Training in progress, step 5000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38caf6d8a9c2b7c18aca76fa2d4a9f08a3ed0a3e45016695116c2fbd41ee2652
+oid sha256:634a74d630fd8c463389ac655754f9dafbd2b5707552164012b81d85d0502597
 size 3025686376

runs/Mar27_19-04-06_hf-dgx-01/events.out.tfevents.1711562657.hf-dgx-01.1893386.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8396ee90e66bcd7c2aee0da8f2c08987080a79f3b01330943b772a7bcc9cb9d5
-size 40397
+oid sha256:fcf36e04fd7fe7eaaf98b63ab7ce98343894650bf7d4bd71d315466c42cf400d
+size 49509

wandb/run-20240327_190418-lwtbcr8s/files/output.log

@@ -4641,3 +4641,1126 @@ Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens':
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|██████████████████████████████████████████████████████████████▎              | 4049/5000 [6:06:58<42:08,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|██████████████████████████████████████████████████████████████▋              | 4074/5000 [6:08:05<41:03,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|███████████████████████████████████████████████████████████████              | 4099/5000 [6:09:11<39:56,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|███████████████████████████████████████████████████████████████▌             | 4125/5000 [6:10:20<38:48,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|███████████████████████████████████████████████████████████████▉             | 4150/5000 [6:11:27<37:40,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████████████████████████████████████████████████████████████▎            | 4174/5000 [6:12:31<36:36,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████████████████████████████████████████████████████████████▋            | 4199/5000 [6:13:37<35:33,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|█████████████████████████████████████████████████████████████████            | 4224/5000 [6:14:55<41:51,  3.24s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|█████████████████████████████████████████████████████████████████▍           | 4249/5000 [6:16:01<33:14,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|█████████████████████████████████████████████████████████████████▊           | 4275/5000 [6:17:11<32:06,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|██████████████████████████████████████████████████████████████████▏          | 4300/5000 [6:18:17<31:01,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|██████████████████████████████████████████████████████████████████▌          | 4325/5000 [6:19:24<29:53,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|██████████████████████████████████████████████████████████████████▉          | 4349/5000 [6:20:27<28:50,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|███████████████████████████████████████████████████████████████████▎         | 4374/5000 [6:21:34<27:45,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|███████████████████████████████████████████████████████████████████▊         | 4400/5000 [6:22:43<26:35,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████████████████████████████████████████████████████████████████▏        | 4425/5000 [6:23:49<25:28,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|█████████████████████████████████████��██████████████████████████████▌        | 4450/5000 [6:25:07<25:35,  2.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|████████████████████████████████████████████████████████████████████▉        | 4475/5000 [6:26:13<23:13,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████████████████████████████████████████████████████████████████▎       | 4500/5000 [6:27:20<22:07,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████████████████████████████████████████████████████████████████▋       | 4525/5000 [6:28:26<21:00,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|██████████████████████████████████████████████████████████████████████       | 4549/5000 [6:29:30<19:57,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|██████████████████████████████████████████████████████████████████████▍      | 4574/5000 [6:30:36<18:50,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|██████████████████████████████████████████████████████████████████████▊      | 4599/5000 [6:31:43<17:43,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|███████████████████████████████████████████████████████████████████████▏     | 4625/5000 [6:32:52<16:34,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|███████████████████████████████████████████████████████████████████████▌     | 4650/5000 [6:33:58<15:29,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|███████████████████████████████████████████████████████████████████████▉     | 4674/5000 [6:35:13<14:45,  2.72s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|████████████████████████████████████████████████████████████████████████▍    | 4700/5000 [6:36:22<13:16,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|████████████████████████████████████████████████████████████████████████▊    | 4725/5000 [6:37:28<12:08,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████████████████████████████████████████████████████████████████████▏   | 4750/5000 [6:38:34<11:03,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████████████████████████████████████████████████████████████████████▌   | 4775/5000 [6:39:41<09:57,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████████████████████████████████████████████████████████████████████▉   | 4800/5000 [6:40:47<08:50,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|██████████████████████████████████████████████████████████████████████████▎  | 4825/5000 [6:41:53<07:44,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████████████████████████████████████████████████████████��████████████▋  | 4849/5000 [6:42:57<06:40,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|███████████████████████████████████████████████████████████████████████████  | 4874/5000 [6:44:03<05:34,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|███████████████████████████████████████████████████████████████████████████▍ | 4900/5000 [6:45:24<04:26,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|███████████████████████████████████████████████████████████████████████████▊ | 4924/5000 [6:46:27<03:21,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|████████████████████████████████████████████████████████████████████████████▏| 4949/5000 [6:47:34<02:15,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|████████████████████████████████████████████████████████████████████████████▌| 4975/5000 [6:48:43<01:06,  2.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████████████████████████████████████████████████████████████████████████| 5000/5000 [6:49:49<00:00,  2.66s/it][INFO|trainer.py:768] 2024-03-28 01:54:08,641 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3544] 2024-03-28 01:54:08,644 >> ***** Running Evaluation *****
+[INFO|trainer.py:3546] 2024-03-28 01:54:08,645 >>   Num examples = 3123
+[INFO|trainer.py:3549] 2024-03-28 01:54:08,645 >>   Batch size = 32
+{'loss': 0.0001, 'grad_norm': 0.002005824586376548, 'learning_rate': 1.1111111111111112e-07, 'epoch': 22.52}
+[INFO|generation_whisper.py:1111] 2024-03-28 01:54:20,047 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+                                                                                                                        [INFO|generation_whisper.py:1111] 2024-03-28 01:54:25,634 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  0%|                                                                                            | 0/98 [00:00<?, ?it/s][INFO|generation_whisper.py:1111] 2024-03-28 01:54:31,244 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  2%|█▋                                                                                  | 2/98 [00:05<04:29,  2.80s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:54:36,893 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  3%|██▌                                                                                 | 3/98 [00:11<06:19,  3.99s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:54:42,481 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  4%|███▍                                                                                | 4/98 [00:16<07:11,  4.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:54:48,095 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  5%|████▎                                                                               | 5/98 [00:22<07:39,  4.94s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:54:53,660 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  6%|█████▏                                                                              | 6/98 [00:28<07:53,  5.15s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:54:59,277 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  7%|██████                                                                              | 7/98 [00:33<08:02,  5.30s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:04,867 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  8%|██████▊                                                                             | 8/98 [00:39<08:05,  5.39s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:10,531 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  9%|███████▋                                                                            | 9/98 [00:44<08:07,  5.48s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:16,158 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 10%|████████▍                                                                          | 10/98 [00:50<08:05,  5.52s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:21,773 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 11%|█████████▎                                                                         | 11/98 [00:56<08:02,  5.55s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:27,372 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 12%|██████████▏                                                                        | 12/98 [01:01<07:58,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:32,934 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 13%|███████████                                                                        | 13/98 [01:07<07:52,  5.56s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:38,535 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 14%|███████████▊                                                                       | 14/98 [01:12<07:48,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:44,199 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 15%|████████████▋                                                                      | 15/98 [01:18<07:44,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:49,790 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 16%|█████████████▌                                                                     | 16/98 [01:24<07:39,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:55:55,406 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 17%|██████████████▍                                                                    | 17/98 [01:29<07:33,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:01,008 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 18%|███████████████▏                                                                   | 18/98 [01:35<07:28,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:06,622 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 19%|████████████████                                                                   | 19/98 [01:40<07:22,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:12,239 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 20%|████████████████▉                                                                  | 20/98 [01:46<07:17,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:17,849 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 21%|█████████████████▊                                                                 | 21/98 [01:52<07:11,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:23,449 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 22%|██████████████████▋                                                                | 22/98 [01:57<07:06,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:29,020 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 23%|███████████████████▍                                                               | 23/98 [02:03<06:59,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:34,703 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 24%|████████████████████▎                                                              | 24/98 [02:09<06:56,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:40,326 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 26%|█████████████████████▏                                                             | 25/98 [02:14<06:50,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:45,980 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 27%|██████████████████████                                                             | 26/98 [02:20<06:45,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:51,588 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 28%|██████████████████████▊                                                            | 27/98 [02:25<06:39,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:56:57,222 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 29%|███████████████████████▋                                                           | 28/98 [02:31<06:33,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:02,821 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 30%|████████████████████████▌                                                          | 29/98 [02:37<06:27,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:08,450 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 31%|█████████████████████████▍                                                         | 30/98 [02:42<06:22,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:14,029 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 32%|██████████████████████████▎                                                        | 31/98 [02:48<06:15,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:19,619 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 33%|███████████████████████████                                                        | 32/98 [02:53<06:09,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:25,192 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 34%|███████████████████████████▉                                                       | 33/98 [02:59<06:03,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:30,806 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 35%|████████████████████████████▊                                                      | 34/98 [03:05<05:58,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:36,416 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 36%|█████████████████████████████▋                                                     | 35/98 [03:10<05:53,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:41,975 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 37%|██████████████████████████████▍                                                    | 36/98 [03:16<05:46,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:47,651 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 38%|███████████████████████████████▎                                                   | 37/98 [03:22<05:42,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:53,235 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 39%|████████████████████████████████▏                                                  | 38/98 [03:27<05:36,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:57:58,862 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 40%|█████████████████████████████████                                                  | 39/98 [03:33<05:31,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:04,434 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 41%|█████████████████████████████████▉                                                 | 40/98 [03:38<05:24,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:10,040 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 42%|██████████████████████████████████▋                                                | 41/98 [03:44<05:19,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:15,650 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 43%|███████████████████████████████████▌                                               | 42/98 [03:50<05:13,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:21,445 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 44%|████████████████████████████████████▍                                              | 43/98 [03:55<05:11,  5.66s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:27,036 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 45%|█████████████████████████████████████▎                                             | 44/98 [04:01<05:04,  5.64s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:32,613 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 46%|██████████████████████████████████████                                             | 45/98 [04:06<04:57,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:38,252 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 47%|██████████████████████████████████████▉                                            | 46/98 [04:12<04:52,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:43,936 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 48%|███████████████████████████████████████▊                                           | 47/98 [04:18<04:47,  5.64s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:49,524 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 49%|████████████████████████████████████████▋                                          | 48/98 [04:23<04:41,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:58:55,174 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 50%|█████████████████████████████████████████▌                                         | 49/98 [04:29<04:36,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:00,778 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 51%|██████████████████████████████████████████▎                                        | 50/98 [04:35<04:30,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:06,349 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 52%|███████████████████████████████████████████▏                                       | 51/98 [04:40<04:23,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:11,948 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 53%|████████████████████████████████████████████                                       | 52/98 [04:46<04:17,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:17,566 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 54%|████████████████████████████████████████████▉                                      | 53/98 [04:51<04:12,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:23,234 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 55%|█████████████████████████████████████████████▋                                     | 54/98 [04:57<04:07,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:28,839 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 56%|██████████████████████████████████████████████▌                                    | 55/98 [05:03<04:01,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:34,416 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 57%|███████████████████████████████████████████████▍                                   | 56/98 [05:08<03:55,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:40,007 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 58%|████████████████████████████████████████████████▎                                  | 57/98 [05:14<03:49,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:45,601 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 59%|█████████████████████████████████████████████████                                  | 58/98 [05:19<03:43,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:51,213 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 60%|█████████████████████████████████████████████████▉                                 | 59/98 [05:25<03:38,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:59:56,810 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 61%|██████████████████████████████████████████████████▊                                | 60/98 [05:31<03:32,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:02,388 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 62%|███████████████████████████████████████████████████▋                               | 61/98 [05:36<03:27,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:07,958 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 63%|████████████████████████████████████████████████████▌                              | 62/98 [05:42<03:21,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:13,555 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 64%|█████████████████████████████████████████████████████▎                             | 63/98 [05:47<03:15,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:19,200 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 65%|██████████████████████████████████████████████████████▏                            | 64/98 [05:53<03:10,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:24,768 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 66%|███████████████████████████████████████████████████████                            | 65/98 [05:59<03:04,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:30,322 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 67%|███████████████████████████████████████████████████████▉                           | 66/98 [06:04<02:58,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:35,925 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 68%|████████████████████████████████████████████████████████▋                          | 67/98 [06:10<02:53,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:41,522 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 69%|█████████████████████████████████████████████████████████▌                         | 68/98 [06:15<02:47,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:47,144 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 70%|██████████████████████████████████████████████████████████▍                        | 69/98 [06:21<02:42,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:52,761 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 71%|███████████████████████████████████████████████████████████▎                       | 70/98 [06:27<02:36,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:00:58,592 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 72%|████████████████████████████████████████████████████████████▏                      | 71/98 [06:32<02:33,  5.67s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:04,175 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 73%|████████████████████████████████████████████████████████████▉                      | 72/98 [06:38<02:26,  5.65s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:09,824 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 74%|█████████████████████████████████████████████████████████████▊                     | 73/98 [06:44<02:21,  5.65s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:15,453 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 76%|██████████████████████████████████████████████████████████████▋                    | 74/98 [06:49<02:15,  5.64s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:21,034 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 77%|██████████████████████████████████████████████████████���████████▌                   | 75/98 [06:55<02:09,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:26,593 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 78%|████████████████████████████████████████████████████████████████▎                  | 76/98 [07:00<02:03,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:32,201 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 79%|█████████████████████████████████████████████████████████████████▏                 | 77/98 [07:06<01:57,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:37,765 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 80%|██████████████████████████████████████████████████████████████████                 | 78/98 [07:12<01:51,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:43,366 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 81%|██████████████████████████████████████████████████████████████████▉                | 79/98 [07:17<01:46,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:48,947 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 82%|███████████████████████████████████████████████████████████████████▊               | 80/98 [07:23<01:40,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:01:54,545 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 83%|████████████████████████████████████████████████████████████████████▌              | 81/98 [07:28<01:35,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:00,185 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 84%|█████████████████████████████████████████████████████████████████████▍             | 82/98 [07:34<01:29,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:05,825 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 85%|██████████████████████████████████████████████████████████████████████▎            | 83/98 [07:40<01:24,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:11,417 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 86%|███████████████████████████████████████████████████████████████████████▏           | 84/98 [07:45<01:18,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:17,187 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 87%|█████████████████████████████████████████████████████████████████��█████▉           | 85/98 [07:51<01:13,  5.66s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:22,703 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 88%|████████████████████████████████████████████████████████████████████████▊          | 86/98 [07:57<01:07,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:28,317 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 89%|█████████████████████████████████████████████████████████████████████████▋         | 87/98 [08:02<01:01,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:33,905 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 90%|██████████████████████████████████████████████████████████████████████████▌        | 88/98 [08:08<00:56,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:39,507 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 91%|███████████████████████████████████████████████████████████████████████████▍       | 89/98 [08:13<00:50,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:45,136 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 92%|████████████████████████████████████████████████████████████████████████████▏      | 90/98 [08:19<00:44,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:50,699 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 93%|█████████████████████████████████████████████████████████████████████████████      | 91/98 [08:25<00:39,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:02:56,295 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 94%|█████████████████████████████████████████████████████████████████████████████▉     | 92/98 [08:30<00:33,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:03:01,887 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 95%|██████████████████████████████████████████████████████████████████████████████▊    | 93/98 [08:36<00:27,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:03:07,439 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 96%|███████████████████████████████████████████████████████████████████████████████▌   | 94/98 [08:41<00:22,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:03:13,034 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 97%|█████████████████████��██████████████████████████████████████████████████████████▍  | 95/98 [08:47<00:16,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:03:18,634 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 98%|█████████████████████████████████████████████████████████████████████████████████▎ | 96/98 [08:52<00:11,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 02:03:24,386 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+100%|█████████████████████████████████████████████████████████████████████████████| 5000/5000 [6:59:09<00:00,  2.66s/it][INFO|trainer.py:3235] 2024-03-28 02:03:28,501 >> Saving model checkpoint to ./checkpoint-5000
+[WARNING|configuration_utils.py:447] 2024-03-28 02:03:28,502 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]}
+[INFO|configuration_utils.py:471] 2024-03-28 02:03:28,502 >> Configuration saved in ./checkpoint-5000/config.json
+[INFO|configuration_utils.py:697] 2024-03-28 02:03:28,503 >> Configuration saved in ./checkpoint-5000/generation_config.json
+{'eval_loss': 0.6148200035095215, 'eval_wer': 0.3297535347291973, 'eval_runtime': 559.8547, 'eval_samples_per_second': 5.578, 'eval_steps_per_second': 0.175, 'epoch': 22.52}
+[INFO|modeling_utils.py:2475] 2024-03-28 02:03:36,138 >> Model weights saved in ./checkpoint-5000/model.safetensors
+[INFO|feature_extraction_utils.py:424] 2024-03-28 02:03:36,139 >> Feature extractor saved in ./checkpoint-5000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:424] 2024-03-28 02:03:59,292 >> Feature extractor saved in ./preprocessor_config.json
+[INFO|trainer.py:3327] 2024-03-28 02:03:59,293 >> Deleting older checkpoint [checkpoint-4000] due to args.save_total_limit
+[INFO|trainer.py:2263] 2024-03-28 02:04:00,438 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+100%|█████████████████████████████████████████████████████████████████████████████| 5000/5000 [6:59:41<00:00,  5.04s/it]
+[INFO|trainer.py:4001] 2024-03-28 02:04:00,440 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.

wandb/run-20240327_190418-lwtbcr8s/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.0005, "train/grad_norm": 0.018902545794844627, "train/learning_rate": 2.177777777777778e-05, "train/epoch": 18.13, "train/global_step": 4025, "_timestamp": 1711584613.86865, "_runtime": 21955.3040599823, "_step": 164, "eval/loss": 0.5731213092803955, "eval/wer": 0.33979757397821214, "eval/runtime": 559.2789, "eval/samples_per_second": 5.584, "eval/steps_per_second": 0.175}
+{"train/loss": 0.0001, "train/grad_norm": 0.002005824586376548, "train/learning_rate": 1.1111111111111112e-07, "train/epoch": 22.52, "train/global_step": 5000, "_timestamp": 1711587840.4393897, "_runtime": 25181.874799728394, "_step": 205, "eval/loss": 0.6148200035095215, "eval/wer": 0.3297535347291973, "eval/runtime": 559.8547, "eval/samples_per_second": 5.578, "eval/steps_per_second": 0.175, "train_runtime": 25183.0848, "train_samples_per_second": 6.353, "train_steps_per_second": 0.199, "total_flos": 2.532745423355904e+20, "train_loss": 0.15328583015645855}

wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311c7a1ba8ad47da67a2e6ad4f3ceef30a17026ee75c8a4adda40a1fea48fef4
-size 5046509
+oid sha256:1393642b3724d50ee1c65a1f63d69a1ba871fe44cbe3d6bf0f7ea5b339b70ec5
+size 6043771