| 2023-10-17 09:51:00,210 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,211 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 09:51:00,211 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 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 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Train: 1214 sentences | |
| 2023-10-17 09:51:00,212 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Training Params: | |
| 2023-10-17 09:51:00,212 - learning_rate: "3e-05" | |
| 2023-10-17 09:51:00,212 - mini_batch_size: "4" | |
| 2023-10-17 09:51:00,212 - max_epochs: "10" | |
| 2023-10-17 09:51:00,212 - shuffle: "True" | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Plugins: | |
| 2023-10-17 09:51:00,212 - TensorboardLogger | |
| 2023-10-17 09:51:00,212 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 09:51:00,212 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Computation: | |
| 2023-10-17 09:51:00,212 - compute on device: cuda:0 | |
| 2023-10-17 09:51:00,212 - embedding storage: none | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:00,212 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 09:51:01,788 epoch 1 - iter 30/304 - loss 4.07852700 - time (sec): 1.57 - samples/sec: 1973.00 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:51:03,383 epoch 1 - iter 60/304 - loss 3.36241177 - time (sec): 3.17 - samples/sec: 1977.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:51:04,993 epoch 1 - iter 90/304 - loss 2.54508670 - time (sec): 4.78 - samples/sec: 1962.06 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:51:06,583 epoch 1 - iter 120/304 - loss 2.06047930 - time (sec): 6.37 - samples/sec: 1959.11 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:51:08,170 epoch 1 - iter 150/304 - loss 1.76806521 - time (sec): 7.96 - samples/sec: 1961.22 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:51:09,772 epoch 1 - iter 180/304 - loss 1.55846369 - time (sec): 9.56 - samples/sec: 1934.88 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:51:11,349 epoch 1 - iter 210/304 - loss 1.38508148 - time (sec): 11.14 - samples/sec: 1925.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:51:12,966 epoch 1 - iter 240/304 - loss 1.26003124 - time (sec): 12.75 - samples/sec: 1913.14 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:51:14,581 epoch 1 - iter 270/304 - loss 1.14581127 - time (sec): 14.37 - samples/sec: 1916.86 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:51:16,192 epoch 1 - iter 300/304 - loss 1.05082438 - time (sec): 15.98 - samples/sec: 1916.76 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:51:16,406 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:16,406 EPOCH 1 done: loss 1.0409 - lr: 0.000030 | |
| 2023-10-17 09:51:17,689 DEV : loss 0.19747845828533173 - f1-score (micro avg) 0.627 | |
| 2023-10-17 09:51:17,695 saving best model | |
| 2023-10-17 09:51:18,027 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:19,619 epoch 2 - iter 30/304 - loss 0.20724438 - time (sec): 1.59 - samples/sec: 1888.01 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:51:21,273 epoch 2 - iter 60/304 - loss 0.19975561 - time (sec): 3.24 - samples/sec: 1872.15 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:51:22,901 epoch 2 - iter 90/304 - loss 0.18249124 - time (sec): 4.87 - samples/sec: 1881.79 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:51:24,504 epoch 2 - iter 120/304 - loss 0.17552555 - time (sec): 6.48 - samples/sec: 1859.74 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:51:26,043 epoch 2 - iter 150/304 - loss 0.16775555 - time (sec): 8.01 - samples/sec: 1906.99 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:51:27,493 epoch 2 - iter 180/304 - loss 0.15498206 - time (sec): 9.46 - samples/sec: 1946.17 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:51:29,096 epoch 2 - iter 210/304 - loss 0.15292885 - time (sec): 11.07 - samples/sec: 1948.43 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:51:30,654 epoch 2 - iter 240/304 - loss 0.14229945 - time (sec): 12.63 - samples/sec: 1948.97 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:51:32,189 epoch 2 - iter 270/304 - loss 0.13732255 - time (sec): 14.16 - samples/sec: 1951.40 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:51:33,594 epoch 2 - iter 300/304 - loss 0.13686760 - time (sec): 15.57 - samples/sec: 1969.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:51:33,776 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:33,776 EPOCH 2 done: loss 0.1362 - lr: 0.000027 | |
| 2023-10-17 09:51:34,696 DEV : loss 0.13579988479614258 - f1-score (micro avg) 0.8132 | |
| 2023-10-17 09:51:34,703 saving best model | |
| 2023-10-17 09:51:35,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:36,703 epoch 3 - iter 30/304 - loss 0.05288770 - time (sec): 1.49 - samples/sec: 1931.00 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:51:38,288 epoch 3 - iter 60/304 - loss 0.05625838 - time (sec): 3.07 - samples/sec: 1921.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:51:39,881 epoch 3 - iter 90/304 - loss 0.07493109 - time (sec): 4.67 - samples/sec: 1885.97 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:51:41,508 epoch 3 - iter 120/304 - loss 0.07855866 - time (sec): 6.29 - samples/sec: 1905.00 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:51:43,098 epoch 3 - iter 150/304 - loss 0.08165868 - time (sec): 7.88 - samples/sec: 1924.75 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:51:44,745 epoch 3 - iter 180/304 - loss 0.07931241 - time (sec): 9.53 - samples/sec: 1906.60 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:51:46,362 epoch 3 - iter 210/304 - loss 0.08005280 - time (sec): 11.15 - samples/sec: 1906.75 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:51:48,009 epoch 3 - iter 240/304 - loss 0.08153903 - time (sec): 12.79 - samples/sec: 1905.36 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:51:49,589 epoch 3 - iter 270/304 - loss 0.08471581 - time (sec): 14.37 - samples/sec: 1917.20 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:51:51,178 epoch 3 - iter 300/304 - loss 0.08599573 - time (sec): 15.96 - samples/sec: 1918.82 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:51:51,379 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:51,379 EPOCH 3 done: loss 0.0857 - lr: 0.000023 | |
| 2023-10-17 09:51:52,332 DEV : loss 0.18125586211681366 - f1-score (micro avg) 0.8029 | |
| 2023-10-17 09:51:52,340 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:51:53,864 epoch 4 - iter 30/304 - loss 0.03834710 - time (sec): 1.52 - samples/sec: 1991.30 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:51:55,292 epoch 4 - iter 60/304 - loss 0.08986155 - time (sec): 2.95 - samples/sec: 1986.04 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:51:56,705 epoch 4 - iter 90/304 - loss 0.08425431 - time (sec): 4.36 - samples/sec: 2090.06 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:51:58,512 epoch 4 - iter 120/304 - loss 0.07403882 - time (sec): 6.17 - samples/sec: 2001.34 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:51:59,919 epoch 4 - iter 150/304 - loss 0.06565302 - time (sec): 7.58 - samples/sec: 2034.39 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:52:01,323 epoch 4 - iter 180/304 - loss 0.05999701 - time (sec): 8.98 - samples/sec: 2046.48 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:52:02,740 epoch 4 - iter 210/304 - loss 0.06133296 - time (sec): 10.40 - samples/sec: 2081.39 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:52:04,061 epoch 4 - iter 240/304 - loss 0.06046200 - time (sec): 11.72 - samples/sec: 2097.93 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:52:05,485 epoch 4 - iter 270/304 - loss 0.06095398 - time (sec): 13.14 - samples/sec: 2088.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:52:06,850 epoch 4 - iter 300/304 - loss 0.06257171 - time (sec): 14.51 - samples/sec: 2108.44 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:52:07,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:07,029 EPOCH 4 done: loss 0.0658 - lr: 0.000020 | |
| 2023-10-17 09:52:07,996 DEV : loss 0.1839369386434555 - f1-score (micro avg) 0.8394 | |
| 2023-10-17 09:52:08,005 saving best model | |
| 2023-10-17 09:52:08,550 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:09,862 epoch 5 - iter 30/304 - loss 0.04090543 - time (sec): 1.31 - samples/sec: 2190.68 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:52:11,280 epoch 5 - iter 60/304 - loss 0.03944668 - time (sec): 2.73 - samples/sec: 2267.96 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:52:12,674 epoch 5 - iter 90/304 - loss 0.03955547 - time (sec): 4.12 - samples/sec: 2250.14 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:52:14,302 epoch 5 - iter 120/304 - loss 0.04825896 - time (sec): 5.75 - samples/sec: 2105.84 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:52:15,918 epoch 5 - iter 150/304 - loss 0.04247104 - time (sec): 7.37 - samples/sec: 2059.45 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:52:17,559 epoch 5 - iter 180/304 - loss 0.03966045 - time (sec): 9.01 - samples/sec: 2036.86 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:52:19,185 epoch 5 - iter 210/304 - loss 0.04135296 - time (sec): 10.63 - samples/sec: 2021.03 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:52:20,778 epoch 5 - iter 240/304 - loss 0.04411659 - time (sec): 12.23 - samples/sec: 2007.74 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:52:22,387 epoch 5 - iter 270/304 - loss 0.04601871 - time (sec): 13.84 - samples/sec: 1993.20 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:52:23,993 epoch 5 - iter 300/304 - loss 0.04773765 - time (sec): 15.44 - samples/sec: 1988.44 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:52:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:24,197 EPOCH 5 done: loss 0.0476 - lr: 0.000017 | |
| 2023-10-17 09:52:25,206 DEV : loss 0.19212624430656433 - f1-score (micro avg) 0.8507 | |
| 2023-10-17 09:52:25,214 saving best model | |
| 2023-10-17 09:52:25,784 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:27,396 epoch 6 - iter 30/304 - loss 0.03115857 - time (sec): 1.61 - samples/sec: 2093.20 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:52:29,014 epoch 6 - iter 60/304 - loss 0.05669481 - time (sec): 3.23 - samples/sec: 1990.85 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:52:30,621 epoch 6 - iter 90/304 - loss 0.04503237 - time (sec): 4.83 - samples/sec: 1911.56 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:52:32,213 epoch 6 - iter 120/304 - loss 0.03875096 - time (sec): 6.43 - samples/sec: 1843.98 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:52:33,777 epoch 6 - iter 150/304 - loss 0.03860255 - time (sec): 7.99 - samples/sec: 1873.28 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:52:35,311 epoch 6 - iter 180/304 - loss 0.03543322 - time (sec): 9.53 - samples/sec: 1899.72 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:52:36,856 epoch 6 - iter 210/304 - loss 0.03589627 - time (sec): 11.07 - samples/sec: 1927.68 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:52:38,413 epoch 6 - iter 240/304 - loss 0.03467174 - time (sec): 12.63 - samples/sec: 1902.09 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:52:39,906 epoch 6 - iter 270/304 - loss 0.03238159 - time (sec): 14.12 - samples/sec: 1939.18 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:52:41,379 epoch 6 - iter 300/304 - loss 0.03627380 - time (sec): 15.59 - samples/sec: 1959.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:52:41,592 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:41,593 EPOCH 6 done: loss 0.0360 - lr: 0.000013 | |
| 2023-10-17 09:52:42,555 DEV : loss 0.2012815922498703 - f1-score (micro avg) 0.8472 | |
| 2023-10-17 09:52:42,562 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:44,172 epoch 7 - iter 30/304 - loss 0.00275605 - time (sec): 1.61 - samples/sec: 1893.89 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:52:45,828 epoch 7 - iter 60/304 - loss 0.01883299 - time (sec): 3.27 - samples/sec: 1914.88 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:52:47,414 epoch 7 - iter 90/304 - loss 0.01731324 - time (sec): 4.85 - samples/sec: 1926.44 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:52:48,838 epoch 7 - iter 120/304 - loss 0.01894647 - time (sec): 6.28 - samples/sec: 2016.38 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:52:50,211 epoch 7 - iter 150/304 - loss 0.01955210 - time (sec): 7.65 - samples/sec: 2045.13 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:52:51,622 epoch 7 - iter 180/304 - loss 0.02253413 - time (sec): 9.06 - samples/sec: 2055.85 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:52:53,025 epoch 7 - iter 210/304 - loss 0.02263703 - time (sec): 10.46 - samples/sec: 2065.24 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:52:54,518 epoch 7 - iter 240/304 - loss 0.02412269 - time (sec): 11.96 - samples/sec: 2057.36 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:52:55,865 epoch 7 - iter 270/304 - loss 0.02580765 - time (sec): 13.30 - samples/sec: 2068.03 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:52:57,255 epoch 7 - iter 300/304 - loss 0.02547610 - time (sec): 14.69 - samples/sec: 2088.00 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:52:57,439 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:57,440 EPOCH 7 done: loss 0.0257 - lr: 0.000010 | |
| 2023-10-17 09:52:58,449 DEV : loss 0.1998499631881714 - f1-score (micro avg) 0.8466 | |
| 2023-10-17 09:52:58,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:52:59,852 epoch 8 - iter 30/304 - loss 0.00321990 - time (sec): 1.39 - samples/sec: 2020.30 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:53:01,295 epoch 8 - iter 60/304 - loss 0.00902312 - time (sec): 2.83 - samples/sec: 2062.07 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:53:02,699 epoch 8 - iter 90/304 - loss 0.01843473 - time (sec): 4.24 - samples/sec: 2150.42 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:53:04,054 epoch 8 - iter 120/304 - loss 0.01858968 - time (sec): 5.59 - samples/sec: 2117.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:53:05,409 epoch 8 - iter 150/304 - loss 0.01736938 - time (sec): 6.95 - samples/sec: 2151.98 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:53:06,773 epoch 8 - iter 180/304 - loss 0.01854106 - time (sec): 8.31 - samples/sec: 2166.56 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:53:08,134 epoch 8 - iter 210/304 - loss 0.01831741 - time (sec): 9.67 - samples/sec: 2198.14 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:53:09,515 epoch 8 - iter 240/304 - loss 0.01728315 - time (sec): 11.05 - samples/sec: 2202.67 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:53:10,875 epoch 8 - iter 270/304 - loss 0.01760548 - time (sec): 12.41 - samples/sec: 2196.38 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:53:12,239 epoch 8 - iter 300/304 - loss 0.01743961 - time (sec): 13.78 - samples/sec: 2222.38 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:53:12,416 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:12,416 EPOCH 8 done: loss 0.0172 - lr: 0.000007 | |
| 2023-10-17 09:53:13,467 DEV : loss 0.21022357046604156 - f1-score (micro avg) 0.8599 | |
| 2023-10-17 09:53:13,474 saving best model | |
| 2023-10-17 09:53:13,966 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:15,268 epoch 9 - iter 30/304 - loss 0.02488038 - time (sec): 1.29 - samples/sec: 2389.32 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:53:16,603 epoch 9 - iter 60/304 - loss 0.01794433 - time (sec): 2.63 - samples/sec: 2264.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:53:18,067 epoch 9 - iter 90/304 - loss 0.02021173 - time (sec): 4.09 - samples/sec: 2168.05 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:53:19,689 epoch 9 - iter 120/304 - loss 0.01519141 - time (sec): 5.71 - samples/sec: 2068.22 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:53:21,303 epoch 9 - iter 150/304 - loss 0.01739672 - time (sec): 7.33 - samples/sec: 2025.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:53:22,787 epoch 9 - iter 180/304 - loss 0.01455353 - time (sec): 8.81 - samples/sec: 2041.08 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:53:24,239 epoch 9 - iter 210/304 - loss 0.01261942 - time (sec): 10.26 - samples/sec: 2050.77 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:53:25,718 epoch 9 - iter 240/304 - loss 0.01230598 - time (sec): 11.74 - samples/sec: 2068.56 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:53:27,377 epoch 9 - iter 270/304 - loss 0.01436046 - time (sec): 13.40 - samples/sec: 2063.26 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:53:28,909 epoch 9 - iter 300/304 - loss 0.01488597 - time (sec): 14.93 - samples/sec: 2050.06 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:53:29,097 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:29,098 EPOCH 9 done: loss 0.0147 - lr: 0.000003 | |
| 2023-10-17 09:53:30,104 DEV : loss 0.209202378988266 - f1-score (micro avg) 0.8568 | |
| 2023-10-17 09:53:30,112 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:31,517 epoch 10 - iter 30/304 - loss 0.01951542 - time (sec): 1.40 - samples/sec: 2191.45 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:53:32,891 epoch 10 - iter 60/304 - loss 0.01074976 - time (sec): 2.78 - samples/sec: 2156.13 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:53:34,300 epoch 10 - iter 90/304 - loss 0.01105287 - time (sec): 4.19 - samples/sec: 2227.74 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:53:35,896 epoch 10 - iter 120/304 - loss 0.01433360 - time (sec): 5.78 - samples/sec: 2118.20 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:53:37,489 epoch 10 - iter 150/304 - loss 0.01453281 - time (sec): 7.38 - samples/sec: 2066.28 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:53:39,023 epoch 10 - iter 180/304 - loss 0.01355270 - time (sec): 8.91 - samples/sec: 2046.70 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:53:40,493 epoch 10 - iter 210/304 - loss 0.01320871 - time (sec): 10.38 - samples/sec: 2027.96 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:53:41,946 epoch 10 - iter 240/304 - loss 0.01329358 - time (sec): 11.83 - samples/sec: 2016.27 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:53:43,379 epoch 10 - iter 270/304 - loss 0.01297779 - time (sec): 13.27 - samples/sec: 2059.54 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:53:44,786 epoch 10 - iter 300/304 - loss 0.01322108 - time (sec): 14.67 - samples/sec: 2084.15 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:53:44,966 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:44,966 EPOCH 10 done: loss 0.0130 - lr: 0.000000 | |
| 2023-10-17 09:53:45,935 DEV : loss 0.2089724838733673 - f1-score (micro avg) 0.8612 | |
| 2023-10-17 09:53:45,943 saving best model | |
| 2023-10-17 09:53:46,800 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:53:46,801 Loading model from best epoch ... | |
| 2023-10-17 09:53:48,490 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 09:53:49,582 | |
| Results: | |
| - F-score (micro) 0.8333 | |
| - F-score (macro) 0.6686 | |
| - Accuracy 0.7194 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7862 0.8278 0.8065 151 | |
| work 0.7706 0.8842 0.8235 95 | |
| pers 0.8990 0.9271 0.9128 96 | |
| date 0.0000 0.0000 0.0000 3 | |
| loc 1.0000 0.6667 0.8000 3 | |
| micro avg 0.8065 0.8621 0.8333 348 | |
| macro avg 0.6912 0.6612 0.6686 348 | |
| weighted avg 0.8081 0.8621 0.8334 348 | |
| 2023-10-17 09:53:49,583 ---------------------------------------------------------------------------------------------------- | |