| 2023-10-17 09:36:26,101 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,102 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 09:36:26,102 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,102 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-17 09:36:26,102 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,102 Train: 1214 sentences | |
| 2023-10-17 09:36:26,102 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 09:36:26,102 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Training Params: | |
| 2023-10-17 09:36:26,103 - learning_rate: "3e-05" | |
| 2023-10-17 09:36:26,103 - mini_batch_size: "8" | |
| 2023-10-17 09:36:26,103 - max_epochs: "10" | |
| 2023-10-17 09:36:26,103 - shuffle: "True" | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Plugins: | |
| 2023-10-17 09:36:26,103 - TensorboardLogger | |
| 2023-10-17 09:36:26,103 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 09:36:26,103 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Computation: | |
| 2023-10-17 09:36:26,103 - compute on device: cuda:0 | |
| 2023-10-17 09:36:26,103 - embedding storage: none | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:26,103 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 09:36:26,932 epoch 1 - iter 15/152 - loss 3.35898714 - time (sec): 0.83 - samples/sec: 3632.65 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:36:27,788 epoch 1 - iter 30/152 - loss 3.02212465 - time (sec): 1.68 - samples/sec: 3534.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:36:28,663 epoch 1 - iter 45/152 - loss 2.45612354 - time (sec): 2.56 - samples/sec: 3670.98 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:36:29,535 epoch 1 - iter 60/152 - loss 1.99749694 - time (sec): 3.43 - samples/sec: 3698.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:36:30,327 epoch 1 - iter 75/152 - loss 1.73641236 - time (sec): 4.22 - samples/sec: 3660.69 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:36:31,127 epoch 1 - iter 90/152 - loss 1.52634135 - time (sec): 5.02 - samples/sec: 3636.89 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:36:32,009 epoch 1 - iter 105/152 - loss 1.36260959 - time (sec): 5.90 - samples/sec: 3626.11 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:36:32,868 epoch 1 - iter 120/152 - loss 1.24452509 - time (sec): 6.76 - samples/sec: 3614.67 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:36:33,728 epoch 1 - iter 135/152 - loss 1.14524406 - time (sec): 7.62 - samples/sec: 3601.31 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:36:34,591 epoch 1 - iter 150/152 - loss 1.05621100 - time (sec): 8.49 - samples/sec: 3611.55 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:36:34,694 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:34,694 EPOCH 1 done: loss 1.0473 - lr: 0.000029 | |
| 2023-10-17 09:36:35,450 DEV : loss 0.23443591594696045 - f1-score (micro avg) 0.5184 | |
| 2023-10-17 09:36:35,456 saving best model | |
| 2023-10-17 09:36:35,781 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:36,672 epoch 2 - iter 15/152 - loss 0.24169486 - time (sec): 0.89 - samples/sec: 3386.25 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:36:37,515 epoch 2 - iter 30/152 - loss 0.23715876 - time (sec): 1.73 - samples/sec: 3525.57 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:36:38,343 epoch 2 - iter 45/152 - loss 0.21104596 - time (sec): 2.56 - samples/sec: 3598.89 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:36:39,220 epoch 2 - iter 60/152 - loss 0.20097868 - time (sec): 3.44 - samples/sec: 3562.82 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:36:40,138 epoch 2 - iter 75/152 - loss 0.19466306 - time (sec): 4.35 - samples/sec: 3541.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:36:40,980 epoch 2 - iter 90/152 - loss 0.18556494 - time (sec): 5.20 - samples/sec: 3523.73 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:36:41,807 epoch 2 - iter 105/152 - loss 0.18053346 - time (sec): 6.02 - samples/sec: 3513.61 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:36:42,670 epoch 2 - iter 120/152 - loss 0.18092533 - time (sec): 6.89 - samples/sec: 3560.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:36:43,530 epoch 2 - iter 135/152 - loss 0.17278558 - time (sec): 7.75 - samples/sec: 3580.87 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:36:44,376 epoch 2 - iter 150/152 - loss 0.17079577 - time (sec): 8.59 - samples/sec: 3571.90 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:36:44,475 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:44,475 EPOCH 2 done: loss 0.1696 - lr: 0.000027 | |
| 2023-10-17 09:36:45,392 DEV : loss 0.13970671594142914 - f1-score (micro avg) 0.7763 | |
| 2023-10-17 09:36:45,398 saving best model | |
| 2023-10-17 09:36:45,846 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:46,710 epoch 3 - iter 15/152 - loss 0.09358125 - time (sec): 0.86 - samples/sec: 3368.12 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:36:47,568 epoch 3 - iter 30/152 - loss 0.09697182 - time (sec): 1.72 - samples/sec: 3416.85 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:36:48,437 epoch 3 - iter 45/152 - loss 0.09722146 - time (sec): 2.59 - samples/sec: 3381.80 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:36:49,280 epoch 3 - iter 60/152 - loss 0.09059189 - time (sec): 3.43 - samples/sec: 3414.31 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:36:50,175 epoch 3 - iter 75/152 - loss 0.08518541 - time (sec): 4.33 - samples/sec: 3498.34 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:36:51,076 epoch 3 - iter 90/152 - loss 0.09661947 - time (sec): 5.23 - samples/sec: 3505.34 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:36:51,931 epoch 3 - iter 105/152 - loss 0.10037094 - time (sec): 6.08 - samples/sec: 3524.40 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:36:52,760 epoch 3 - iter 120/152 - loss 0.09624042 - time (sec): 6.91 - samples/sec: 3540.82 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:36:53,578 epoch 3 - iter 135/152 - loss 0.09198926 - time (sec): 7.73 - samples/sec: 3538.43 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:36:54,489 epoch 3 - iter 150/152 - loss 0.08944775 - time (sec): 8.64 - samples/sec: 3547.63 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:36:54,591 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:54,591 EPOCH 3 done: loss 0.0897 - lr: 0.000023 | |
| 2023-10-17 09:36:55,531 DEV : loss 0.13742879033088684 - f1-score (micro avg) 0.8245 | |
| 2023-10-17 09:36:55,538 saving best model | |
| 2023-10-17 09:36:56,022 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:36:56,879 epoch 4 - iter 15/152 - loss 0.03956629 - time (sec): 0.86 - samples/sec: 3634.93 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:36:57,724 epoch 4 - iter 30/152 - loss 0.05596716 - time (sec): 1.70 - samples/sec: 3605.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:36:58,546 epoch 4 - iter 45/152 - loss 0.06316567 - time (sec): 2.52 - samples/sec: 3561.13 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:36:59,461 epoch 4 - iter 60/152 - loss 0.06216934 - time (sec): 3.44 - samples/sec: 3598.96 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:37:00,333 epoch 4 - iter 75/152 - loss 0.05941341 - time (sec): 4.31 - samples/sec: 3549.57 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:37:01,339 epoch 4 - iter 90/152 - loss 0.05979395 - time (sec): 5.32 - samples/sec: 3425.34 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:37:02,210 epoch 4 - iter 105/152 - loss 0.06163013 - time (sec): 6.19 - samples/sec: 3460.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:37:03,064 epoch 4 - iter 120/152 - loss 0.06016428 - time (sec): 7.04 - samples/sec: 3488.96 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:37:03,947 epoch 4 - iter 135/152 - loss 0.06300382 - time (sec): 7.92 - samples/sec: 3490.01 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:37:04,785 epoch 4 - iter 150/152 - loss 0.06228708 - time (sec): 8.76 - samples/sec: 3504.62 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:37:04,891 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:04,891 EPOCH 4 done: loss 0.0623 - lr: 0.000020 | |
| 2023-10-17 09:37:05,831 DEV : loss 0.1494779735803604 - f1-score (micro avg) 0.8282 | |
| 2023-10-17 09:37:05,837 saving best model | |
| 2023-10-17 09:37:06,323 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:07,248 epoch 5 - iter 15/152 - loss 0.05545218 - time (sec): 0.92 - samples/sec: 3654.78 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:37:08,170 epoch 5 - iter 30/152 - loss 0.04238699 - time (sec): 1.85 - samples/sec: 3436.50 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:37:09,096 epoch 5 - iter 45/152 - loss 0.04725187 - time (sec): 2.77 - samples/sec: 3492.98 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:37:09,967 epoch 5 - iter 60/152 - loss 0.04013426 - time (sec): 3.64 - samples/sec: 3489.30 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:37:10,857 epoch 5 - iter 75/152 - loss 0.03634974 - time (sec): 4.53 - samples/sec: 3481.04 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:37:11,741 epoch 5 - iter 90/152 - loss 0.03798504 - time (sec): 5.42 - samples/sec: 3448.37 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:37:12,629 epoch 5 - iter 105/152 - loss 0.03712308 - time (sec): 6.30 - samples/sec: 3439.13 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:37:13,452 epoch 5 - iter 120/152 - loss 0.04227013 - time (sec): 7.13 - samples/sec: 3428.06 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:37:14,334 epoch 5 - iter 135/152 - loss 0.04112595 - time (sec): 8.01 - samples/sec: 3442.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:37:15,191 epoch 5 - iter 150/152 - loss 0.04377806 - time (sec): 8.87 - samples/sec: 3462.64 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:37:15,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:15,289 EPOCH 5 done: loss 0.0436 - lr: 0.000017 | |
| 2023-10-17 09:37:16,234 DEV : loss 0.1704065203666687 - f1-score (micro avg) 0.8434 | |
| 2023-10-17 09:37:16,241 saving best model | |
| 2023-10-17 09:37:16,697 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:17,588 epoch 6 - iter 15/152 - loss 0.04317289 - time (sec): 0.88 - samples/sec: 3518.38 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:37:18,416 epoch 6 - iter 30/152 - loss 0.03691780 - time (sec): 1.71 - samples/sec: 3462.62 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:37:19,300 epoch 6 - iter 45/152 - loss 0.03511291 - time (sec): 2.59 - samples/sec: 3430.87 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:37:20,183 epoch 6 - iter 60/152 - loss 0.03753407 - time (sec): 3.48 - samples/sec: 3432.90 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:37:21,052 epoch 6 - iter 75/152 - loss 0.03621585 - time (sec): 4.34 - samples/sec: 3482.89 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:37:21,890 epoch 6 - iter 90/152 - loss 0.03430368 - time (sec): 5.18 - samples/sec: 3495.93 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:37:22,787 epoch 6 - iter 105/152 - loss 0.04059258 - time (sec): 6.08 - samples/sec: 3504.70 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:37:23,646 epoch 6 - iter 120/152 - loss 0.03799652 - time (sec): 6.94 - samples/sec: 3498.07 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:37:24,486 epoch 6 - iter 135/152 - loss 0.03759158 - time (sec): 7.78 - samples/sec: 3520.77 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:37:25,379 epoch 6 - iter 150/152 - loss 0.03898740 - time (sec): 8.67 - samples/sec: 3535.40 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:37:25,472 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:25,472 EPOCH 6 done: loss 0.0392 - lr: 0.000013 | |
| 2023-10-17 09:37:26,445 DEV : loss 0.17794041335582733 - f1-score (micro avg) 0.839 | |
| 2023-10-17 09:37:26,453 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:27,356 epoch 7 - iter 15/152 - loss 0.01465965 - time (sec): 0.90 - samples/sec: 3112.14 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:37:28,224 epoch 7 - iter 30/152 - loss 0.01342575 - time (sec): 1.77 - samples/sec: 3298.14 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:37:29,082 epoch 7 - iter 45/152 - loss 0.01948712 - time (sec): 2.63 - samples/sec: 3395.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:37:29,937 epoch 7 - iter 60/152 - loss 0.02268211 - time (sec): 3.48 - samples/sec: 3401.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:37:30,759 epoch 7 - iter 75/152 - loss 0.02031838 - time (sec): 4.30 - samples/sec: 3481.55 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:37:31,605 epoch 7 - iter 90/152 - loss 0.01853079 - time (sec): 5.15 - samples/sec: 3495.72 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:37:32,460 epoch 7 - iter 105/152 - loss 0.02027409 - time (sec): 6.00 - samples/sec: 3505.39 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:37:33,390 epoch 7 - iter 120/152 - loss 0.02176488 - time (sec): 6.93 - samples/sec: 3522.89 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:37:34,284 epoch 7 - iter 135/152 - loss 0.02344965 - time (sec): 7.83 - samples/sec: 3542.75 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:37:35,098 epoch 7 - iter 150/152 - loss 0.02710869 - time (sec): 8.64 - samples/sec: 3544.50 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:37:35,204 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:35,204 EPOCH 7 done: loss 0.0273 - lr: 0.000010 | |
| 2023-10-17 09:37:36,183 DEV : loss 0.18339850008487701 - f1-score (micro avg) 0.8421 | |
| 2023-10-17 09:37:36,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:37,052 epoch 8 - iter 15/152 - loss 0.01167967 - time (sec): 0.86 - samples/sec: 3917.73 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:37:37,918 epoch 8 - iter 30/152 - loss 0.01022357 - time (sec): 1.73 - samples/sec: 3699.27 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:37:38,811 epoch 8 - iter 45/152 - loss 0.01816524 - time (sec): 2.62 - samples/sec: 3626.56 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:37:39,640 epoch 8 - iter 60/152 - loss 0.01610311 - time (sec): 3.45 - samples/sec: 3532.16 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:37:40,532 epoch 8 - iter 75/152 - loss 0.01399500 - time (sec): 4.34 - samples/sec: 3577.81 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:37:41,328 epoch 8 - iter 90/152 - loss 0.01508785 - time (sec): 5.14 - samples/sec: 3587.85 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:37:42,196 epoch 8 - iter 105/152 - loss 0.01972651 - time (sec): 6.00 - samples/sec: 3563.80 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:37:43,084 epoch 8 - iter 120/152 - loss 0.02152978 - time (sec): 6.89 - samples/sec: 3557.71 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:37:43,960 epoch 8 - iter 135/152 - loss 0.02068304 - time (sec): 7.77 - samples/sec: 3555.58 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:37:44,816 epoch 8 - iter 150/152 - loss 0.02075768 - time (sec): 8.62 - samples/sec: 3550.64 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:37:44,924 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:44,924 EPOCH 8 done: loss 0.0205 - lr: 0.000007 | |
| 2023-10-17 09:37:45,870 DEV : loss 0.19150298833847046 - f1-score (micro avg) 0.8436 | |
| 2023-10-17 09:37:45,876 saving best model | |
| 2023-10-17 09:37:46,342 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:47,201 epoch 9 - iter 15/152 - loss 0.01688113 - time (sec): 0.86 - samples/sec: 3585.02 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:37:48,035 epoch 9 - iter 30/152 - loss 0.00892330 - time (sec): 1.69 - samples/sec: 3535.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:37:48,912 epoch 9 - iter 45/152 - loss 0.01524391 - time (sec): 2.57 - samples/sec: 3566.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:37:49,759 epoch 9 - iter 60/152 - loss 0.01537673 - time (sec): 3.42 - samples/sec: 3525.94 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:37:50,636 epoch 9 - iter 75/152 - loss 0.01573533 - time (sec): 4.29 - samples/sec: 3549.94 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:37:51,497 epoch 9 - iter 90/152 - loss 0.01569790 - time (sec): 5.15 - samples/sec: 3561.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:37:52,387 epoch 9 - iter 105/152 - loss 0.01417753 - time (sec): 6.04 - samples/sec: 3527.35 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:37:53,184 epoch 9 - iter 120/152 - loss 0.01521950 - time (sec): 6.84 - samples/sec: 3546.82 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:37:54,034 epoch 9 - iter 135/152 - loss 0.01501499 - time (sec): 7.69 - samples/sec: 3567.29 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:37:54,900 epoch 9 - iter 150/152 - loss 0.01607239 - time (sec): 8.56 - samples/sec: 3582.08 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:37:55,000 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:55,000 EPOCH 9 done: loss 0.0159 - lr: 0.000004 | |
| 2023-10-17 09:37:55,939 DEV : loss 0.19435930252075195 - f1-score (micro avg) 0.8479 | |
| 2023-10-17 09:37:55,945 saving best model | |
| 2023-10-17 09:37:56,410 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:37:57,241 epoch 10 - iter 15/152 - loss 0.01021824 - time (sec): 0.83 - samples/sec: 3542.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:37:58,114 epoch 10 - iter 30/152 - loss 0.01670466 - time (sec): 1.70 - samples/sec: 3509.32 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:37:58,988 epoch 10 - iter 45/152 - loss 0.01789261 - time (sec): 2.58 - samples/sec: 3597.82 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:37:59,849 epoch 10 - iter 60/152 - loss 0.02154099 - time (sec): 3.44 - samples/sec: 3547.31 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:38:00,669 epoch 10 - iter 75/152 - loss 0.01827148 - time (sec): 4.26 - samples/sec: 3556.10 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:38:01,580 epoch 10 - iter 90/152 - loss 0.01773986 - time (sec): 5.17 - samples/sec: 3509.28 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:38:02,467 epoch 10 - iter 105/152 - loss 0.01550723 - time (sec): 6.06 - samples/sec: 3526.34 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:38:03,330 epoch 10 - iter 120/152 - loss 0.01531261 - time (sec): 6.92 - samples/sec: 3517.18 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:38:04,227 epoch 10 - iter 135/152 - loss 0.01532677 - time (sec): 7.82 - samples/sec: 3505.78 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:38:05,120 epoch 10 - iter 150/152 - loss 0.01646360 - time (sec): 8.71 - samples/sec: 3515.50 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:38:05,232 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:38:05,232 EPOCH 10 done: loss 0.0164 - lr: 0.000000 | |
| 2023-10-17 09:38:06,206 DEV : loss 0.19792957603931427 - f1-score (micro avg) 0.8419 | |
| 2023-10-17 09:38:06,568 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:38:06,570 Loading model from best epoch ... | |
| 2023-10-17 09:38:08,115 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-17 09:38:09,020 | |
| Results: | |
| - F-score (micro) 0.8368 | |
| - F-score (macro) 0.67 | |
| - Accuracy 0.7282 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7898 0.8212 0.8052 151 | |
| work 0.7810 0.8632 0.8200 95 | |
| pers 0.8932 0.9583 0.9246 96 | |
| loc 1.0000 0.6667 0.8000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8130 0.8621 0.8368 348 | |
| macro avg 0.6928 0.6619 0.6700 348 | |
| weighted avg 0.8109 0.8621 0.8352 348 | |
| 2023-10-17 09:38:09,021 ---------------------------------------------------------------------------------------------------- | |