| 2023-10-17 17:34:24,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,573 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 17:34:24,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,573 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences | |
| - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator | |
| 2023-10-17 17:34:24,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,573 Train: 14465 sentences | |
| 2023-10-17 17:34:24,574 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Training Params: | |
| 2023-10-17 17:34:24,574 - learning_rate: "3e-05" | |
| 2023-10-17 17:34:24,574 - mini_batch_size: "4" | |
| 2023-10-17 17:34:24,574 - max_epochs: "10" | |
| 2023-10-17 17:34:24,574 - shuffle: "True" | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Plugins: | |
| 2023-10-17 17:34:24,574 - TensorboardLogger | |
| 2023-10-17 17:34:24,574 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 17:34:24,574 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Computation: | |
| 2023-10-17 17:34:24,574 - compute on device: cuda:0 | |
| 2023-10-17 17:34:24,574 - embedding storage: none | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:24,574 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 17:34:46,275 epoch 1 - iter 361/3617 - loss 1.76323200 - time (sec): 21.70 - samples/sec: 1673.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 17:35:08,329 epoch 1 - iter 722/3617 - loss 0.97719233 - time (sec): 43.75 - samples/sec: 1722.16 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 17:35:29,907 epoch 1 - iter 1083/3617 - loss 0.70773638 - time (sec): 65.33 - samples/sec: 1727.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 17:35:52,050 epoch 1 - iter 1444/3617 - loss 0.57489064 - time (sec): 87.47 - samples/sec: 1695.61 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:36:14,121 epoch 1 - iter 1805/3617 - loss 0.48505733 - time (sec): 109.55 - samples/sec: 1700.09 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:36:37,171 epoch 1 - iter 2166/3617 - loss 0.42060030 - time (sec): 132.60 - samples/sec: 1702.95 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:37:01,165 epoch 1 - iter 2527/3617 - loss 0.37530833 - time (sec): 156.59 - samples/sec: 1690.36 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:37:25,310 epoch 1 - iter 2888/3617 - loss 0.34369782 - time (sec): 180.73 - samples/sec: 1670.51 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:37:48,132 epoch 1 - iter 3249/3617 - loss 0.31710623 - time (sec): 203.56 - samples/sec: 1671.28 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:38:10,854 epoch 1 - iter 3610/3617 - loss 0.29710226 - time (sec): 226.28 - samples/sec: 1676.21 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 17:38:11,280 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:38:11,281 EPOCH 1 done: loss 0.2968 - lr: 0.000030 | |
| 2023-10-17 17:38:16,764 DEV : loss 0.11850162595510483 - f1-score (micro avg) 0.6174 | |
| 2023-10-17 17:38:16,803 saving best model | |
| 2023-10-17 17:38:17,296 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:38:40,328 epoch 2 - iter 361/3617 - loss 0.09918424 - time (sec): 23.03 - samples/sec: 1616.49 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 17:39:04,096 epoch 2 - iter 722/3617 - loss 0.09676193 - time (sec): 46.80 - samples/sec: 1648.48 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 17:39:27,692 epoch 2 - iter 1083/3617 - loss 0.09693761 - time (sec): 70.39 - samples/sec: 1636.68 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 17:39:49,271 epoch 2 - iter 1444/3617 - loss 0.09587484 - time (sec): 91.97 - samples/sec: 1657.05 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 17:40:10,888 epoch 2 - iter 1805/3617 - loss 0.09859513 - time (sec): 113.59 - samples/sec: 1677.81 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 17:40:32,627 epoch 2 - iter 2166/3617 - loss 0.09848297 - time (sec): 135.33 - samples/sec: 1691.64 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 17:40:54,465 epoch 2 - iter 2527/3617 - loss 0.09927284 - time (sec): 157.17 - samples/sec: 1706.12 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 17:41:16,183 epoch 2 - iter 2888/3617 - loss 0.10032862 - time (sec): 178.89 - samples/sec: 1700.71 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:41:38,079 epoch 2 - iter 3249/3617 - loss 0.09865403 - time (sec): 200.78 - samples/sec: 1696.74 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:42:00,005 epoch 2 - iter 3610/3617 - loss 0.09788190 - time (sec): 222.71 - samples/sec: 1702.38 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:42:00,414 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:42:00,414 EPOCH 2 done: loss 0.0979 - lr: 0.000027 | |
| 2023-10-17 17:42:07,594 DEV : loss 0.17727647721767426 - f1-score (micro avg) 0.643 | |
| 2023-10-17 17:42:07,634 saving best model | |
| 2023-10-17 17:42:08,219 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:42:30,667 epoch 3 - iter 361/3617 - loss 0.08733342 - time (sec): 22.45 - samples/sec: 1697.48 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 17:42:52,590 epoch 3 - iter 722/3617 - loss 0.07748900 - time (sec): 44.37 - samples/sec: 1700.86 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 17:43:14,458 epoch 3 - iter 1083/3617 - loss 0.07705997 - time (sec): 66.24 - samples/sec: 1715.97 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 17:43:36,400 epoch 3 - iter 1444/3617 - loss 0.08038163 - time (sec): 88.18 - samples/sec: 1709.07 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 17:43:58,644 epoch 3 - iter 1805/3617 - loss 0.08125813 - time (sec): 110.42 - samples/sec: 1713.75 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 17:44:20,982 epoch 3 - iter 2166/3617 - loss 0.08039951 - time (sec): 132.76 - samples/sec: 1706.36 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 17:44:43,036 epoch 3 - iter 2527/3617 - loss 0.07890125 - time (sec): 154.81 - samples/sec: 1724.23 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:45:04,833 epoch 3 - iter 2888/3617 - loss 0.07839290 - time (sec): 176.61 - samples/sec: 1728.39 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:45:26,509 epoch 3 - iter 3249/3617 - loss 0.07824675 - time (sec): 198.29 - samples/sec: 1726.88 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:45:48,660 epoch 3 - iter 3610/3617 - loss 0.07807987 - time (sec): 220.44 - samples/sec: 1720.66 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 17:45:49,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:45:49,124 EPOCH 3 done: loss 0.0781 - lr: 0.000023 | |
| 2023-10-17 17:45:55,465 DEV : loss 0.1918492317199707 - f1-score (micro avg) 0.6362 | |
| 2023-10-17 17:45:55,506 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:46:17,278 epoch 4 - iter 361/3617 - loss 0.05176746 - time (sec): 21.77 - samples/sec: 1799.54 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 17:46:39,033 epoch 4 - iter 722/3617 - loss 0.05224585 - time (sec): 43.53 - samples/sec: 1735.45 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 17:47:00,821 epoch 4 - iter 1083/3617 - loss 0.05378626 - time (sec): 65.31 - samples/sec: 1742.41 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 17:47:22,689 epoch 4 - iter 1444/3617 - loss 0.05274648 - time (sec): 87.18 - samples/sec: 1742.54 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 17:47:44,755 epoch 4 - iter 1805/3617 - loss 0.05592921 - time (sec): 109.25 - samples/sec: 1745.76 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 17:48:07,116 epoch 4 - iter 2166/3617 - loss 0.05602792 - time (sec): 131.61 - samples/sec: 1740.39 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:48:29,541 epoch 4 - iter 2527/3617 - loss 0.05664568 - time (sec): 154.03 - samples/sec: 1726.97 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:48:52,183 epoch 4 - iter 2888/3617 - loss 0.05768577 - time (sec): 176.68 - samples/sec: 1727.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:49:14,599 epoch 4 - iter 3249/3617 - loss 0.05774333 - time (sec): 199.09 - samples/sec: 1723.30 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 17:49:36,705 epoch 4 - iter 3610/3617 - loss 0.05929256 - time (sec): 221.20 - samples/sec: 1714.57 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 17:49:37,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:49:37,109 EPOCH 4 done: loss 0.0592 - lr: 0.000020 | |
| 2023-10-17 17:49:44,205 DEV : loss 0.28038784861564636 - f1-score (micro avg) 0.6488 | |
| 2023-10-17 17:49:44,246 saving best model | |
| 2023-10-17 17:49:44,837 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:50:07,317 epoch 5 - iter 361/3617 - loss 0.04250399 - time (sec): 22.48 - samples/sec: 1649.11 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 17:50:30,124 epoch 5 - iter 722/3617 - loss 0.03994872 - time (sec): 45.29 - samples/sec: 1656.90 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 17:50:47,769 epoch 5 - iter 1083/3617 - loss 0.04097508 - time (sec): 62.93 - samples/sec: 1792.79 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 17:51:05,557 epoch 5 - iter 1444/3617 - loss 0.04166533 - time (sec): 80.72 - samples/sec: 1875.53 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 17:51:23,292 epoch 5 - iter 1805/3617 - loss 0.04056126 - time (sec): 98.45 - samples/sec: 1921.77 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:51:41,012 epoch 5 - iter 2166/3617 - loss 0.04115083 - time (sec): 116.17 - samples/sec: 1961.30 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:51:58,679 epoch 5 - iter 2527/3617 - loss 0.04043008 - time (sec): 133.84 - samples/sec: 1982.69 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:52:18,914 epoch 5 - iter 2888/3617 - loss 0.04158883 - time (sec): 154.08 - samples/sec: 1968.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 17:52:40,783 epoch 5 - iter 3249/3617 - loss 0.04115229 - time (sec): 175.94 - samples/sec: 1934.98 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 17:53:02,556 epoch 5 - iter 3610/3617 - loss 0.04082194 - time (sec): 197.72 - samples/sec: 1917.98 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 17:53:02,991 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:53:02,991 EPOCH 5 done: loss 0.0408 - lr: 0.000017 | |
| 2023-10-17 17:53:09,293 DEV : loss 0.2820379436016083 - f1-score (micro avg) 0.6496 | |
| 2023-10-17 17:53:09,334 saving best model | |
| 2023-10-17 17:53:09,916 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:53:31,840 epoch 6 - iter 361/3617 - loss 0.02861178 - time (sec): 21.92 - samples/sec: 1722.24 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 17:53:53,637 epoch 6 - iter 722/3617 - loss 0.02877966 - time (sec): 43.72 - samples/sec: 1739.65 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 17:54:15,471 epoch 6 - iter 1083/3617 - loss 0.02687634 - time (sec): 65.55 - samples/sec: 1738.76 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 17:54:37,386 epoch 6 - iter 1444/3617 - loss 0.02735026 - time (sec): 87.47 - samples/sec: 1743.92 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:54:59,875 epoch 6 - iter 1805/3617 - loss 0.02863562 - time (sec): 109.96 - samples/sec: 1741.78 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:55:22,840 epoch 6 - iter 2166/3617 - loss 0.02936955 - time (sec): 132.92 - samples/sec: 1726.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:55:45,079 epoch 6 - iter 2527/3617 - loss 0.02920557 - time (sec): 155.16 - samples/sec: 1725.78 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 17:56:07,698 epoch 6 - iter 2888/3617 - loss 0.02871883 - time (sec): 177.78 - samples/sec: 1719.38 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 17:56:30,375 epoch 6 - iter 3249/3617 - loss 0.02854119 - time (sec): 200.46 - samples/sec: 1709.07 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 17:56:52,589 epoch 6 - iter 3610/3617 - loss 0.02909474 - time (sec): 222.67 - samples/sec: 1702.40 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 17:56:53,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:56:53,011 EPOCH 6 done: loss 0.0290 - lr: 0.000013 | |
| 2023-10-17 17:57:00,078 DEV : loss 0.29600751399993896 - f1-score (micro avg) 0.6426 | |
| 2023-10-17 17:57:00,126 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:57:22,403 epoch 7 - iter 361/3617 - loss 0.02256972 - time (sec): 22.28 - samples/sec: 1687.99 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 17:57:44,247 epoch 7 - iter 722/3617 - loss 0.01992930 - time (sec): 44.12 - samples/sec: 1709.63 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 17:58:06,222 epoch 7 - iter 1083/3617 - loss 0.01936052 - time (sec): 66.09 - samples/sec: 1688.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:58:27,958 epoch 7 - iter 1444/3617 - loss 0.02131053 - time (sec): 87.83 - samples/sec: 1716.41 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:58:49,581 epoch 7 - iter 1805/3617 - loss 0.02100541 - time (sec): 109.45 - samples/sec: 1713.74 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:59:11,493 epoch 7 - iter 2166/3617 - loss 0.02021921 - time (sec): 131.37 - samples/sec: 1720.34 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 17:59:33,198 epoch 7 - iter 2527/3617 - loss 0.02012324 - time (sec): 153.07 - samples/sec: 1729.52 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 17:59:55,204 epoch 7 - iter 2888/3617 - loss 0.01995187 - time (sec): 175.08 - samples/sec: 1726.12 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:00:17,089 epoch 7 - iter 3249/3617 - loss 0.02065452 - time (sec): 196.96 - samples/sec: 1729.41 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:00:38,909 epoch 7 - iter 3610/3617 - loss 0.02030197 - time (sec): 218.78 - samples/sec: 1733.29 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:00:39,320 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:00:39,321 EPOCH 7 done: loss 0.0203 - lr: 0.000010 | |
| 2023-10-17 18:00:45,581 DEV : loss 0.36072632670402527 - f1-score (micro avg) 0.6493 | |
| 2023-10-17 18:00:45,624 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:01:07,188 epoch 8 - iter 361/3617 - loss 0.01488249 - time (sec): 21.56 - samples/sec: 1705.12 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:01:28,983 epoch 8 - iter 722/3617 - loss 0.01173994 - time (sec): 43.36 - samples/sec: 1701.96 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:01:50,897 epoch 8 - iter 1083/3617 - loss 0.01172267 - time (sec): 65.27 - samples/sec: 1717.40 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:02:12,572 epoch 8 - iter 1444/3617 - loss 0.01239870 - time (sec): 86.95 - samples/sec: 1716.68 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:02:34,782 epoch 8 - iter 1805/3617 - loss 0.01203878 - time (sec): 109.16 - samples/sec: 1726.53 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:02:56,772 epoch 8 - iter 2166/3617 - loss 0.01229690 - time (sec): 131.15 - samples/sec: 1723.41 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:03:19,358 epoch 8 - iter 2527/3617 - loss 0.01220534 - time (sec): 153.73 - samples/sec: 1711.58 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:03:41,056 epoch 8 - iter 2888/3617 - loss 0.01250368 - time (sec): 175.43 - samples/sec: 1719.43 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:04:03,226 epoch 8 - iter 3249/3617 - loss 0.01250331 - time (sec): 197.60 - samples/sec: 1722.51 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:04:25,843 epoch 8 - iter 3610/3617 - loss 0.01215736 - time (sec): 220.22 - samples/sec: 1722.37 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:04:26,278 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:04:26,278 EPOCH 8 done: loss 0.0122 - lr: 0.000007 | |
| 2023-10-17 18:04:33,346 DEV : loss 0.3847675919532776 - f1-score (micro avg) 0.6523 | |
| 2023-10-17 18:04:33,386 saving best model | |
| 2023-10-17 18:04:33,971 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:04:55,982 epoch 9 - iter 361/3617 - loss 0.01548248 - time (sec): 22.01 - samples/sec: 1718.42 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:05:18,605 epoch 9 - iter 722/3617 - loss 0.01155917 - time (sec): 44.63 - samples/sec: 1687.13 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:05:41,248 epoch 9 - iter 1083/3617 - loss 0.01030921 - time (sec): 67.28 - samples/sec: 1668.56 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:06:04,188 epoch 9 - iter 1444/3617 - loss 0.00923199 - time (sec): 90.22 - samples/sec: 1647.00 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:06:27,599 epoch 9 - iter 1805/3617 - loss 0.00874837 - time (sec): 113.63 - samples/sec: 1645.30 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:06:50,980 epoch 9 - iter 2166/3617 - loss 0.00882996 - time (sec): 137.01 - samples/sec: 1645.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:07:14,442 epoch 9 - iter 2527/3617 - loss 0.00865169 - time (sec): 160.47 - samples/sec: 1643.59 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:07:37,588 epoch 9 - iter 2888/3617 - loss 0.00811406 - time (sec): 183.62 - samples/sec: 1642.69 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:08:00,984 epoch 9 - iter 3249/3617 - loss 0.00831608 - time (sec): 207.01 - samples/sec: 1648.34 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:08:24,144 epoch 9 - iter 3610/3617 - loss 0.00812836 - time (sec): 230.17 - samples/sec: 1647.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:08:24,588 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:24,588 EPOCH 9 done: loss 0.0082 - lr: 0.000003 | |
| 2023-10-17 18:08:30,995 DEV : loss 0.3781038522720337 - f1-score (micro avg) 0.6514 | |
| 2023-10-17 18:08:31,037 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:54,748 epoch 10 - iter 361/3617 - loss 0.00510416 - time (sec): 23.71 - samples/sec: 1590.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:09:17,569 epoch 10 - iter 722/3617 - loss 0.00489821 - time (sec): 46.53 - samples/sec: 1609.05 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:09:39,437 epoch 10 - iter 1083/3617 - loss 0.00501388 - time (sec): 68.40 - samples/sec: 1655.25 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:10:01,410 epoch 10 - iter 1444/3617 - loss 0.00452399 - time (sec): 90.37 - samples/sec: 1685.07 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:10:23,363 epoch 10 - iter 1805/3617 - loss 0.00468649 - time (sec): 112.32 - samples/sec: 1705.08 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:10:45,165 epoch 10 - iter 2166/3617 - loss 0.00503756 - time (sec): 134.13 - samples/sec: 1710.08 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:07,122 epoch 10 - iter 2527/3617 - loss 0.00499945 - time (sec): 156.08 - samples/sec: 1712.08 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:28,917 epoch 10 - iter 2888/3617 - loss 0.00532812 - time (sec): 177.88 - samples/sec: 1716.51 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:50,588 epoch 10 - iter 3249/3617 - loss 0.00527748 - time (sec): 199.55 - samples/sec: 1714.00 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:12:12,769 epoch 10 - iter 3610/3617 - loss 0.00530741 - time (sec): 221.73 - samples/sec: 1710.95 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:12:13,184 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:12:13,184 EPOCH 10 done: loss 0.0053 - lr: 0.000000 | |
| 2023-10-17 18:12:20,278 DEV : loss 0.39976608753204346 - f1-score (micro avg) 0.6548 | |
| 2023-10-17 18:12:20,319 saving best model | |
| 2023-10-17 18:12:21,394 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:12:21,395 Loading model from best epoch ... | |
| 2023-10-17 18:12:23,141 SequenceTagger predicts: Dictionary with 13 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 | |
| 2023-10-17 18:12:31,270 | |
| Results: | |
| - F-score (micro) 0.6652 | |
| - F-score (macro) 0.5352 | |
| - Accuracy 0.5099 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.6652 0.7733 0.7152 591 | |
| pers 0.5817 0.7675 0.6618 357 | |
| org 0.2623 0.2025 0.2286 79 | |
| micro avg 0.6128 0.7274 0.6652 1027 | |
| macro avg 0.5031 0.5811 0.5352 1027 | |
| weighted avg 0.6052 0.7274 0.6592 1027 | |
| 2023-10-17 18:12:31,270 ---------------------------------------------------------------------------------------------------- | |