it/s]
 12%|█▏        | 83/705 [00:21<02:45,  3.76it/s]
 12%|█▏        | 84/705 [00:22<02:42,  3.83it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.81it/s]
 12%|█▏        | 86/705 [00:22<02:44,  3.77it/s]
 12%|█▏        | 87/705 [00:23<02:44,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:44,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<03:00,  3.40it/s]
 13%|█▎        | 91/705 [00:24<02:53,  3.54it/s]
 13%|█▎        | 92/705 [00:24<02:50,  3.60it/s]
 13%|█▎        | 93/705 [00:24<02:48,  3.64it/s]
 13%|█▎        | 94/705 [00:24<02:46,  3.67it/s]
 13%|█▎        | 95/705 [00:25<02:45,  3.69it/s]
 14%|█▎        | 96/705 [00:25<02:43,  3.72it/s]
 14%|█▍        | 97/705 [00:25<02:43,  3.71it/s]
 14%|█▍        | 98/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.72it/s]
 14%|█▍        | 100/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 101/705 [00:26<02:42,  3.73it/s]
 14%|█▍        | 102/705 [00:27<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:41,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:28<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.78it/s]
 15%|█▌        | 109/705 [00:29<02:47,  3.56it/s]
 16%|█▌        | 110/705 [00:29<02:44,  3.62it/s]
 16%|█▌        | 111/705 [00:29<02:41,  3.68it/s]
 16%|█▌        | 112/705 [00:29<02:40,  3.69it/s]
 16%|█▌        | 113/705 [00:30<02:36,  3.77it/s]
 16%|█▌        | 114/705 [00:30<02:36,  3.77it/s]
 16%|█▋        | 115/705 [00:30<02:37,  3.75it/s]
 16%|█▋        | 116/705 [00:30<02:36,  3.76it/s]
 17%|█▋        | 117/705 [00:31<02:35,  3.78it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.76it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:32<02:32,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.90it/s]
 18%|█▊        | 125/705 [00:33<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:30,  3.86it/s]
 18%|█▊        | 127/705 [00:33<02:30,  3.85it/s]
 18%|█▊        | 128/705 [00:34<02:48,  3.42it/s]
 18%|█▊        | 129/705 [00:34<02:42,  3.54it/s]
 18%|█▊        | 130/705 [00:34<02:39,  3.61it/s]
 19%|█▊        | 131/705 [00:34<02:37,  3.66it/s]
 19%|█▊        | 132/705 [00:35<02:34,  3.71it/s]
 19%|█▉        | 133/705 [00:35<02:33,  3.72it/s]
 19%|█▉        | 134/705 [00:35<02:32,  3.74it/s]
 19%|█▉        | 135/705 [00:35<02:32,  3.75it/s]
 19%|█▉        | 136/705 [00:36<02:31,  3.76it/s]
 19%|█▉        | 137/705 [00:36<02:30,  3.78it/s]
 20%|█▉        | 138/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 139/705 [00:36<02:30,  3.77it/s]
 20%|█▉        | 140/705 [00:37<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:38<02:26,  3.83it/s]
 20%|██        | 144/705 [00:38<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:39<02:24,  3.87it/s]
 21%|██        | 148/705 [00:39<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:40<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.80it/s]
 22%|██▏       | 155/705 [00:41<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.94it/s]
 22%|██▏       | 158/705 [00:41<02:20,  3.88it/s]
 23%|██▎       | 159/705 [00:42<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:43<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:43<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.83it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:44<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:44<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:17,  3.88it/s]
 24%|██▍       | 170/705 [00:45<02:18,  3.85it/s]
 24%|██▍       | 171/705 [00:45<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.75it/s]
 25%|██▍       | 174/705 [00:46<02:21,  3.76it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.88it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:47<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.78it/s]
 26%|██▌       | 182/705 [00:48<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:49<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:49<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:50<02:15,  3.80it/s]
 27%|██▋       | 190/705 [00:50<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:51<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:52<02:12,  3.84it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.85it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.93it/s]
 29%|██▊       | 201/705 [00:53<02:09,  3.90it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.86it/s]
 29%|██▉       | 203/705 [00:53<02:03,  4.05it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.97it/s]
 29%|██▉       | 205/705 [00:54<02:08,  3.91it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:55<02:10,  3.81it/s]
 30%|██▉       | 209/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:10,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:56<02:07,  3.87it/s]
 30%|███       | 213/705 [00:56<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:57<02:07,  3.84it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.76it/s]
 31%|███       | 219/705 [00:57<02:09,  3.77it/s]
 31%|███       | 220/705 [00:58<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.78it/s]
 32%|███▏      | 224/705 [00:59<02:07,  3.78it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [01:00<02:06,  3.79it/s]
 32%|███▏      | 228/705 [01:00<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:01<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:01<02:01,  3.90it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.86it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.7667, 'learning_rate': 3.3129482852262054e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.67it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.32it/s]

 21%|██        | 65/313 [00:00<00:01, 204.26it/s]

 27%|██▋       | 86/313 [00:00<00:01, 194.65it/s]

 34%|███▍      | 106/313 [00:00<00:01, 187.98it/s]

 40%|███▉      | 125/313 [00:00<00:01, 184.63it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.28it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 183.90it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 178.28it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 172.22it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.16it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.32it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 182.41it/s]

 88%|████████▊ | 277/313 [00:01<00:00, 184.52it/s]

 95%|█████████▍| 296/313 [00:01<00:00, 177.91it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 177.91it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 33%|███▎      | 236/705 [01:04<08:07,  1.04s/it]
 34%|███▎      | 237/705 [01:05<06:16,  1.24it/s]
 34%|███▍      | 238/705 [01:05<05:00,  1.55it/s]
 34%|███▍      | 239/705 [01:05<04:06,  1.89it/s]
 34%|███▍      | 240/705 [01:05<03:30,  2.21it/s]
 34%|███▍      | 241/705 [01:06<03:02,  2.54it/s]
 34%|███▍      | 242/705 [01:06<02:45,  2.80it/s]
 34%|███▍      | 243/705 [01:06<02:32,  3.04it/s]
 35%|███▍      | 244/705 [01:07<02:21,  3.27it/s]
 35%|███▍      | 245/705 [01:07<02:15,  3.40it/s]
 35%|███▍      | 246/705 [01:07<02:11,  3.48it/s]
 35%|███▌      | 247/705 [01:07<02:09,  3.54it/s]
 35%|███▌      | 248/705 [01:08<02:03,  3.70it/s]
 35%|███▌      | 249/705 [01:08<02:02,  3.72it/s]
 35%|███▌      | 250/705 [01:08<02:02,  3.72it/s]
 36%|███▌      | 251/705 [01:08<01:55,  3.94it/s]
 36%|███▌      | 252/705 [01:09<01:55,  3.91it/s]
 36%|███▌      | 253/705 [01:09<01:51,  4.07it/s]
 36%|███▌      | 254/705 [01:09<01:54,  3.95it/s]
 36%|███▌      | 255/705 [01:09<01:54,  3.93it/s]
 36%|███▋      | 256/705 [01:10<01:56,  3.86it/s]
 36%|███▋      | 257/705 [01:10<01:57,  3.81it/s]
 37%|███▋      | 258/705 [01:10<01:55,  3.85it/s]
 37%|███▋      | 259/705 [01:10<01:56,  3.83it/s]
 37%|███▋      | 260/705 [01:11<01:57,  3.80it/s]
 37%|███▋      | 261/705 [01:11<02:01,  3.64it/s]
 37%|███▋      | 262/705 [01:11<02:01,  3.66it/s]
 37%|███▋      | 263/705 [01:11<01:55,  3.82it/s]
 37%|███▋      | 264/705 [01:12<01:55,  3.81it/s]
 38%|███▊      | 265/705 [01:12<01:54,  3.85it/s]
 38%|███▊      | 266/705 [01:12<01:54,  3.83it/s]
 38%|███▊      | 267/705 [01:13<01:55,  3.80it/s]
 38%|███▊      | 268/705 [01:13<01:56,  3.77it/s]
 38%|███▊      | 269/705 [01:13<01:56,  3.75it/s]
 38%|███▊      | 270/705 [01:13<01:55,  3.76it/s]
 38%|███▊      | 271/705 [01:14<01:54,  3.80it/s]
 39%|███▊      | 272/705 [01:14<01:52,  3.85it/s]
 39%|███▊      | 273/705 [01:14<01:52,  3.85it/s]
 39%|███▉      | 274/705 [01:14<01:53,  3.81it/s]
 39%|███▉      | 275/705 [01:15<01:46,  4.04it/s]
 39%|███▉      | 276/705 [01:15<01:46,  4.02it/s]
 39%|███▉      | 277/705 [01:15<01:47,  3.99it/s]
 39%|███▉      | 278/705 [01:15<01:49,  3.90it/s]
 40%|███▉      | 279/705 [01:16<01:50,  3.84it/s]
 40%|███▉      | 280/705 [01:16<01:51,  3.82it/s]
 40%|███▉      | 281/705 [01:16<02:02,  3.46it/s]
 40%|████      | 282/705 [01:16<01:57,  3.60it/s]
 40%|████      | 283/705 [01:17<01:55,  3.65it/s]
 40%|████      | 284/705 [01:17<01:52,  3.74it/s]
 40%|████      | 285/705 [01:17<01:52,  3.74it/s]
 41%|████      | 286/705 [01:18<01:52,  3.74it/s]
 41%|████      | 287/705 [01:18<01:50,  3.77it/s]
 41%|████      | 288/705 [01:18<01:51,  3.75it/s]
 41%|████      | 289/705 [01:18<01:49,  3.81it/s]
 41%|████      | 290/705 [01:19<01:48,  3.82it/s]
 41%|████▏     | 291/705 [01:19<01:48,  3.81it/s]
 41%|████▏     | 292/705 [01:19<01:46,  3.88it/s]
 42%|████▏     | 293/705 [01:19<01:47,  3.84it/s]
 42%|████▏     | 294/705 [01:20<01:47,  3.81it/s]
 42%|████▏     | 295/705 [01:20<01:48,  3.79it/s]
 42%|████▏     | 296/705 [01:20<01:47,  3.82it/s]
 42%|████▏     | 297/705 [01:20<01:44,  3.92it/s]
 42%|████▏     | 298/705 [01:21<01:45,  3.87it/s]
 42%|████▏     | 299/705 [01:21<01:45,  3.85it/s]
 43%|████▎     | 300/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 301/705 [01:21<01:45,  3.84it/s]
 43%|████▎     | 302/705 [01:22<01:45,  3.82it/s]
 43%|████▎     | 303/705 [01:22<01:45,  3.80it/s]
 43%|████▎     | 304/705 [01:22<01:42,  3.91it/s]
 43%|████▎     | 305/705 [01:22<01:41,  3.95it/s]
 43%|████▎     | 306/705 [01:23<01:42,  3.90it/s]
 44%|████▎     | 307/705 [01:23<01:43,  3.83it/s]
 44%|████▎     | 308/705 [01:23<01:44,  3.79it/s]
 44%|████▍     | 309/705 [01:24<01:44,  3.81it/s]
 44%|████▍     | 310/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 311/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 312/705 [01:24<01:44,  3.77it/s]
 44%|████▍     | 313/705 [01:25<01:44,  3.77it/s]
 45%|████▍     | 314/705 [01:25<01:37,  4.00it/s]
 45%|████▍     | 315/705 [01:25<01:39,  3.92it/s]
 45%|████▍     | 316/705 [01:25<01:40,  3.87it/s]
 45%|████▍     | 317/705 [01:26<01:39,  3.89it/s]
 45%|████▌     | 318/705 [01:26<01:40,  3.84it/s]
 45%|████▌     | 319/705 [01:26<01:41,  3.79it/s]
 45%|████▌     | 320/705 [01:26<01:51,  3.46it/s]
 46%|████▌     | 321/705 [01:27<01:47,  3.57it/s]
 46%|████▌     | 322/705 [01:27<01:45,  3.63it/s]
 46%|████▌     | 323/705 [01:27<01:44,  3.65it/s]
 46%|████▌     | 324/705 [01:28<01:43,  3.67it/s]
 46%|████▌     | 325/705 [01:28<01:42,  3.72it/s]
 46%|████▌     | 326/705 [01:28<01:40,  3.76it/s]
 46%|████▋     | 327/705 [01:28<01:41,  3.74it/s]
 47%|████▋     | 328/705 [01:29<01:41,  3.72it/s]
 47%|████▋     | 329/705 [01:29<01:39,  3.79it/s]
 47%|████▋     | 330/705 [01:29<01:39,  3.77it/s]
 47%|████▋     | 331/705 [01:29<01:39,  3.77it/s]
 47%|████▋     | 332/705 [01:30<01:39,  3.75it/s]
 47%|████▋     | 333/705 [01:30<01:39,  3.75it/s]
 47%|████▋     | 334/705 [01:30<01:39,  3.74it/s]
 48%|████▊     | 335/705 [01:30<01:38,  3.77it/s]
 48%|████▊     | 336/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 337/705 [01:31<01:37,  3.76it/s]
 48%|████▊     | 338/705 [01:31<01:37,  3.78it/s]
 48%|████▊     | 339/705 [01:32<01:37,  3.75it/s]
 48%|████▊     | 340/705 [01:32<01:37,  3.74it/s]
 48%|████▊     | 341/705 [01:32<01:37,  3.73it/s]
 49%|████▊     | 342/705 [01:32<01:33,  3.88it/s]
 49%|████▊     | 343/705 [01:33<01:33,  3.86it/s]
 49%|████▉     | 344/705 [01:33<01:34,  3.81it/s]
 49%|████▉     | 345/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 346/705 [01:33<01:33,  3.85it/s]
 49%|████▉     | 347/705 [01:34<01:33,  3.84it/s]
 49%|████▉     | 348/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 349/705 [01:34<01:32,  3.86it/s]
 50%|████▉     | 350/705 [01:34<01:33,  3.81it/s]
 50%|████▉     | 351/705 [01:35<01:33,  3.78it/s]
 50%|████▉     | 352/705 [01:35<01:32,  3.81it/s]
 50%|█████     | 353/705 [01:35<01:32,  3.80it/s]
 50%|█████     | 354/705 [01:35<01:33,  3.76it/s]
 50%|█████     | 355/705 [01:36<01:33,  3.74it/s]
 50%|█████     | 356/705 [01:36<01:33,  3.75it/s]
 51%|█████     | 357/705 [01:36<01:33,  3.73it/s]
 51%|█████     | 358/705 [01:37<01:45,  3.29it/s]
 51%|█████     | 359/705 [01:37<01:41,  3.42it/s]
 51%|█████     | 360/705 [01:37<01:37,  3.52it/s]
 51%|█████     | 361/705 [01:37<01:36,  3.58it/s]
 51%|█████▏    | 362/705 [01:38<01:34,  3.63it/s]
 51%|█████▏    | 363/705 [01:38<01:33,  3.66it/s]
 52%|█████▏    | 364/705 [01:38<01:33,  3.67it/s]
 52%|█████▏    | 365/705 [01:39<01:32,  3.68it/s]
 52%|█████▏    | 366/705 [01:39<01:31,  3.71it/s]
 52%|█████▏    | 367/705 [01:39<01:29,  3.76it/s]
 52%|█████▏    | 368/705 [01:39<01:29,  3.77it/s]
 52%|█████▏    | 369/705 [01:40<01:29,  3.77it/s]
 52%|█████▏    | 370/705 [01:40<01:28,  3.79it/s]
 53%|█████▎    | 371/705 [01:40<01:26,  3.84it/s]
 53%|█████▎    | 372/705 [01:40<01:27,  3.80it/s]
 53%|█████▎    | 373/705 [01:41<01:27,  3.79it/s]
 53%|█████▎    | 374/705 [01:41<01:28,  3.76it/s]
 53%|█████▎    | 375/705 [01:41<01:27,  3.76it/s]
 53%|█████▎    | 376/705 [01:41<01:27,  3.74it/s]
 53%|█████▎    | 377/705 [01:42<01:25,  3.85it/s]
 54%|█████▎    | 378/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 379/705 [01:42<01:25,  3.83it/s]
 54%|█████▍    | 380/705 [01:42<01:24,  3.83it/s]
 54%|█████▍    | 381/705 [01:43<01:25,  3.81it/s]
 54%|█████▍    | 382/705 [01:43<01:25,  3.80it/s]
 54%|█████▍    | 383/705 [01:43<01:23,  3.84it/s]
 54%|█████▍    | 384/705 [01:44<01:24,  3.79it/s]
 55%|█████▍    | 385/705 [01:44<01:25,  3.76it/s]
 55%|█████▍    | 386/705 [01:44<01:23,  3.80it/s]
 55%|█████▍    | 387/705 [01:44<01:24,  3.78it/s]
 55%|█████▌    | 388/705 [01:45<01:24,  3.76it/s]
 55%|█████▌    | 389/705 [01:45<01:23,  3.80it/s]
 55%|█████▌    | 390/705 [01:45<01:23,  3.79it/s]
 55%|█████▌    | 391/705 [01:45<01:23,  3.76it/s]
 56%|█████▌    | 392/705 [01:46<01:22,  3.81it/s]
 56%|█████▌    | 393/705 [01:46<01:22,  3.79it/s]
 56%|█████▌    | 394/705 [01:46<01:21,  3.83it/s]
 56%|█████▌    | 395/705 [01:46<01:21,  3.80it/s]
 56%|█████▌    | 396/705 [01:47<01:21,  3.77it/s]
 56%|█████▋    | 397/705 [01:47<01:22,  3.75it/s]
 56%|█████▋    | 398/705 [01:47<01:21,  3.75it/s]
 57%|█████▋    | 399/705 [01:47<01:21,  3.76it/s]
 57%|█████▋    | 400/705 [01:48<01:21,  3.76it/s]
 57%|█████▋    | 401/705 [01:48<01:18,  3.85it/s]
 57%|█████▋    | 402/705 [01:48<01:19,  3.80it/s]
 57%|█████▋    | 403/705 [01:49<01:20,  3.77it/s]
 57%|█████▋    | 404/705 [01:49<01:16,  3.91it/s]
 57%|█████▋    | 405/705 [01:49<01:17,  3.87it/s]
 58%|█████▊    | 406/705 [01:49<01:18,  3.82it/s]
 58%|█████▊    | 407/705 [01:50<01:16,  3.91it/s]
 58%|█████▊    | 408/705 [01:50<01:16,  3.89it/s]
 58%|█████▊    | 409/705 [01:50<01:16,  3.86it/s]
 58%|█████▊    | 410/705 [01:50<01:17,  3.82it/s]
 58%|█████▊    | 411/705 [01:51<01:17,  3.80it/s]
 58%|█████▊    | 412/705 [01:51<01:16,  3.81it/s]
 59%|█████▊    | 413/705 [01:51<01:16,  3.84it/s]
 59%|█████▊    | 414/705 [01:51<01:16,  3.82it/s]
 59%|█████▉    | 415/705 [01:52<01:16,  3.80it/s]
 59%|█████▉    | 416/705 [01:52<01:15,  3.81it/s]
 59%|█████▉    | 417/705 [01:52<01:15,  3.83it/s]
 59%|█████▉    | 418/705 [01:52<01:13,  3.89it/s]
 59%|█████▉    | 419/705 [01:53<01:13,  3.88it/s]
 60%|█████▉    | 420/705 [01:53<01:13,  3.87it/s]
 60%|█████▉    | 421/705 [01:53<01:14,  3.83it/s]
 60%|█████▉    | 422/705 [01:53<01:14,  3.82it/s]
 60%|██████    | 423/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 424/705 [01:54<01:14,  3.78it/s]
 60%|██████    | 425/705 [01:54<01:13,  3.79it/s]
 60%|██████    | 426/705 [01:55<01:13,  3.80it/s]
 61%|██████    | 427/705 [01:55<01:13,  3.79it/s]
 61%|██████    | 428/705 [01:55<01:13,  3.76it/s]
 61%|██████    | 429/705 [01:55<01:12,  3.81it/s]
 61%|██████    | 430/705 [01:56<01:12,  3.80it/s]
 61%|██████    | 431/705 [01:56<01:12,  3.77it/s]
 61%|██████▏   | 432/705 [01:56<01:11,  3.79it/s]
 61%|██████▏   | 433/705 [01:56<01:11,  3.78it/s]
 62%|██████▏   | 434/705 [01:57<01:11,  3.78it/s]
 62%|██████▏   | 435/705 [01:57<01:09,  3.86it/s]
 62%|██████▏   | 436/705 [01:57<01:09,  3.85it/s]
 62%|██████▏   | 437/705 [01:57<01:10,  3.82it/s]
 62%|██████▏   | 438/705 [01:58<01:10,  3.80it/s]
 62%|██████▏   | 439/705 [01:58<01:10,  3.79it/s]
 62%|██████▏   | 440/705 [01:58<01:10,  3.76it/s]
 63%|██████▎   | 441/705 [01:58<01:10,  3.74it/s]
 63%|██████▎   | 442/705 [01:59<01:10,  3.75it/s]
 63%|██████▎   | 443/705 [01:59<01:08,  3.80it/s]
 63%|██████▎   | 444/705 [01:59<01:09,  3.77it/s]
 63%|██████▎   | 445/705 [02:00<01:08,  3.77it/s]
 63%|██████▎   | 446/705 [02:00<01:06,  3.89it/s]
 63%|██████▎   | 447/705 [02:00<01:06,  3.87it/s]
 64%|██████▎   | 448/705 [02:00<01:06,  3.84it/s]
 64%|██████▎   | 449/705 [02:01<01:06,  3.86it/s]
 64%|██████▍   | 450/705 [02:01<01:06,  3.81it/s]
 64%|██████▍   | 451/705 [02:01<01:06,  3.80it/s]
 64%|██████▍   | 452/705 [02:01<01:06,  3.83it/s]
 64%|██████▍   | 453/705 [02:02<01:05,  3.87it/s]
 64%|██████▍   | 454/705 [02:02<01:04,  3.88it/s]
 65%|██████▍   | 455/705 [02:02<01:05,  3.85it/s]
 65%|██████▍   | 456/705 [02:02<01:04,  3.84it/s]
 65%|██████▍   | 457/705 [02:03<01:04,  3.82it/s]
 65%|██████▍   | 458/705 [02:03<01:04,  3.81it/s]
 65%|██████▌   | 459/705 [02:03<01:04,  3.80it/s]
 65%|██████▌   | 460/705 [02:03<01:04,  3.79it/s]
 65%|██████▌   | 461/705 [02:04<01:04,  3.78it/s]
 66%|██████▌   | 462/705 [02:04<01:04,  3.77it/s]
 66%|██████▌   | 463/705 [02:04<01:04,  3.75it/s]
 66%|██████▌   | 464/705 [02:05<01:04,  3.73it/s]
 66%|██████▌   | 465/705 [02:05<01:03,  3.76it/s]
 66%|██████▌   | 466/705 [02:05<01:03,  3.74it/s]
 66%|██████▌   | 467/705 [02:05<01:03,  3.77it/s]
 66%|██████▋   | 468/705 [02:06<01:03,  3.75it/s]
 67%|██████▋   | 469/705 [02:06<01:02,  3.79it/s]
 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]
                                                 

 67%|██████▋   | 470/705 [02:06<00:51,  4.53it/s]{'eval_loss': 0.6643490791320801, 'eval_accuracy': 0.7012, 'eval_f1': 0.7008924823263979, 'eval_runtime': 1.7373, 'eval_samples_per_second': 1439.017, 'eval_steps_per_second': 180.165, 'epoch': 1.0}
{'loss': 0.5632, 'learning_rate': 3.3129482852262054e-05, 'epoch': 2.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.62it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.74it/s]

 21%|██        | 65/313 [00:00<00:01, 204.70it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.08it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.34it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.04it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.60it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.48it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.10it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.01it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 167.89it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 164.99it/s]

 82%|████████▏ | 258/313 [00:01<00:00, 183.17it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 184.79it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 178.91it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.91it/s]
 67%|██████▋   | 470/705 [02:08<00:51,  4.53it/s]

                                                  /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

 67%|██████▋   | 471/705 [02:09<04:03,  1.04s/it]
 67%|██████▋   | 472/705 [02:09<03:08,  1.24it/s]
 67%|██████▋   | 473/705 [02:09<02:29,  1.55it/s]
 67%|██████▋   | 474/705 [02:10<02:02,  1.89it/s]
 67%|██████▋   | 475/705 [02:10<01:43,  2.22it/s]
 68%|██████▊   | 476/705 [02:10<01:30,  2.52it/s]
 68%|██████▊   | 477/705 [02:11<01:21,  2.79it/s]
 68%|██████▊   | 478/705 [02:11<01:15,  3.01it/s]
 68%|██████▊   | 479/705 [02:11<01:10,  3.21it/s]
 68%|██████▊   | 480/705 [02:11<01:07,  3.35it/s]
 68%|██████▊   | 481/705 [02:12<01:03,  3.50it/s]
 68%|██████▊   | 482/705 [02:12<01:02,  3.56it/s]
 69%|██████▊   | 483/705 [02:12<01:01,  3.61it/s]
 69%|██████▊   | 484/705 [02:12<01:00,  3.64it/s]
 69%|██████▉   | 485/705 [02:13<00:58,  3.77it/s]
 69%|██████▉   | 486/705 [02:13<00:58,  3.76it/s]
 69%|██████▉   | 487/705 [02:13<00:57,  3.76it/s]
 69%|██████▉   | 488/705 [02:13<00:56,  3.83it/s]
 69%|██████▉   | 489/705 [02:14<00:57,  3.79it/s]
 70%|██████▉   | 490/705 [02:14<00:56,  3.78it/s]
 70%|██████▉   | 491/705 [02:14<00:55,  3.82it/s]
 70%|██████▉   | 492/705 [02:14<00:56,  3.79it/s]
 70%|██████▉   | 493/705 [02:15<00:56,  3.78it/s]
 70%|███████   | 494/705 [02:15<00:56,  3.75it/s]
 70%|███████   | 495/705 [02:15<00:54,  3.86it/s]
 70%|███████   | 496/705 [02:16<00:54,  3.85it/s]
 70%|███████   | 497/705 [02:16<00:54,  3.80it/s]
 71%|███████   | 498/705 [02:16<00:53,  3.87it/s]
 71%|███████   | 499/705 [02:16<00:53,  3.84it/s]
 71%|███████   | 500/705 [02:17<00:53,  3.86it/s]
 71%|███████   | 501/705 [02:17<00:53,  3.84it/s]
 71%|███████   | 502/705 [02:17<00:53,  3.82it/s]
 71%|███████▏  | 503/705 [02:17<00:53,  3.81it/s]
 71%|███████▏  | 504/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 505/705 [02:18<00:53,  3.77it/s]
 72%|███████▏  | 506/705 [02:18<00:52,  3.78it/s]
 72%|███████▏  | 507/705 [02:18<00:52,  3.80it/s]
 72%|███████▏  | 508/705 [02:19<00:52,  3.76it/s]
 72%|███████▏  | 509/705 [02:19<00:51,  3.80it/s]
 72%|███████▏  | 510/705 [02:19<00:56,  3.47it/s]
 72%|███████▏  | 511/705 [02:20<00:54,  3.58it/s]
 73%|███████▎  | 512/705 [02:20<00:53,  3.64it/s]
 73%|███████▎  | 513/705 [02:20<00:52,  3.67it/s]
 73%|███████▎  | 514/705 [02:20<00:51,  3.68it/s]
 73%|███████▎  | 515/705 [02:21<00:51,  3.71it/s]
 73%|███████▎  | 516/705 [02:21<00:50,  3.72it/s]
 73%|███████▎  | 517/705 [02:21<00:50,  3.73it/s]
 73%|███████▎  | 518/705 [02:21<00:50,  3.74it/s]
 74%|███████▎  | 519/705 [02:22<00:49,  3.77it/s]
 74%|███████▍  | 520/705 [02:22<00:48,  3.83it/s]
 74%|███████▍  | 521/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 522/705 [02:22<00:47,  3.84it/s]
 74%|███████▍  | 523/705 [02:23<00:47,  3.82it/s]
 74%|███████▍  | 524/705 [02:23<00:46,  3.85it/s]
 74%|███████▍  | 525/705 [02:23<00:46,  3.83it/s]
 75%|███████▍  | 526/705 [02:23<00:47,  3.79it/s]
 75%|███████▍  | 527/705 [02:24<00:47,  3.76it/s]
 75%|███████▍  | 528/705 [02:24<00:47,  3.74it/s]
 75%|███████▌  | 529/705 [02:24<00:46,  3.75it/s]
 75%|███████▌  | 530/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 531/705 [02:25<00:45,  3.82it/s]
 75%|███████▌  | 532/705 [02:25<00:45,  3.78it/s]
 76%|███████▌  | 533/705 [02:25<00:45,  3.79it/s]
 76%|███████▌  | 534/705 [02:26<00:45,  3.77it/s]
 76%|███████▌  | 535/705 [02:26<00:44,  3.83it/s]
 76%|███████▌  | 536/705 [02:26<00:44,  3.79it/s]
 76%|███████▌  | 537/705 [02:26<00:44,  3.78it/s]
 76%|███████▋  | 538/705 [02:27<00:44,  3.75it/s]
 76%|███████▋  | 539/705 [02:27<00:44,  3.73it/s]
 77%|███████▋  | 540/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 541/705 [02:27<00:43,  3.78it/s]
 77%|███████▋  | 542/705 [02:28<00:42,  3.84it/s]
 77%|███████▋  | 543/705 [02:28<00:42,  3.80it/s]
 77%|███████▋  | 544/705 [02:28<00:42,  3.79it/s]
 77%|███████▋  | 545/705 [02:29<00:42,  3.76it/s]
 77%|███████▋  | 546/705 [02:29<00:41,  3.81it/s]
 78%|███████▊  | 547/705 [02:29<00:41,  3.82it/s]
 78%|███████▊  | 548/705 [02:29<00:45,  3.45it/s]
 78%|███████▊  | 549/705 [02:30<00:43,  3.58it/s]
 78%|███████▊  | 550/705 [02:30<00:42,  3.66it/s]
 78%|███████▊  | 551/705 [02:30<00:41,  3.69it/s]
 78%|███████▊  | 552/705 [02:30<00:41,  3.71it/s]
 78%|███████▊  | 553/705 [02:31<00:41,  3.70it/s]
 79%|███████▊  | 554/705 [02:31<00:40,  3.70it/s]
 79%|███████▊  | 555/705 [02:31<00:40,  3.70it/s]
 79%|███████▉  | 556/705 [02:31<00:38,  3.82it/s]
 79%|███████▉  | 557/705 [02:32<00:38,  3.81it/s]
 79%|███████▉  | 558/705 [02:32<00:38,  3.82it/s]
 79%|███████▉  | 559/705 [02:32<00:38,  3.80it/s]
 79%|███████▉  | 560/705 [02:33<00:37,  3.83it/s]
 80%|███████▉  | 561/705 [02:33<00:37,  3.85it/s]
 80%|███████▉  | 562/705 [02:33<00:35,  4.03it/s]
 80%|███████▉  | 563/705 [02:33<00:35,  3.97it/s]
 80%|████████  | 564/705 [02:33<00:33,  4.16it/s]
 80%|████████  | 565/705 [02:34<00:33,  4.18it/s]
 80%|████████  | 566/705 [02:34<00:34,  4.02it/s]
 80%|████████  | 567/705 [02:34<00:35,  3.93it/s]
 81%|████████  | 568/705 [02:35<00:38,  3.57it/s]
 81%|████████  | 569/705 [02:35<00:36,  3.71it/s]
 81%|████████  | 570/705 [02:35<00:35,  3.77it/s]
 81%|████████  | 571/705 [02:35<00:35,  3.81it/s]
 81%|████████  | 572/705 [02:36<00:35,  3.77it/s]
 81%|████████▏ | 573/705 [02:36<00:35,  3.75it/s]
 81%|████████▏ | 574/705 [02:36<00:34,  3.75it/s]
 82%|████████▏ | 575/705 [02:36<00:34,  3.75it/s]
 82%|████████▏ | 576/705 [02:37<00:33,  3.81it/s]
 82%|████████▏ | 577/705 [02:37<00:33,  3.80it/s]
 82%|████████▏ | 578/705 [02:37<00:33,  3.78it/s]
 82%|████████▏ | 579/705 [02:37<00:33,  3.75it/s]
 82%|████████▏ | 580/705 [02:38<00:33,  3.73it/s]
 82%|████████▏ | 581/705 [02:38<00:32,  3.78it/s]
 83%|████████▎ | 582/705 [02:38<00:32,  3.76it/s]
 83%|████████▎ | 583/705 [02:39<00:32,  3.74it/s]
 83%|████████▎ | 584/705 [02:39<00:31,  3.81it/s]
 83%|████████▎ | 585/705 [02:39<00:31,  3.80it/s]
 83%|████████▎ | 586/705 [02:39<00:31,  3.79it/s]
 83%|████████▎ | 587/705 [02:40<00:33,  3.47it/s]
 83%|████████▎ | 588/705 [02:40<00:32,  3.55it/s]
 84%|████████▎ | 589/705 [02:40<00:32,  3.60it/s]
 84%|████████▎ | 590/705 [02:40<00:31,  3.63it/s]
 84%|████████▍ | 591/705 [02:41<00:31,  3.65it/s]
 84%|████████▍ | 592/705 [02:41<00:30,  3.73it/s]
 84%|████████▍ | 593/705 [02:41<00:30,  3.73it/s]
 84%|████████▍ | 594/705 [02:42<00:29,  3.72it/s]
 84%|████████▍ | 595/705 [02:42<00:29,  3.79it/s]
 85%|████████▍ | 596/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 597/705 [02:42<00:28,  3.79it/s]
 85%|████████▍ | 598/705 [02:43<00:28,  3.77it/s]
 85%|████████▍ | 599/705 [02:43<00:27,  3.85it/s]
 85%|████████▌ | 600/705 [02:43<00:27,  3.83it/s]
 85%|████████▌ | 601/705 [02:43<00:25,  4.05it/s]
 85%|████████▌ | 602/705 [02:44<00:26,  3.93it/s]
 86%|████████▌ | 603/705 [02:44<00:26,  3.88it/s]
 86%|████████▌ | 604/705 [02:44<00:26,  3.85it/s]
 86%|████████▌ | 605/705 [02:44<00:25,  3.85it/s]
 86%|████████▌ | 606/705 [02:45<00:25,  3.81it/s]
 86%|████████▌ | 607/705 [02:45<00:24,  3.99it/s]
 86%|████████▌ | 608/705 [02:45<00:24,  3.93it/s]
 86%|████████▋ | 609/705 [02:45<00:24,  3.85it/s]
 87%|████████▋ | 610/705 [02:46<00:24,  3.91it/s]
 87%|████████▋ | 611/705 [02:46<00:23,  3.98it/s]
 87%|████████▋ | 612/705 [02:46<00:23,  3.93it/s]
 87%|████████▋ | 613/705 [02:46<00:23,  3.86it/s]
 87%|████████▋ | 614/705 [02:47<00:23,  3.87it/s]
 87%|████████▋ | 615/705 [02:47<00:23,  3.86it/s]
 87%|████████▋ | 616/705 [02:47<00:22,  3.87it/s]
 88%|████████▊ | 617/705 [02:47<00:22,  3.92it/s]
 88%|████████▊ | 618/705 [02:48<00:22,  3.88it/s]
 88%|████████▊ | 619/705 [02:48<00:21,  3.97it/s]
 88%|████████▊ | 620/705 [02:48<00:21,  3.91it/s]
 88%|████████▊ | 621/705 [02:48<00:21,  3.93it/s]
 88%|████████▊ | 622/705 [02:49<00:21,  3.85it/s]
 88%|████████▊ | 623/705 [02:49<00:21,  3.88it/s]
 89%|████████▊ | 624/705 [02:49<00:20,  3.88it/s]
 89%|████████▊ | 625/705 [02:50<00:20,  3.85it/s]
 89%|████████▉ | 626/705 [02:50<00:20,  3.83it/s]
 89%|████████▉ | 627/705 [02:50<00:20,  3.80it/s]
 89%|████████▉ | 628/705 [02:50<00:20,  3.84it/s]
 89%|████████▉ | 629/705 [02:51<00:19,  3.82it/s]
 89%|████████▉ | 630/705 [02:51<00:19,  3.80it/s]
 90%|████████▉ | 631/705 [02:51<00:19,  3.76it/s]
 90%|████████▉ | 632/705 [02:51<00:19,  3.75it/s]
 90%|████████▉ | 633/705 [02:52<00:18,  3.80it/s]
 90%|████████▉ | 634/705 [02:52<00:18,  3.85it/s]
 90%|█████████ | 635/705 [02:52<00:18,  3.80it/s]
 90%|█████████ | 636/705 [02:52<00:18,  3.79it/s]
 90%|█████████ | 637/705 [02:53<00:17,  3.79it/s]
 90%|█████████ | 638/705 [02:53<00:17,  3.78it/s]
 91%|█████████ | 639/705 [02:53<00:17,  3.79it/s]
 91%|█████████ | 640/705 [02:53<00:16,  3.93it/s]
 91%|█████████ | 641/705 [02:54<00:16,  3.88it/s]
 91%|█████████ | 642/705 [02:54<00:16,  3.93it/s]
 91%|█████████ | 643/705 [02:54<00:16,  3.87it/s]
 91%|█████████▏| 644/705 [02:54<00:15,  3.82it/s]
 91%|█████████▏| 645/705 [02:55<00:15,  3.80it/s]
 92%|█████████▏| 646/705 [02:55<00:15,  3.79it/s]
 92%|█████████▏| 647/705 [02:55<00:15,  3.76it/s]
 92%|█████████▏| 648/705 [02:56<00:15,  3.79it/s]
 92%|█████████▏| 649/705 [02:56<00:14,  3.78it/s]
 92%|█████████▏| 650/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 651/705 [02:56<00:14,  3.79it/s]
 92%|█████████▏| 652/705 [02:57<00:14,  3.76it/s]
 93%|█████████▎| 653/705 [02:57<00:13,  3.87it/s]
 93%|█████████▎| 654/705 [02:57<00:13,  3.84it/s]
 93%|█████████▎| 655/705 [02:57<00:13,  3.79it/s]
 93%|█████████▎| 656/705 [02:58<00:12,  3.79it/s]
 93%|█████████▎| 657/705 [02:58<00:12,  3.80it/s]
 93%|█████████▎| 658/705 [02:58<00:12,  3.83it/s]
 93%|█████████▎| 659/705 [02:58<00:12,  3.81it/s]
 94%|█████████▎| 660/705 [02:59<00:11,  3.84it/s]
 94%|█████████▍| 661/705 [02:59<00:11,  3.82it/s]
 94%|█████████▍| 662/705 [02:59<00:11,  3.78it/s]
 94%|█████████▍| 663/705 [02:59<00:11,  3.77it/s]
 94%|█████████▍| 664/705 [03:00<00:10,  3.76it/s]
 94%|█████████▍| 665/705 [03:00<00:10,  3.89it/s]
 94%|█████████▍| 666/705 [03:00<00:10,  3.86it/s]
 95%|█████████▍| 667/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 668/705 [03:01<00:09,  3.82it/s]
 95%|█████████▍| 669/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 670/705 [03:01<00:09,  3.79it/s]
 95%|█████████▌| 671/705 [03:02<00:08,  3.78it/s]
 95%|█████████▌| 672/705 [03:02<00:08,  3.77it/s]
 95%|█████████▌| 673/705 [03:02<00:08,  3.83it/s]
 96%|█████████▌| 674/705 [03:02<00:07,  3.89it/s]
 96%|█████████▌| 675/705 [03:03<00:07,  3.83it/s]
 96%|█████████▌| 676/705 [03:03<00:07,  3.85it/s]
 96%|█████████▌| 677/705 [03:03<00:07,  3.81it/s]
 96%|█████████▌| 678/705 [03:03<00:07,  3.77it/s]
 96%|█████████▋| 679/705 [03:04<00:06,  3.76it/s]
 96%|█████████▋| 680/705 [03:04<00:06,  3.76it/s]
 97%|█████████▋| 681/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 682/705 [03:04<00:06,  3.75it/s]
 97%|█████████▋| 683/705 [03:05<00:05,  3.76it/s]
 97%|█████████▋| 684/705 [03:05<00:05,  3.74it/s]
 97%|█████████▋| 685/705 [03:05<00:05,  3.73it/s]
 97%|█████████▋| 686/705 [03:06<00:05,  3.74it/s]
 97%|█████████▋| 687/705 [03:06<00:04,  3.77it/s]
 98%|█████████▊| 688/705 [03:06<00:04,  3.82it/s]
 98%|█████████▊| 689/705 [03:06<00:04,  3.78it/s]
 98%|█████████▊| 690/705 [03:07<00:03,  3.77it/s]
 98%|█████████▊| 691/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 692/705 [03:07<00:03,  3.83it/s]
 98%|█████████▊| 693/705 [03:07<00:03,  3.79it/s]
 98%|█████████▊| 694/705 [03:08<00:02,  3.82it/s]
 99%|█████████▊| 695/705 [03:08<00:02,  3.78it/s]
 99%|█████████▊| 696/705 [03:08<00:02,  3.76it/s]
 99%|█████████▉| 697/705 [03:08<00:02,  3.86it/s]
 99%|█████████▉| 698/705 [03:09<00:01,  3.87it/s]
 99%|█████████▉| 699/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 700/705 [03:09<00:01,  3.84it/s]
 99%|█████████▉| 701/705 [03:09<00:01,  3.79it/s]
100%|█████████▉| 702/705 [03:10<00:00,  3.77it/s]
100%|█████████▉| 703/705 [03:10<00:00,  3.76it/s]
100%|█████████▉| 704/705 [03:10<00:00,  3.80it/s]
100%|██████████| 705/705 [03:10<00:00,  4.54it/s]
                                                 

100%|██████████| 705/705 [03:10<00:00,  4.54it/s]{'eval_loss': 0.6645968556404114, 'eval_accuracy': 0.7184, 'eval_f1': 0.7184606603668567, 'eval_runtime': 1.7319, 'eval_samples_per_second': 1443.48, 'eval_steps_per_second': 180.724, 'epoch': 2.0}
{'loss': 0.4132, 'learning_rate': 3.3129482852262054e-05, 'epoch': 3.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 209.77it/s]

 14%|█▎        | 43/313 [00:00<00:01, 197.67it/s]

 21%|██        | 65/313 [00:00<00:01, 204.72it/s]

 27%|██▋       | 86/313 [00:00<00:01, 195.11it/s]

 34%|███▍      | 106/313 [00:00<00:01, 188.30it/s]

 40%|███▉      | 125/313 [00:00<00:01, 185.06it/s]

 46%|████▌     | 144/313 [00:00<00:00, 183.70it/s]

 52%|█████▏    | 163/313 [00:00<00:00, 184.51it/s]

 58%|█████▊    | 182/313 [00:00<00:00, 179.18it/s]

 64%|██████▍   | 200/313 [00:01<00:00, 173.19it/s]

 70%|██████▉   | 218/313 [00:01<00:00, 168.05it/s]

 75%|███████▌  | 235/313 [00:01<00:00, 165.18it/s]

 83%|████████▎ | 259/313 [00:01<00:00, 184.32it/s]

 89%|████████▉ | 278/313 [00:01<00:00, 185.11it/s]

 95%|█████████▍| 297/313 [00:01<00:00, 179.30it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 179.30it/s]
100%|██████████| 705/705 [03:12<00:00,  4.54it/s]

                                                  
100%|██████████| 705/705 [03:12<00:00,  3.66it/s]
[I 2023-10-27 00:09:19,441] Trial 48 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.7065294981002808, 'eval_accuracy': 0.716, 'eval_f1': 0.7154299360113029, 'eval_runtime': 1.7298, 'eval_samples_per_second': 1445.23, 'eval_steps_per_second': 180.943, 'epoch': 3.0}

  0%|          | 0/705 [00:00<?, ?it/s]
  0%|          | 1/705 [00:00<03:10,  3.70it/s]
  0%|          | 2/705 [00:00<03:10,  3.69it/s]
  0%|          | 3/705 [00:00<03:09,  3.70it/s]
  1%|          | 4/705 [00:01<03:09,  3.70it/s]
  1%|          | 5/705 [00:01<03:08,  3.72it/s]
  1%|          | 6/705 [00:01<03:03,  3.81it/s]
  1%|          | 7/705 [00:01<03:03,  3.80it/s]
  1%|          | 8/705 [00:02<03:01,  3.84it/s]
  1%|▏         | 9/705 [00:02<03:03,  3.79it/s]
  1%|▏         | 10/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 11/705 [00:02<03:04,  3.76it/s]
  2%|▏         | 12/705 [00:03<03:03,  3.78it/s]
  2%|▏         | 13/705 [00:03<03:00,  3.84it/s]
  2%|▏         | 14/705 [00:03<02:59,  3.84it/s]
  2%|▏         | 15/705 [00:03<03:01,  3.80it/s]
  2%|▏         | 16/705 [00:04<03:00,  3.81it/s]
  2%|▏         | 17/705 [00:04<03:02,  3.77it/s]
  3%|▎         | 18/705 [00:04<03:03,  3.75it/s]
  3%|▎         | 19/705 [00:05<03:00,  3.80it/s]
  3%|▎         | 20/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 21/705 [00:05<03:00,  3.79it/s]
  3%|▎         | 22/705 [00:05<02:58,  3.82it/s]
  3%|▎         | 23/705 [00:06<03:00,  3.78it/s]
  3%|▎         | 24/705 [00:06<03:01,  3.76it/s]
  4%|▎         | 25/705 [00:06<02:59,  3.78it/s]
  4%|▎         | 26/705 [00:06<03:00,  3.77it/s]
  4%|▍         | 27/705 [00:07<03:01,  3.74it/s]
  4%|▍         | 28/705 [00:07<03:01,  3.73it/s]
  4%|▍         | 29/705 [00:07<02:55,  3.84it/s]
  4%|▍         | 30/705 [00:07<02:57,  3.81it/s]
  4%|▍         | 31/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 32/705 [00:08<02:57,  3.78it/s]
  5%|▍         | 33/705 [00:08<02:55,  3.82it/s]
  5%|▍         | 34/705 [00:08<02:57,  3.79it/s]
  5%|▍         | 35/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 36/705 [00:09<02:55,  3.82it/s]
  5%|▌         | 37/705 [00:09<02:51,  3.89it/s]
  5%|▌         | 38/705 [00:10<02:53,  3.85it/s]
  6%|▌         | 39/705 [00:10<02:53,  3.83it/s]
  6%|▌         | 40/705 [00:10<02:55,  3.80it/s]
  6%|▌         | 41/705 [00:10<02:55,  3.78it/s]
  6%|▌         | 42/705 [00:11<02:55,  3.78it/s]
  6%|▌         | 43/705 [00:11<02:56,  3.75it/s]
  6%|▌         | 44/705 [00:11<02:54,  3.80it/s]
  6%|▋         | 45/705 [00:11<02:55,  3.77it/s]
  7%|▋         | 46/705 [00:12<02:56,  3.74it/s]
  7%|▋         | 47/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 48/705 [00:12<02:55,  3.75it/s]
  7%|▋         | 49/705 [00:12<02:54,  3.76it/s]
  7%|▋         | 50/705 [00:13<02:55,  3.74it/s]
  7%|▋         | 51/705 [00:13<02:53,  3.76it/s]
  7%|▋         | 52/705 [00:13<02:54,  3.74it/s]
  8%|▊         | 53/705 [00:13<02:49,  3.85it/s]
  8%|▊         | 54/705 [00:14<02:49,  3.85it/s]
  8%|▊         | 55/705 [00:14<02:49,  3.82it/s]
  8%|▊         | 56/705 [00:14<02:50,  3.81it/s]
  8%|▊         | 57/705 [00:15<02:50,  3.80it/s]
  8%|▊         | 58/705 [00:15<02:51,  3.77it/s]
  8%|▊         | 59/705 [00:15<02:52,  3.74it/s]
  9%|▊         | 60/705 [00:15<02:51,  3.75it/s]
  9%|▊         | 61/705 [00:16<02:50,  3.78it/s]
  9%|▉         | 62/705 [00:16<02:44,  3.90it/s]
  9%|▉         | 63/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 64/705 [00:16<02:46,  3.85it/s]
  9%|▉         | 65/705 [00:17<02:48,  3.80it/s]
  9%|▉         | 66/705 [00:17<02:49,  3.78it/s]
 10%|▉         | 67/705 [00:17<02:49,  3.75it/s]
 10%|▉         | 68/705 [00:17<02:47,  3.81it/s]
 10%|▉         | 69/705 [00:18<02:45,  3.85it/s]
 10%|▉         | 70/705 [00:18<02:44,  3.85it/s]
 10%|█         | 71/705 [00:18<02:45,  3.83it/s]
 10%|█         | 72/705 [00:18<02:41,  3.92it/s]
 10%|█         | 73/705 [00:19<02:43,  3.88it/s]
 10%|█         | 74/705 [00:19<02:44,  3.85it/s]
 11%|█         | 75/705 [00:19<02:45,  3.82it/s]
 11%|█         | 76/705 [00:20<02:43,  3.84it/s]
 11%|█         | 77/705 [00:20<02:44,  3.82it/s]
 11%|█         | 78/705 [00:20<02:42,  3.86it/s]
 11%|█         | 79/705 [00:20<02:44,  3.81it/s]
 11%|█▏        | 80/705 [00:21<02:44,  3.80it/s]
 11%|█▏        | 81/705 [00:21<02:45,  3.77it/s]
 12%|█▏        | 82/705 [00:21<02:46,  3.75it/s]
 12%|█▏        | 83/705 [00:21<02:44,  3.78it/s]
 12%|█▏        | 84/705 [00:22<02:41,  3.84it/s]
 12%|█▏        | 85/705 [00:22<02:42,  3.82it/s]
 12%|█▏        | 86/705 [00:22<02:43,  3.78it/s]
 12%|█▏        | 87/705 [00:22<02:43,  3.77it/s]
 12%|█▏        | 88/705 [00:23<02:43,  3.76it/s]
 13%|█▎        | 89/705 [00:23<02:43,  3.77it/s]
 13%|█▎        | 90/705 [00:23<02:44,  3.75it/s]
 13%|█▎        | 91/705 [00:23<02:41,  3.80it/s]
 13%|█▎        | 92/705 [00:24<02:42,  3.78it/s]
 13%|█▎        | 93/705 [00:24<02:42,  3.77it/s]
 13%|█▎        | 94/705 [00:24<02:42,  3.76it/s]
 13%|█▎        | 95/705 [00:25<02:42,  3.76it/s]
 14%|█▎        | 96/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 97/705 [00:25<02:42,  3.74it/s]
 14%|█▍        | 98/705 [00:25<02:41,  3.76it/s]
 14%|█▍        | 99/705 [00:26<02:42,  3.74it/s]
 14%|█▍        | 100/705 [00:26<02:41,  3.74it/s]
 14%|█▍        | 101/705 [00:26<02:41,  3.73it/s]
 14%|█▍        | 102/705 [00:26<02:42,  3.72it/s]
 15%|█▍        | 103/705 [00:27<02:40,  3.74it/s]
 15%|█▍        | 104/705 [00:27<02:40,  3.75it/s]
 15%|█▍        | 105/705 [00:27<02:37,  3.80it/s]
 15%|█▌        | 106/705 [00:27<02:36,  3.83it/s]
 15%|█▌        | 107/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 108/705 [00:28<02:37,  3.79it/s]
 15%|█▌        | 109/705 [00:28<02:37,  3.78it/s]
 16%|█▌        | 110/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 111/705 [00:29<02:36,  3.80it/s]
 16%|█▌        | 112/705 [00:29<02:37,  3.77it/s]
 16%|█▌        | 113/705 [00:29<02:34,  3.83it/s]
 16%|█▌        | 114/705 [00:30<02:34,  3.82it/s]
 16%|█▋        | 115/705 [00:30<02:36,  3.78it/s]
 16%|█▋        | 116/705 [00:30<02:35,  3.78it/s]
 17%|█▋        | 117/705 [00:30<02:35,  3.79it/s]
 17%|█▋        | 118/705 [00:31<02:34,  3.80it/s]
 17%|█▋        | 119/705 [00:31<02:35,  3.77it/s]
 17%|█▋        | 120/705 [00:31<02:34,  3.79it/s]
 17%|█▋        | 121/705 [00:31<02:31,  3.84it/s]
 17%|█▋        | 122/705 [00:32<02:32,  3.81it/s]
 17%|█▋        | 123/705 [00:32<02:32,  3.82it/s]
 18%|█▊        | 124/705 [00:32<02:28,  3.91it/s]
 18%|█▊        | 125/705 [00:32<02:29,  3.88it/s]
 18%|█▊        | 126/705 [00:33<02:29,  3.87it/s]
 18%|█▊        | 127/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 128/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 129/705 [00:33<02:29,  3.85it/s]
 18%|█▊        | 130/705 [00:34<02:30,  3.83it/s]
 19%|█▊        | 131/705 [00:34<02:30,  3.81it/s]
 19%|█▊        | 132/705 [00:34<02:29,  3.82it/s]
 19%|█▉        | 133/705 [00:35<02:30,  3.80it/s]
 19%|█▉        | 134/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 135/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 136/705 [00:35<02:30,  3.79it/s]
 19%|█▉        | 137/705 [00:36<02:29,  3.80it/s]
 20%|█▉        | 138/705 [00:36<02:28,  3.82it/s]
 20%|█▉        | 139/705 [00:36<02:29,  3.78it/s]
 20%|█▉        | 140/705 [00:36<02:30,  3.76it/s]
 20%|██        | 141/705 [00:37<02:30,  3.74it/s]
 20%|██        | 142/705 [00:37<02:24,  3.89it/s]
 20%|██        | 143/705 [00:37<02:26,  3.83it/s]
 20%|██        | 144/705 [00:37<02:25,  3.85it/s]
 21%|██        | 145/705 [00:38<02:27,  3.80it/s]
 21%|██        | 146/705 [00:38<02:28,  3.77it/s]
 21%|██        | 147/705 [00:38<02:23,  3.88it/s]
 21%|██        | 148/705 [00:38<02:22,  3.90it/s]
 21%|██        | 149/705 [00:39<02:23,  3.86it/s]
 21%|██▏       | 150/705 [00:39<02:25,  3.81it/s]
 21%|██▏       | 151/705 [00:39<02:24,  3.83it/s]
 22%|██▏       | 152/705 [00:40<02:22,  3.87it/s]
 22%|██▏       | 153/705 [00:40<02:24,  3.81it/s]
 22%|██▏       | 154/705 [00:40<02:25,  3.80it/s]
 22%|██▏       | 155/705 [00:40<02:25,  3.78it/s]
 22%|██▏       | 156/705 [00:41<02:23,  3.82it/s]
 22%|██▏       | 157/705 [00:41<02:19,  3.93it/s]
 22%|██▏       | 158/705 [00:41<02:21,  3.88it/s]
 23%|██▎       | 159/705 [00:41<02:22,  3.82it/s]
 23%|██▎       | 160/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 161/705 [00:42<02:23,  3.79it/s]
 23%|██▎       | 162/705 [00:42<02:24,  3.77it/s]
 23%|██▎       | 163/705 [00:42<02:24,  3.76it/s]
 23%|██▎       | 164/705 [00:43<02:21,  3.82it/s]
 23%|██▎       | 165/705 [00:43<02:20,  3.83it/s]
 24%|██▎       | 166/705 [00:43<02:21,  3.82it/s]
 24%|██▎       | 167/705 [00:43<02:19,  3.86it/s]
 24%|██▍       | 168/705 [00:44<02:19,  3.84it/s]
 24%|██▍       | 169/705 [00:44<02:18,  3.88it/s]
 24%|██▍       | 170/705 [00:44<02:19,  3.85it/s]
 24%|██▍       | 171/705 [00:44<02:20,  3.81it/s]
 24%|██▍       | 172/705 [00:45<02:20,  3.78it/s]
 25%|██▍       | 173/705 [00:45<02:21,  3.76it/s]
 25%|██▍       | 174/705 [00:45<02:20,  3.77it/s]
 25%|██▍       | 175/705 [00:46<02:16,  3.89it/s]
 25%|██▍       | 176/705 [00:46<02:17,  3.85it/s]
 25%|██▌       | 177/705 [00:46<02:18,  3.80it/s]
 25%|██▌       | 178/705 [00:46<02:19,  3.77it/s]
 25%|██▌       | 179/705 [00:47<02:16,  3.85it/s]
 26%|██▌       | 180/705 [00:47<02:18,  3.80it/s]
 26%|██▌       | 181/705 [00:47<02:18,  3.79it/s]
 26%|██▌       | 182/705 [00:47<02:19,  3.76it/s]
 26%|██▌       | 183/705 [00:48<02:19,  3.75it/s]
 26%|██▌       | 184/705 [00:48<02:18,  3.76it/s]
 26%|██▌       | 185/705 [00:48<02:17,  3.78it/s]
 26%|██▋       | 186/705 [00:48<02:15,  3.83it/s]
 27%|██▋       | 187/705 [00:49<02:16,  3.79it/s]
 27%|██▋       | 188/705 [00:49<02:17,  3.76it/s]
 27%|██▋       | 189/705 [00:49<02:15,  3.80it/s]
 27%|██▋       | 190/705 [00:49<02:14,  3.84it/s]
 27%|██▋       | 191/705 [00:50<02:14,  3.82it/s]
 27%|██▋       | 192/705 [00:50<02:14,  3.81it/s]
 27%|██▋       | 193/705 [00:50<02:15,  3.79it/s]
 28%|██▊       | 194/705 [00:51<02:14,  3.79it/s]
 28%|██▊       | 195/705 [00:51<02:11,  3.88it/s]
 28%|██▊       | 196/705 [00:51<02:11,  3.87it/s]
 28%|██▊       | 197/705 [00:51<02:12,  3.85it/s]
 28%|██▊       | 198/705 [00:52<02:11,  3.84it/s]
 28%|██▊       | 199/705 [00:52<02:10,  3.87it/s]
 28%|██▊       | 200/705 [00:52<02:08,  3.92it/s]
 29%|██▊       | 201/705 [00:52<02:09,  3.89it/s]
 29%|██▊       | 202/705 [00:53<02:10,  3.85it/s]
 29%|██▉       | 203/705 [00:53<02:04,  4.04it/s]
 29%|██▉       | 204/705 [00:53<02:06,  3.96it/s]
 29%|██▉       | 205/705 [00:53<02:08,  3.90it/s]
 29%|██▉       | 206/705 [00:54<02:09,  3.86it/s]
 29%|██▉       | 207/705 [00:54<02:09,  3.85it/s]
 30%|██▉       | 208/705 [00:54<02:10,  3.80it/s]
 30%|██▉       | 209/705 [00:54<02:11,  3.78it/s]
 30%|██▉       | 210/705 [00:55<02:11,  3.78it/s]
 30%|██▉       | 211/705 [00:55<02:11,  3.75it/s]
 30%|███       | 212/705 [00:55<02:07,  3.87it/s]
 30%|███       | 213/705 [00:55<02:08,  3.84it/s]
 30%|███       | 214/705 [00:56<02:08,  3.82it/s]
 30%|███       | 215/705 [00:56<02:09,  3.79it/s]
 31%|███       | 216/705 [00:56<02:07,  3.85it/s]
 31%|███       | 217/705 [00:57<02:08,  3.80it/s]
 31%|███       | 218/705 [00:57<02:09,  3.77it/s]
 31%|███       | 219/705 [00:57<02:08,  3.77it/s]
 31%|███       | 220/705 [00:57<02:07,  3.81it/s]
 31%|███▏      | 221/705 [00:58<02:06,  3.83it/s]
 31%|███▏      | 222/705 [00:58<02:06,  3.81it/s]
 32%|███▏      | 223/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 224/705 [00:58<02:07,  3.77it/s]
 32%|███▏      | 225/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 226/705 [00:59<02:06,  3.78it/s]
 32%|███▏      | 227/705 [00:59<02:06,  3.79it/s]
 32%|███▏      | 228/705 [00:59<02:05,  3.81it/s]
 32%|███▏      | 229/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 230/705 [01:00<02:04,  3.82it/s]
 33%|███▎      | 231/705 [01:00<02:05,  3.78it/s]
 33%|███▎      | 232/705 [01:00<02:01,  3.89it/s]
 33%|███▎      | 233/705 [01:01<02:01,  3.87it/s]
 33%|███▎      | 234/705 [01:01<02:02,  3.85it/s]
 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]
                                                 

 33%|███▎      | 235/705 [01:01<01:41,  4.61it/s]{'loss': 0.8385, 'learning_rate': 1.8386875932540568e-05, 'epoch': 1.0}


  0%|          | 0/313 [00:00<?, ?it/s]

  7%|▋         | 22/313 [00:00<00:01, 210.19it/s]

 14%|█▍        | 44/313 [00:00<00:01, 197.53it/s]

 21%|██        | 66/313 [00:00<00:01, 205.84it/s]

 28%|██▊       | 87/313 [00:00<00:01, 195.00it/s]

 34%|███▍      | 107/313 [00:00<00:01, 187.43it/s]

 40%|████      | 126/313 [00:00<00:01, 185.13it/s]

 46%|████▋     | 145/313 [00:00<00:00, 182.94it/s]

 52%|█████▏    | 164/313 [00:00<00:00, 183.85it/s]

 58%|█████▊    | 183/313 [00:00<00:00, 179.01it/s]

 64%|██████▍   | 201/313 [00:01<00:00, 173.12it/s]

 70%|██████▉   | 219/313 [00:01<00:00, 167.21it/s]

 75%|███████▌  | 236/313 [00:01<00:00, 164.91it/s]

 83%|████████▎ | 260/313 [00:01<00:00, 184.54it/s]

 89%|████████▉ | 279/313 [00:01<00:00, 184.34it/s]

 95%|█████████▌| 298/313 [00:01<00:00, 178.44it/s]

                                                  

                                                 

100%|██████████| 313/313 [00:01<00:00, 178.44it/s]
 33%|███▎      | 235/705 [01:03<01:41,  4.61it/s]

                                                  
 33%|███▎      | 235/705 [01:03<02:06,  3.71it/s]
[I 2023-10-27 00:10:23,831] Trial 49 pruned. 
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at cl-tohoku/bert-base-japanese-whole-word-masking and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.6973730325698853, 'eval_accuracy': 0.6932, 'eval_f1': 0.6922606648818475, 'eval_runtime': 1.7331, 'eval_samples_per_second': 1442.506, 'eval_steps_per_second': 180.602, 'epoch': 1.0}
--------------------------------------------------------------------------------
optimizer: adamw_torch
BestRun(run_id='22', objective=0.7303298984454403, hyperparameters={'lr_scheduler_type': 'cosine', 'learning_rate': 3.912141264809884e-05, 'per_device_train_batch_size': 128, 'weight_decay': 5.220051265759252e-05}, run_summary=None)
BertForSequenceClassification

  0%|          | 0/23500 [00:00<?, ?it/s]
  0%|          | 1/23500 [00:00<1:22:44,  4.73it/s]
  0%|          | 2/23500 [00:00<1:21:22,  4.81it/s]
  0%|          | 3/23500 [00:00<1:18:57,  4.96it/s]
  0%|          | 4/23500 [00:00<1:19:24,  4.93it/s]
  0%|          | 5/23500 [00:01<1:19:15,  4.94it/s]
  0%|          | 6/23500 [00:01<1:19:10,  4.95it/s]
  0%|          | 7/23500 [00:01<1:19:24,  4.93it/s]
  0%|          | 8/23500 [00:01<1:20:13,  4.88it/s]
  0%|          | 9/23500 [00:01<1:18:54,  4.96it/s]
  0%|          | 10/23500 [00:02<1:19:41,  4.91it/s]
  0%|          | 11/23500 [00:02<1:20:25,  4.87it/s]
  0%|          | 12/23500 [00:02<1:20:11,  4.88it/s]
  0%|          | 13/23500 [00:02<1:20:47,  4.85it/s]
  0%|          | 14/23500 [00:02<1:19:21,  4.93it/s]
  0%|          | 15/23500 [00:03<1:19:51,  4.90it/s]
  0%|          | 16/23500 [00:03<1:19:54,  4.90it/s]
  0%|          | 17/23500 [00:03<1:20:30,  4.86it/s]
  0%|          | 18/23500 [00:03<1:20:40,  4.85it/s]
  0%|          | 19/23500 [00:03<1:20:43,  4.85it/s]
  0%|          | 20/23500 [00:04<1:18:52,  4.96it/s]
  0%|          | 21/23500 [00:04<1:18:55,  4.96it/s]
  0%|          | 22/23500 [00:04<1:19:29,  4.92it/s]
  0%|          | 23/23500 [00:04<1:19:34,  4.92it/s]
  0%|          | 24/23500 [00:04<1:19:47,  4.90it/s]
  0%|          | 25/23500 [00:05<1:19:34,  4.92it/s]
  0%|          | 26/23500 [00:05<1:19:41,  4.91it/s]
  0%|          | 27/23500 [00:05<1:19:44,  4.91it/s]
  0%|          | 28/23500 [00:05<1:20:14,  4.88it/s]
  0%|          | 29/23500 [00:05<1:20:16,  4.87it/s]
  0%|          | 30/23500 [00:06<1:18:11,  5.00it/s]
  0%|          | 31/23500 [00:06<1:19:19,  4.93it/s]
  0%|          | 32/23500 [00:06<1:19:57,  4.89it/s]
  0%|          | 33/23500 [00:06<1:18:02,  5.01it/s]
  0%|          | 34/23500 [00:06<1:18:45,  4.97it/s]
  0%|          | 35/23500 [00:07<1:18:12,  5.00it/s]
  0%|          | 36/23500 [00:07<1:18:40,  4.97it/s]
  0%|          | 37/23500 [00:07<1:18:45,  4.97it/s]
  0%|          | 38/23500 [00:07<1:19:41,  4.91it/s]
  0%|          | 39/23500 [00:07<1:19:19,  4.93it/s]
  0%|          | 40/23500 [00:08<1:19:09,  4.94it/s]
  0%|          | 41/23500 [00:08<1:19:36,  4.91it/s]
  0%|          | 42/23500 [00:08<1:17:39,  5.03it/s]
  0%|          | 43/23500 [00:08<1:17:04,  5.07it/s]
  0%|          | 44/23500 [00:08<1:17:05,  5.07it/s]
  0%|          | 45/23500 [00:09<1:17:06,  5.07it/s]
  0%|          | 46/23500 [00:09<1:18:36,  4.97it/s]
  0%|          | 47/23500 [00:09<1:19:25,  4.92it/s]
  0%|          | 48/23500 [00:09<1:19:50,  4.90it/s]
  0%|          | 49/23500 [00:09<1:19:44,  4.90it/s]
  0%|          | 50/23500 [00:10<1:18:47,  4.96it/s]
  0%|          | 51/23500 [00:10<1:18:15,  4.99it/s]
  0%|          | 52/23500 [00:10<1:18:42,  4.96it/s]
  0%|          | 53/23500 [00:10<1:19:08,  4.94it/s]
  0%|          | 54/23500 [00:10<1:19:58,  4.89it/s]
  0%|          | 55/23500 [00:11<1:20:33,  4.85it/s]
  0%|          | 56/23500 [00:11<1:20:23,  4.86it/s]
  0%|          | 57/23500 [00:11<1:20:11,  4.87it/s]
  0%|          | 58/23500 [00:11<1:20:43,  4.84it/s]
  0%|          | 59/23500 [00:11<1:20:03,  4.88it/s]
  0%|          | 60/23500 [00:12<1:19:50,  4.89it/s]
  0%|          | 61/23500 [00:12<1:20:19,  4.86it/s]
  0%|          | 62/23500 [00:12<1:20:52,  4.83it/s]
  0%|          | 63/23500 [00:12<1:19:45,  4.90it/s]
  0%|          | 64/23500 [00:13<1:19:24,  4.92it/s]
  0%|          | 65/23500 [00:13<1:16:58,  5.07it/s]
  0%|          | 66/23500 [00:13<1:17:24,  5.05it/s]
  0%|          | 67/23500 [00:13<1:18:06,  5.00it/s]
  0%|          | 68/23500 [00:13<1:18:36,  4.97it/s]
  0%|          | 69/23500 [00:13<1:18:07,  5.00it/s]
  0%|          | 70/23500 [00:14<1:19:07,  4.94it/s]
  0%|          | 71/23500 [00:14<1:17:58,  5.01it/s]
  0%|          | 72/23500 [00:14<1:17:20,  5.05it/s]
  0%|          | 73/23500 [00:14<1:18:36,  4.97it/s]
  0%|          | 74/23500 [00:15<1:19:34,  4.91it/s]
  0%|          | 75/23500 [00:15<1:20:13,  4.87it/s]
  0%|          | 76/23500 [00:15<1:20:00,  4.88it/s]
  0%|          | 77/23500 [00:15<1:17:53,  5.01it/s]
  0%|          | 78/23500 [00:15<1:19:08,  4.93it/s]
  0%|          | 79/23500 [00:16<1:19:59,  4.88it/s]
  0%|          | 80/23500 [00:16<1:20:03,  4.88it/s]
  0%|          | 81/23500 [00:16<1:20:08,  4.87it/s]
  0%|          | 82/23500 [00:16<1:20:05,  4.87it/s]
  0%|          | 83/23500 [00:16<1:19:39,  4.90it/s]
  0%|          | 84/23500 [00:17<1:19:38,  4.90it/s]
  0%|          | 85/23500 [00:17<1:18:53,  4.95it/s]
  0%|          | 86/23500 [00:17<1:18:50,  4.95it/s]
  0%|          | 87/23500 [00:17<1:18:51,  4.95it/s]
  0%|          | 88/23500 [00:17<1:19:47,  4.89it/s]
  0%|          | 89/23500 [00:18<1:19:21,  4.92it/s]
  0%|          | 90/23500 [00:18<1:17:10,  5.06it/s]
  0%|          | 91/23500 [00:18<1:18:36,  4.96it/s]
  0%|          | 92/23500 [00:18<1:16:59,  5.07it/s]
  0%|          | 93/23500 [00:18<1:18:14,  4.99it/s]
  0%|          | 94/23500 [00:19<1:16:51,  5.08it/s]
  0%|          | 95/23500 [00:19<1:17:36,  5.03it/s]
  0%|          | 96/23500 [00:19<1:17:51,  5.01it/s]
  0%|          | 97/23500 [00:19<1:19:04,  4.93it/s]
  0%|          | 98/23500 [00:19<1:18:21,  4.98it/s]
  0%|          | 99/23500 [00:20<1:18:47,  4.95it/s]
  0%|          | 100/23500 [00:20<1:18:30,  4.97it/s]
  0%|          | 101/23500 [00:20<1:18:42,  4.95it/s]
  0%|          | 102/23500 [00:20<1:19:34,  4.90it/s]
  0%|          | 103/23500 [00:20<1:20:13,  4.86it/s]
  0%|          | 104/23500 [00:21<1:19:36,  4.90it/s]
  0%|          | 105/23500 [00:21<1:19:12,  4.92it/s]
  0%|          | 106/23500 [00:21<1:19:55,  4.88it/s]
  0%|          | 107/23500 [00:21<1:20:28,  4.84it/s]
  0%|          | 108/23500 [00:21<1:20:07,  4.87it/s]
  0%|          | 109/23500 [00:22<1:19:40,  4.89it/s]
  0%|          | 110/23500 [00:22<1:18:44,  4.95it/s]
  0%|          | 111/23500 [00:22<1:17:46,  5.01it/s]
  0%|          | 112/23500 [00:22<1:18:19,  4.98it/s]
  0%|          | 113/23500 [00:22<1:18:59,  4.93it/s]
  0%|          | 114/23500 [00:23<1:19:53,  4.88it/s]
  0%|          | 115/23500 [00:23<1:20:26,  4.85it/s]
  0%|          | 116/23500 [00:23<1:18:55,  4.94it/s]
  0%|          | 117/23500 [00:23<1:19:45,  4.89it/s]
  1%|          | 118/23500 [00:23<1:19:45,  4.89it/s]
  1%|          | 119/23500 [00:24<1:20:08,  4.86it/s]
  1%|          | 120/23500 [00:24<1:20:34,  4.84it/s]
  1%|          | 121/23500 [00:24<1:19:21,  4.91it/s]
  1%|          | 122/23500 [00:24<1:19:28,  4.90it/s]
  1%|          | 123/23500 [00:24<1:20:07,  4.86it/s]
  1%|          | 124/23500 [00:25<1:18:58,  4.93it/s]
  1%|          | 125/23500 [00:25<1:18:15,  4.98it/s]
  1%|          | 126/23500 [00:25<1:18:56,  4.93it/s]
  1%|          | 127/23500 [00:25<1:19:43,  4.89it/s]
  1%|          | 128/23500 [00:25<1:19:59,  4.87it/s]
  1%|          | 129/23500 [00:26<1:19:44,  4.88it/s]
  1%|          | 130/23500 [00:26<1:19:42,  4.89it/s]
  1%|          | 131/23500 [00:26<1:19:57,  4.87it/s]
  1%|          | 132/23500 [00:26<1:20:26,  4.84it/s]
  1%|          | 133/23500 [00:26<1:18:57,  4.93it/s]
  1%|          | 134/23500 [00:27<1:19:43,  4.89it/s]
  1%|          | 135/23500 [00:27<1:20:08,  4.86it/s]
  1%|          | 136/23500 [00:27<1:19:58,  4.87it/s]
  1%|          | 137/23500 [00:27<1:20:04,  4.86it/s]
  1%|          | 138/23500 [00:28<1:20:34,  4.83it/s]
  1%|          | 139/23500 [00:28<1:20:10,  4.86it/s]
  1%|          | 140/23500 [00:28<1:19:29,  4.90it/s]
  1%|          | 141/23500 [00:28<1:19:45,  4.88it/s]
  1%|          | 142/23500 [00:28<1:19:37,  4.89it/s]
  1%|          | 143/23500 [00:29<1:18:49,  4.94it/s]
  1%|          | 144/23500 [00:29<1:18:40,  4.95it/s]
  1%|          | 145/23500 [00:29<1:17:42,  5.01it/s]
  1%|          | 146/23500 [00:29<1:18:51,  4.94it/s]
  1%|          | 147/23500 [00:29<1:19:11,  4.91it/s]
  1%|          | 148/23500 [00:30<1:18:53,  4.93it/s]
  1%|          | 149/23500 [00:30<1:19:41,  4.88it/s]
  1%|          | 150/23500 [00:30<1:19:53,  4.87it/s]
  1%|          | 151/23500 [00:30<1:19:47,  4.88it/s]
  1%|          | 152/23500 [00:30<1:18:43,  4.94it/s]
  1%|          | 153/23500 [00:31<1:19:33,  4.89it/s]
  1%|          | 154/23500 [00:31<1:19:49,  4.87it/s]
  1%|          | 155/23500 [00:31<1:18:31,  4.95it/s]
  1%|          | 156/23500 [00:31<1:19:16,  4.91it/s]
  1%|          | 157/23500 [00:31<1:19:58,  4.86it/s]
  1%|          | 158/23500 [00:32<1:20:13,  4.85it/s]
  1%|          | 159/23500 [00:32<1:20:02,  4.86it/s]
  1%|          | 160/23500 [00:32<1:19:02,  4.92it/s]
  1%|          | 161/23500 [00:32<1:19:46,  4.88it/s]
  1%|          | 162/23500 [00:32<1:20:03,  4.86it/s]
  1%|          | 163/23500 [00:33<1:18:38,  4.95it/s]
  1%|          | 164/23500 [00:33<1:18:27,  4.96it/s]
  1%|          | 165/23500 [00:33<1:18:59,  4.92it/s]
  1%|          | 166/23500 [00:33<1:19:45,  4.88it/s]
  1%|          | 167/23500 [00:33<1:20:21,  4.84it/s]
  1%|          | 168/23500 [00:34<1:20:42,  4.82it/s]
  1%|          | 169/23500 [00:34<1:20:23,  4.84it/s]
  1%|          | 170/23500 [00:34<1:20:46,  4.81it/s]
  1%|          | 171/23500 [00:34<1:20:57,  4.80it/s]
  1%|          | 172/23500 [00:34<1:20:37,  4.82it/s]
  1%|          | 173/23500 [00:35<1:20:25,  4.83it/s]
  1%|          | 174/23500 [00:35<1:19:37,  4.88it/s]
  1%|          | 175/23500 [00:35<1:19:48,  4.87it/s]
  1%|          | 176/23500 [00:35<1:17:26,  5.02it/s]
  1%|          | 177/23500 [00:35<1:18:30,  4.95it/s]
  1%|          | 178/23500 [00:36<1:18:51,  4.93it/s]
  1%|          | 179/23500 [00:36<1:18:56,  4.92it/s]
  1%|          | 180/23500 [00:36<1:19:45,  4.87it/s]
  1%|          | 181/23500 [00:36<1:19:56,  4.86it/s]
  1%|          | 182/23500 [00:37<1:20:00,  4.86it/s]
  1%|          | 183/23500 [00:37<1:20:18,  4.84it/s]
  1%|          | 184/23500 [00:37<1:20:28,  4.83it/s]
  1%|          | 185/23500 [00:37<1:20:18,  4.84it/s]
  1%|          | 186/23500 [00:37<1:19:10,  4.91it/s]
  1%|          | 187/23500 [00:38<1:19:19,  4.90it/s]
  1%|          | 188/23500 [00:38<1:19:45,  4.87it/s]
  1%|          | 189/23500 [00:38<1:20:12,  4.84it/s]
  1%|          | 190/23500 [00:38<1:19:00,  4.92it/s]
  1%|          | 191/23500 [00:38<1:19:10,  4.91it/s]
  1%|          | 192/23500 [00:39<1:19:44,  4.87it/s]
  1%|          | 193/23500 [00:39<1:19:15,  4.90it/s]
  1%|          | 194/23500 [00:39<1:19:19,  4.90it/s]
  1%|          | 195/23500 [00:39<1:19:28,  4.89it/s]
  1%|          | 196/23500 [00:39<1:19:53,  4.86it/s]
  1%|          | 197/23500 [00:40<1:19:14,  4.90it/s]
  1%|          | 198/23500 [00:40<1:19:09,  4.91it/s]
  1%|          | 199/23500 [00:40<1:17:11,  5.03it/s]
  1%|          | 200/23500 [00:40<1:18:00,  4.98it/s]
  1%|          | 201/23500 [00:40<1:18:15,  4.96it/s]
  1%|          | 202/23500 [00:41<1:18:29,  4.95it/s]
  1%|          | 203/23500 [00:41<1:19:23,  4.89it/s]
  1%|          | 204/23500 [00:41<1:19:37,  4.88it/s]
  1%|          | 205/23500 [00:41<1:19:58,  4.85it/s]
  1%|          | 206/23500 [00:41<1:20:05,  4.85it/s]
  1%|          | 207/23500 [00:42<1:20:06,  4.85it/s]
  1%|          | 208/23500 [00:42<1:18:36,  4.94it/s]
  1%|          | 209/23500 [00:42<1:17:59,  4.98it/s]
  1%|          | 210/23500 [00:42<1:18:02,  4.97it/s]
  1%|          | 211/23500 [00:42<1:18:42,  4.93it/s]
  1%|          | 212/23500 [00:43<1:19:29,  4.88it/s]
  1%|          | 213/23500 [00:43<1:19:28,  4.88it/s]
  1%|          | 214/23500 [00:43<1:18:57,  4.92it/s]
  1%|          | 215/23500 [00:43<1:19:28,  4.88it/s]
  1%|          | 216/23500 [00:43<1:18:31,  4.94it/s]
  1%|          | 217/23500 [00:44<1:18:51,  4.92it/s]
  1%|          | 218/23500 [00:44<1:19:38,  4.87it/s]
  1%|          | 219/23500 [00:44<1:19:02,  4.91it/s]
  1%|          | 220/23500 [00:44<1:19:11,  4.90it/s]
  1%|          | 221/23500 [00:44<1:19:51,  4.86it/s]
  1%|          | 222/23500 [00:45<1:18:31,  4.94it/s]
  1%|          | 223/23500 [00:45<1:19:24,  4.89it/s]
  1%|          | 224/23500 [00:45<1:19:59,  4.85it/s]
  1%|          | 225/23500 [00:45<1:20:28,  4.82it/s]
  1%|          | 226/23500 [00:46<1:20:31,  4.82it/s]
  1%|          | 227/23500 [00:46<1:20:09,  4.84it/s]
  1%|          | 228/23500 [00:46<1:20:21,  4.83it/s]
  1%|          | 229/23500 [00:46<1:20:18,  4.83it/s]
  1%|          | 230/23500 [00:46<1:20:03,  4.84it/s]
  1%|          | 231/23500 [00:47<1:18:12,  4.96it/s]
  1%|          | 232/23500 [00:47<1:18:56,  4.91it/s]
  1%|          | 233/23500 [00:47<1:17:48,  4.98it/s]
  1%|          | 234/23500 [00:47<1:17:56,  4.97it/s]
                                                     

  1%|          | 235/23500 [00:47<1:17:56,  4.97it/s]{'loss': 1.0375, 'learning_rate': 3.912141264809884e-06, 'epoch': 1.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.73it/s]

 30%|███       | 6/20 [00:00<00:00, 18.50it/s]

 40%|████      | 8/20 [00:00<00:00, 16.77it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.11it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.48it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.05it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.29it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.84it/s]

                                               

                                                     

100%|██████████| 20/20 [00:01<00:00, 15.84it/s]
  1%|          | 235/23500 [00:48<1:17:56,  4.97it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  1%|          | 236/23500 [00:50<4:26:36,  1.45it/s]
  1%|          | 237/23500 [00:50<3:40:08,  1.76it/s]
  1%|          | 238/23500 [00:50<3:02:59,  2.12it/s]
  1%|          | 239/23500 [00:50<2:34:47,  2.50it/s]
  1%|          | 240/23500 [00:50<2:12:24,  2.93it/s]
  1%|          | 241/23500 [00:51<1:56:49,  3.32it/s]
  1%|          | 242/23500 [00:51<1:44:57,  3.69it/s]
  1%|          | 243/23500 [00:51<1:37:24,  3.98it/s]
  1%|          | 244/23500 [00:51<1:31:37,  4.23it/s]
  1%|          | 245/23500 [00:51<1:27:58,  4.41it/s]
  1%|          | 246/23500 [00:52<1:24:54,  4.56it/s]
  1%|          | 247/23500 [00:52<1:23:50,  4.62it/s]
  1%|          | 248/23500 [00:52<1:23:04,  4.67it/s]
  1%|          | 249/23500 [00:52<1:21:54,  4.73it/s]
  1%|          | 250/23500 [00:52<1:21:17,  4.77it/s]
  1%|          | 251/23500 [00:53<1:21:16,  4.77it/s]
  1%|          | 252/23500 [00:53<1:20:18,  4.82it/s]
  1%|          | 253/23500 [00:53<1:18:59,  4.90it/s]
  1%|          | 254/23500 [00:53<1:18:38,  4.93it/s]
  1%|          | 255/23500 [00:54<1:19:23,  4.88it/s]
  1%|          | 256/23500 [00:54<1:18:23,  4.94it/s]
  1%|          | 257/23500 [00:54<1:19:14,  4.89it/s]
  1%|          | 258/23500 [00:54<1:17:59,  4.97it/s]
  1%|          | 259/23500 [00:54<1:18:57,  4.91it/s]
  1%|          | 260/23500 [00:55<1:19:06,  4.90it/s]
  1%|          | 261/23500 [00:55<1:19:33,  4.87it/s]
  1%|          | 262/23500 [00:55<1:19:40,  4.86it/s]
  1%|          | 263/23500 [00:55<1:19:34,  4.87it/s]
  1%|          | 264/23500 [00:55<1:18:32,  4.93it/s]
  1%|          | 265/23500 [00:56<1:18:40,  4.92it/s]
  1%|          | 266/23500 [00:56<1:16:59,  5.03it/s]
  1%|          | 267/23500 [00:56<1:18:03,  4.96it/s]
  1%|          | 268/23500 [00:56<1:18:00,  4.96it/s]
  1%|          | 269/23500 [00:56<1:18:00,  4.96it/s]
  1%|          | 270/23500 [00:57<1:18:38,  4.92it/s]
  1%|          | 271/23500 [00:57<1:19:23,  4.88it/s]
  1%|          | 272/23500 [00:57<1:19:36,  4.86it/s]
  1%|          | 273/23500 [00:57<1:20:07,  4.83it/s]
  1%|          | 274/23500 [00:57<1:20:05,  4.83it/s]
  1%|          | 275/23500 [00:58<1:20:09,  4.83it/s]
  1%|          | 276/23500 [00:58<1:19:50,  4.85it/s]
  1%|          | 277/23500 [00:58<1:19:09,  4.89it/s]
  1%|          | 278/23500 [00:58<1:19:43,  4.85it/s]
  1%|          | 279/23500 [00:58<1:18:23,  4.94it/s]
  1%|          | 280/23500 [00:59<1:18:37,  4.92it/s]
  1%|          | 281/23500 [00:59<1:17:08,  5.02it/s]
  1%|          | 282/23500 [00:59<1:17:21,  5.00it/s]
  1%|          | 283/23500 [00:59<1:18:06,  4.95it/s]
  1%|          | 284/23500 [00:59<1:16:35,  5.05it/s]
  1%|          | 285/23500 [01:00<1:13:01,  5.30it/s]
  1%|          | 286/23500 [01:00<1:15:30,  5.12it/s]
  1%|          | 287/23500 [01:00<1:15:39,  5.11it/s]
  1%|          | 288/23500 [01:00<1:14:45,  5.18it/s]
  1%|          | 289/23500 [01:00<1:16:40,  5.04it/s]
  1%|          | 290/23500 [01:01<1:18:01,  4.96it/s]
  1%|          | 291/23500 [01:01<1:18:20,  4.94it/s]
  1%|          | 292/23500 [01:01<1:19:09,  4.89it/s]
  1%|          | 293/23500 [01:01<1:19:24,  4.87it/s]
  1%|▏         | 294/23500 [01:01<1:19:42,  4.85it/s]
  1%|▏         | 295/23500 [01:02<1:18:20,  4.94it/s]
  1%|▏         | 296/23500 [01:02<1:19:12,  4.88it/s]
  1%|▏         | 297/23500 [01:02<1:18:48,  4.91it/s]
  1%|▏         | 298/23500 [01:02<1:19:17,  4.88it/s]
  1%|▏         | 299/23500 [01:02<1:17:57,  4.96it/s]
  1%|▏         | 300/23500 [01:03<1:17:18,  5.00it/s]
  1%|▏         | 301/23500 [01:03<1:18:06,  4.95it/s]
  1%|▏         | 302/23500 [01:03<1:18:57,  4.90it/s]
  1%|▏         | 303/23500 [01:03<1:18:05,  4.95it/s]
  1%|▏         | 304/23500 [01:03<1:19:02,  4.89it/s]
  1%|▏         | 305/23500 [01:04<1:19:16,  4.88it/s]
  1%|▏         | 306/23500 [01:04<1:18:22,  4.93it/s]
  1%|▏         | 307/23500 [01:04<1:16:54,  5.03it/s]
  1%|▏         | 308/23500 [01:04<1:17:13,  5.01it/s]
  1%|▏         | 309/23500 [01:04<1:15:30,  5.12it/s]
  1%|▏         | 310/23500 [01:05<1:14:52,  5.16it/s]
  1%|▏         | 311/23500 [01:05<1:16:09,  5.07it/s]
  1%|▏         | 312/23500 [01:05<1:15:24,  5.13it/s]
  1%|▏         | 313/23500 [01:05<1:17:08,  5.01it/s]
  1%|▏         | 314/23500 [01:05<1:18:17,  4.94it/s]
  1%|▏         | 315/23500 [01:06<1:17:39,  4.98it/s]
  1%|▏         | 316/23500 [01:06<1:18:39,  4.91it/s]
  1%|▏         | 317/23500 [01:06<1:28:05,  4.39it/s]
  1%|▏         | 318/23500 [01:06<1:25:25,  4.52it/s]
  1%|▏         | 319/23500 [01:06<1:21:53,  4.72it/s]
  1%|▏         | 320/23500 [01:07<1:20:43,  4.79it/s]
  1%|▏         | 321/23500 [01:07<1:19:15,  4.87it/s]
  1%|▏         | 322/23500 [01:07<1:19:14,  4.88it/s]
  1%|▏         | 323/23500 [01:07<1:19:46,  4.84it/s]
  1%|▏         | 324/23500 [01:08<1:19:37,  4.85it/s]
  1%|▏         | 325/23500 [01:08<1:20:02,  4.83it/s]
  1%|▏         | 326/23500 [01:08<1:20:07,  4.82it/s]
  1%|▏         | 327/23500 [01:08<1:20:13,  4.81it/s]
  1%|▏         | 328/23500 [01:08<1:19:20,  4.87it/s]
  1%|▏         | 329/23500 [01:09<1:18:44,  4.90it/s]
  1%|▏         | 330/23500 [01:09<1:16:57,  5.02it/s]
  1%|▏         | 331/23500 [01:09<1:17:28,  4.98it/s]
  1%|▏         | 332/23500 [01:09<1:17:01,  5.01it/s]
  1%|▏         | 333/23500 [01:09<1:17:34,  4.98it/s]
  1%|▏         | 334/23500 [01:10<1:17:10,  5.00it/s]
  1%|▏         | 335/23500 [01:10<1:17:44,  4.97it/s]
  1%|▏         | 336/23500 [01:10<1:18:22,  4.93it/s]
  1%|▏         | 337/23500 [01:10<1:17:30,  4.98it/s]
  1%|▏         | 338/23500 [01:10<1:15:54,  5.09it/s]
  1%|▏         | 339/23500 [01:11<1:16:19,  5.06it/s]
  1%|▏         | 340/23500 [01:11<1:17:40,  4.97it/s]
  1%|▏         | 341/23500 [01:11<1:17:59,  4.95it/s]
  1%|▏         | 342/23500 [01:11<1:24:21,  4.58it/s]
  1%|▏         | 343/23500 [01:11<1:18:18,  4.93it/s]
  1%|▏         | 344/23500 [01:12<1:19:06,  4.88it/s]
  1%|▏         | 345/23500 [01:12<1:19:00,  4.88it/s]
  1%|▏         | 346/23500 [01:12<1:19:33,  4.85it/s]
  1%|▏         | 347/23500 [01:12<1:19:57,  4.83it/s]
  1%|▏         | 348/23500 [01:12<1:19:10,  4.87it/s]
  1%|▏         | 349/23500 [01:13<1:17:14,  4.99it/s]
  1%|▏         | 350/23500 [01:13<1:17:41,  4.97it/s]
  1%|▏         | 351/23500 [01:13<1:17:05,  5.00it/s]
  1%|▏         | 352/23500 [01:13<1:15:39,  5.10it/s]
  2%|▏         | 353/23500 [01:13<1:16:13,  5.06it/s]
  2%|▏         | 354/23500 [01:14<1:17:19,  4.99it/s]
  2%|▏         | 355/23500 [01:14<1:17:48,  4.96it/s]
  2%|▏         | 356/23500 [01:14<1:18:35,  4.91it/s]
  2%|▏         | 357/23500 [01:14<1:18:40,  4.90it/s]
  2%|▏         | 358/23500 [01:14<1:19:20,  4.86it/s]
  2%|▏         | 359/23500 [01:15<1:19:35,  4.85it/s]
  2%|▏         | 360/23500 [01:15<1:18:33,  4.91it/s]
  2%|▏         | 361/23500 [01:15<1:17:27,  4.98it/s]
  2%|▏         | 362/23500 [01:15<1:15:40,  5.10it/s]
  2%|▏         | 363/23500 [01:15<1:16:47,  5.02it/s]
  2%|▏         | 364/23500 [01:16<1:17:15,  4.99it/s]
  2%|▏         | 365/23500 [01:16<1:17:45,  4.96it/s]
  2%|▏         | 366/23500 [01:16<1:17:06,  5.00it/s]
  2%|▏         | 367/23500 [01:16<1:17:28,  4.98it/s]
  2%|▏         | 368/23500 [01:16<1:16:54,  5.01it/s]
  2%|▏         | 369/23500 [01:17<1:17:29,  4.98it/s]
  2%|▏         | 370/23500 [01:17<1:18:16,  4.92it/s]
  2%|▏         | 371/23500 [01:17<1:17:28,  4.98it/s]
  2%|▏         | 372/23500 [01:17<1:17:54,  4.95it/s]
  2%|▏         | 373/23500 [01:17<1:17:46,  4.96it/s]
  2%|▏         | 374/23500 [01:18<1:18:40,  4.90it/s]
  2%|▏         | 375/23500 [01:18<1:18:36,  4.90it/s]
  2%|▏         | 376/23500 [01:18<1:19:07,  4.87it/s]
  2%|▏         | 377/23500 [01:18<1:19:14,  4.86it/s]
  2%|▏         | 378/23500 [01:18<1:18:15,  4.92it/s]
  2%|▏         | 379/23500 [01:19<1:18:59,  4.88it/s]
  2%|▏         | 380/23500 [01:19<1:18:08,  4.93it/s]
  2%|▏         | 381/23500 [01:19<1:17:25,  4.98it/s]
  2%|▏         | 382/23500 [01:19<1:16:31,  5.04it/s]
  2%|▏         | 383/23500 [01:19<1:17:42,  4.96it/s]
  2%|▏         | 384/23500 [01:20<1:18:39,  4.90it/s]
  2%|▏         | 385/23500 [01:20<1:17:02,  5.00it/s]
  2%|▏         | 386/23500 [01:20<1:18:12,  4.93it/s]
  2%|▏         | 387/23500 [01:20<1:18:54,  4.88it/s]
  2%|▏         | 388/23500 [01:20<1:18:24,  4.91it/s]
  2%|▏         | 389/23500 [01:21<1:16:56,  5.01it/s]
  2%|▏         | 390/23500 [01:21<1:18:04,  4.93it/s]
  2%|▏         | 391/23500 [01:21<1:18:20,  4.92it/s]
  2%|▏         | 392/23500 [01:21<1:18:03,  4.93it/s]
  2%|▏         | 393/23500 [01:21<1:17:52,  4.95it/s]
  2%|▏         | 394/23500 [01:22<1:18:14,  4.92it/s]
  2%|▏         | 395/23500 [01:22<1:18:28,  4.91it/s]
  2%|▏         | 396/23500 [01:22<1:18:39,  4.90it/s]
  2%|▏         | 397/23500 [01:22<1:18:37,  4.90it/s]
  2%|▏         | 398/23500 [01:23<1:18:54,  4.88it/s]
  2%|▏         | 399/23500 [01:23<1:18:23,  4.91it/s]
  2%|▏         | 400/23500 [01:23<1:19:05,  4.87it/s]
  2%|▏         | 401/23500 [01:23<1:19:16,  4.86it/s]
  2%|▏         | 402/23500 [01:23<1:18:43,  4.89it/s]
  2%|▏         | 403/23500 [01:24<1:18:54,  4.88it/s]
  2%|▏         | 404/23500 [01:24<1:19:19,  4.85it/s]
  2%|▏         | 405/23500 [01:24<1:19:42,  4.83it/s]
  2%|▏         | 406/23500 [01:24<1:18:34,  4.90it/s]
  2%|▏         | 407/23500 [01:24<1:19:11,  4.86it/s]
  2%|▏         | 408/23500 [01:25<1:19:05,  4.87it/s]
  2%|▏         | 409/23500 [01:25<1:19:15,  4.86it/s]
  2%|▏         | 410/23500 [01:25<1:19:34,  4.84it/s]
  2%|▏         | 411/23500 [01:25<1:19:52,  4.82it/s]
  2%|▏         | 412/23500 [01:25<1:18:14,  4.92it/s]
  2%|▏         | 413/23500 [01:26<1:16:28,  5.03it/s]
  2%|▏         | 414/23500 [01:26<1:16:48,  5.01it/s]
  2%|▏         | 415/23500 [01:26<1:18:02,  4.93it/s]
  2%|▏         | 416/23500 [01:26<1:18:29,  4.90it/s]
  2%|▏         | 417/23500 [01:26<1:26:29,  4.45it/s]
  2%|▏         | 418/23500 [01:27<1:24:41,  4.54it/s]
  2%|▏         | 419/23500 [01:27<1:20:52,  4.76it/s]
  2%|▏         | 420/23500 [01:27<1:20:19,  4.79it/s]
  2%|▏         | 421/23500 [01:27<1:18:56,  4.87it/s]
  2%|▏         | 422/23500 [01:27<1:17:37,  4.96it/s]
  2%|▏         | 423/23500 [01:28<1:17:58,  4.93it/s]
  2%|▏         | 424/23500 [01:28<1:16:58,  5.00it/s]
  2%|▏         | 425/23500 [01:28<1:18:07,  4.92it/s]
  2%|▏         | 426/23500 [01:28<1:18:42,  4.89it/s]
  2%|▏         | 427/23500 [01:28<1:19:19,  4.85it/s]
  2%|▏         | 428/23500 [01:29<1:17:14,  4.98it/s]
  2%|▏         | 429/23500 [01:29<1:18:12,  4.92it/s]
  2%|▏         | 430/23500 [01:29<1:18:21,  4.91it/s]
  2%|▏         | 431/23500 [01:29<1:18:59,  4.87it/s]
  2%|▏         | 432/23500 [01:29<1:17:36,  4.95it/s]
  2%|▏         | 433/23500 [01:30<1:17:05,  4.99it/s]
  2%|▏         | 434/23500 [01:30<1:17:11,  4.98it/s]
  2%|▏         | 435/23500 [01:30<1:18:01,  4.93it/s]
  2%|▏         | 436/23500 [01:30<1:17:48,  4.94it/s]
  2%|▏         | 437/23500 [01:30<1:18:05,  4.92it/s]
  2%|▏         | 438/23500 [01:31<1:18:41,  4.88it/s]
  2%|▏         | 439/23500 [01:31<1:18:43,  4.88it/s]
  2%|▏         | 440/23500 [01:31<1:18:39,  4.89it/s]
  2%|▏         | 441/23500 [01:31<1:19:05,  4.86it/s]
  2%|▏         | 442/23500 [01:32<1:18:52,  4.87it/s]
  2%|▏         | 443/23500 [01:32<1:19:05,  4.86it/s]
  2%|▏         | 444/23500 [01:32<1:17:41,  4.95it/s]
  2%|▏         | 445/23500 [01:32<1:17:58,  4.93it/s]
  2%|▏         | 446/23500 [01:32<1:18:25,  4.90it/s]
  2%|▏         | 447/23500 [01:33<1:16:22,  5.03it/s]
  2%|▏         | 448/23500 [01:33<1:16:40,  5.01it/s]
  2%|▏         | 449/23500 [01:33<1:17:32,  4.95it/s]
  2%|▏         | 450/23500 [01:33<1:18:28,  4.90it/s]
  2%|▏         | 451/23500 [01:33<1:19:05,  4.86it/s]
  2%|▏         | 452/23500 [01:34<1:17:37,  4.95it/s]
  2%|▏         | 453/23500 [01:34<1:15:07,  5.11it/s]
  2%|▏         | 454/23500 [01:34<1:14:55,  5.13it/s]
  2%|▏         | 455/23500 [01:34<1:15:55,  5.06it/s]
  2%|▏         | 456/23500 [01:34<1:17:19,  4.97it/s]
  2%|▏         | 457/23500 [01:35<1:18:05,  4.92it/s]
  2%|▏         | 458/23500 [01:35<1:18:18,  4.90it/s]
  2%|▏         | 459/23500 [01:35<1:18:49,  4.87it/s]
  2%|▏         | 460/23500 [01:35<1:18:41,  4.88it/s]
  2%|▏         | 461/23500 [01:35<1:19:10,  4.85it/s]
  2%|▏         | 462/23500 [01:36<1:19:05,  4.85it/s]
  2%|▏         | 463/23500 [01:36<1:19:30,  4.83it/s]
  2%|▏         | 464/23500 [01:36<1:18:44,  4.88it/s]
  2%|▏         | 465/23500 [01:36<1:19:07,  4.85it/s]
  2%|▏         | 466/23500 [01:36<1:19:31,  4.83it/s]
  2%|▏         | 467/23500 [01:37<1:19:46,  4.81it/s]
  2%|▏         | 468/23500 [01:37<1:19:01,  4.86it/s]
  2%|▏         | 469/23500 [01:37<1:18:54,  4.86it/s]
                                                     

  2%|▏         | 470/23500 [01:37<1:18:54,  4.86it/s]{'eval_loss': 0.836928129196167, 'eval_accuracy': 0.6248, 'eval_f1': 0.612402481155663, 'eval_runtime': 1.266, 'eval_samples_per_second': 1974.649, 'eval_steps_per_second': 15.797, 'epoch': 1.0}
{'loss': 0.7758, 'learning_rate': 7.807635119982278e-06, 'epoch': 2.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.74it/s]

 30%|███       | 6/20 [00:00<00:00, 18.49it/s]

 40%|████      | 8/20 [00:00<00:00, 16.77it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.12it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.49it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.06it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.31it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.85it/s]

                                               

                                                     

100%|██████████| 20/20 [00:01<00:00, 15.85it/s]
  2%|▏         | 470/23500 [01:38<1:18:54,  4.86it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  2%|▏         | 471/23500 [01:40<4:26:19,  1.44it/s]
  2%|▏         | 472/23500 [01:40<3:38:23,  1.76it/s]
  2%|▏         | 473/23500 [01:40<3:02:07,  2.11it/s]
  2%|▏         | 474/23500 [01:40<2:33:32,  2.50it/s]
  2%|▏         | 475/23500 [01:40<2:13:06,  2.88it/s]
  2%|▏         | 476/23500 [01:41<1:56:20,  3.30it/s]
  2%|▏         | 477/23500 [01:41<1:45:37,  3.63it/s]
  2%|▏         | 478/23500 [01:41<1:37:16,  3.94it/s]
  2%|▏         | 479/23500 [01:41<1:31:13,  4.21it/s]
  2%|▏         | 480/23500 [01:41<1:26:54,  4.41it/s]
  2%|▏         | 481/23500 [01:42<1:24:36,  4.53it/s]
  2%|▏         | 482/23500 [01:42<1:22:50,  4.63it/s]
  2%|▏         | 483/23500 [01:42<1:19:55,  4.80it/s]
  2%|▏         | 484/23500 [01:42<1:20:03,  4.79it/s]
  2%|▏         | 485/23500 [01:42<1:19:09,  4.85it/s]
  2%|▏         | 486/23500 [01:43<1:18:32,  4.88it/s]
  2%|▏         | 487/23500 [01:43<1:19:06,  4.85it/s]
  2%|▏         | 488/23500 [01:43<1:19:20,  4.83it/s]
  2%|▏         | 489/23500 [01:43<1:19:22,  4.83it/s]
  2%|▏         | 490/23500 [01:43<1:19:40,  4.81it/s]
  2%|▏         | 491/23500 [01:44<1:18:09,  4.91it/s]
  2%|▏         | 492/23500 [01:44<1:18:49,  4.87it/s]
  2%|▏         | 493/23500 [01:44<1:18:19,  4.90it/s]
  2%|▏         | 494/23500 [01:44<1:17:34,  4.94it/s]
  2%|▏         | 495/23500 [01:44<1:17:56,  4.92it/s]
  2%|▏         | 496/23500 [01:45<1:17:09,  4.97it/s]
  2%|▏         | 497/23500 [01:45<1:16:20,  5.02it/s]
  2%|▏         | 498/23500 [01:45<1:17:14,  4.96it/s]
  2%|▏         | 499/23500 [01:45<1:17:27,  4.95it/s]
  2%|▏         | 500/23500 [01:45<1:18:18,  4.90it/s]
  2%|▏         | 501/23500 [01:46<1:18:58,  4.85it/s]
  2%|▏         | 502/23500 [01:46<1:18:39,  4.87it/s]
  2%|▏         | 503/23500 [01:46<1:18:51,  4.86it/s]
  2%|▏         | 504/23500 [01:46<1:19:01,  4.85it/s]
  2%|▏         | 505/23500 [01:46<1:19:17,  4.83it/s]
  2%|▏         | 506/23500 [01:47<1:19:08,  4.84it/s]
  2%|▏         | 507/23500 [01:47<1:19:30,  4.82it/s]
  2%|▏         | 508/23500 [01:47<1:18:11,  4.90it/s]
  2%|▏         | 509/23500 [01:47<1:18:11,  4.90it/s]
  2%|▏         | 510/23500 [01:47<1:18:49,  4.86it/s]
  2%|▏         | 511/23500 [01:48<1:16:28,  5.01it/s]
  2%|▏         | 512/23500 [01:48<1:17:28,  4.95it/s]
  2%|▏         | 513/23500 [01:48<1:17:59,  4.91it/s]
  2%|▏         | 514/23500 [01:48<1:18:09,  4.90it/s]
  2%|▏         | 515/23500 [01:48<1:17:49,  4.92it/s]
  2%|▏         | 516/23500 [01:49<1:18:19,  4.89it/s]
  2%|▏         | 517/23500 [01:49<1:17:58,  4.91it/s]
  2%|▏         | 518/23500 [01:49<1:18:41,  4.87it/s]
  2%|▏         | 519/23500 [01:49<1:18:11,  4.90it/s]
  2%|▏         | 520/23500 [01:50<1:18:38,  4.87it/s]
  2%|▏         | 521/23500 [01:50<1:18:57,  4.85it/s]
  2%|▏         | 522/23500 [01:50<1:18:43,  4.86it/s]
  2%|▏         | 523/23500 [01:50<1:17:24,  4.95it/s]
  2%|▏         | 524/23500 [01:50<1:18:21,  4.89it/s]
  2%|▏         | 525/23500 [01:51<1:17:53,  4.92it/s]
  2%|▏         | 526/23500 [01:51<1:18:03,  4.91it/s]
  2%|▏         | 527/23500 [01:51<1:18:43,  4.86it/s]
  2%|▏         | 528/23500 [01:51<1:17:43,  4.93it/s]
  2%|▏         | 529/23500 [01:51<1:18:00,  4.91it/s]
  2%|▏         | 530/23500 [01:52<1:18:39,  4.87it/s]
  2%|▏         | 531/23500 [01:52<1:17:41,  4.93it/s]
  2%|▏         | 532/23500 [01:52<1:16:13,  5.02it/s]
  2%|▏         | 533/23500 [01:52<1:17:23,  4.95it/s]
  2%|▏         | 534/23500 [01:52<1:16:49,  4.98it/s]
  2%|▏         | 535/23500 [01:53<1:17:36,  4.93it/s]
  2%|▏         | 536/23500 [01:53<1:16:36,  5.00it/s]
  2%|▏         | 537/23500 [01:53<1:17:12,  4.96it/s]
  2%|▏         | 538/23500 [01:53<1:18:06,  4.90it/s]
  2%|▏         | 539/23500 [01:53<1:17:42,  4.92it/s]
  2%|▏         | 540/23500 [01:54<1:17:42,  4.92it/s]
  2%|▏         | 541/23500 [01:54<1:15:39,  5.06it/s]
  2%|▏         | 542/23500 [01:54<1:17:05,  4.96it/s]
  2%|▏         | 543/23500 [01:54<1:17:59,  4.91it/s]
  2%|▏         | 544/23500 [01:54<1:16:17,  5.02it/s]
  2%|▏         | 545/23500 [01:55<1:17:28,  4.94it/s]
  2%|▏         | 546/23500 [01:55<1:16:54,  4.97it/s]
  2%|▏         | 547/23500 [01:55<1:17:20,  4.95it/s]
  2%|▏         | 548/23500 [01:55<1:18:04,  4.90it/s]
  2%|▏         | 549/23500 [01:55<1:18:40,  4.86it/s]
  2%|▏         | 550/23500 [01:56<1:18:15,  4.89it/s]
  2%|▏         | 551/23500 [01:56<1:18:22,  4.88it/s]
  2%|▏         | 552/23500 [01:56<1:18:52,  4.85it/s]
  2%|▏         | 553/23500 [01:56<1:18:34,  4.87it/s]
  2%|▏         | 554/23500 [01:56<1:19:01,  4.84it/s]
  2%|▏         | 555/23500 [01:57<1:18:19,  4.88it/s]
  2%|▏         | 556/23500 [01:57<1:18:29,  4.87it/s]
  2%|▏         | 557/23500 [01:57<1:19:00,  4.84it/s]
  2%|▏         | 558/23500 [01:57<1:17:55,  4.91it/s]
  2%|▏         | 559/23500 [01:57<1:17:37,  4.93it/s]
  2%|▏         | 560/23500 [01:58<1:18:12,  4.89it/s]
  2%|▏         | 561/23500 [01:58<1:18:12,  4.89it/s]
  2%|▏         | 562/23500 [01:58<1:17:54,  4.91it/s]
  2%|▏         | 563/23500 [01:58<1:17:42,  4.92it/s]
  2%|▏         | 564/23500 [01:58<1:18:10,  4.89it/s]
  2%|▏         | 565/23500 [01:59<1:18:43,  4.86it/s]
  2%|▏         | 566/23500 [01:59<1:16:58,  4.97it/s]
  2%|▏         | 567/23500 [01:59<1:17:32,  4.93it/s]
  2%|▏         | 568/23500 [01:59<1:17:43,  4.92it/s]
  2%|▏         | 569/23500 [01:59<1:17:49,  4.91it/s]
  2%|▏         | 570/23500 [02:00<1:18:28,  4.87it/s]
  2%|▏         | 571/23500 [02:00<1:16:44,  4.98it/s]
  2%|▏         | 572/23500 [02:00<1:17:43,  4.92it/s]
  2%|▏         | 573/23500 [02:00<1:15:59,  5.03it/s]
  2%|▏         | 574/23500 [02:00<1:17:17,  4.94it/s]
  2%|▏         | 575/23500 [02:01<1:16:44,  4.98it/s]
  2%|▏         | 576/23500 [02:01<1:16:42,  4.98it/s]
  2%|▏         | 577/23500 [02:01<1:16:37,  4.99it/s]
  2%|▏         | 578/23500 [02:01<1:17:02,  4.96it/s]
  2%|▏         | 579/23500 [02:02<1:17:58,  4.90it/s]
  2%|▏         | 580/23500 [02:02<1:18:30,  4.87it/s]
  2%|▏         | 581/23500 [02:02<1:18:49,  4.85it/s]
  2%|▏         | 582/23500 [02:02<1:19:16,  4.82it/s]
  2%|▏         | 583/23500 [02:02<1:18:55,  4.84it/s]
  2%|▏         | 584/23500 [02:03<1:18:47,  4.85it/s]
  2%|▏         | 585/23500 [02:03<1:18:49,  4.85it/s]
  2%|▏         | 586/23500 [02:03<1:19:09,  4.82it/s]
  2%|▏         | 587/23500 [02:03<1:19:26,  4.81it/s]
  3%|▎         | 588/23500 [02:03<1:30:25,  4.22it/s]
  3%|▎         | 589/23500 [02:04<1:26:56,  4.39it/s]
  3%|▎         | 590/23500 [02:04<1:22:30,  4.63it/s]
  3%|▎         | 591/23500 [02:04<1:21:36,  4.68it/s]
  3%|▎         | 592/23500 [02:04<1:20:38,  4.73it/s]
  3%|▎         | 593/23500 [02:04<1:20:30,  4.74it/s]
  3%|▎         | 594/23500 [02:05<1:20:22,  4.75it/s]
  3%|▎         | 595/23500 [02:05<1:19:44,  4.79it/s]
  3%|▎         | 596/23500 [02:05<1:19:48,  4.78it/s]
  3%|▎         | 597/23500 [02:05<1:19:32,  4.80it/s]
  3%|▎         | 598/23500 [02:06<1:17:50,  4.90it/s]
  3%|▎         | 599/23500 [02:06<1:17:48,  4.91it/s]
  3%|▎         | 600/23500 [02:06<1:18:08,  4.88it/s]
  3%|▎         | 601/23500 [02:06<1:17:10,  4.95it/s]
  3%|▎         | 602/23500 [02:06<1:18:04,  4.89it/s]
  3%|▎         | 603/23500 [02:07<1:18:17,  4.87it/s]
  3%|▎         | 604/23500 [02:07<1:16:34,  4.98it/s]
  3%|▎         | 605/23500 [02:07<1:16:09,  5.01it/s]
  3%|▎         | 606/23500 [02:07<1:16:40,  4.98it/s]
  3%|▎         | 607/23500 [02:07<1:17:08,  4.95it/s]
  3%|▎         | 608/23500 [02:08<1:17:41,  4.91it/s]
  3%|▎         | 609/23500 [02:08<1:17:41,  4.91it/s]
  3%|▎         | 610/23500 [02:08<1:17:23,  4.93it/s]
  3%|▎         | 611/23500 [02:08<1:17:26,  4.93it/s]
  3%|▎         | 612/23500 [02:08<1:17:51,  4.90it/s]
  3%|▎         | 613/23500 [02:09<1:18:33,  4.86it/s]
  3%|▎         | 614/23500 [02:09<1:18:15,  4.87it/s]
  3%|▎         | 615/23500 [02:09<1:18:50,  4.84it/s]
  3%|▎         | 616/23500 [02:09<1:18:16,  4.87it/s]
  3%|▎         | 617/23500 [02:09<1:18:34,  4.85it/s]
  3%|▎         | 618/23500 [02:10<1:18:26,  4.86it/s]
  3%|▎         | 619/23500 [02:10<1:18:35,  4.85it/s]
  3%|▎         | 620/23500 [02:10<1:18:27,  4.86it/s]
  3%|▎         | 621/23500 [02:10<1:18:14,  4.87it/s]
  3%|▎         | 622/23500 [02:10<1:16:57,  4.95it/s]
  3%|▎         | 623/23500 [02:11<1:16:05,  5.01it/s]
  3%|▎         | 624/23500 [02:11<1:15:44,  5.03it/s]
  3%|▎         | 625/23500 [02:11<1:14:46,  5.10it/s]
  3%|▎         | 626/23500 [02:11<1:14:50,  5.09it/s]
  3%|▎         | 627/23500 [02:11<1:13:27,  5.19it/s]
  3%|▎         | 628/23500 [02:12<1:12:21,  5.27it/s]
  3%|▎         | 629/23500 [02:12<1:14:09,  5.14it/s]
  3%|▎         | 630/23500 [02:12<1:14:22,  5.12it/s]
  3%|▎         | 631/23500 [02:12<1:15:27,  5.05it/s]
  3%|▎         | 632/23500 [02:12<1:16:28,  4.98it/s]
  3%|▎         | 633/23500 [02:13<1:15:35,  5.04it/s]
  3%|▎         | 634/23500 [02:13<1:16:20,  4.99it/s]
  3%|▎         | 635/23500 [02:13<1:16:54,  4.96it/s]
  3%|▎         | 636/23500 [02:13<1:16:45,  4.96it/s]
  3%|▎         | 637/23500 [02:13<1:15:56,  5.02it/s]
  3%|▎         | 638/23500 [02:14<1:17:07,  4.94it/s]
  3%|▎         | 639/23500 [02:14<1:17:47,  4.90it/s]
  3%|▎         | 640/23500 [02:14<1:16:31,  4.98it/s]
  3%|▎         | 641/23500 [02:14<1:17:14,  4.93it/s]
  3%|▎         | 642/23500 [02:14<1:18:02,  4.88it/s]
  3%|▎         | 643/23500 [02:15<1:18:05,  4.88it/s]
  3%|▎         | 644/23500 [02:15<1:18:04,  4.88it/s]
  3%|▎         | 645/23500 [02:15<1:16:43,  4.96it/s]
  3%|▎         | 646/23500 [02:15<1:17:01,  4.94it/s]
  3%|▎         | 647/23500 [02:15<1:17:22,  4.92it/s]
  3%|▎         | 648/23500 [02:16<1:15:52,  5.02it/s]
  3%|▎         | 649/23500 [02:16<1:17:06,  4.94it/s]
  3%|▎         | 650/23500 [02:16<1:16:06,  5.00it/s]
  3%|▎         | 651/23500 [02:16<1:16:15,  4.99it/s]
  3%|▎         | 652/23500 [02:16<1:16:50,  4.96it/s]
  3%|▎         | 653/23500 [02:17<1:16:59,  4.95it/s]
  3%|▎         | 654/23500 [02:17<1:17:30,  4.91it/s]
  3%|▎         | 655/23500 [02:17<1:18:03,  4.88it/s]
  3%|▎         | 656/23500 [02:17<1:18:23,  4.86it/s]
  3%|▎         | 657/23500 [02:17<1:18:11,  4.87it/s]
  3%|▎         | 658/23500 [02:18<1:18:41,  4.84it/s]
  3%|▎         | 659/23500 [02:18<1:18:26,  4.85it/s]
  3%|▎         | 660/23500 [02:18<1:18:24,  4.86it/s]
  3%|▎         | 661/23500 [02:18<1:18:10,  4.87it/s]
  3%|▎         | 662/23500 [02:18<1:17:42,  4.90it/s]
  3%|▎         | 663/23500 [02:19<1:32:19,  4.12it/s]
  3%|▎         | 664/23500 [02:19<1:27:01,  4.37it/s]
  3%|▎         | 665/23500 [02:19<1:23:56,  4.53it/s]
  3%|▎         | 666/23500 [02:19<1:22:19,  4.62it/s]
  3%|▎         | 667/23500 [02:20<1:21:16,  4.68it/s]
  3%|▎         | 668/23500 [02:20<1:20:05,  4.75it/s]
  3%|▎         | 669/23500 [02:20<1:19:57,  4.76it/s]
  3%|▎         | 670/23500 [02:20<1:19:36,  4.78it/s]
  3%|▎         | 671/23500 [02:20<1:17:49,  4.89it/s]
  3%|▎         | 672/23500 [02:21<1:16:12,  4.99it/s]
  3%|▎         | 673/23500 [02:21<1:16:55,  4.95it/s]
  3%|▎         | 674/23500 [02:21<1:17:48,  4.89it/s]
  3%|▎         | 675/23500 [02:21<1:17:43,  4.89it/s]
  3%|▎         | 676/23500 [02:21<1:16:27,  4.97it/s]
  3%|▎         | 677/23500 [02:22<1:16:45,  4.96it/s]
  3%|▎         | 678/23500 [02:22<1:17:39,  4.90it/s]
  3%|▎         | 679/23500 [02:22<1:18:07,  4.87it/s]
  3%|▎         | 680/23500 [02:22<1:17:55,  4.88it/s]
  3%|▎         | 681/23500 [02:22<1:16:59,  4.94it/s]
  3%|▎         | 682/23500 [02:23<1:17:05,  4.93it/s]
  3%|▎         | 683/23500 [02:23<1:17:31,  4.90it/s]
  3%|▎         | 684/23500 [02:23<1:17:13,  4.92it/s]
  3%|▎         | 685/23500 [02:23<1:17:20,  4.92it/s]
  3%|▎         | 686/23500 [02:23<1:17:20,  4.92it/s]
  3%|▎         | 687/23500 [02:24<1:17:24,  4.91it/s]
  3%|▎         | 688/23500 [02:24<1:17:57,  4.88it/s]
  3%|▎         | 689/23500 [02:24<1:16:59,  4.94it/s]
  3%|▎         | 690/23500 [02:24<1:17:50,  4.88it/s]
  3%|▎         | 691/23500 [02:24<1:16:51,  4.95it/s]
  3%|▎         | 692/23500 [02:25<1:17:42,  4.89it/s]
  3%|▎         | 693/23500 [02:25<1:15:54,  5.01it/s]
  3%|▎         | 694/23500 [02:25<1:14:38,  5.09it/s]
  3%|▎         | 695/23500 [02:25<1:15:11,  5.06it/s]
  3%|▎         | 696/23500 [02:25<1:15:00,  5.07it/s]
  3%|▎         | 697/23500 [02:26<1:16:28,  4.97it/s]
  3%|▎         | 698/23500 [02:26<1:17:27,  4.91it/s]
  3%|▎         | 699/23500 [02:26<1:18:05,  4.87it/s]
  3%|▎         | 700/23500 [02:26<1:18:25,  4.85it/s]
  3%|▎         | 701/23500 [02:27<1:18:18,  4.85it/s]
  3%|▎         | 702/23500 [02:27<1:14:15,  5.12it/s]
  3%|▎         | 703/23500 [02:27<1:15:56,  5.00it/s]
  3%|▎         | 704/23500 [02:27<1:16:38,  4.96it/s]
                                                     

  3%|▎         | 705/23500 [02:27<1:16:38,  4.96it/s]{'eval_loss': 0.7121442556381226, 'eval_accuracy': 0.6932, 'eval_f1': 0.6899832814917121, 'eval_runtime': 1.2656, 'eval_samples_per_second': 1975.323, 'eval_steps_per_second': 15.803, 'epoch': 2.0}
{'loss': 0.6803, 'learning_rate': 1.1719776384792164e-05, 'epoch': 3.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.71it/s]

 30%|███       | 6/20 [00:00<00:00, 18.48it/s]

 40%|████      | 8/20 [00:00<00:00, 16.75it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.10it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.49it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.06it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.29it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.84it/s]

                                               

                                                     

100%|██████████| 20/20 [00:01<00:00, 15.84it/s]
  3%|▎         | 705/23500 [02:28<1:16:38,  4.96it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  3%|▎         | 706/23500 [02:30<4:30:29,  1.40it/s]
  3%|▎         | 707/23500 [02:30<3:41:13,  1.72it/s]
  3%|▎         | 708/23500 [02:30<3:04:15,  2.06it/s]
  3%|▎         | 709/23500 [02:30<2:34:33,  2.46it/s]
  3%|▎         | 710/23500 [02:31<2:13:21,  2.85it/s]
  3%|▎         | 711/23500 [02:31<1:57:54,  3.22it/s]
  3%|▎         | 712/23500 [02:31<1:46:30,  3.57it/s]
  3%|▎         | 713/23500 [02:31<1:38:43,  3.85it/s]
  3%|▎         | 714/23500 [02:31<1:32:10,  4.12it/s]
  3%|▎         | 715/23500 [02:32<1:28:16,  4.30it/s]
  3%|▎         | 716/23500 [02:32<1:23:16,  4.56it/s]
  3%|▎         | 717/23500 [02:32<1:20:45,  4.70it/s]
  3%|▎         | 718/23500 [02:32<1:20:23,  4.72it/s]
  3%|▎         | 719/23500 [02:32<1:19:45,  4.76it/s]
  3%|▎         | 720/23500 [02:33<1:19:06,  4.80it/s]
  3%|▎         | 721/23500 [02:33<1:19:05,  4.80it/s]
  3%|▎         | 722/23500 [02:33<1:19:12,  4.79it/s]
  3%|▎         | 723/23500 [02:33<1:18:26,  4.84it/s]
  3%|▎         | 724/23500 [02:33<1:18:46,  4.82it/s]
  3%|▎         | 725/23500 [02:34<1:17:09,  4.92it/s]
  3%|▎         | 726/23500 [02:34<1:15:35,  5.02it/s]
  3%|▎         | 727/23500 [02:34<1:16:30,  4.96it/s]
  3%|▎         | 728/23500 [02:34<1:16:53,  4.94it/s]
  3%|▎         | 729/23500 [02:34<1:17:31,  4.90it/s]
  3%|▎         | 730/23500 [02:35<1:17:57,  4.87it/s]
  3%|▎         | 731/23500 [02:35<1:17:52,  4.87it/s]
  3%|▎         | 732/23500 [02:35<1:18:19,  4.84it/s]
  3%|▎         | 733/23500 [02:35<1:18:33,  4.83it/s]
  3%|▎         | 734/23500 [02:35<1:18:50,  4.81it/s]
  3%|▎         | 735/23500 [02:36<1:19:03,  4.80it/s]
  3%|▎         | 736/23500 [02:36<1:18:28,  4.83it/s]
  3%|▎         | 737/23500 [02:36<1:18:38,  4.82it/s]
  3%|▎         | 738/23500 [02:36<1:18:56,  4.81it/s]
  3%|▎         | 739/23500 [02:36<1:17:33,  4.89it/s]
  3%|▎         | 740/23500 [02:37<1:18:00,  4.86it/s]
  3%|▎         | 741/23500 [02:37<1:18:25,  4.84it/s]
  3%|▎         | 742/23500 [02:37<1:17:43,  4.88it/s]
  3%|▎         | 743/23500 [02:37<1:17:49,  4.87it/s]
  3%|▎         | 744/23500 [02:37<1:17:19,  4.91it/s]
  3%|▎         | 745/23500 [02:38<1:17:28,  4.90it/s]
  3%|▎         | 746/23500 [02:38<1:18:06,  4.86it/s]
  3%|▎         | 747/23500 [02:38<1:17:36,  4.89it/s]
  3%|▎         | 748/23500 [02:38<1:17:26,  4.90it/s]
  3%|▎         | 749/23500 [02:38<1:16:11,  4.98it/s]
  3%|▎         | 750/23500 [02:39<1:16:40,  4.94it/s]
  3%|▎         | 751/23500 [02:39<1:16:03,  4.99it/s]
  3%|▎         | 752/23500 [02:39<1:17:03,  4.92it/s]
  3%|▎         | 753/23500 [02:39<1:17:10,  4.91it/s]
  3%|▎         | 754/23500 [02:40<1:17:17,  4.90it/s]
  3%|▎         | 755/23500 [02:40<1:18:02,  4.86it/s]
  3%|▎         | 756/23500 [02:40<1:17:48,  4.87it/s]
  3%|▎         | 757/23500 [02:40<1:18:00,  4.86it/s]
  3%|▎         | 758/23500 [02:40<1:17:28,  4.89it/s]
  3%|▎         | 759/23500 [02:41<1:17:27,  4.89it/s]
  3%|▎         | 760/23500 [02:41<1:16:36,  4.95it/s]
  3%|▎         | 761/23500 [02:41<1:17:05,  4.92it/s]
  3%|▎         | 762/23500 [02:41<1:16:43,  4.94it/s]
  3%|▎         | 763/23500 [02:41<1:17:00,  4.92it/s]
  3%|▎         | 764/23500 [02:42<1:17:48,  4.87it/s]
  3%|▎         | 765/23500 [02:42<1:18:04,  4.85it/s]
  3%|▎         | 766/23500 [02:42<1:15:32,  5.02it/s]
  3%|▎         | 767/23500 [02:42<1:16:47,  4.93it/s]
  3%|▎         | 768/23500 [02:42<1:16:38,  4.94it/s]
  3%|▎         | 769/23500 [02:43<1:16:53,  4.93it/s]
  3%|▎         | 770/23500 [02:43<1:16:17,  4.97it/s]
  3%|▎         | 771/23500 [02:43<1:17:10,  4.91it/s]
  3%|▎         | 772/23500 [02:43<1:17:29,  4.89it/s]
  3%|▎         | 773/23500 [02:43<1:17:50,  4.87it/s]
  3%|▎         | 774/23500 [02:44<1:16:45,  4.93it/s]
  3%|▎         | 775/23500 [02:44<1:17:11,  4.91it/s]
  3%|▎         | 776/23500 [02:44<1:17:31,  4.89it/s]
  3%|▎         | 777/23500 [02:44<1:17:43,  4.87it/s]
  3%|▎         | 778/23500 [02:44<1:17:30,  4.89it/s]
  3%|▎         | 779/23500 [02:45<1:15:50,  4.99it/s]
  3%|▎         | 780/23500 [02:45<1:15:21,  5.02it/s]
  3%|▎         | 781/23500 [02:45<1:14:49,  5.06it/s]
  3%|▎         | 782/23500 [02:45<1:15:50,  4.99it/s]
  3%|▎         | 783/23500 [02:45<1:15:21,  5.02it/s]
  3%|▎         | 784/23500 [02:46<1:16:05,  4.98it/s]
  3%|▎         | 785/23500 [02:46<1:17:02,  4.91it/s]
  3%|▎         | 786/23500 [02:46<1:15:19,  5.03it/s]
  3%|▎         | 787/23500 [02:46<1:16:32,  4.95it/s]
  3%|▎         | 788/23500 [02:46<1:16:23,  4.95it/s]
  3%|▎         | 789/23500 [02:47<1:16:40,  4.94it/s]
  3%|▎         | 790/23500 [02:47<1:16:31,  4.95it/s]
  3%|▎         | 791/23500 [02:47<1:17:24,  4.89it/s]
  3%|▎         | 792/23500 [02:47<1:17:29,  4.88it/s]
  3%|▎         | 793/23500 [02:47<1:16:32,  4.94it/s]
  3%|▎         | 794/23500 [02:48<1:16:24,  4.95it/s]
  3%|▎         | 795/23500 [02:48<1:16:38,  4.94it/s]
  3%|▎         | 796/23500 [02:48<1:17:17,  4.90it/s]
  3%|▎         | 797/23500 [02:48<1:17:51,  4.86it/s]
  3%|▎         | 798/23500 [02:48<1:17:24,  4.89it/s]
  3%|▎         | 799/23500 [02:49<1:17:40,  4.87it/s]
  3%|▎         | 800/23500 [02:49<1:17:34,  4.88it/s]
  3%|▎         | 801/23500 [02:49<1:18:03,  4.85it/s]
  3%|▎         | 802/23500 [02:49<1:17:47,  4.86it/s]
  3%|▎         | 803/23500 [02:49<1:18:18,  4.83it/s]
  3%|▎         | 804/23500 [02:50<1:17:42,  4.87it/s]
  3%|▎         | 805/23500 [02:50<1:18:07,  4.84it/s]
  3%|▎         | 806/23500 [02:50<1:16:57,  4.91it/s]
  3%|▎         | 807/23500 [02:50<1:17:21,  4.89it/s]
  3%|▎         | 808/23500 [02:50<1:17:52,  4.86it/s]
  3%|▎         | 809/23500 [02:51<1:17:21,  4.89it/s]
  3%|▎         | 810/23500 [02:51<1:15:44,  4.99it/s]
  3%|▎         | 811/23500 [02:51<1:16:03,  4.97it/s]
  3%|▎         | 812/23500 [02:51<1:16:22,  4.95it/s]
  3%|▎         | 813/23500 [02:52<1:16:37,  4.93it/s]
  3%|▎         | 814/23500 [02:52<1:14:55,  5.05it/s]
  3%|▎         | 815/23500 [02:52<1:16:02,  4.97it/s]
  3%|▎         | 816/23500 [02:52<1:17:01,  4.91it/s]
  3%|▎         | 817/23500 [02:52<1:16:08,  4.97it/s]
  3%|▎         | 818/23500 [02:53<1:17:06,  4.90it/s]
  3%|▎         | 819/23500 [02:53<1:17:23,  4.88it/s]
  3%|▎         | 820/23500 [02:53<1:16:10,  4.96it/s]
  3%|▎         | 821/23500 [02:53<1:16:37,  4.93it/s]
  3%|▎         | 822/23500 [02:53<1:16:49,  4.92it/s]
  4%|▎         | 823/23500 [02:54<1:17:35,  4.87it/s]
  4%|▎         | 824/23500 [02:54<1:15:33,  5.00it/s]
  4%|▎         | 825/23500 [02:54<1:15:17,  5.02it/s]
  4%|▎         | 826/23500 [02:54<1:15:06,  5.03it/s]
  4%|▎         | 827/23500 [02:54<1:14:56,  5.04it/s]
  4%|▎         | 828/23500 [02:55<1:16:11,  4.96it/s]
  4%|▎         | 829/23500 [02:55<1:14:44,  5.06it/s]
  4%|▎         | 830/23500 [02:55<1:15:34,  5.00it/s]
  4%|▎         | 831/23500 [02:55<1:13:54,  5.11it/s]
  4%|▎         | 832/23500 [02:55<1:14:26,  5.08it/s]
  4%|▎         | 833/23500 [02:55<1:14:08,  5.10it/s]
  4%|▎         | 834/23500 [02:56<1:15:28,  5.01it/s]
  4%|▎         | 835/23500 [02:56<1:16:35,  4.93it/s]
  4%|▎         | 836/23500 [02:56<1:17:19,  4.89it/s]
  4%|▎         | 837/23500 [02:56<1:17:29,  4.87it/s]
  4%|▎         | 838/23500 [02:57<1:16:32,  4.94it/s]
  4%|▎         | 839/23500 [02:57<1:16:14,  4.95it/s]
  4%|▎         | 840/23500 [02:57<1:17:03,  4.90it/s]
  4%|▎         | 841/23500 [02:57<1:14:52,  5.04it/s]
  4%|▎         | 842/23500 [02:57<1:14:25,  5.07it/s]
  4%|▎         | 843/23500 [02:58<1:14:53,  5.04it/s]
  4%|▎         | 844/23500 [02:58<1:15:52,  4.98it/s]
  4%|▎         | 845/23500 [02:58<1:16:38,  4.93it/s]
  4%|▎         | 846/23500 [02:58<1:17:22,  4.88it/s]
  4%|▎         | 847/23500 [02:58<1:16:54,  4.91it/s]
  4%|▎         | 848/23500 [02:59<1:17:00,  4.90it/s]
  4%|▎         | 849/23500 [02:59<1:16:33,  4.93it/s]
  4%|▎         | 850/23500 [02:59<1:16:21,  4.94it/s]
  4%|▎         | 851/23500 [02:59<1:17:09,  4.89it/s]
  4%|▎         | 852/23500 [02:59<1:16:21,  4.94it/s]
  4%|▎         | 853/23500 [03:00<1:14:45,  5.05it/s]
  4%|▎         | 854/23500 [03:00<1:13:17,  5.15it/s]
  4%|▎         | 855/23500 [03:00<1:15:00,  5.03it/s]
  4%|▎         | 856/23500 [03:00<1:15:40,  4.99it/s]
  4%|▎         | 857/23500 [03:00<1:15:48,  4.98it/s]
  4%|▎         | 858/23500 [03:01<1:16:48,  4.91it/s]
  4%|▎         | 859/23500 [03:01<1:16:03,  4.96it/s]
  4%|▎         | 860/23500 [03:01<1:15:31,  5.00it/s]
  4%|▎         | 861/23500 [03:01<1:15:51,  4.97it/s]
  4%|▎         | 862/23500 [03:01<1:16:39,  4.92it/s]
  4%|▎         | 863/23500 [03:02<1:17:25,  4.87it/s]
  4%|▎         | 864/23500 [03:02<1:17:33,  4.86it/s]
  4%|▎         | 865/23500 [03:02<1:18:06,  4.83it/s]
  4%|▎         | 866/23500 [03:02<1:17:40,  4.86it/s]
  4%|▎         | 867/23500 [03:02<1:16:41,  4.92it/s]
  4%|▎         | 868/23500 [03:03<1:17:25,  4.87it/s]
  4%|▎         | 869/23500 [03:03<1:17:38,  4.86it/s]
  4%|▎         | 870/23500 [03:03<1:17:11,  4.89it/s]
  4%|▎         | 871/23500 [03:03<1:17:26,  4.87it/s]
  4%|▎         | 872/23500 [03:03<1:17:23,  4.87it/s]
  4%|▎         | 873/23500 [03:04<1:17:35,  4.86it/s]
  4%|▎         | 874/23500 [03:04<1:17:20,  4.88it/s]
  4%|▎         | 875/23500 [03:04<1:17:27,  4.87it/s]
  4%|▎         | 876/23500 [03:04<1:16:55,  4.90it/s]
  4%|▎         | 877/23500 [03:04<1:16:52,  4.91it/s]
  4%|▎         | 878/23500 [03:05<1:16:08,  4.95it/s]
  4%|▎         | 879/23500 [03:05<1:16:20,  4.94it/s]
  4%|▎         | 880/23500 [03:05<1:12:48,  5.18it/s]
  4%|▎         | 881/23500 [03:05<1:14:36,  5.05it/s]
  4%|▍         | 882/23500 [03:06<1:28:28,  4.26it/s]
  4%|▍         | 883/23500 [03:06<1:21:18,  4.64it/s]
  4%|▍         | 884/23500 [03:06<1:20:15,  4.70it/s]
  4%|▍         | 885/23500 [03:06<1:19:17,  4.75it/s]
  4%|▍         | 886/23500 [03:06<1:18:45,  4.79it/s]
  4%|▍         | 887/23500 [03:07<1:17:02,  4.89it/s]
  4%|▍         | 888/23500 [03:07<1:17:17,  4.88it/s]
  4%|▍         | 889/23500 [03:07<1:17:17,  4.88it/s]
  4%|▍         | 890/23500 [03:07<1:17:16,  4.88it/s]
  4%|▍         | 891/23500 [03:07<1:14:31,  5.06it/s]
  4%|▍         | 892/23500 [03:08<1:14:07,  5.08it/s]
  4%|▍         | 893/23500 [03:08<1:15:05,  5.02it/s]
  4%|▍         | 894/23500 [03:08<1:15:41,  4.98it/s]
  4%|▍         | 895/23500 [03:08<1:16:39,  4.92it/s]
  4%|▍         | 896/23500 [03:08<1:16:40,  4.91it/s]
  4%|▍         | 897/23500 [03:09<1:16:45,  4.91it/s]
  4%|▍         | 898/23500 [03:09<1:17:14,  4.88it/s]
  4%|▍         | 899/23500 [03:09<1:17:19,  4.87it/s]
  4%|▍         | 900/23500 [03:09<1:17:51,  4.84it/s]
  4%|▍         | 901/23500 [03:09<1:17:14,  4.88it/s]
  4%|▍         | 902/23500 [03:10<1:16:40,  4.91it/s]
  4%|▍         | 903/23500 [03:10<1:15:35,  4.98it/s]
  4%|▍         | 904/23500 [03:10<1:16:17,  4.94it/s]
  4%|▍         | 905/23500 [03:10<1:16:22,  4.93it/s]
  4%|▍         | 906/23500 [03:10<1:16:11,  4.94it/s]
  4%|▍         | 907/23500 [03:11<1:16:58,  4.89it/s]
  4%|▍         | 908/23500 [03:11<1:17:22,  4.87it/s]
  4%|▍         | 909/23500 [03:11<1:17:10,  4.88it/s]
  4%|▍         | 910/23500 [03:11<1:17:10,  4.88it/s]
  4%|▍         | 911/23500 [03:11<1:17:42,  4.85it/s]
  4%|▍         | 912/23500 [03:12<1:16:17,  4.94it/s]
  4%|▍         | 913/23500 [03:12<1:16:24,  4.93it/s]
  4%|▍         | 914/23500 [03:12<1:16:11,  4.94it/s]
  4%|▍         | 915/23500 [03:12<1:16:16,  4.93it/s]
  4%|▍         | 916/23500 [03:12<1:16:52,  4.90it/s]
  4%|▍         | 917/23500 [03:13<1:17:01,  4.89it/s]
  4%|▍         | 918/23500 [03:13<1:16:30,  4.92it/s]
  4%|▍         | 919/23500 [03:13<1:16:32,  4.92it/s]
  4%|▍         | 920/23500 [03:13<1:17:13,  4.87it/s]
  4%|▍         | 921/23500 [03:13<1:15:35,  4.98it/s]
  4%|▍         | 922/23500 [03:14<1:16:13,  4.94it/s]
  4%|▍         | 923/23500 [03:14<1:15:27,  4.99it/s]
  4%|▍         | 924/23500 [03:14<1:15:24,  4.99it/s]
  4%|▍         | 925/23500 [03:14<1:14:38,  5.04it/s]
  4%|▍         | 926/23500 [03:14<1:15:52,  4.96it/s]
  4%|▍         | 927/23500 [03:15<1:14:36,  5.04it/s]
  4%|▍         | 928/23500 [03:15<1:15:52,  4.96it/s]
  4%|▍         | 929/23500 [03:15<1:16:46,  4.90it/s]
  4%|▍         | 930/23500 [03:15<1:16:20,  4.93it/s]
  4%|▍         | 931/23500 [03:15<1:16:53,  4.89it/s]
  4%|▍         | 932/23500 [03:16<1:16:58,  4.89it/s]
  4%|▍         | 933/23500 [03:16<1:17:34,  4.85it/s]
  4%|▍         | 934/23500 [03:16<1:17:55,  4.83it/s]
  4%|▍         | 935/23500 [03:16<1:16:20,  4.93it/s]
  4%|▍         | 936/23500 [03:16<1:15:41,  4.97it/s]
  4%|▍         | 937/23500 [03:17<1:14:46,  5.03it/s]
  4%|▍         | 938/23500 [03:17<1:15:24,  4.99it/s]
  4%|▍         | 939/23500 [03:17<1:15:44,  4.96it/s]
                                                     

  4%|▍         | 940/23500 [03:17<1:15:44,  4.96it/s]{'eval_loss': 0.6878911852836609, 'eval_accuracy': 0.7044, 'eval_f1': 0.7069424431108294, 'eval_runtime': 1.2664, 'eval_samples_per_second': 1974.166, 'eval_steps_per_second': 15.793, 'epoch': 3.0}
{'loss': 0.6025, 'learning_rate': 1.5631917649602047e-05, 'epoch': 4.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.72it/s]

 30%|███       | 6/20 [00:00<00:00, 18.51it/s]

 40%|████      | 8/20 [00:00<00:00, 16.77it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.12it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.49it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.05it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.28it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.83it/s]

                                               

                                                     

100%|██████████| 20/20 [00:01<00:00, 15.83it/s]
  4%|▍         | 940/23500 [03:18<1:15:44,  4.96it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  4%|▍         | 941/23500 [03:20<4:20:53,  1.44it/s]
  4%|▍         | 942/23500 [03:20<3:35:42,  1.74it/s]
  4%|▍         | 943/23500 [03:20<2:59:25,  2.10it/s]
  4%|▍         | 944/23500 [03:20<2:31:12,  2.49it/s]
  4%|▍         | 945/23500 [03:20<2:10:18,  2.88it/s]
  4%|▍         | 946/23500 [03:21<1:55:33,  3.25it/s]
  4%|▍         | 947/23500 [03:21<1:43:30,  3.63it/s]
  4%|▍         | 948/23500 [03:21<1:45:50,  3.55it/s]
  4%|▍         | 949/23500 [03:21<1:37:23,  3.86it/s]
  4%|▍         | 950/23500 [03:22<1:31:41,  4.10it/s]
  4%|▍         | 951/23500 [03:22<1:26:04,  4.37it/s]
  4%|▍         | 952/23500 [03:22<1:23:33,  4.50it/s]
  4%|▍         | 953/23500 [03:22<1:17:30,  4.85it/s]
  4%|▍         | 954/23500 [03:22<1:17:20,  4.86it/s]
  4%|▍         | 955/23500 [03:23<1:17:35,  4.84it/s]
  4%|▍         | 956/23500 [03:23<1:16:56,  4.88it/s]
  4%|▍         | 957/23500 [03:23<1:14:55,  5.01it/s]
  4%|▍         | 958/23500 [03:23<1:15:44,  4.96it/s]
  4%|▍         | 959/23500 [03:23<1:16:24,  4.92it/s]
  4%|▍         | 960/23500 [03:24<1:16:28,  4.91it/s]
  4%|▍         | 961/23500 [03:24<1:16:48,  4.89it/s]
  4%|▍         | 962/23500 [03:24<1:16:01,  4.94it/s]
  4%|▍         | 963/23500 [03:24<1:16:17,  4.92it/s]
  4%|▍         | 964/23500 [03:24<1:16:33,  4.91it/s]
  4%|▍         | 965/23500 [03:25<1:15:42,  4.96it/s]
  4%|▍         | 966/23500 [03:25<1:16:35,  4.90it/s]
  4%|▍         | 967/23500 [03:25<1:17:12,  4.86it/s]
  4%|▍         | 968/23500 [03:25<1:17:12,  4.86it/s]
  4%|▍         | 969/23500 [03:25<1:15:49,  4.95it/s]
  4%|▍         | 970/23500 [03:26<1:15:42,  4.96it/s]
  4%|▍         | 971/23500 [03:26<1:16:36,  4.90it/s]
  4%|▍         | 972/23500 [03:26<1:16:45,  4.89it/s]
  4%|▍         | 973/23500 [03:26<1:17:23,  4.85it/s]
  4%|▍         | 974/23500 [03:26<1:17:26,  4.85it/s]
  4%|▍         | 975/23500 [03:27<1:17:15,  4.86it/s]
  4%|▍         | 976/23500 [03:27<1:15:53,  4.95it/s]
  4%|▍         | 977/23500 [03:27<1:15:45,  4.96it/s]
  4%|▍         | 978/23500 [03:27<1:16:18,  4.92it/s]
  4%|▍         | 979/23500 [03:27<1:16:29,  4.91it/s]
  4%|▍         | 980/23500 [03:28<1:17:08,  4.87it/s]
  4%|▍         | 981/23500 [03:28<1:17:38,  4.83it/s]
  4%|▍         | 982/23500 [03:28<1:15:41,  4.96it/s]
  4%|▍         | 983/23500 [03:28<1:16:36,  4.90it/s]
  4%|▍         | 984/23500 [03:28<1:16:14,  4.92it/s]
  4%|▍         | 985/23500 [03:29<1:16:32,  4.90it/s]
  4%|▍         | 986/23500 [03:29<1:17:00,  4.87it/s]
  4%|▍         | 987/23500 [03:29<1:16:50,  4.88it/s]
  4%|▍         | 988/23500 [03:29<1:17:04,  4.87it/s]
  4%|▍         | 989/23500 [03:29<1:17:20,  4.85it/s]
  4%|▍         | 990/23500 [03:30<1:15:00,  5.00it/s]
  4%|▍         | 991/23500 [03:30<1:16:08,  4.93it/s]
  4%|▍         | 992/23500 [03:30<1:16:57,  4.87it/s]
  4%|▍         | 993/23500 [03:30<1:17:00,  4.87it/s]
  4%|▍         | 994/23500 [03:30<1:17:19,  4.85it/s]
  4%|▍         | 995/23500 [03:31<1:17:10,  4.86it/s]
  4%|▍         | 996/23500 [03:31<1:16:53,  4.88it/s]
  4%|▍         | 997/23500 [03:31<1:14:16,  5.05it/s]
  4%|▍         | 998/23500 [03:31<1:11:13,  5.26it/s]
  4%|▍         | 999/23500 [03:32<1:21:32,  4.60it/s]
  4%|▍         | 1000/23500 [03:32<1:19:13,  4.73it/s]
  4%|▍         | 1001/23500 [03:32<1:19:05,  4.74it/s]
  4%|▍         | 1002/23500 [03:32<1:18:55,  4.75it/s]
  4%|▍         | 1003/23500 [03:32<1:17:58,  4.81it/s]
  4%|▍         | 1004/23500 [03:33<1:18:15,  4.79it/s]
  4%|▍         | 1005/23500 [03:33<1:18:00,  4.81it/s]
  4%|▍         | 1006/23500 [03:33<1:17:37,  4.83it/s]
  4%|▍         | 1007/23500 [03:33<1:16:03,  4.93it/s]
  4%|▍         | 1008/23500 [03:33<1:16:53,  4.88it/s]
  4%|▍         | 1009/23500 [03:34<1:15:58,  4.93it/s]
  4%|▍         | 1010/23500 [03:34<1:14:57,  5.00it/s]
  4%|▍         | 1011/23500 [03:34<1:15:31,  4.96it/s]
  4%|▍         | 1012/23500 [03:34<1:16:28,  4.90it/s]
  4%|▍         | 1013/23500 [03:34<1:16:58,  4.87it/s]
  4%|▍         | 1014/23500 [03:35<1:17:08,  4.86it/s]
  4%|▍         | 1015/23500 [03:35<1:16:28,  4.90it/s]
  4%|▍         | 1016/23500 [03:35<1:16:02,  4.93it/s]
  4%|▍         | 1017/23500 [03:35<1:16:05,  4.92it/s]
  4%|▍         | 1018/23500 [03:35<1:15:52,  4.94it/s]
  4%|▍         | 1019/23500 [03:36<1:15:47,  4.94it/s]
  4%|▍         | 1020/23500 [03:36<1:16:40,  4.89it/s]
  4%|▍         | 1021/23500 [03:36<1:16:17,  4.91it/s]
  4%|▍         | 1022/23500 [03:36<1:13:55,  5.07it/s]
  4%|▍         | 1023/23500 [03:36<1:14:56,  5.00it/s]
  4%|▍         | 1024/23500 [03:37<1:14:11,  5.05it/s]
  4%|▍         | 1025/23500 [03:37<1:15:29,  4.96it/s]
  4%|▍         | 1026/23500 [03:37<1:15:28,  4.96it/s]
  4%|▍         | 1027/23500 [03:37<1:16:25,  4.90it/s]
  4%|▍         | 1028/23500 [03:37<1:16:24,  4.90it/s]
  4%|▍         | 1029/23500 [03:38<1:15:39,  4.95it/s]
  4%|▍         | 1030/23500 [03:38<1:15:30,  4.96it/s]
  4%|▍         | 1031/23500 [03:38<1:15:30,  4.96it/s]
  4%|▍         | 1032/23500 [03:38<1:15:02,  4.99it/s]
  4%|▍         | 1033/23500 [03:38<1:15:32,  4.96it/s]
  4%|▍         | 1034/23500 [03:39<1:15:53,  4.93it/s]
  4%|▍         | 1035/23500 [03:39<1:16:23,  4.90it/s]
  4%|▍         | 1036/23500 [03:39<1:16:52,  4.87it/s]
  4%|▍         | 1037/23500 [03:39<1:17:22,  4.84it/s]
  4%|▍         | 1038/23500 [03:39<1:17:01,  4.86it/s]
  4%|▍         | 1039/23500 [03:40<1:17:27,  4.83it/s]
  4%|▍         | 1040/23500 [03:40<1:17:37,  4.82it/s]
  4%|▍         | 1041/23500 [03:40<1:16:01,  4.92it/s]
  4%|▍         | 1042/23500 [03:40<1:15:51,  4.93it/s]
  4%|▍         | 1043/23500 [03:40<1:13:52,  5.07it/s]
  4%|▍         | 1044/23500 [03:41<1:15:04,  4.98it/s]
  4%|▍         | 1045/23500 [03:41<1:15:04,  4.98it/s]
  4%|▍         | 1046/23500 [03:41<1:15:34,  4.95it/s]
  4%|▍         | 1047/23500 [03:41<1:15:59,  4.92it/s]
  4%|▍         | 1048/23500 [03:41<1:15:39,  4.95it/s]
  4%|▍         | 1049/23500 [03:42<1:14:18,  5.04it/s]
  4%|▍         | 1050/23500 [03:42<1:15:05,  4.98it/s]
  4%|▍         | 1051/23500 [03:42<1:15:24,  4.96it/s]
  4%|▍         | 1052/23500 [03:42<1:16:17,  4.90it/s]
  4%|▍         | 1053/23500 [03:42<1:14:35,  5.02it/s]
  4%|▍         | 1054/23500 [03:43<1:14:18,  5.03it/s]
  4%|▍         | 1055/23500 [03:43<1:12:45,  5.14it/s]
  4%|▍         | 1056/23500 [03:43<1:13:25,  5.09it/s]
  4%|▍         | 1057/23500 [03:43<1:14:35,  5.01it/s]
  5%|▍         | 1058/23500 [03:43<1:14:15,  5.04it/s]
  5%|▍         | 1059/23500 [03:44<1:14:32,  5.02it/s]
  5%|▍         | 1060/23500 [03:44<1:15:11,  4.97it/s]
  5%|▍         | 1061/23500 [03:44<1:15:16,  4.97it/s]
  5%|▍         | 1062/23500 [03:44<1:16:06,  4.91it/s]
  5%|▍         | 1063/23500 [03:44<1:15:44,  4.94it/s]
  5%|▍         | 1064/23500 [03:45<1:15:53,  4.93it/s]
  5%|▍         | 1065/23500 [03:45<1:15:09,  4.98it/s]
  5%|▍         | 1066/23500 [03:45<1:15:26,  4.96it/s]
  5%|▍         | 1067/23500 [03:45<1:15:20,  4.96it/s]
  5%|▍         | 1068/23500 [03:45<1:15:53,  4.93it/s]
  5%|▍         | 1069/23500 [03:46<1:15:46,  4.93it/s]
  5%|▍         | 1070/23500 [03:46<1:15:30,  4.95it/s]
  5%|▍         | 1071/23500 [03:46<1:14:51,  4.99it/s]
  5%|▍         | 1072/23500 [03:46<1:15:56,  4.92it/s]
  5%|▍         | 1073/23500 [03:46<1:16:39,  4.88it/s]
  5%|▍         | 1074/23500 [03:47<1:16:52,  4.86it/s]
  5%|▍         | 1075/23500 [03:47<1:17:07,  4.85it/s]
  5%|▍         | 1076/23500 [03:47<1:17:29,  4.82it/s]
  5%|▍         | 1077/23500 [03:47<1:17:45,  4.81it/s]
  5%|▍         | 1078/23500 [03:48<1:16:26,  4.89it/s]
  5%|▍         | 1079/23500 [03:48<1:16:32,  4.88it/s]
  5%|▍         | 1080/23500 [03:48<1:16:24,  4.89it/s]
  5%|▍         | 1081/23500 [03:48<1:16:39,  4.87it/s]
  5%|▍         | 1082/23500 [03:48<1:17:04,  4.85it/s]
  5%|▍         | 1083/23500 [03:49<1:17:10,  4.84it/s]
  5%|▍         | 1084/23500 [03:49<1:17:31,  4.82it/s]
  5%|▍         | 1085/23500 [03:49<1:17:09,  4.84it/s]
  5%|▍         | 1086/23500 [03:49<1:15:40,  4.94it/s]
  5%|▍         | 1087/23500 [03:49<1:14:18,  5.03it/s]
  5%|▍         | 1088/23500 [03:50<1:11:11,  5.25it/s]
  5%|▍         | 1089/23500 [03:50<1:11:47,  5.20it/s]
  5%|▍         | 1090/23500 [03:50<1:13:35,  5.08it/s]
  5%|▍         | 1091/23500 [03:50<1:15:01,  4.98it/s]
  5%|▍         | 1092/23500 [03:50<1:15:03,  4.98it/s]
  5%|▍         | 1093/23500 [03:51<1:16:01,  4.91it/s]
  5%|▍         | 1094/23500 [03:51<1:15:48,  4.93it/s]
  5%|▍         | 1095/23500 [03:51<1:15:58,  4.91it/s]
  5%|▍         | 1096/23500 [03:51<1:14:51,  4.99it/s]
  5%|▍         | 1097/23500 [03:51<1:15:48,  4.93it/s]
  5%|▍         | 1098/23500 [03:52<1:16:32,  4.88it/s]
  5%|▍         | 1099/23500 [03:52<1:17:06,  4.84it/s]
  5%|▍         | 1100/23500 [03:52<1:15:15,  4.96it/s]
  5%|▍         | 1101/23500 [03:52<1:15:42,  4.93it/s]
  5%|▍         | 1102/23500 [03:53<1:30:44,  4.11it/s]
  5%|▍         | 1103/23500 [03:53<1:26:35,  4.31it/s]
  5%|▍         | 1104/23500 [03:53<1:23:22,  4.48it/s]
  5%|▍         | 1105/23500 [03:53<1:20:06,  4.66it/s]
  5%|▍         | 1106/23500 [03:53<1:19:26,  4.70it/s]
  5%|▍         | 1107/23500 [03:54<1:18:45,  4.74it/s]
  5%|▍         | 1108/23500 [03:54<1:18:41,  4.74it/s]
  5%|▍         | 1109/23500 [03:54<1:18:35,  4.75it/s]
  5%|▍         | 1110/23500 [03:54<1:18:12,  4.77it/s]
  5%|▍         | 1111/23500 [03:54<1:17:16,  4.83it/s]
  5%|▍         | 1112/23500 [03:55<1:17:11,  4.83it/s]
  5%|▍         | 1113/23500 [03:55<1:15:10,  4.96it/s]
  5%|▍         | 1114/23500 [03:55<1:15:26,  4.95it/s]
  5%|▍         | 1115/23500 [03:55<1:16:01,  4.91it/s]
  5%|▍         | 1116/23500 [03:55<1:16:41,  4.86it/s]
  5%|▍         | 1117/23500 [03:56<1:17:11,  4.83it/s]
  5%|▍         | 1118/23500 [03:56<1:16:54,  4.85it/s]
  5%|▍         | 1119/23500 [03:56<1:17:18,  4.83it/s]
  5%|▍         | 1120/23500 [03:56<1:15:46,  4.92it/s]
  5%|▍         | 1121/23500 [03:56<1:16:34,  4.87it/s]
  5%|▍         | 1122/23500 [03:57<1:16:48,  4.86it/s]
  5%|▍         | 1123/23500 [03:57<1:16:57,  4.85it/s]
  5%|▍         | 1124/23500 [03:57<1:17:18,  4.82it/s]
  5%|▍         | 1125/23500 [03:57<1:16:42,  4.86it/s]
  5%|▍         | 1126/23500 [03:58<1:32:11,  4.04it/s]
  5%|▍         | 1127/23500 [03:58<1:27:59,  4.24it/s]
  5%|▍         | 1128/23500 [03:58<1:24:24,  4.42it/s]
  5%|▍         | 1129/23500 [03:58<1:21:10,  4.59it/s]
  5%|▍         | 1130/23500 [03:58<1:19:47,  4.67it/s]
  5%|▍         | 1131/23500 [03:59<1:19:12,  4.71it/s]
  5%|▍         | 1132/23500 [03:59<1:18:50,  4.73it/s]
  5%|▍         | 1133/23500 [03:59<1:16:11,  4.89it/s]
  5%|▍         | 1134/23500 [03:59<1:16:45,  4.86it/s]
  5%|▍         | 1135/23500 [03:59<1:17:12,  4.83it/s]
  5%|▍         | 1136/23500 [04:00<1:16:52,  4.85it/s]
  5%|▍         | 1137/23500 [04:00<1:16:16,  4.89it/s]
  5%|▍         | 1138/23500 [04:00<1:15:48,  4.92it/s]
  5%|▍         | 1139/23500 [04:00<1:15:37,  4.93it/s]
  5%|▍         | 1140/23500 [04:00<1:15:48,  4.92it/s]
  5%|▍         | 1141/23500 [04:01<1:16:31,  4.87it/s]
  5%|▍         | 1142/23500 [04:01<1:15:37,  4.93it/s]
  5%|▍         | 1143/23500 [04:01<1:16:12,  4.89it/s]
  5%|▍         | 1144/23500 [04:01<1:16:37,  4.86it/s]
  5%|▍         | 1145/23500 [04:01<1:16:04,  4.90it/s]
  5%|▍         | 1146/23500 [04:02<1:16:34,  4.87it/s]
  5%|▍         | 1147/23500 [04:02<1:17:00,  4.84it/s]
  5%|▍         | 1148/23500 [04:02<1:17:04,  4.83it/s]
  5%|▍         | 1149/23500 [04:02<1:17:21,  4.82it/s]
  5%|▍         | 1150/23500 [04:02<1:17:27,  4.81it/s]
  5%|▍         | 1151/23500 [04:03<1:27:14,  4.27it/s]
  5%|▍         | 1152/23500 [04:03<1:21:59,  4.54it/s]
  5%|▍         | 1153/23500 [04:03<1:20:09,  4.65it/s]
  5%|▍         | 1154/23500 [04:03<1:17:20,  4.82it/s]
  5%|▍         | 1155/23500 [04:04<1:15:21,  4.94it/s]
  5%|▍         | 1156/23500 [04:04<1:15:35,  4.93it/s]
  5%|▍         | 1157/23500 [04:04<1:15:46,  4.91it/s]
  5%|▍         | 1158/23500 [04:04<1:14:59,  4.97it/s]
  5%|▍         | 1159/23500 [04:04<1:15:55,  4.90it/s]
  5%|▍         | 1160/23500 [04:05<1:14:23,  5.00it/s]
  5%|▍         | 1161/23500 [04:05<1:15:23,  4.94it/s]
  5%|▍         | 1162/23500 [04:05<1:15:41,  4.92it/s]
  5%|▍         | 1163/23500 [04:05<1:15:45,  4.91it/s]
  5%|▍         | 1164/23500 [04:05<1:16:29,  4.87it/s]
  5%|▍         | 1165/23500 [04:06<1:16:54,  4.84it/s]
  5%|▍         | 1166/23500 [04:06<1:15:28,  4.93it/s]
  5%|▍         | 1167/23500 [04:06<1:14:43,  4.98it/s]
  5%|▍         | 1168/23500 [04:06<1:12:38,  5.12it/s]
  5%|▍         | 1169/23500 [04:06<1:13:13,  5.08it/s]
  5%|▍         | 1170/23500 [04:07<1:12:50,  5.11it/s]
  5%|▍         | 1171/23500 [04:07<1:14:24,  5.00it/s]
  5%|▍         | 1172/23500 [04:07<1:13:08,  5.09it/s]
  5%|▍         | 1173/23500 [04:07<1:14:16,  5.01it/s]
  5%|▍         | 1174/23500 [04:07<1:14:56,  4.97it/s]
                                                      

  5%|▌         | 1175/23500 [04:07<1:14:55,  4.97it/s]{'eval_loss': 0.6585601568222046, 'eval_accuracy': 0.7184, 'eval_f1': 0.7168436594753593, 'eval_runtime': 1.266, 'eval_samples_per_second': 1974.74, 'eval_steps_per_second': 15.798, 'epoch': 4.0}
{'loss': 0.5176, 'learning_rate': 1.9544058914411928e-05, 'epoch': 5.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.76it/s]

 30%|███       | 6/20 [00:00<00:00, 18.48it/s]

 40%|████      | 8/20 [00:00<00:00, 16.74it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.11it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.49it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.06it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.29it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.84it/s]

                                               

                                                      

100%|██████████| 20/20 [00:01<00:00, 15.84it/s]
  5%|▌         | 1175/23500 [04:09<1:14:55,  4.97it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  5%|▌         | 1176/23500 [04:10<4:27:32,  1.39it/s]
  5%|▌         | 1177/23500 [04:10<3:39:45,  1.69it/s]
  5%|▌         | 1178/23500 [04:10<3:02:32,  2.04it/s]
  5%|▌         | 1179/23500 [04:11<2:33:46,  2.42it/s]
  5%|▌         | 1180/23500 [04:11<2:11:57,  2.82it/s]
  5%|▌         | 1181/23500 [04:11<1:55:35,  3.22it/s]
  5%|▌         | 1182/23500 [04:11<1:44:15,  3.57it/s]
  5%|▌         | 1183/23500 [04:11<1:33:52,  3.96it/s]
  5%|▌         | 1184/23500 [04:12<1:27:47,  4.24it/s]
  5%|▌         | 1185/23500 [04:12<1:24:21,  4.41it/s]
  5%|▌         | 1186/23500 [04:12<1:22:09,  4.53it/s]
  5%|▌         | 1187/23500 [04:12<1:20:55,  4.60it/s]
  5%|▌         | 1188/23500 [04:12<1:19:53,  4.65it/s]
  5%|▌         | 1189/23500 [04:13<1:19:10,  4.70it/s]
  5%|▌         | 1190/23500 [04:13<1:27:10,  4.27it/s]
  5%|▌         | 1191/23500 [04:13<1:24:23,  4.41it/s]
  5%|▌         | 1192/23500 [04:13<1:18:25,  4.74it/s]
  5%|▌         | 1193/23500 [04:14<1:18:18,  4.75it/s]
  5%|▌         | 1194/23500 [04:14<1:17:56,  4.77it/s]
  5%|▌         | 1195/23500 [04:14<1:17:34,  4.79it/s]
  5%|▌         | 1196/23500 [04:14<1:13:21,  5.07it/s]
  5%|▌         | 1197/23500 [04:14<1:12:55,  5.10it/s]
  5%|▌         | 1198/23500 [04:15<1:13:02,  5.09it/s]
  5%|▌         | 1199/23500 [04:15<1:14:28,  4.99it/s]
  5%|▌         | 1200/23500 [04:15<1:15:02,  4.95it/s]
  5%|▌         | 1201/23500 [04:15<1:14:58,  4.96it/s]
  5%|▌         | 1202/23500 [04:15<1:14:57,  4.96it/s]
  5%|▌         | 1203/23500 [04:16<1:15:53,  4.90it/s]
  5%|▌         | 1204/23500 [04:16<1:16:28,  4.86it/s]
  5%|▌         | 1205/23500 [04:16<1:16:01,  4.89it/s]
  5%|▌         | 1206/23500 [04:16<1:14:14,  5.00it/s]
  5%|▌         | 1207/23500 [04:16<1:14:22,  5.00it/s]
  5%|▌         | 1208/23500 [04:17<1:14:54,  4.96it/s]
  5%|▌         | 1209/23500 [04:17<1:15:49,  4.90it/s]
  5%|▌         | 1210/23500 [04:17<1:13:54,  5.03it/s]
  5%|▌         | 1211/23500 [04:17<1:14:56,  4.96it/s]
  5%|▌         | 1212/23500 [04:17<1:14:21,  5.00it/s]
  5%|▌         | 1213/23500 [04:18<1:15:27,  4.92it/s]
  5%|▌         | 1214/23500 [04:18<1:16:11,  4.88it/s]
  5%|▌         | 1215/23500 [04:18<1:27:48,  4.23it/s]
  5%|▌         | 1216/23500 [04:18<1:24:26,  4.40it/s]
  5%|▌         | 1217/23500 [04:18<1:21:34,  4.55it/s]
  5%|▌         | 1218/23500 [04:19<1:19:54,  4.65it/s]
  5%|▌         | 1219/23500 [04:19<1:17:09,  4.81it/s]
  5%|▌         | 1220/23500 [04:19<1:17:21,  4.80it/s]
  5%|▌         | 1221/23500 [04:19<1:17:26,  4.79it/s]
  5%|▌         | 1222/23500 [04:19<1:13:16,  5.07it/s]
  5%|▌         | 1223/23500 [04:20<1:14:30,  4.98it/s]
  5%|▌         | 1224/23500 [04:20<1:14:49,  4.96it/s]
  5%|▌         | 1225/23500 [04:20<1:14:13,  5.00it/s]
  5%|▌         | 1226/23500 [04:20<1:14:41,  4.97it/s]
  5%|▌         | 1227/23500 [04:20<1:15:30,  4.92it/s]
  5%|▌         | 1228/23500 [04:21<1:15:33,  4.91it/s]
  5%|▌         | 1229/23500 [04:21<1:15:29,  4.92it/s]
  5%|▌         | 1230/23500 [04:21<1:14:00,  5.02it/s]
  5%|▌         | 1231/23500 [04:21<1:15:10,  4.94it/s]
  5%|▌         | 1232/23500 [04:21<1:13:38,  5.04it/s]
  5%|▌         | 1233/23500 [04:22<1:14:55,  4.95it/s]
  5%|▌         | 1234/23500 [04:22<1:15:47,  4.90it/s]
  5%|▌         | 1235/23500 [04:22<1:16:19,  4.86it/s]
  5%|▌         | 1236/23500 [04:22<1:15:43,  4.90it/s]
  5%|▌         | 1237/23500 [04:23<1:15:39,  4.90it/s]
  5%|▌         | 1238/23500 [04:23<1:16:06,  4.88it/s]
  5%|▌         | 1239/23500 [04:23<1:16:31,  4.85it/s]
  5%|▌         | 1240/23500 [04:23<1:16:31,  4.85it/s]
  5%|▌         | 1241/23500 [04:23<1:16:54,  4.82it/s]
  5%|▌         | 1242/23500 [04:24<1:15:45,  4.90it/s]
  5%|▌         | 1243/23500 [04:24<1:15:26,  4.92it/s]
  5%|▌         | 1244/23500 [04:24<1:15:47,  4.89it/s]
  5%|▌         | 1245/23500 [04:24<1:16:21,  4.86it/s]
  5%|▌         | 1246/23500 [04:24<1:16:10,  4.87it/s]
  5%|▌         | 1247/23500 [04:25<1:15:13,  4.93it/s]
  5%|▌         | 1248/23500 [04:25<1:15:21,  4.92it/s]
  5%|▌         | 1249/23500 [04:25<1:15:35,  4.91it/s]
  5%|▌         | 1250/23500 [04:25<1:15:47,  4.89it/s]
  5%|▌         | 1251/23500 [04:25<1:13:10,  5.07it/s]
  5%|▌         | 1252/23500 [04:26<1:14:01,  5.01it/s]
  5%|▌         | 1253/23500 [04:26<1:14:16,  4.99it/s]
  5%|▌         | 1254/23500 [04:26<1:14:44,  4.96it/s]
  5%|▌         | 1255/23500 [04:26<1:15:26,  4.91it/s]
  5%|▌         | 1256/23500 [04:26<1:22:44,  4.48it/s]
  5%|▌         | 1257/23500 [04:27<1:19:04,  4.69it/s]
  5%|▌         | 1258/23500 [04:27<1:18:42,  4.71it/s]
  5%|▌         | 1259/23500 [04:27<1:14:04,  5.00it/s]
  5%|▌         | 1260/23500 [04:27<1:15:01,  4.94it/s]
  5%|▌         | 1261/23500 [04:27<1:15:49,  4.89it/s]
  5%|▌         | 1262/23500 [04:28<1:15:48,  4.89it/s]
  5%|▌         | 1263/23500 [04:28<1:15:47,  4.89it/s]
  5%|▌         | 1264/23500 [04:28<1:16:12,  4.86it/s]
  5%|▌         | 1265/23500 [04:28<1:15:45,  4.89it/s]
  5%|▌         | 1266/23500 [04:28<1:16:16,  4.86it/s]
  5%|▌         | 1267/23500 [04:29<1:16:40,  4.83it/s]
  5%|▌         | 1268/23500 [04:29<1:16:57,  4.81it/s]
  5%|▌         | 1269/23500 [04:29<1:16:47,  4.82it/s]
  5%|▌         | 1270/23500 [04:29<1:12:10,  5.13it/s]
  5%|▌         | 1271/23500 [04:29<1:13:49,  5.02it/s]
  5%|▌         | 1272/23500 [04:30<1:14:35,  4.97it/s]
  5%|▌         | 1273/23500 [04:30<1:14:53,  4.95it/s]
  5%|▌         | 1274/23500 [04:30<1:15:22,  4.91it/s]
  5%|▌         | 1275/23500 [04:30<1:15:12,  4.93it/s]
  5%|▌         | 1276/23500 [04:30<1:14:57,  4.94it/s]
  5%|▌         | 1277/23500 [04:31<1:15:10,  4.93it/s]
  5%|▌         | 1278/23500 [04:31<1:15:16,  4.92it/s]
  5%|▌         | 1279/23500 [04:31<1:16:00,  4.87it/s]
  5%|▌         | 1280/23500 [04:31<1:15:33,  4.90it/s]
  5%|▌         | 1281/23500 [04:32<1:15:36,  4.90it/s]
  5%|▌         | 1282/23500 [04:32<1:15:41,  4.89it/s]
  5%|▌         | 1283/23500 [04:32<1:14:56,  4.94it/s]
  5%|▌         | 1284/23500 [04:32<1:15:15,  4.92it/s]
  5%|▌         | 1285/23500 [04:32<1:14:35,  4.96it/s]
  5%|▌         | 1286/23500 [04:33<1:14:51,  4.95it/s]
  5%|▌         | 1287/23500 [04:33<1:15:13,  4.92it/s]
  5%|▌         | 1288/23500 [04:33<1:14:12,  4.99it/s]
  5%|▌         | 1289/23500 [04:33<1:14:21,  4.98it/s]
  5%|▌         | 1290/23500 [04:33<1:15:01,  4.93it/s]
  5%|▌         | 1291/23500 [04:34<1:15:05,  4.93it/s]
  5%|▌         | 1292/23500 [04:34<1:15:48,  4.88it/s]
  6%|▌         | 1293/23500 [04:34<1:14:58,  4.94it/s]
  6%|▌         | 1294/23500 [04:34<1:13:57,  5.00it/s]
  6%|▌         | 1295/23500 [04:34<1:14:04,  5.00it/s]
  6%|▌         | 1296/23500 [04:35<1:13:20,  5.05it/s]
  6%|▌         | 1297/23500 [04:35<1:13:05,  5.06it/s]
  6%|▌         | 1298/23500 [04:35<1:13:35,  5.03it/s]
  6%|▌         | 1299/23500 [04:35<1:14:18,  4.98it/s]
  6%|▌         | 1300/23500 [04:35<1:12:46,  5.08it/s]
  6%|▌         | 1301/23500 [04:36<1:14:16,  4.98it/s]
  6%|▌         | 1302/23500 [04:36<1:13:30,  5.03it/s]
  6%|▌         | 1303/23500 [04:36<1:14:18,  4.98it/s]
  6%|▌         | 1304/23500 [04:36<1:14:19,  4.98it/s]
  6%|▌         | 1305/23500 [04:36<1:14:34,  4.96it/s]
  6%|▌         | 1306/23500 [04:37<1:14:25,  4.97it/s]
  6%|▌         | 1307/23500 [04:37<1:15:01,  4.93it/s]
  6%|▌         | 1308/23500 [04:37<1:14:15,  4.98it/s]
  6%|▌         | 1309/23500 [04:37<1:14:51,  4.94it/s]
  6%|▌         | 1310/23500 [04:37<1:13:18,  5.04it/s]
  6%|▌         | 1311/23500 [04:38<1:12:46,  5.08it/s]
  6%|▌         | 1312/23500 [04:38<1:14:05,  4.99it/s]
  6%|▌         | 1313/23500 [04:38<1:14:39,  4.95it/s]
  6%|▌         | 1314/23500 [04:38<1:14:01,  5.00it/s]
  6%|▌         | 1315/23500 [04:38<1:13:44,  5.01it/s]
  6%|▌         | 1316/23500 [04:39<1:14:15,  4.98it/s]
  6%|▌         | 1317/23500 [04:39<1:14:17,  4.98it/s]
  6%|▌         | 1318/23500 [04:39<1:14:16,  4.98it/s]
  6%|▌         | 1319/23500 [04:39<1:14:19,  4.97it/s]
  6%|▌         | 1320/23500 [04:39<1:14:45,  4.95it/s]
  6%|▌         | 1321/23500 [04:40<1:15:00,  4.93it/s]
  6%|▌         | 1322/23500 [04:40<1:15:30,  4.90it/s]
  6%|▌         | 1323/23500 [04:40<1:15:23,  4.90it/s]
  6%|▌         | 1324/23500 [04:40<1:13:40,  5.02it/s]
  6%|▌         | 1325/23500 [04:40<1:13:24,  5.03it/s]
  6%|▌         | 1326/23500 [04:41<1:14:25,  4.97it/s]
  6%|▌         | 1327/23500 [04:41<1:14:58,  4.93it/s]
  6%|▌         | 1328/23500 [04:41<1:15:07,  4.92it/s]
  6%|▌         | 1329/23500 [04:41<1:15:30,  4.89it/s]
  6%|▌         | 1330/23500 [04:41<1:16:05,  4.86it/s]
  6%|▌         | 1331/23500 [04:42<1:15:54,  4.87it/s]
  6%|▌         | 1332/23500 [04:42<1:16:23,  4.84it/s]
  6%|▌         | 1333/23500 [04:42<1:16:40,  4.82it/s]
  6%|▌         | 1334/23500 [04:42<1:16:15,  4.84it/s]
  6%|▌         | 1335/23500 [04:42<1:15:31,  4.89it/s]
  6%|▌         | 1336/23500 [04:43<1:14:43,  4.94it/s]
  6%|▌         | 1337/23500 [04:43<1:13:23,  5.03it/s]
  6%|▌         | 1338/23500 [04:43<1:13:56,  5.00it/s]
  6%|▌         | 1339/23500 [04:43<1:13:40,  5.01it/s]
  6%|▌         | 1340/23500 [04:43<1:14:37,  4.95it/s]
  6%|▌         | 1341/23500 [04:44<1:15:28,  4.89it/s]
  6%|▌         | 1342/23500 [04:44<1:15:24,  4.90it/s]
  6%|▌         | 1343/23500 [04:44<1:13:52,  5.00it/s]
  6%|▌         | 1344/23500 [04:44<1:14:27,  4.96it/s]
  6%|▌         | 1345/23500 [04:44<1:13:56,  4.99it/s]
  6%|▌         | 1346/23500 [04:45<1:14:50,  4.93it/s]
  6%|▌         | 1347/23500 [04:45<1:15:36,  4.88it/s]
  6%|▌         | 1348/23500 [04:45<1:15:36,  4.88it/s]
  6%|▌         | 1349/23500 [04:45<1:15:46,  4.87it/s]
  6%|▌         | 1350/23500 [04:45<1:11:30,  5.16it/s]
  6%|▌         | 1351/23500 [04:46<1:12:35,  5.09it/s]
  6%|▌         | 1352/23500 [04:46<1:13:29,  5.02it/s]
  6%|▌         | 1353/23500 [04:46<1:14:43,  4.94it/s]
  6%|▌         | 1354/23500 [04:46<1:15:04,  4.92it/s]
  6%|▌         | 1355/23500 [04:46<1:14:48,  4.93it/s]
  6%|▌         | 1356/23500 [04:47<1:14:44,  4.94it/s]
  6%|▌         | 1357/23500 [04:47<1:15:37,  4.88it/s]
  6%|▌         | 1358/23500 [04:47<1:15:36,  4.88it/s]
  6%|▌         | 1359/23500 [04:47<1:15:11,  4.91it/s]
  6%|▌         | 1360/23500 [04:47<1:15:23,  4.89it/s]
  6%|▌         | 1361/23500 [04:48<1:16:04,  4.85it/s]
  6%|▌         | 1362/23500 [04:48<1:16:30,  4.82it/s]
  6%|▌         | 1363/23500 [04:48<1:15:50,  4.87it/s]
  6%|▌         | 1364/23500 [04:48<1:15:26,  4.89it/s]
  6%|▌         | 1365/23500 [04:48<1:14:35,  4.95it/s]
  6%|▌         | 1366/23500 [04:49<1:15:15,  4.90it/s]
  6%|▌         | 1367/23500 [04:49<1:15:53,  4.86it/s]
  6%|▌         | 1368/23500 [04:49<1:15:42,  4.87it/s]
  6%|▌         | 1369/23500 [04:49<1:14:26,  4.95it/s]
  6%|▌         | 1370/23500 [04:50<1:14:21,  4.96it/s]
  6%|▌         | 1371/23500 [04:50<1:15:17,  4.90it/s]
  6%|▌         | 1372/23500 [04:50<1:15:18,  4.90it/s]
  6%|▌         | 1373/23500 [04:50<1:14:57,  4.92it/s]
  6%|▌         | 1374/23500 [04:50<1:15:45,  4.87it/s]
  6%|▌         | 1375/23500 [04:51<1:16:17,  4.83it/s]
  6%|▌         | 1376/23500 [04:51<1:16:34,  4.82it/s]
  6%|▌         | 1377/23500 [04:51<1:15:56,  4.86it/s]
  6%|▌         | 1378/23500 [04:51<1:15:29,  4.88it/s]
  6%|▌         | 1379/23500 [04:51<1:16:01,  4.85it/s]
  6%|▌         | 1380/23500 [04:52<1:16:08,  4.84it/s]
  6%|▌         | 1381/23500 [04:52<1:16:31,  4.82it/s]
  6%|▌         | 1382/23500 [04:52<1:16:25,  4.82it/s]
  6%|▌         | 1383/23500 [04:52<1:15:47,  4.86it/s]
  6%|▌         | 1384/23500 [04:52<1:13:56,  4.98it/s]
  6%|▌         | 1385/23500 [04:53<1:14:56,  4.92it/s]
  6%|▌         | 1386/23500 [04:53<1:15:38,  4.87it/s]
  6%|▌         | 1387/23500 [04:53<1:16:05,  4.84it/s]
  6%|▌         | 1388/23500 [04:53<1:14:44,  4.93it/s]
  6%|▌         | 1389/23500 [04:53<1:14:31,  4.95it/s]
  6%|▌         | 1390/23500 [04:54<1:14:27,  4.95it/s]
  6%|▌         | 1391/23500 [04:54<1:15:22,  4.89it/s]
  6%|▌         | 1392/23500 [04:54<1:15:56,  4.85it/s]
  6%|▌         | 1393/23500 [04:54<1:13:50,  4.99it/s]
  6%|▌         | 1394/23500 [04:54<1:13:57,  4.98it/s]
  6%|▌         | 1395/23500 [04:55<1:14:57,  4.91it/s]
  6%|▌         | 1396/23500 [04:55<1:15:41,  4.87it/s]
  6%|▌         | 1397/23500 [04:55<1:15:50,  4.86it/s]
  6%|▌         | 1398/23500 [04:55<1:15:35,  4.87it/s]
  6%|▌         | 1399/23500 [04:55<1:13:44,  5.00it/s]
  6%|▌         | 1400/23500 [04:56<1:14:12,  4.96it/s]
  6%|▌         | 1401/23500 [04:56<1:12:47,  5.06it/s]
  6%|▌         | 1402/23500 [04:56<1:13:41,  5.00it/s]
  6%|▌         | 1403/23500 [04:56<1:13:43,  5.00it/s]
  6%|▌         | 1404/23500 [04:56<1:13:48,  4.99it/s]
  6%|▌         | 1405/23500 [04:57<1:14:48,  4.92it/s]
  6%|▌         | 1406/23500 [04:57<1:15:04,  4.90it/s]
  6%|▌         | 1407/23500 [04:57<1:15:09,  4.90it/s]
  6%|▌         | 1408/23500 [04:57<1:15:47,  4.86it/s]
  6%|▌         | 1409/23500 [04:57<1:14:19,  4.95it/s]
                                                      

  6%|▌         | 1410/23500 [04:58<1:14:19,  4.95it/s]{'eval_loss': 0.6809464693069458, 'eval_accuracy': 0.7144, 'eval_f1': 0.7137994849164195, 'eval_runtime': 1.2678, 'eval_samples_per_second': 1971.987, 'eval_steps_per_second': 15.776, 'epoch': 5.0}
{'loss': 0.428, 'learning_rate': 2.3456200179221815e-05, 'epoch': 6.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.74it/s]

 30%|███       | 6/20 [00:00<00:00, 18.47it/s]

 40%|████      | 8/20 [00:00<00:00, 16.74it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.11it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.48it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.05it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.28it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.83it/s]

                                               

                                                      

100%|██████████| 20/20 [00:01<00:00, 15.83it/s]
  6%|▌         | 1410/23500 [04:59<1:14:19,  4.95it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

  6%|▌         | 1411/23500 [05:00<4:13:30,  1.45it/s]
  6%|▌         | 1412/23500 [05:00<3:28:58,  1.76it/s]
  6%|▌         | 1413/23500 [05:00<2:53:40,  2.12it/s]
  6%|▌         | 1414/23500 [05:01<2:27:14,  2.50it/s]
  6%|▌         | 1415/23500 [05:01<2:06:59,  2.90it/s]
  6%|▌         | 1416/23500 [05:01<1:52:40,  3.27it/s]
  6%|▌         | 1417/23500 [05:01<1:42:11,  3.60it/s]
  6%|▌         | 1418/23500 [05:01<1:34:51,  3.88it/s]
  6%|▌         | 1419/23500 [05:02<1:29:20,  4.12it/s]
  6%|▌         | 1420/23500 [05:02<1:24:43,  4.34it/s]
  6%|▌         | 1421/23500 [05:02<1:22:27,  4.46it/s]
  6%|▌         | 1422/23500 [05:02<1:20:54,  4.55it/s]
  6%|▌         | 1423/23500 [05:02<1:18:43,  4.67it/s]
  6%|▌         | 1424/23500 [05:03<1:18:04,  4.71it/s]
  6%|▌         | 1425/23500 [05:03<1:16:46,  4.79it/s]
  6%|▌         | 1426/23500 [05:03<1:15:28,  4.87it/s]
  6%|▌         | 1427/23500 [05:03<1:15:51,  4.85it/s]
  6%|▌         | 1428/23500 [05:03<1:15:17,  4.89it/s]
  6%|▌         | 1429/23500 [05:04<1:14:03,  4.97it/s]
  6%|▌         | 1430/23500 [05:04<1:14:02,  4.97it/s]
  6%|▌         | 1431/23500 [05:04<1:13:15,  5.02it/s]
  6%|▌         | 1432/23500 [05:04<1:11:44,  5.13it/s]
  6%|▌         | 1433/23500 [05:04<1:13:21,  5.01it/s]
  6%|▌         | 1434/23500 [05:05<1:14:29,  4.94it/s]
  6%|▌         | 1435/23500 [05:05<1:19:25,  4.63it/s]
  6%|▌         | 1436/23500 [05:05<1:17:59,  4.71it/s]
  6%|▌         | 1437/23500 [05:05<1:15:53,  4.84it/s]
  6%|▌         | 1438/23500 [05:05<1:15:47,  4.85it/s]
  6%|▌         | 1439/23500 [05:06<1:16:08,  4.83it/s]
  6%|▌         | 1440/23500 [05:06<1:16:15,  4.82it/s]
  6%|▌         | 1441/23500 [05:06<1:15:58,  4.84it/s]
  6%|▌         | 1442/23500 [05:06<1:15:36,  4.86it/s]
  6%|▌         | 1443/23500 [05:07<1:16:05,  4.83it/s]
  6%|▌         | 1444/23500 [05:07<1:16:23,  4.81it/s]
  6%|▌         | 1445/23500 [05:07<1:15:36,  4.86it/s]
  6%|▌         | 1446/23500 [05:07<1:15:24,  4.87it/s]
  6%|▌         | 1447/23500 [05:07<1:15:54,  4.84it/s]
  6%|▌         | 1448/23500 [05:08<1:16:12,  4.82it/s]
  6%|▌         | 1449/23500 [05:08<1:15:30,  4.87it/s]
  6%|▌         | 1450/23500 [05:08<1:15:58,  4.84it/s]
  6%|▌         | 1451/23500 [05:08<1:15:36,  4.86it/s]
  6%|▌         | 1452/23500 [05:08<1:15:23,  4.87it/s]
  6%|▌         | 1453/23500 [05:09<1:15:18,  4.88it/s]
  6%|▌         | 1454/23500 [05:09<1:15:51,  4.84it/s]
  6%|▌         | 1455/23500 [05:09<1:16:11,  4.82it/s]
  6%|▌         | 1456/23500 [05:09<1:15:01,  4.90it/s]
  6%|▌         | 1457/23500 [05:09<1:15:39,  4.86it/s]
  6%|▌         | 1458/23500 [05:10<1:16:01,  4.83it/s]
  6%|▌         | 1459/23500 [05:10<1:28:50,  4.14it/s]
  6%|▌         | 1460/23500 [05:10<1:23:51,  4.38it/s]
  6%|▌         | 1461/23500 [05:10<1:21:28,  4.51it/s]
  6%|▌         | 1462/23500 [05:11<1:20:07,  4.58it/s]
  6%|▌         | 1463/23500 [05:11<1:17:02,  4.77it/s]
  6%|▌         | 1464/23500 [05:11<1:16:05,  4.83it/s]
  6%|▌         | 1465/23500 [05:11<1:15:42,  4.85it/s]
  6%|▌         | 1466/23500 [05:11<1:15:54,  4.84it/s]
  6%|▌         | 1467/23500 [05:12<1:14:28,  4.93it/s]
  6%|▌         | 1468/23500 [05:12<1:13:41,  4.98it/s]
  6%|▋         | 1469/23500 [05:12<1:13:11,  5.02it/s]
  6%|▋         | 1470/23500 [05:12<1:14:10,  4.95it/s]
  6%|▋         | 1471/23500 [05:12<1:14:34,  4.92it/s]
  6%|▋         | 1472/23500 [05:13<1:14:18,  4.94it/s]
  6%|▋         | 1473/23500 [05:13<1:14:46,  4.91it/s]
  6%|▋         | 1474/23500 [05:13<1:15:13,  4.88it/s]
  6%|▋         | 1475/23500 [05:13<1:14:18,  4.94it/s]
  6%|▋         | 1476/23500 [05:13<1:10:45,  5.19it/s]
  6%|▋         | 1477/23500 [05:14<1:11:37,  5.13it/s]
  6%|▋         | 1478/23500 [05:14<1:12:39,  5.05it/s]
  6%|▋         | 1479/23500 [05:14<1:11:46,  5.11it/s]
  6%|▋         | 1480/23500 [05:14<1:13:09,  5.02it/s]
  6%|▋         | 1481/23500 [05:14<1:13:44,  4.98it/s]
  6%|▋         | 1482/23500 [05:15<1:13:59,  4.96it/s]
  6%|▋         | 1483/23500 [05:15<1:13:23,  5.00it/s]
  6%|▋         | 1484/23500 [05:15<1:14:05,  4.95it/s]
  6%|▋         | 1485/23500 [05:15<1:14:57,  4.90it/s]
  6%|▋         | 1486/23500 [05:15<1:15:32,  4.86it/s]
  6%|▋         | 1487/23500 [05:16<1:15:36,  4.85it/s]
  6%|▋         | 1488/23500 [05:16<1:15:51,  4.84it/s]
  6%|▋         | 1489/23500 [05:16<1:15:12,  4.88it/s]
  6%|▋         | 1490/23500 [05:16<1:14:17,  4.94it/s]
  6%|▋         | 1491/23500 [05:16<1:14:34,  4.92it/s]
  6%|▋         | 1492/23500 [05:17<1:13:45,  4.97it/s]
  6%|▋         | 1493/23500 [05:17<1:14:12,  4.94it/s]
  6%|▋         | 1494/23500 [05:17<1:14:27,  4.93it/s]
  6%|▋         | 1495/23500 [05:17<1:15:03,  4.89it/s]
  6%|▋         | 1496/23500 [05:17<1:15:10,  4.88it/s]
  6%|▋         | 1497/23500 [05:18<1:15:22,  4.87it/s]
  6%|▋         | 1498/23500 [05:18<1:15:42,  4.84it/s]
  6%|▋         | 1499/23500 [05:18<1:14:40,  4.91it/s]
  6%|▋         | 1500/23500 [05:18<1:11:21,  5.14it/s]
  6%|▋         | 1501/23500 [05:18<1:12:20,  5.07it/s]
  6%|▋         | 1502/23500 [05:19<1:12:19,  5.07it/s]
  6%|▋         | 1503/23500 [05:19<1:13:44,  4.97it/s]
  6%|▋         | 1504/23500 [05:19<1:14:12,  4.94it/s]
  6%|▋         | 1505/23500 [05:19<1:15:03,  4.88it/s]
  6%|▋         | 1506/23500 [05:19<1:15:08,  4.88it/s]
  6%|▋         | 1507/23500 [05:20<1:15:16,  4.87it/s]
  6%|▋         | 1508/23500 [05:20<1:15:15,  4.87it/s]
  6%|▋         | 1509/23500 [05:20<1:15:38,  4.85it/s]
  6%|▋         | 1510/23500 [05:20<1:15:22,  4.86it/s]
  6%|▋         | 1511/23500 [05:20<1:14:55,  4.89it/s]
  6%|▋         | 1512/23500 [05:21<1:15:23,  4.86it/s]
  6%|▋         | 1513/23500 [05:21<1:15:50,  4.83it/s]
  6%|▋         | 1514/23500 [05:21<1:16:11,  4.81it/s]
  6%|▋         | 1515/23500 [05:21<1:14:37,  4.91it/s]
  6%|▋         | 1516/23500 [05:21<1:14:58,  4.89it/s]
  6%|▋         | 1517/23500 [05:22<1:13:22,  4.99it/s]
  6%|▋         | 1518/23500 [05:22<1:14:08,  4.94it/s]
  6%|▋         | 1519/23500 [05:22<1:14:44,  4.90it/s]
  6%|▋         | 1520/23500 [05:22<1:13:11,  5.00it/s]
  6%|▋         | 1521/23500 [05:22<1:13:26,  4.99it/s]
  6%|▋         | 1522/23500 [05:23<1:13:59,  4.95it/s]
  6%|▋         | 1523/23500 [05:23<1:14:48,  4.90it/s]
  6%|▋         | 1524/23500 [05:23<1:13:40,  4.97it/s]
  6%|▋         | 1525/23500 [05:23<1:14:03,  4.95it/s]
  6%|▋         | 1526/23500 [05:23<1:13:56,  4.95it/s]
  6%|▋         | 1527/23500 [05:24<1:14:08,  4.94it/s]
  7%|▋         | 1528/23500 [05:24<1:11:53,  5.09it/s]
  7%|▋         | 1529/23500 [05:24<1:13:20,  4.99it/s]
  7%|▋         | 1530/23500 [05:24<1:13:02,  5.01it/s]
  7%|▋         | 1531/23500 [05:24<1:13:07,  5.01it/s]
  7%|▋         | 1532/23500 [05:25<1:14:10,  4.94it/s]
  7%|▋         | 1533/23500 [05:25<1:14:24,  4.92it/s]
  7%|▋         | 1534/23500 [05:25<1:15:07,  4.87it/s]
  7%|▋         | 1535/23500 [05:25<1:13:55,  4.95it/s]
  7%|▋         | 1536/23500 [05:26<1:13:49,  4.96it/s]
  7%|▋         | 1537/23500 [05:26<1:13:13,  5.00it/s]
  7%|▋         | 1538/23500 [05:26<1:13:20,  4.99it/s]
  7%|▋         | 1539/23500 [05:26<1:14:20,  4.92it/s]
  7%|▋         | 1540/23500 [05:26<1:14:26,  4.92it/s]
  7%|▋         | 1541/23500 [05:27<1:14:40,  4.90it/s]
  7%|▋         | 1542/23500 [05:27<1:13:51,  4.95it/s]
  7%|▋         | 1543/23500 [05:27<1:14:45,  4.89it/s]
  7%|▋         | 1544/23500 [05:27<1:14:54,  4.89it/s]
  7%|▋         | 1545/23500 [05:27<1:14:31,  4.91it/s]
  7%|▋         | 1546/23500 [05:28<1:14:39,  4.90it/s]
  7%|▋         | 1547/23500 [05:28<1:14:35,  4.91it/s]
  7%|▋         | 1548/23500 [05:28<1:13:46,  4.96it/s]
  7%|▋         | 1549/23500 [05:28<1:12:57,  5.02it/s]
  7%|▋         | 1550/23500 [05:28<1:13:14,  4.99it/s]
  7%|▋         | 1551/23500 [05:29<1:13:47,  4.96it/s]
  7%|▋         | 1552/23500 [05:29<1:13:15,  4.99it/s]
  7%|▋         | 1553/23500 [05:29<1:13:49,  4.95it/s]
  7%|▋         | 1554/23500 [05:29<1:10:44,  5.17it/s]
  7%|▋         | 1555/23500 [05:29<1:11:57,  5.08it/s]
  7%|▋         | 1556/23500 [05:30<1:13:21,  4.99it/s]
  7%|▋         | 1557/23500 [05:30<1:14:04,  4.94it/s]
  7%|▋         | 1558/23500 [05:30<1:14:48,  4.89it/s]
  7%|▋         | 1559/23500 [05:30<1:14:48,  4.89it/s]
  7%|▋         | 1560/23500 [05:30<1:15:29,  4.84it/s]
  7%|▋         | 1561/23500 [05:31<1:15:21,  4.85it/s]
  7%|▋         | 1562/23500 [05:31<1:15:36,  4.84it/s]
  7%|▋         | 1563/23500 [05:31<1:15:45,  4.83it/s]
  7%|▋         | 1564/23500 [05:31<1:16:03,  4.81it/s]
  7%|▋         | 1565/23500 [05:31<1:16:10,  4.80it/s]
  7%|▋         | 1566/23500 [05:32<1:15:17,  4.86it/s]
  7%|▋         | 1567/23500 [05:32<1:15:35,  4.84it/s]
  7%|▋         | 1568/23500 [05:32<1:15:37,  4.83it/s]
  7%|▋         | 1569/23500 [05:32<1:15:14,  4.86it/s]
  7%|▋         | 1570/23500 [05:32<1:15:37,  4.83it/s]
  7%|▋         | 1571/23500 [05:33<1:15:18,  4.85it/s]
  7%|▋         | 1572/23500 [05:33<1:14:41,  4.89it/s]
  7%|▋         | 1573/23500 [05:33<1:14:39,  4.90it/s]
  7%|▋         | 1574/23500 [05:33<1:15:14,  4.86it/s]
  7%|▋         | 1575/23500 [05:33<1:15:43,  4.83it/s]
  7%|▋         | 1576/23500 [05:34<1:14:14,  4.92it/s]
  7%|▋         | 1577/23500 [05:34<1:14:54,  4.88it/s]
  7%|▋         | 1578/23500 [05:34<1:11:09,  5.14it/s]
  7%|▋         | 1579/23500 [05:34<1:12:07,  5.07it/s]
  7%|▋         | 1580/23500 [05:34<1:12:45,  5.02it/s]
  7%|▋         | 1581/23500 [05:35<1:12:24,  5.05it/s]
  7%|▋         | 1582/23500 [05:35<1:12:38,  5.03it/s]
  7%|▋         | 1583/23500 [05:35<1:13:08,  4.99it/s]
  7%|▋         | 1584/23500 [05:35<1:13:51,  4.95it/s]
  7%|▋         | 1585/23500 [05:35<1:14:41,  4.89it/s]
  7%|▋         | 1586/23500 [05:36<1:14:52,  4.88it/s]
  7%|▋         | 1587/23500 [05:36<1:13:02,  5.00it/s]
  7%|▋         | 1588/23500 [05:36<1:18:37,  4.64it/s]
  7%|▋         | 1589/23500 [05:36<1:17:39,  4.70it/s]
  7%|▋         | 1590/23500 [05:37<1:15:31,  4.83it/s]
  7%|▋         | 1591/23500 [05:37<1:08:42,  5.31it/s]
  7%|▋         | 1592/23500 [05:37<1:09:44,  5.24it/s]
  7%|▋         | 1593/23500 [05:37<1:11:38,  5.10it/s]
  7%|▋         | 1594/23500 [05:37<1:13:09,  4.99it/s]
  7%|▋         | 1595/23500 [05:37<1:13:11,  4.99it/s]
  7%|▋         | 1596/23500 [05:38<1:12:27,  5.04it/s]
  7%|▋         | 1597/23500 [05:38<1:11:37,  5.10it/s]
  7%|▋         | 1598/23500 [05:38<1:12:38,  5.02it/s]
  7%|▋         | 1599/23500 [05:38<1:13:46,  4.95it/s]
  7%|▋         | 1600/23500 [05:38<1:14:13,  4.92it/s]
  7%|▋         | 1601/23500 [05:39<1:14:03,  4.93it/s]
  7%|▋         | 1602/23500 [05:39<1:14:48,  4.88it/s]
  7%|▋         | 1603/23500 [05:39<1:15:20,  4.84it/s]
  7%|▋         | 1604/23500 [05:39<1:15:08,  4.86it/s]
  7%|▋         | 1605/23500 [05:39<1:14:34,  4.89it/s]
  7%|▋         | 1606/23500 [05:40<1:14:46,  4.88it/s]
  7%|▋         | 1607/23500 [05:40<1:14:43,  4.88it/s]
  7%|▋         | 1608/23500 [05:40<1:14:57,  4.87it/s]
  7%|▋         | 1609/23500 [05:40<1:15:15,  4.85it/s]
  7%|▋         | 1610/23500 [05:41<1:15:06,  4.86it/s]
  7%|▋         | 1611/23500 [05:41<1:15:12,  4.85it/s]
  7%|▋         | 1612/23500 [05:41<1:13:11,  4.98it/s]
  7%|▋         | 1613/23500 [05:41<1:28:38,  4.12it/s]
  7%|▋         | 1614/23500 [05:41<1:24:29,  4.32it/s]
  7%|▋         | 1615/23500 [05:42<1:21:54,  4.45it/s]
  7%|▋         | 1616/23500 [05:42<1:18:48,  4.63it/s]
  7%|▋         | 1617/23500 [05:42<1:18:02,  4.67it/s]
  7%|▋         | 1618/23500 [05:42<1:16:38,  4.76it/s]
  7%|▋         | 1619/23500 [05:42<1:14:27,  4.90it/s]
  7%|▋         | 1620/23500 [05:43<1:14:20,  4.91it/s]
  7%|▋         | 1621/23500 [05:43<1:14:56,  4.87it/s]
  7%|▋         | 1622/23500 [05:43<1:14:31,  4.89it/s]
  7%|▋         | 1623/23500 [05:43<1:14:33,  4.89it/s]
  7%|▋         | 1624/23500 [05:43<1:14:05,  4.92it/s]
  7%|▋         | 1625/23500 [05:44<1:14:46,  4.88it/s]
  7%|▋         | 1626/23500 [05:44<1:15:10,  4.85it/s]
  7%|▋         | 1627/23500 [05:44<1:15:34,  4.82it/s]
  7%|▋         | 1628/23500 [05:44<1:14:50,  4.87it/s]
  7%|▋         | 1629/23500 [05:45<1:12:33,  5.02it/s]
  7%|▋         | 1630/23500 [05:45<1:13:18,  4.97it/s]
  7%|▋         | 1631/23500 [05:45<1:14:12,  4.91it/s]
  7%|▋         | 1632/23500 [05:45<1:13:54,  4.93it/s]
  7%|▋         | 1633/23500 [05:45<1:14:39,  4.88it/s]
  7%|▋         | 1634/23500 [05:46<1:15:09,  4.85it/s]
  7%|▋         | 1635/23500 [05:46<1:14:04,  4.92it/s]
  7%|▋         | 1636/23500 [05:46<1:14:25,  4.90it/s]
  7%|▋         | 1637/23500 [05:46<1:14:33,  4.89it/s]
  7%|▋         | 1638/23500 [05:46<1:20:32,  4.52it/s]
  7%|▋         | 1639/23500 [05:47<1:19:05,  4.61it/s]
  7%|▋         | 1640/23500 [05:47<1:17:21,  4.71it/s]
  7%|▋         | 1641/23500 [05:47<1:16:44,  4.75it/s]
  7%|▋         | 1642/23500 [05:47<1:16:20,  4.77it/s]
  7%|▋         | 1643/23500 [05:47<1:15:25,  4.83it/s]
  7%|▋         | 1644/23500 [05:48<1:15:22,  4.83it/s]
                                                      

  7%|▋         | 1645/23500 [05:48<1:15:21,  4.83it/s]{'eval_loss': 0.7105868458747864, 'eval_accuracy': 0.7124, 'eval_f1': 0.710171369539371, 'eval_runtime': 1.2665, 'eval_samples_per_second': 1973.953, 'eval_steps_per_second': 15.792, 'epoch': 6.0}
{'loss': 0.3298, 'learning_rate': 2.7368341444031695e-05, 'epoch': 7.0}


  0%|          | 0/20 [00:00<?, ?it/s]

 15%|█▌        | 3/20 [00:00<00:00, 21.79it/s]

 30%|███       | 6/20 [00:00<00:00, 18.49it/s]

 40%|████      | 8/20 [00:00<00:00, 16.76it/s]

 50%|█████     | 10/20 [00:00<00:00, 16.12it/s]

 60%|██████    | 12/20 [00:00<00:00, 15.49it/s]

 70%|███████   | 14/20 [00:00<00:00, 15.06it/s]

 85%|████████▌ | 17/20 [00:01<00:00, 16.30it/s]

 95%|█████████▌| 19/20 [00:01<00:00, 15.84it/s]

                                               

                                                      

100%|██████████| 20/20 [00:01<00:00, 15.84it/s]
  7%|▋         | 1645/23500 [05:49<1:15:21,  4.83it/s]

                                               /usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(

                                                      

  7%|▋         | 1645/23500 [05:50<1:15:21,  4.83it/s]
  7%|▋         | 1645/23500 [05:50<1:17:37,  4.69it/s]
/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py:1383: UserWarning: positional arguments and argument "destination" are deprecated. nn.Module.state_dict will not accept them in the future. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
  warnings.warn(
{'eval_loss': 0.8034451603889465, 'eval_accuracy': 0.7064, 'eval_f1': 0.7055785145607243, 'eval_runtime': 1.2652, 'eval_samples_per_second': 1975.987, 'eval_steps_per_second': 15.808, 'epoch': 7.0}
{'train_runtime': 350.5605, 'train_samples_per_second': 8557.724, 'train_steps_per_second': 67.036, 'train_loss': 0.6244962929954645, 'epoch': 7.0}