| 2023-10-17 11:01:03,142 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,143 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 768) | |
| (position_embeddings): Embedding(512, 768) | |
| (token_type_embeddings): Embedding(2, 768) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): ElectraSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 11:01:03,143 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,143 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-17 11:01:03,143 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,143 Train: 966 sentences | |
| 2023-10-17 11:01:03,144 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Training Params: | |
| 2023-10-17 11:01:03,144 - learning_rate: "3e-05" | |
| 2023-10-17 11:01:03,144 - mini_batch_size: "4" | |
| 2023-10-17 11:01:03,144 - max_epochs: "10" | |
| 2023-10-17 11:01:03,144 - shuffle: "True" | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Plugins: | |
| 2023-10-17 11:01:03,144 - TensorboardLogger | |
| 2023-10-17 11:01:03,144 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 11:01:03,144 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Computation: | |
| 2023-10-17 11:01:03,144 - compute on device: cuda:0 | |
| 2023-10-17 11:01:03,144 - embedding storage: none | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Model training base path: "hmbench-ajmc/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:03,144 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 11:01:04,327 epoch 1 - iter 24/242 - loss 4.39176709 - time (sec): 1.18 - samples/sec: 2213.65 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:01:05,487 epoch 1 - iter 48/242 - loss 3.86583745 - time (sec): 2.34 - samples/sec: 2128.18 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:01:06,584 epoch 1 - iter 72/242 - loss 3.00347919 - time (sec): 3.44 - samples/sec: 2151.97 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:01:07,718 epoch 1 - iter 96/242 - loss 2.45538499 - time (sec): 4.57 - samples/sec: 2136.48 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:01:08,841 epoch 1 - iter 120/242 - loss 2.03995694 - time (sec): 5.70 - samples/sec: 2175.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:01:09,974 epoch 1 - iter 144/242 - loss 1.76867960 - time (sec): 6.83 - samples/sec: 2180.09 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:01:11,054 epoch 1 - iter 168/242 - loss 1.58535234 - time (sec): 7.91 - samples/sec: 2173.90 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:01:12,210 epoch 1 - iter 192/242 - loss 1.43442965 - time (sec): 9.06 - samples/sec: 2165.83 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:01:13,297 epoch 1 - iter 216/242 - loss 1.29449651 - time (sec): 10.15 - samples/sec: 2190.69 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:01:14,402 epoch 1 - iter 240/242 - loss 1.20191505 - time (sec): 11.26 - samples/sec: 2188.92 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:01:14,492 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:14,493 EPOCH 1 done: loss 1.1981 - lr: 0.000030 | |
| 2023-10-17 11:01:15,385 DEV : loss 0.274255633354187 - f1-score (micro avg) 0.5116 | |
| 2023-10-17 11:01:15,393 saving best model | |
| 2023-10-17 11:01:15,881 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:17,059 epoch 2 - iter 24/242 - loss 0.25584963 - time (sec): 1.18 - samples/sec: 2267.47 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:01:18,200 epoch 2 - iter 48/242 - loss 0.22869599 - time (sec): 2.32 - samples/sec: 2212.45 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:01:19,333 epoch 2 - iter 72/242 - loss 0.21938132 - time (sec): 3.45 - samples/sec: 2133.13 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:01:20,471 epoch 2 - iter 96/242 - loss 0.20884183 - time (sec): 4.59 - samples/sec: 2169.95 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:01:21,627 epoch 2 - iter 120/242 - loss 0.20385812 - time (sec): 5.74 - samples/sec: 2118.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:01:22,758 epoch 2 - iter 144/242 - loss 0.20103300 - time (sec): 6.88 - samples/sec: 2130.74 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:01:23,901 epoch 2 - iter 168/242 - loss 0.19345290 - time (sec): 8.02 - samples/sec: 2158.20 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:01:25,002 epoch 2 - iter 192/242 - loss 0.18517283 - time (sec): 9.12 - samples/sec: 2175.74 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:01:26,104 epoch 2 - iter 216/242 - loss 0.18565657 - time (sec): 10.22 - samples/sec: 2181.71 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:01:27,224 epoch 2 - iter 240/242 - loss 0.18141421 - time (sec): 11.34 - samples/sec: 2172.99 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:01:27,309 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:27,310 EPOCH 2 done: loss 0.1817 - lr: 0.000027 | |
| 2023-10-17 11:01:28,073 DEV : loss 0.14404645562171936 - f1-score (micro avg) 0.7981 | |
| 2023-10-17 11:01:28,080 saving best model | |
| 2023-10-17 11:01:28,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:29,720 epoch 3 - iter 24/242 - loss 0.07866805 - time (sec): 1.14 - samples/sec: 1991.30 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:01:30,880 epoch 3 - iter 48/242 - loss 0.09788918 - time (sec): 2.30 - samples/sec: 2073.73 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:01:32,034 epoch 3 - iter 72/242 - loss 0.09483576 - time (sec): 3.45 - samples/sec: 2126.61 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:01:33,198 epoch 3 - iter 96/242 - loss 0.09409418 - time (sec): 4.62 - samples/sec: 2125.35 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:01:34,306 epoch 3 - iter 120/242 - loss 0.10326053 - time (sec): 5.73 - samples/sec: 2137.50 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:01:35,475 epoch 3 - iter 144/242 - loss 0.10622132 - time (sec): 6.90 - samples/sec: 2113.66 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:01:36,568 epoch 3 - iter 168/242 - loss 0.10585369 - time (sec): 7.99 - samples/sec: 2106.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:01:37,660 epoch 3 - iter 192/242 - loss 0.10668339 - time (sec): 9.08 - samples/sec: 2119.36 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:01:38,762 epoch 3 - iter 216/242 - loss 0.10382207 - time (sec): 10.18 - samples/sec: 2147.20 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:01:39,910 epoch 3 - iter 240/242 - loss 0.10487434 - time (sec): 11.33 - samples/sec: 2167.59 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:01:40,000 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:40,001 EPOCH 3 done: loss 0.1043 - lr: 0.000023 | |
| 2023-10-17 11:01:40,750 DEV : loss 0.15008682012557983 - f1-score (micro avg) 0.8107 | |
| 2023-10-17 11:01:40,755 saving best model | |
| 2023-10-17 11:01:41,290 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:42,510 epoch 4 - iter 24/242 - loss 0.08302536 - time (sec): 1.22 - samples/sec: 2027.01 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:01:43,675 epoch 4 - iter 48/242 - loss 0.09252726 - time (sec): 2.38 - samples/sec: 1998.76 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:01:44,800 epoch 4 - iter 72/242 - loss 0.08470306 - time (sec): 3.51 - samples/sec: 2089.90 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:01:45,924 epoch 4 - iter 96/242 - loss 0.08088082 - time (sec): 4.63 - samples/sec: 2091.43 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:01:47,061 epoch 4 - iter 120/242 - loss 0.08006269 - time (sec): 5.77 - samples/sec: 2101.80 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:01:48,212 epoch 4 - iter 144/242 - loss 0.07433784 - time (sec): 6.92 - samples/sec: 2136.61 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:01:49,313 epoch 4 - iter 168/242 - loss 0.07626262 - time (sec): 8.02 - samples/sec: 2126.39 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:01:50,429 epoch 4 - iter 192/242 - loss 0.07742048 - time (sec): 9.14 - samples/sec: 2154.11 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:01:51,584 epoch 4 - iter 216/242 - loss 0.07627739 - time (sec): 10.29 - samples/sec: 2149.68 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:01:52,698 epoch 4 - iter 240/242 - loss 0.07293290 - time (sec): 11.40 - samples/sec: 2152.62 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:01:52,788 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:52,788 EPOCH 4 done: loss 0.0724 - lr: 0.000020 | |
| 2023-10-17 11:01:53,545 DEV : loss 0.1953733116388321 - f1-score (micro avg) 0.8044 | |
| 2023-10-17 11:01:53,550 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:01:54,591 epoch 5 - iter 24/242 - loss 0.02802847 - time (sec): 1.04 - samples/sec: 2253.93 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:01:55,658 epoch 5 - iter 48/242 - loss 0.03277181 - time (sec): 2.11 - samples/sec: 2251.90 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:01:56,716 epoch 5 - iter 72/242 - loss 0.05308526 - time (sec): 3.17 - samples/sec: 2278.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:01:57,796 epoch 5 - iter 96/242 - loss 0.05323942 - time (sec): 4.25 - samples/sec: 2321.22 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:01:58,875 epoch 5 - iter 120/242 - loss 0.05349475 - time (sec): 5.32 - samples/sec: 2296.48 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:01:59,949 epoch 5 - iter 144/242 - loss 0.05288895 - time (sec): 6.40 - samples/sec: 2330.28 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:02:00,997 epoch 5 - iter 168/242 - loss 0.05558359 - time (sec): 7.45 - samples/sec: 2296.01 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:02:02,086 epoch 5 - iter 192/242 - loss 0.05649590 - time (sec): 8.54 - samples/sec: 2298.84 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:02:03,153 epoch 5 - iter 216/242 - loss 0.05858168 - time (sec): 9.60 - samples/sec: 2305.13 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:02:04,209 epoch 5 - iter 240/242 - loss 0.05564483 - time (sec): 10.66 - samples/sec: 2305.48 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:02:04,293 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:04,294 EPOCH 5 done: loss 0.0553 - lr: 0.000017 | |
| 2023-10-17 11:02:05,052 DEV : loss 0.19550347328186035 - f1-score (micro avg) 0.8358 | |
| 2023-10-17 11:02:05,058 saving best model | |
| 2023-10-17 11:02:05,602 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:06,806 epoch 6 - iter 24/242 - loss 0.03575701 - time (sec): 1.20 - samples/sec: 2009.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:02:07,906 epoch 6 - iter 48/242 - loss 0.03388522 - time (sec): 2.30 - samples/sec: 2111.95 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:02:09,025 epoch 6 - iter 72/242 - loss 0.03595020 - time (sec): 3.42 - samples/sec: 2206.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:02:10,106 epoch 6 - iter 96/242 - loss 0.04148901 - time (sec): 4.50 - samples/sec: 2211.59 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:02:11,185 epoch 6 - iter 120/242 - loss 0.04053036 - time (sec): 5.58 - samples/sec: 2203.09 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:02:12,253 epoch 6 - iter 144/242 - loss 0.04251098 - time (sec): 6.65 - samples/sec: 2208.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:02:13,325 epoch 6 - iter 168/242 - loss 0.04325255 - time (sec): 7.72 - samples/sec: 2240.93 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:02:14,402 epoch 6 - iter 192/242 - loss 0.04259240 - time (sec): 8.79 - samples/sec: 2266.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:02:15,493 epoch 6 - iter 216/242 - loss 0.03996921 - time (sec): 9.88 - samples/sec: 2255.15 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:02:16,590 epoch 6 - iter 240/242 - loss 0.03999941 - time (sec): 10.98 - samples/sec: 2241.47 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:02:16,678 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:16,678 EPOCH 6 done: loss 0.0399 - lr: 0.000013 | |
| 2023-10-17 11:02:17,438 DEV : loss 0.20514720678329468 - f1-score (micro avg) 0.8424 | |
| 2023-10-17 11:02:17,443 saving best model | |
| 2023-10-17 11:02:18,154 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:19,242 epoch 7 - iter 24/242 - loss 0.04718458 - time (sec): 1.09 - samples/sec: 2020.91 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:02:20,348 epoch 7 - iter 48/242 - loss 0.02664133 - time (sec): 2.19 - samples/sec: 2052.00 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:02:21,464 epoch 7 - iter 72/242 - loss 0.03174458 - time (sec): 3.31 - samples/sec: 2151.98 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:02:22,588 epoch 7 - iter 96/242 - loss 0.03850162 - time (sec): 4.43 - samples/sec: 2176.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:02:23,697 epoch 7 - iter 120/242 - loss 0.03568146 - time (sec): 5.54 - samples/sec: 2182.59 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:02:24,826 epoch 7 - iter 144/242 - loss 0.03225348 - time (sec): 6.67 - samples/sec: 2237.65 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:02:25,952 epoch 7 - iter 168/242 - loss 0.02798295 - time (sec): 7.80 - samples/sec: 2248.01 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:02:27,070 epoch 7 - iter 192/242 - loss 0.02721135 - time (sec): 8.91 - samples/sec: 2246.42 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:02:28,177 epoch 7 - iter 216/242 - loss 0.02906095 - time (sec): 10.02 - samples/sec: 2233.27 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:02:29,268 epoch 7 - iter 240/242 - loss 0.02890529 - time (sec): 11.11 - samples/sec: 2215.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:02:29,353 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:29,353 EPOCH 7 done: loss 0.0292 - lr: 0.000010 | |
| 2023-10-17 11:02:30,120 DEV : loss 0.2213190793991089 - f1-score (micro avg) 0.8479 | |
| 2023-10-17 11:02:30,125 saving best model | |
| 2023-10-17 11:02:30,648 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:31,827 epoch 8 - iter 24/242 - loss 0.03217162 - time (sec): 1.17 - samples/sec: 1961.12 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:02:33,007 epoch 8 - iter 48/242 - loss 0.02156918 - time (sec): 2.35 - samples/sec: 2003.91 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:02:34,199 epoch 8 - iter 72/242 - loss 0.02558088 - time (sec): 3.54 - samples/sec: 2053.03 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:02:35,395 epoch 8 - iter 96/242 - loss 0.02768730 - time (sec): 4.74 - samples/sec: 1965.05 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:02:36,580 epoch 8 - iter 120/242 - loss 0.02573442 - time (sec): 5.92 - samples/sec: 2022.09 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:02:37,736 epoch 8 - iter 144/242 - loss 0.02661062 - time (sec): 7.08 - samples/sec: 2048.05 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:02:38,869 epoch 8 - iter 168/242 - loss 0.02295086 - time (sec): 8.21 - samples/sec: 2062.47 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:02:40,041 epoch 8 - iter 192/242 - loss 0.02188132 - time (sec): 9.38 - samples/sec: 2078.77 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:02:41,217 epoch 8 - iter 216/242 - loss 0.02015179 - time (sec): 10.56 - samples/sec: 2091.19 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:02:42,399 epoch 8 - iter 240/242 - loss 0.02036847 - time (sec): 11.74 - samples/sec: 2094.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:02:42,500 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:42,500 EPOCH 8 done: loss 0.0206 - lr: 0.000007 | |
| 2023-10-17 11:02:43,260 DEV : loss 0.22766046226024628 - f1-score (micro avg) 0.8525 | |
| 2023-10-17 11:02:43,265 saving best model | |
| 2023-10-17 11:02:43,732 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:44,922 epoch 9 - iter 24/242 - loss 0.02488024 - time (sec): 1.19 - samples/sec: 1979.77 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:02:46,054 epoch 9 - iter 48/242 - loss 0.02293484 - time (sec): 2.32 - samples/sec: 2026.75 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:02:47,280 epoch 9 - iter 72/242 - loss 0.02436717 - time (sec): 3.54 - samples/sec: 1935.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:02:48,420 epoch 9 - iter 96/242 - loss 0.01983546 - time (sec): 4.68 - samples/sec: 2016.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:02:49,522 epoch 9 - iter 120/242 - loss 0.01993513 - time (sec): 5.79 - samples/sec: 2013.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:02:50,632 epoch 9 - iter 144/242 - loss 0.02265769 - time (sec): 6.90 - samples/sec: 2035.06 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:02:51,876 epoch 9 - iter 168/242 - loss 0.02028048 - time (sec): 8.14 - samples/sec: 2048.06 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:02:53,141 epoch 9 - iter 192/242 - loss 0.01777955 - time (sec): 9.41 - samples/sec: 2059.79 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:02:54,384 epoch 9 - iter 216/242 - loss 0.01629753 - time (sec): 10.65 - samples/sec: 2064.07 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:02:55,542 epoch 9 - iter 240/242 - loss 0.01504966 - time (sec): 11.81 - samples/sec: 2076.26 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:02:55,642 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:55,642 EPOCH 9 done: loss 0.0150 - lr: 0.000003 | |
| 2023-10-17 11:02:56,399 DEV : loss 0.232917919754982 - f1-score (micro avg) 0.8344 | |
| 2023-10-17 11:02:56,404 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:02:57,534 epoch 10 - iter 24/242 - loss 0.00349215 - time (sec): 1.13 - samples/sec: 2118.40 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:02:58,669 epoch 10 - iter 48/242 - loss 0.01074842 - time (sec): 2.26 - samples/sec: 2202.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:02:59,816 epoch 10 - iter 72/242 - loss 0.01331582 - time (sec): 3.41 - samples/sec: 2134.76 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:03:00,933 epoch 10 - iter 96/242 - loss 0.01660198 - time (sec): 4.53 - samples/sec: 2152.00 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:03:02,036 epoch 10 - iter 120/242 - loss 0.01328807 - time (sec): 5.63 - samples/sec: 2177.49 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:03:03,205 epoch 10 - iter 144/242 - loss 0.01327793 - time (sec): 6.80 - samples/sec: 2160.32 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:03:04,330 epoch 10 - iter 168/242 - loss 0.01148726 - time (sec): 7.92 - samples/sec: 2149.72 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:03:05,465 epoch 10 - iter 192/242 - loss 0.01154038 - time (sec): 9.06 - samples/sec: 2161.15 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:03:06,627 epoch 10 - iter 216/242 - loss 0.01039636 - time (sec): 10.22 - samples/sec: 2166.33 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 11:03:07,721 epoch 10 - iter 240/242 - loss 0.01098193 - time (sec): 11.32 - samples/sec: 2173.41 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 11:03:07,810 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:03:07,810 EPOCH 10 done: loss 0.0109 - lr: 0.000000 | |
| 2023-10-17 11:03:08,563 DEV : loss 0.23618429899215698 - f1-score (micro avg) 0.8451 | |
| 2023-10-17 11:03:08,926 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:03:08,927 Loading model from best epoch ... | |
| 2023-10-17 11:03:10,359 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-17 11:03:11,225 | |
| Results: | |
| - F-score (micro) 0.8322 | |
| - F-score (macro) 0.5913 | |
| - Accuracy 0.7332 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8582 0.8705 0.8643 139 | |
| scope 0.8417 0.9070 0.8731 129 | |
| work 0.7191 0.8000 0.7574 80 | |
| loc 0.7500 0.3333 0.4615 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8177 0.8472 0.8322 360 | |
| macro avg 0.6338 0.5822 0.5913 360 | |
| weighted avg 0.8115 0.8472 0.8264 360 | |
| 2023-10-17 11:03:11,225 ---------------------------------------------------------------------------------------------------- | |