| 2023-10-17 18:22:56,458 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,460 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 18:22:56,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,460 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-17 18:22:56,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,460 Train: 3575 sentences | |
| 2023-10-17 18:22:56,460 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:22:56,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,460 Training Params: | |
| 2023-10-17 18:22:56,461 - learning_rate: "3e-05" | |
| 2023-10-17 18:22:56,461 - mini_batch_size: "8" | |
| 2023-10-17 18:22:56,461 - max_epochs: "10" | |
| 2023-10-17 18:22:56,461 - shuffle: "True" | |
| 2023-10-17 18:22:56,461 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,461 Plugins: | |
| 2023-10-17 18:22:56,461 - TensorboardLogger | |
| 2023-10-17 18:22:56,461 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:22:56,461 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,461 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:22:56,461 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:22:56,461 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,461 Computation: | |
| 2023-10-17 18:22:56,461 - compute on device: cuda:0 | |
| 2023-10-17 18:22:56,461 - embedding storage: none | |
| 2023-10-17 18:22:56,462 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,462 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:22:56,462 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,462 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:56,462 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:23:00,459 epoch 1 - iter 44/447 - loss 3.47864138 - time (sec): 4.00 - samples/sec: 2030.88 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:23:04,581 epoch 1 - iter 88/447 - loss 2.55710229 - time (sec): 8.12 - samples/sec: 2032.52 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:23:08,886 epoch 1 - iter 132/447 - loss 1.86053232 - time (sec): 12.42 - samples/sec: 2020.82 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:23:12,858 epoch 1 - iter 176/447 - loss 1.50695410 - time (sec): 16.39 - samples/sec: 2015.45 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:23:17,209 epoch 1 - iter 220/447 - loss 1.29221222 - time (sec): 20.74 - samples/sec: 1991.95 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:23:21,488 epoch 1 - iter 264/447 - loss 1.14030675 - time (sec): 25.02 - samples/sec: 1988.13 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:23:25,570 epoch 1 - iter 308/447 - loss 1.02286371 - time (sec): 29.11 - samples/sec: 1989.96 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:23:29,803 epoch 1 - iter 352/447 - loss 0.92044886 - time (sec): 33.34 - samples/sec: 2001.84 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:23:33,922 epoch 1 - iter 396/447 - loss 0.83590367 - time (sec): 37.46 - samples/sec: 2028.50 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:23:38,350 epoch 1 - iter 440/447 - loss 0.77269581 - time (sec): 41.89 - samples/sec: 2032.07 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:23:38,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:38,986 EPOCH 1 done: loss 0.7632 - lr: 0.000029 | |
| 2023-10-17 18:23:45,635 DEV : loss 0.1704760640859604 - f1-score (micro avg) 0.5929 | |
| 2023-10-17 18:23:45,691 saving best model | |
| 2023-10-17 18:23:46,230 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:50,723 epoch 2 - iter 44/447 - loss 0.19666925 - time (sec): 4.49 - samples/sec: 2213.33 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:23:55,147 epoch 2 - iter 88/447 - loss 0.19892337 - time (sec): 8.91 - samples/sec: 2059.19 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:23:59,486 epoch 2 - iter 132/447 - loss 0.18893141 - time (sec): 13.25 - samples/sec: 1977.00 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:24:03,659 epoch 2 - iter 176/447 - loss 0.17899012 - time (sec): 17.43 - samples/sec: 1995.89 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:24:07,581 epoch 2 - iter 220/447 - loss 0.17159262 - time (sec): 21.35 - samples/sec: 2002.25 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:24:11,986 epoch 2 - iter 264/447 - loss 0.16684092 - time (sec): 25.75 - samples/sec: 2016.70 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:24:15,928 epoch 2 - iter 308/447 - loss 0.16348986 - time (sec): 29.70 - samples/sec: 2029.33 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:24:20,022 epoch 2 - iter 352/447 - loss 0.16073205 - time (sec): 33.79 - samples/sec: 2035.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:24:24,189 epoch 2 - iter 396/447 - loss 0.15953827 - time (sec): 37.96 - samples/sec: 2024.86 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:24:28,341 epoch 2 - iter 440/447 - loss 0.15682018 - time (sec): 42.11 - samples/sec: 2024.85 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:24:28,988 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:28,988 EPOCH 2 done: loss 0.1561 - lr: 0.000027 | |
| 2023-10-17 18:24:40,469 DEV : loss 0.13275983929634094 - f1-score (micro avg) 0.7155 | |
| 2023-10-17 18:24:40,525 saving best model | |
| 2023-10-17 18:24:41,904 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:45,996 epoch 3 - iter 44/447 - loss 0.10231429 - time (sec): 4.09 - samples/sec: 2070.71 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:24:50,353 epoch 3 - iter 88/447 - loss 0.09837450 - time (sec): 8.45 - samples/sec: 1960.79 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:24:54,770 epoch 3 - iter 132/447 - loss 0.08928842 - time (sec): 12.86 - samples/sec: 1997.73 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:24:59,020 epoch 3 - iter 176/447 - loss 0.08587204 - time (sec): 17.11 - samples/sec: 1990.85 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:25:03,231 epoch 3 - iter 220/447 - loss 0.08780169 - time (sec): 21.32 - samples/sec: 1994.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:25:07,773 epoch 3 - iter 264/447 - loss 0.08849332 - time (sec): 25.87 - samples/sec: 2014.73 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:25:11,823 epoch 3 - iter 308/447 - loss 0.08785527 - time (sec): 29.91 - samples/sec: 2011.18 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:25:15,770 epoch 3 - iter 352/447 - loss 0.08793258 - time (sec): 33.86 - samples/sec: 2015.16 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:25:19,769 epoch 3 - iter 396/447 - loss 0.08667014 - time (sec): 37.86 - samples/sec: 2022.88 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:25:24,022 epoch 3 - iter 440/447 - loss 0.08804741 - time (sec): 42.11 - samples/sec: 2022.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:25:24,684 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:24,684 EPOCH 3 done: loss 0.0873 - lr: 0.000023 | |
| 2023-10-17 18:25:36,642 DEV : loss 0.12239837646484375 - f1-score (micro avg) 0.7448 | |
| 2023-10-17 18:25:36,699 saving best model | |
| 2023-10-17 18:25:38,097 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:42,133 epoch 4 - iter 44/447 - loss 0.04228104 - time (sec): 4.03 - samples/sec: 1847.41 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:25:46,467 epoch 4 - iter 88/447 - loss 0.04192572 - time (sec): 8.37 - samples/sec: 1942.68 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:25:50,981 epoch 4 - iter 132/447 - loss 0.04579833 - time (sec): 12.88 - samples/sec: 1997.86 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:25:55,113 epoch 4 - iter 176/447 - loss 0.04637274 - time (sec): 17.01 - samples/sec: 2023.77 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:25:59,247 epoch 4 - iter 220/447 - loss 0.05171639 - time (sec): 21.15 - samples/sec: 2023.94 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:26:03,672 epoch 4 - iter 264/447 - loss 0.04922290 - time (sec): 25.57 - samples/sec: 2008.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:26:07,840 epoch 4 - iter 308/447 - loss 0.05116720 - time (sec): 29.74 - samples/sec: 2012.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:26:12,058 epoch 4 - iter 352/447 - loss 0.05417139 - time (sec): 33.96 - samples/sec: 2016.53 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:26:16,379 epoch 4 - iter 396/447 - loss 0.05412233 - time (sec): 38.28 - samples/sec: 2015.16 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:26:20,315 epoch 4 - iter 440/447 - loss 0.05304027 - time (sec): 42.21 - samples/sec: 2025.18 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:26:20,936 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:20,936 EPOCH 4 done: loss 0.0528 - lr: 0.000020 | |
| 2023-10-17 18:26:32,048 DEV : loss 0.15048351883888245 - f1-score (micro avg) 0.7634 | |
| 2023-10-17 18:26:32,112 saving best model | |
| 2023-10-17 18:26:33,525 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:37,619 epoch 5 - iter 44/447 - loss 0.03447358 - time (sec): 4.09 - samples/sec: 2087.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:26:41,725 epoch 5 - iter 88/447 - loss 0.03612779 - time (sec): 8.20 - samples/sec: 2077.75 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:26:46,105 epoch 5 - iter 132/447 - loss 0.03196480 - time (sec): 12.57 - samples/sec: 2104.83 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:26:50,102 epoch 5 - iter 176/447 - loss 0.03188731 - time (sec): 16.57 - samples/sec: 2098.67 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:26:54,032 epoch 5 - iter 220/447 - loss 0.03579741 - time (sec): 20.50 - samples/sec: 2075.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:26:58,319 epoch 5 - iter 264/447 - loss 0.03656570 - time (sec): 24.79 - samples/sec: 2059.65 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:27:02,597 epoch 5 - iter 308/447 - loss 0.03466670 - time (sec): 29.07 - samples/sec: 2049.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:27:06,755 epoch 5 - iter 352/447 - loss 0.03453502 - time (sec): 33.23 - samples/sec: 2034.28 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:27:10,873 epoch 5 - iter 396/447 - loss 0.03511712 - time (sec): 37.34 - samples/sec: 2026.61 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:27:14,974 epoch 5 - iter 440/447 - loss 0.03542620 - time (sec): 41.44 - samples/sec: 2035.88 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:27:16,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:16,386 EPOCH 5 done: loss 0.0350 - lr: 0.000017 | |
| 2023-10-17 18:27:27,531 DEV : loss 0.1623251587152481 - f1-score (micro avg) 0.7844 | |
| 2023-10-17 18:27:27,594 saving best model | |
| 2023-10-17 18:27:29,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:33,401 epoch 6 - iter 44/447 - loss 0.01509559 - time (sec): 4.33 - samples/sec: 2206.74 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:27:37,584 epoch 6 - iter 88/447 - loss 0.01823388 - time (sec): 8.52 - samples/sec: 2079.31 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:27:41,590 epoch 6 - iter 132/447 - loss 0.01937156 - time (sec): 12.52 - samples/sec: 2051.81 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:27:45,621 epoch 6 - iter 176/447 - loss 0.01793456 - time (sec): 16.55 - samples/sec: 2041.66 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:27:49,595 epoch 6 - iter 220/447 - loss 0.01946342 - time (sec): 20.53 - samples/sec: 2042.92 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:27:53,724 epoch 6 - iter 264/447 - loss 0.02107942 - time (sec): 24.66 - samples/sec: 2059.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:27:57,943 epoch 6 - iter 308/447 - loss 0.02236597 - time (sec): 28.88 - samples/sec: 2051.73 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:28:02,225 epoch 6 - iter 352/447 - loss 0.02262167 - time (sec): 33.16 - samples/sec: 2052.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:28:06,722 epoch 6 - iter 396/447 - loss 0.02326928 - time (sec): 37.66 - samples/sec: 2057.37 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:28:10,793 epoch 6 - iter 440/447 - loss 0.02302421 - time (sec): 41.73 - samples/sec: 2049.48 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:28:11,421 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:11,421 EPOCH 6 done: loss 0.0230 - lr: 0.000013 | |
| 2023-10-17 18:28:22,898 DEV : loss 0.18466560542583466 - f1-score (micro avg) 0.7896 | |
| 2023-10-17 18:28:22,963 saving best model | |
| 2023-10-17 18:28:24,375 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:28,484 epoch 7 - iter 44/447 - loss 0.01071602 - time (sec): 4.10 - samples/sec: 2124.81 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:28:32,529 epoch 7 - iter 88/447 - loss 0.01722305 - time (sec): 8.15 - samples/sec: 2079.46 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:28:36,648 epoch 7 - iter 132/447 - loss 0.01562625 - time (sec): 12.27 - samples/sec: 2048.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:28:40,896 epoch 7 - iter 176/447 - loss 0.01506616 - time (sec): 16.52 - samples/sec: 2039.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:28:45,030 epoch 7 - iter 220/447 - loss 0.01543355 - time (sec): 20.65 - samples/sec: 2035.10 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:28:49,087 epoch 7 - iter 264/447 - loss 0.01583832 - time (sec): 24.71 - samples/sec: 2030.05 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:28:53,199 epoch 7 - iter 308/447 - loss 0.01579137 - time (sec): 28.82 - samples/sec: 2038.85 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:28:57,215 epoch 7 - iter 352/447 - loss 0.01554866 - time (sec): 32.84 - samples/sec: 2025.54 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:29:01,841 epoch 7 - iter 396/447 - loss 0.01580312 - time (sec): 37.46 - samples/sec: 2044.11 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:29:06,083 epoch 7 - iter 440/447 - loss 0.01627817 - time (sec): 41.70 - samples/sec: 2038.44 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:29:06,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:29:06,720 EPOCH 7 done: loss 0.0160 - lr: 0.000010 | |
| 2023-10-17 18:29:18,210 DEV : loss 0.1884232461452484 - f1-score (micro avg) 0.7829 | |
| 2023-10-17 18:29:18,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:29:22,356 epoch 8 - iter 44/447 - loss 0.00844862 - time (sec): 4.08 - samples/sec: 1946.01 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:29:26,631 epoch 8 - iter 88/447 - loss 0.00991015 - time (sec): 8.36 - samples/sec: 1976.96 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:29:31,495 epoch 8 - iter 132/447 - loss 0.00813816 - time (sec): 13.22 - samples/sec: 2024.96 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:29:35,485 epoch 8 - iter 176/447 - loss 0.00781880 - time (sec): 17.21 - samples/sec: 2003.52 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:29:39,968 epoch 8 - iter 220/447 - loss 0.00905071 - time (sec): 21.69 - samples/sec: 1973.23 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:29:44,408 epoch 8 - iter 264/447 - loss 0.00964617 - time (sec): 26.13 - samples/sec: 1955.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:29:48,891 epoch 8 - iter 308/447 - loss 0.01023682 - time (sec): 30.62 - samples/sec: 1964.53 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:29:53,138 epoch 8 - iter 352/447 - loss 0.01126515 - time (sec): 34.86 - samples/sec: 1964.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:29:57,471 epoch 8 - iter 396/447 - loss 0.01068923 - time (sec): 39.20 - samples/sec: 1947.11 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:30:01,738 epoch 8 - iter 440/447 - loss 0.01036581 - time (sec): 43.46 - samples/sec: 1966.25 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:30:02,342 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:30:02,342 EPOCH 8 done: loss 0.0102 - lr: 0.000007 | |
| 2023-10-17 18:30:14,071 DEV : loss 0.20807437598705292 - f1-score (micro avg) 0.8002 | |
| 2023-10-17 18:30:14,141 saving best model | |
| 2023-10-17 18:30:15,594 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:30:19,632 epoch 9 - iter 44/447 - loss 0.01126364 - time (sec): 4.03 - samples/sec: 1945.90 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:30:23,938 epoch 9 - iter 88/447 - loss 0.00956380 - time (sec): 8.34 - samples/sec: 1948.16 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:30:28,056 epoch 9 - iter 132/447 - loss 0.00736466 - time (sec): 12.46 - samples/sec: 1977.24 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:30:32,761 epoch 9 - iter 176/447 - loss 0.00652351 - time (sec): 17.16 - samples/sec: 1987.56 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:30:36,806 epoch 9 - iter 220/447 - loss 0.00638266 - time (sec): 21.21 - samples/sec: 1966.54 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:30:40,969 epoch 9 - iter 264/447 - loss 0.00625169 - time (sec): 25.37 - samples/sec: 1963.44 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:30:45,081 epoch 9 - iter 308/447 - loss 0.00658656 - time (sec): 29.48 - samples/sec: 1972.54 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:30:49,485 epoch 9 - iter 352/447 - loss 0.00665066 - time (sec): 33.89 - samples/sec: 1988.90 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:30:54,117 epoch 9 - iter 396/447 - loss 0.00700973 - time (sec): 38.52 - samples/sec: 1987.54 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:30:58,353 epoch 9 - iter 440/447 - loss 0.00692549 - time (sec): 42.75 - samples/sec: 1996.72 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:30:58,976 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:30:58,977 EPOCH 9 done: loss 0.0069 - lr: 0.000003 | |
| 2023-10-17 18:31:10,510 DEV : loss 0.20884786546230316 - f1-score (micro avg) 0.8053 | |
| 2023-10-17 18:31:10,590 saving best model | |
| 2023-10-17 18:31:12,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:31:16,504 epoch 10 - iter 44/447 - loss 0.00304434 - time (sec): 4.37 - samples/sec: 2074.87 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:31:21,479 epoch 10 - iter 88/447 - loss 0.00250309 - time (sec): 9.35 - samples/sec: 2027.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:31:25,867 epoch 10 - iter 132/447 - loss 0.00262760 - time (sec): 13.73 - samples/sec: 1988.83 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:31:29,989 epoch 10 - iter 176/447 - loss 0.00262202 - time (sec): 17.86 - samples/sec: 2011.63 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:31:34,089 epoch 10 - iter 220/447 - loss 0.00294347 - time (sec): 21.96 - samples/sec: 2004.03 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:31:38,444 epoch 10 - iter 264/447 - loss 0.00372192 - time (sec): 26.31 - samples/sec: 1990.88 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:31:42,924 epoch 10 - iter 308/447 - loss 0.00443006 - time (sec): 30.79 - samples/sec: 1961.30 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:31:47,821 epoch 10 - iter 352/447 - loss 0.00455511 - time (sec): 35.69 - samples/sec: 1910.52 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:31:52,601 epoch 10 - iter 396/447 - loss 0.00430018 - time (sec): 40.47 - samples/sec: 1890.24 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:31:56,738 epoch 10 - iter 440/447 - loss 0.00448107 - time (sec): 44.60 - samples/sec: 1909.00 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:31:57,429 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:31:57,429 EPOCH 10 done: loss 0.0044 - lr: 0.000000 | |
| 2023-10-17 18:32:08,477 DEV : loss 0.2179129272699356 - f1-score (micro avg) 0.8045 | |
| 2023-10-17 18:32:09,127 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:09,130 Loading model from best epoch ... | |
| 2023-10-17 18:32:11,833 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-17 18:32:19,302 | |
| Results: | |
| - F-score (micro) 0.7693 | |
| - F-score (macro) 0.706 | |
| - Accuracy 0.6448 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8632 0.8473 0.8552 596 | |
| pers 0.6787 0.7928 0.7313 333 | |
| org 0.5500 0.5833 0.5662 132 | |
| prod 0.6885 0.6364 0.6614 66 | |
| time 0.7391 0.6939 0.7158 49 | |
| micro avg 0.7551 0.7840 0.7693 1176 | |
| macro avg 0.7039 0.7107 0.7060 1176 | |
| weighted avg 0.7608 0.7840 0.7710 1176 | |
| 2023-10-17 18:32:19,303 ---------------------------------------------------------------------------------------------------- | |