| 2023-10-17 11:06:07,910 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 768) | |
| (position_embeddings): Embedding(512, 768) | |
| (token_type_embeddings): Embedding(2, 768) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): ElectraSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Train: 966 sentences | |
| 2023-10-17 11:06:07,911 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Training Params: | |
| 2023-10-17 11:06:07,911 - learning_rate: "3e-05" | |
| 2023-10-17 11:06:07,911 - mini_batch_size: "8" | |
| 2023-10-17 11:06:07,911 - max_epochs: "10" | |
| 2023-10-17 11:06:07,911 - shuffle: "True" | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Plugins: | |
| 2023-10-17 11:06:07,911 - TensorboardLogger | |
| 2023-10-17 11:06:07,911 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 11:06:07,911 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,911 Computation: | |
| 2023-10-17 11:06:07,911 - compute on device: cuda:0 | |
| 2023-10-17 11:06:07,911 - embedding storage: none | |
| 2023-10-17 11:06:07,911 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,912 Model training base path: "hmbench-ajmc/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 11:06:07,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:07,912 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 11:06:08,692 epoch 1 - iter 12/121 - loss 4.71657886 - time (sec): 0.78 - samples/sec: 3355.68 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:06:09,439 epoch 1 - iter 24/121 - loss 4.28366633 - time (sec): 1.53 - samples/sec: 3264.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:06:10,156 epoch 1 - iter 36/121 - loss 3.66015277 - time (sec): 2.24 - samples/sec: 3298.43 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:06:10,859 epoch 1 - iter 48/121 - loss 3.02855067 - time (sec): 2.95 - samples/sec: 3315.31 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:06:11,630 epoch 1 - iter 60/121 - loss 2.51399731 - time (sec): 3.72 - samples/sec: 3333.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:06:12,393 epoch 1 - iter 72/121 - loss 2.19672285 - time (sec): 4.48 - samples/sec: 3322.76 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:06:13,089 epoch 1 - iter 84/121 - loss 1.97940754 - time (sec): 5.18 - samples/sec: 3321.46 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:06:13,831 epoch 1 - iter 96/121 - loss 1.79789448 - time (sec): 5.92 - samples/sec: 3316.91 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:06:14,563 epoch 1 - iter 108/121 - loss 1.62977052 - time (sec): 6.65 - samples/sec: 3344.21 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:06:15,297 epoch 1 - iter 120/121 - loss 1.51079741 - time (sec): 7.38 - samples/sec: 3336.71 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:06:15,346 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:15,347 EPOCH 1 done: loss 1.5059 - lr: 0.000030 | |
| 2023-10-17 11:06:15,961 DEV : loss 0.27024656534194946 - f1-score (micro avg) 0.4834 | |
| 2023-10-17 11:06:15,968 saving best model | |
| 2023-10-17 11:06:16,350 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:17,109 epoch 2 - iter 12/121 - loss 0.28578716 - time (sec): 0.76 - samples/sec: 3522.89 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:06:17,907 epoch 2 - iter 24/121 - loss 0.26801399 - time (sec): 1.56 - samples/sec: 3296.46 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:06:18,672 epoch 2 - iter 36/121 - loss 0.26147152 - time (sec): 2.32 - samples/sec: 3171.52 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:06:19,487 epoch 2 - iter 48/121 - loss 0.25971566 - time (sec): 3.14 - samples/sec: 3175.70 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:06:20,160 epoch 2 - iter 60/121 - loss 0.25226103 - time (sec): 3.81 - samples/sec: 3195.15 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:06:20,925 epoch 2 - iter 72/121 - loss 0.24570325 - time (sec): 4.57 - samples/sec: 3203.49 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:06:21,683 epoch 2 - iter 84/121 - loss 0.23921590 - time (sec): 5.33 - samples/sec: 3246.01 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:06:22,426 epoch 2 - iter 96/121 - loss 0.22522049 - time (sec): 6.07 - samples/sec: 3266.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:06:23,170 epoch 2 - iter 108/121 - loss 0.22308683 - time (sec): 6.82 - samples/sec: 3270.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:06:23,946 epoch 2 - iter 120/121 - loss 0.21673177 - time (sec): 7.59 - samples/sec: 3245.21 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:06:24,000 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:24,000 EPOCH 2 done: loss 0.2170 - lr: 0.000027 | |
| 2023-10-17 11:06:24,935 DEV : loss 0.13171441853046417 - f1-score (micro avg) 0.7187 | |
| 2023-10-17 11:06:24,940 saving best model | |
| 2023-10-17 11:06:25,514 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:26,303 epoch 3 - iter 12/121 - loss 0.10627790 - time (sec): 0.79 - samples/sec: 2888.63 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:06:27,051 epoch 3 - iter 24/121 - loss 0.12080428 - time (sec): 1.54 - samples/sec: 3108.09 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:06:27,858 epoch 3 - iter 36/121 - loss 0.12284649 - time (sec): 2.34 - samples/sec: 3137.68 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:06:28,658 epoch 3 - iter 48/121 - loss 0.12517420 - time (sec): 3.14 - samples/sec: 3124.07 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:06:29,401 epoch 3 - iter 60/121 - loss 0.12871513 - time (sec): 3.88 - samples/sec: 3151.04 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:06:30,151 epoch 3 - iter 72/121 - loss 0.12922199 - time (sec): 4.64 - samples/sec: 3144.55 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:06:30,836 epoch 3 - iter 84/121 - loss 0.12814688 - time (sec): 5.32 - samples/sec: 3163.15 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:06:31,556 epoch 3 - iter 96/121 - loss 0.12444366 - time (sec): 6.04 - samples/sec: 3186.88 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:06:32,255 epoch 3 - iter 108/121 - loss 0.12385304 - time (sec): 6.74 - samples/sec: 3244.24 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:06:33,048 epoch 3 - iter 120/121 - loss 0.12353435 - time (sec): 7.53 - samples/sec: 3261.01 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:06:33,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:33,094 EPOCH 3 done: loss 0.1227 - lr: 0.000023 | |
| 2023-10-17 11:06:33,847 DEV : loss 0.13011731207370758 - f1-score (micro avg) 0.8123 | |
| 2023-10-17 11:06:33,853 saving best model | |
| 2023-10-17 11:06:34,408 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:35,181 epoch 4 - iter 12/121 - loss 0.08763121 - time (sec): 0.77 - samples/sec: 3204.79 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:06:35,910 epoch 4 - iter 24/121 - loss 0.10553822 - time (sec): 1.50 - samples/sec: 3175.38 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:06:36,659 epoch 4 - iter 36/121 - loss 0.09791444 - time (sec): 2.25 - samples/sec: 3260.01 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:06:37,432 epoch 4 - iter 48/121 - loss 0.09517240 - time (sec): 3.02 - samples/sec: 3205.86 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:06:38,199 epoch 4 - iter 60/121 - loss 0.09247144 - time (sec): 3.79 - samples/sec: 3199.87 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:06:39,019 epoch 4 - iter 72/121 - loss 0.08827230 - time (sec): 4.61 - samples/sec: 3207.69 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:06:39,740 epoch 4 - iter 84/121 - loss 0.08937727 - time (sec): 5.33 - samples/sec: 3200.14 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:06:40,488 epoch 4 - iter 96/121 - loss 0.08808138 - time (sec): 6.08 - samples/sec: 3238.56 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:06:41,227 epoch 4 - iter 108/121 - loss 0.08461841 - time (sec): 6.82 - samples/sec: 3245.47 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:06:41,986 epoch 4 - iter 120/121 - loss 0.08147914 - time (sec): 7.57 - samples/sec: 3240.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:06:42,039 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:42,040 EPOCH 4 done: loss 0.0809 - lr: 0.000020 | |
| 2023-10-17 11:06:42,798 DEV : loss 0.14415650069713593 - f1-score (micro avg) 0.8163 | |
| 2023-10-17 11:06:42,803 saving best model | |
| 2023-10-17 11:06:43,293 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:43,985 epoch 5 - iter 12/121 - loss 0.03148198 - time (sec): 0.69 - samples/sec: 3403.72 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:06:44,728 epoch 5 - iter 24/121 - loss 0.03636269 - time (sec): 1.43 - samples/sec: 3314.63 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:06:45,473 epoch 5 - iter 36/121 - loss 0.05860519 - time (sec): 2.18 - samples/sec: 3313.60 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:06:46,251 epoch 5 - iter 48/121 - loss 0.05845807 - time (sec): 2.96 - samples/sec: 3334.43 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:06:47,029 epoch 5 - iter 60/121 - loss 0.05644647 - time (sec): 3.73 - samples/sec: 3275.14 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:06:47,816 epoch 5 - iter 72/121 - loss 0.05546351 - time (sec): 4.52 - samples/sec: 3298.91 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:06:48,506 epoch 5 - iter 84/121 - loss 0.05713502 - time (sec): 5.21 - samples/sec: 3281.18 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:06:49,304 epoch 5 - iter 96/121 - loss 0.05781539 - time (sec): 6.01 - samples/sec: 3265.91 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:06:50,061 epoch 5 - iter 108/121 - loss 0.05805281 - time (sec): 6.77 - samples/sec: 3271.87 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:06:50,781 epoch 5 - iter 120/121 - loss 0.05588702 - time (sec): 7.49 - samples/sec: 3282.77 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:06:50,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:50,832 EPOCH 5 done: loss 0.0558 - lr: 0.000017 | |
| 2023-10-17 11:06:51,580 DEV : loss 0.1458047777414322 - f1-score (micro avg) 0.8293 | |
| 2023-10-17 11:06:51,585 saving best model | |
| 2023-10-17 11:06:52,147 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:52,869 epoch 6 - iter 12/121 - loss 0.02975957 - time (sec): 0.72 - samples/sec: 3352.52 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:06:53,576 epoch 6 - iter 24/121 - loss 0.03866415 - time (sec): 1.43 - samples/sec: 3404.57 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:06:54,372 epoch 6 - iter 36/121 - loss 0.03587945 - time (sec): 2.22 - samples/sec: 3394.11 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:06:55,104 epoch 6 - iter 48/121 - loss 0.04025476 - time (sec): 2.95 - samples/sec: 3367.95 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:06:55,856 epoch 6 - iter 60/121 - loss 0.03849824 - time (sec): 3.71 - samples/sec: 3316.08 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:06:56,615 epoch 6 - iter 72/121 - loss 0.04250399 - time (sec): 4.46 - samples/sec: 3287.21 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:06:57,373 epoch 6 - iter 84/121 - loss 0.04356166 - time (sec): 5.22 - samples/sec: 3311.11 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:06:58,143 epoch 6 - iter 96/121 - loss 0.04330969 - time (sec): 5.99 - samples/sec: 3326.33 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:06:58,852 epoch 6 - iter 108/121 - loss 0.04260343 - time (sec): 6.70 - samples/sec: 3326.60 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:06:59,545 epoch 6 - iter 120/121 - loss 0.04313233 - time (sec): 7.39 - samples/sec: 3328.84 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:06:59,594 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:06:59,594 EPOCH 6 done: loss 0.0431 - lr: 0.000013 | |
| 2023-10-17 11:07:00,356 DEV : loss 0.17940106987953186 - f1-score (micro avg) 0.8156 | |
| 2023-10-17 11:07:00,361 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:01,004 epoch 7 - iter 12/121 - loss 0.04782824 - time (sec): 0.64 - samples/sec: 3420.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:07:01,723 epoch 7 - iter 24/121 - loss 0.03144486 - time (sec): 1.36 - samples/sec: 3304.05 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:07:02,460 epoch 7 - iter 36/121 - loss 0.03132860 - time (sec): 2.10 - samples/sec: 3393.84 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:07:03,183 epoch 7 - iter 48/121 - loss 0.03687959 - time (sec): 2.82 - samples/sec: 3418.98 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:07:03,896 epoch 7 - iter 60/121 - loss 0.03756955 - time (sec): 3.53 - samples/sec: 3422.17 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:07:04,673 epoch 7 - iter 72/121 - loss 0.03675647 - time (sec): 4.31 - samples/sec: 3461.96 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:07:05,462 epoch 7 - iter 84/121 - loss 0.03617214 - time (sec): 5.10 - samples/sec: 3435.95 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:07:06,227 epoch 7 - iter 96/121 - loss 0.03496919 - time (sec): 5.87 - samples/sec: 3413.83 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:07:06,954 epoch 7 - iter 108/121 - loss 0.03466051 - time (sec): 6.59 - samples/sec: 3394.89 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:07:07,684 epoch 7 - iter 120/121 - loss 0.03408582 - time (sec): 7.32 - samples/sec: 3362.30 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:07:07,729 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:07,729 EPOCH 7 done: loss 0.0344 - lr: 0.000010 | |
| 2023-10-17 11:07:08,486 DEV : loss 0.17554134130477905 - f1-score (micro avg) 0.8225 | |
| 2023-10-17 11:07:08,491 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:09,186 epoch 8 - iter 12/121 - loss 0.02997440 - time (sec): 0.69 - samples/sec: 3309.46 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:07:09,899 epoch 8 - iter 24/121 - loss 0.02784253 - time (sec): 1.41 - samples/sec: 3348.41 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:07:10,645 epoch 8 - iter 36/121 - loss 0.02640009 - time (sec): 2.15 - samples/sec: 3379.71 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:07:11,304 epoch 8 - iter 48/121 - loss 0.02731240 - time (sec): 2.81 - samples/sec: 3311.74 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:07:12,016 epoch 8 - iter 60/121 - loss 0.02588441 - time (sec): 3.52 - samples/sec: 3399.51 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:07:12,774 epoch 8 - iter 72/121 - loss 0.02699633 - time (sec): 4.28 - samples/sec: 3386.81 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:07:13,540 epoch 8 - iter 84/121 - loss 0.02447097 - time (sec): 5.05 - samples/sec: 3355.88 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:07:14,290 epoch 8 - iter 96/121 - loss 0.02398239 - time (sec): 5.80 - samples/sec: 3364.99 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:07:15,054 epoch 8 - iter 108/121 - loss 0.02346321 - time (sec): 6.56 - samples/sec: 3366.06 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:07:15,764 epoch 8 - iter 120/121 - loss 0.02442648 - time (sec): 7.27 - samples/sec: 3382.12 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:07:15,810 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:15,810 EPOCH 8 done: loss 0.0243 - lr: 0.000007 | |
| 2023-10-17 11:07:16,559 DEV : loss 0.18656818568706512 - f1-score (micro avg) 0.8454 | |
| 2023-10-17 11:07:16,564 saving best model | |
| 2023-10-17 11:07:17,078 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:17,802 epoch 9 - iter 12/121 - loss 0.02485013 - time (sec): 0.72 - samples/sec: 3257.55 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:07:18,545 epoch 9 - iter 24/121 - loss 0.02382192 - time (sec): 1.46 - samples/sec: 3209.18 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:07:19,264 epoch 9 - iter 36/121 - loss 0.02089084 - time (sec): 2.18 - samples/sec: 3142.60 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:07:20,023 epoch 9 - iter 48/121 - loss 0.01824474 - time (sec): 2.94 - samples/sec: 3211.13 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:07:20,726 epoch 9 - iter 60/121 - loss 0.01945334 - time (sec): 3.65 - samples/sec: 3196.42 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:07:21,446 epoch 9 - iter 72/121 - loss 0.02353394 - time (sec): 4.37 - samples/sec: 3215.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:07:22,231 epoch 9 - iter 84/121 - loss 0.02079467 - time (sec): 5.15 - samples/sec: 3237.25 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:07:23,019 epoch 9 - iter 96/121 - loss 0.01935617 - time (sec): 5.94 - samples/sec: 3262.35 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:07:23,789 epoch 9 - iter 108/121 - loss 0.01836797 - time (sec): 6.71 - samples/sec: 3276.76 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:07:24,534 epoch 9 - iter 120/121 - loss 0.01861060 - time (sec): 7.45 - samples/sec: 3288.92 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:07:24,596 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:24,596 EPOCH 9 done: loss 0.0187 - lr: 0.000004 | |
| 2023-10-17 11:07:25,394 DEV : loss 0.19949409365653992 - f1-score (micro avg) 0.8369 | |
| 2023-10-17 11:07:25,399 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:26,145 epoch 10 - iter 12/121 - loss 0.01038954 - time (sec): 0.74 - samples/sec: 3211.80 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:07:26,902 epoch 10 - iter 24/121 - loss 0.02137487 - time (sec): 1.50 - samples/sec: 3321.85 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:07:27,653 epoch 10 - iter 36/121 - loss 0.02121961 - time (sec): 2.25 - samples/sec: 3232.21 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:07:28,368 epoch 10 - iter 48/121 - loss 0.02812268 - time (sec): 2.97 - samples/sec: 3283.44 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:07:29,125 epoch 10 - iter 60/121 - loss 0.02298155 - time (sec): 3.72 - samples/sec: 3291.77 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:07:29,887 epoch 10 - iter 72/121 - loss 0.02128602 - time (sec): 4.49 - samples/sec: 3274.34 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:07:30,711 epoch 10 - iter 84/121 - loss 0.01849297 - time (sec): 5.31 - samples/sec: 3208.06 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:07:31,499 epoch 10 - iter 96/121 - loss 0.01788888 - time (sec): 6.10 - samples/sec: 3210.40 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:07:32,233 epoch 10 - iter 108/121 - loss 0.01667339 - time (sec): 6.83 - samples/sec: 3240.89 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:07:32,942 epoch 10 - iter 120/121 - loss 0.01640886 - time (sec): 7.54 - samples/sec: 3261.23 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 11:07:32,993 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:32,994 EPOCH 10 done: loss 0.0164 - lr: 0.000000 | |
| 2023-10-17 11:07:33,747 DEV : loss 0.20607183873653412 - f1-score (micro avg) 0.8337 | |
| 2023-10-17 11:07:34,222 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:07:34,223 Loading model from best epoch ... | |
| 2023-10-17 11:07:35,639 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-17 11:07:36,811 | |
| Results: | |
| - F-score (micro) 0.8197 | |
| - F-score (macro) 0.5577 | |
| - Accuracy 0.716 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8500 0.8561 0.8530 139 | |
| scope 0.8657 0.8992 0.8821 129 | |
| work 0.6632 0.7875 0.7200 80 | |
| loc 0.6667 0.2222 0.3333 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8065 0.8333 0.8197 360 | |
| macro avg 0.6091 0.5530 0.5577 360 | |
| weighted avg 0.8024 0.8333 0.8138 360 | |
| 2023-10-17 11:07:36,811 ---------------------------------------------------------------------------------------------------- | |