| 2023-10-25 14:33:10,198 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,199 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 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): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (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): BertSelfOutput( | |
| (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): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 14:33:10,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,199 MultiCorpus: 7142 train + 698 dev + 2570 test sentences | |
| - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator | |
| 2023-10-25 14:33:10,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,199 Train: 7142 sentences | |
| 2023-10-25 14:33:10,199 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 14:33:10,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,199 Training Params: | |
| 2023-10-25 14:33:10,199 - learning_rate: "3e-05" | |
| 2023-10-25 14:33:10,199 - mini_batch_size: "4" | |
| 2023-10-25 14:33:10,199 - max_epochs: "10" | |
| 2023-10-25 14:33:10,199 - shuffle: "True" | |
| 2023-10-25 14:33:10,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,199 Plugins: | |
| 2023-10-25 14:33:10,199 - TensorboardLogger | |
| 2023-10-25 14:33:10,199 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 14:33:10,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,200 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 14:33:10,200 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 14:33:10,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,200 Computation: | |
| 2023-10-25 14:33:10,200 - compute on device: cuda:0 | |
| 2023-10-25 14:33:10,200 - embedding storage: none | |
| 2023-10-25 14:33:10,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,200 Model training base path: "hmbench-newseye/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-25 14:33:10,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:33:10,200 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 14:33:19,310 epoch 1 - iter 178/1786 - loss 2.16458401 - time (sec): 9.11 - samples/sec: 2742.31 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 14:33:28,441 epoch 1 - iter 356/1786 - loss 1.31146865 - time (sec): 18.24 - samples/sec: 2768.14 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 14:33:37,814 epoch 1 - iter 534/1786 - loss 0.98905009 - time (sec): 27.61 - samples/sec: 2714.22 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 14:33:47,347 epoch 1 - iter 712/1786 - loss 0.80131301 - time (sec): 37.15 - samples/sec: 2700.70 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 14:33:56,710 epoch 1 - iter 890/1786 - loss 0.68410190 - time (sec): 46.51 - samples/sec: 2690.07 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 14:34:06,145 epoch 1 - iter 1068/1786 - loss 0.60428359 - time (sec): 55.94 - samples/sec: 2664.84 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 14:34:15,401 epoch 1 - iter 1246/1786 - loss 0.53636662 - time (sec): 65.20 - samples/sec: 2688.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 14:34:24,423 epoch 1 - iter 1424/1786 - loss 0.49020486 - time (sec): 74.22 - samples/sec: 2680.72 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 14:34:33,280 epoch 1 - iter 1602/1786 - loss 0.45227059 - time (sec): 83.08 - samples/sec: 2690.51 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 14:34:42,376 epoch 1 - iter 1780/1786 - loss 0.42340790 - time (sec): 92.18 - samples/sec: 2688.93 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 14:34:42,696 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:34:42,697 EPOCH 1 done: loss 0.4222 - lr: 0.000030 | |
| 2023-10-25 14:34:46,074 DEV : loss 0.10848163068294525 - f1-score (micro avg) 0.7428 | |
| 2023-10-25 14:34:46,097 saving best model | |
| 2023-10-25 14:34:46,612 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:34:55,533 epoch 2 - iter 178/1786 - loss 0.11053417 - time (sec): 8.92 - samples/sec: 2766.89 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 14:35:04,481 epoch 2 - iter 356/1786 - loss 0.11490130 - time (sec): 17.87 - samples/sec: 2767.94 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 14:35:13,392 epoch 2 - iter 534/1786 - loss 0.11620114 - time (sec): 26.78 - samples/sec: 2743.47 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 14:35:22,226 epoch 2 - iter 712/1786 - loss 0.11705674 - time (sec): 35.61 - samples/sec: 2754.07 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 14:35:31,022 epoch 2 - iter 890/1786 - loss 0.11188865 - time (sec): 44.41 - samples/sec: 2756.31 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 14:35:40,149 epoch 2 - iter 1068/1786 - loss 0.11149373 - time (sec): 53.53 - samples/sec: 2737.48 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 14:35:49,571 epoch 2 - iter 1246/1786 - loss 0.11380784 - time (sec): 62.96 - samples/sec: 2733.71 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 14:35:58,760 epoch 2 - iter 1424/1786 - loss 0.11159461 - time (sec): 72.15 - samples/sec: 2745.59 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 14:36:07,970 epoch 2 - iter 1602/1786 - loss 0.10992030 - time (sec): 81.36 - samples/sec: 2753.77 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 14:36:17,118 epoch 2 - iter 1780/1786 - loss 0.10952342 - time (sec): 90.50 - samples/sec: 2739.06 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 14:36:17,436 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:36:17,436 EPOCH 2 done: loss 0.1093 - lr: 0.000027 | |
| 2023-10-25 14:36:22,069 DEV : loss 0.1350429803133011 - f1-score (micro avg) 0.782 | |
| 2023-10-25 14:36:22,090 saving best model | |
| 2023-10-25 14:36:22,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:36:31,752 epoch 3 - iter 178/1786 - loss 0.06695239 - time (sec): 8.94 - samples/sec: 2747.53 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 14:36:40,887 epoch 3 - iter 356/1786 - loss 0.07437336 - time (sec): 18.08 - samples/sec: 2833.12 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 14:36:49,890 epoch 3 - iter 534/1786 - loss 0.07186971 - time (sec): 27.08 - samples/sec: 2785.30 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 14:36:58,844 epoch 3 - iter 712/1786 - loss 0.07348943 - time (sec): 36.04 - samples/sec: 2761.89 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 14:37:07,815 epoch 3 - iter 890/1786 - loss 0.07319247 - time (sec): 45.01 - samples/sec: 2735.26 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 14:37:17,039 epoch 3 - iter 1068/1786 - loss 0.07440492 - time (sec): 54.23 - samples/sec: 2728.33 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 14:37:25,994 epoch 3 - iter 1246/1786 - loss 0.07390108 - time (sec): 63.19 - samples/sec: 2748.86 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 14:37:34,720 epoch 3 - iter 1424/1786 - loss 0.07488194 - time (sec): 71.91 - samples/sec: 2763.21 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 14:37:43,623 epoch 3 - iter 1602/1786 - loss 0.07447046 - time (sec): 80.82 - samples/sec: 2757.27 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 14:37:52,704 epoch 3 - iter 1780/1786 - loss 0.07537153 - time (sec): 89.90 - samples/sec: 2760.28 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 14:37:53,003 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:37:53,003 EPOCH 3 done: loss 0.0753 - lr: 0.000023 | |
| 2023-10-25 14:37:57,933 DEV : loss 0.13353045284748077 - f1-score (micro avg) 0.7897 | |
| 2023-10-25 14:37:57,956 saving best model | |
| 2023-10-25 14:37:58,732 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:38:08,143 epoch 4 - iter 178/1786 - loss 0.05605084 - time (sec): 9.41 - samples/sec: 2743.99 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 14:38:17,438 epoch 4 - iter 356/1786 - loss 0.05402125 - time (sec): 18.70 - samples/sec: 2672.51 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 14:38:26,525 epoch 4 - iter 534/1786 - loss 0.05499568 - time (sec): 27.79 - samples/sec: 2651.13 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 14:38:35,548 epoch 4 - iter 712/1786 - loss 0.05241855 - time (sec): 36.81 - samples/sec: 2711.98 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 14:38:44,562 epoch 4 - iter 890/1786 - loss 0.05240254 - time (sec): 45.83 - samples/sec: 2735.61 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 14:38:53,859 epoch 4 - iter 1068/1786 - loss 0.05285922 - time (sec): 55.12 - samples/sec: 2707.20 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 14:39:03,020 epoch 4 - iter 1246/1786 - loss 0.05189605 - time (sec): 64.28 - samples/sec: 2701.14 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 14:39:12,115 epoch 4 - iter 1424/1786 - loss 0.05211141 - time (sec): 73.38 - samples/sec: 2702.33 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 14:39:21,412 epoch 4 - iter 1602/1786 - loss 0.05237397 - time (sec): 82.68 - samples/sec: 2709.90 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 14:39:30,629 epoch 4 - iter 1780/1786 - loss 0.05151436 - time (sec): 91.89 - samples/sec: 2698.68 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 14:39:30,954 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:39:30,955 EPOCH 4 done: loss 0.0518 - lr: 0.000020 | |
| 2023-10-25 14:39:34,712 DEV : loss 0.1849958300590515 - f1-score (micro avg) 0.7773 | |
| 2023-10-25 14:39:34,734 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:39:44,192 epoch 5 - iter 178/1786 - loss 0.04597938 - time (sec): 9.46 - samples/sec: 2793.42 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 14:39:53,753 epoch 5 - iter 356/1786 - loss 0.04466867 - time (sec): 19.02 - samples/sec: 2708.97 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 14:40:03,388 epoch 5 - iter 534/1786 - loss 0.04058169 - time (sec): 28.65 - samples/sec: 2664.94 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 14:40:13,272 epoch 5 - iter 712/1786 - loss 0.04127086 - time (sec): 38.54 - samples/sec: 2597.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 14:40:22,719 epoch 5 - iter 890/1786 - loss 0.04095590 - time (sec): 47.98 - samples/sec: 2566.83 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 14:40:32,011 epoch 5 - iter 1068/1786 - loss 0.04113038 - time (sec): 57.27 - samples/sec: 2571.21 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 14:40:41,479 epoch 5 - iter 1246/1786 - loss 0.04188631 - time (sec): 66.74 - samples/sec: 2550.79 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 14:40:50,828 epoch 5 - iter 1424/1786 - loss 0.04177759 - time (sec): 76.09 - samples/sec: 2595.45 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 14:40:59,684 epoch 5 - iter 1602/1786 - loss 0.04071695 - time (sec): 84.95 - samples/sec: 2627.35 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 14:41:08,330 epoch 5 - iter 1780/1786 - loss 0.04018851 - time (sec): 93.59 - samples/sec: 2649.76 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 14:41:08,618 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:41:08,619 EPOCH 5 done: loss 0.0401 - lr: 0.000017 | |
| 2023-10-25 14:41:13,493 DEV : loss 0.19509676098823547 - f1-score (micro avg) 0.7897 | |
| 2023-10-25 14:41:13,516 saving best model | |
| 2023-10-25 14:41:14,286 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:41:23,859 epoch 6 - iter 178/1786 - loss 0.02929917 - time (sec): 9.57 - samples/sec: 2793.46 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 14:41:33,563 epoch 6 - iter 356/1786 - loss 0.03057329 - time (sec): 19.27 - samples/sec: 2683.12 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 14:41:43,148 epoch 6 - iter 534/1786 - loss 0.03026210 - time (sec): 28.86 - samples/sec: 2613.08 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 14:41:52,622 epoch 6 - iter 712/1786 - loss 0.03139423 - time (sec): 38.33 - samples/sec: 2649.33 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 14:42:02,141 epoch 6 - iter 890/1786 - loss 0.03141974 - time (sec): 47.85 - samples/sec: 2637.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 14:42:11,399 epoch 6 - iter 1068/1786 - loss 0.03227820 - time (sec): 57.11 - samples/sec: 2644.91 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 14:42:20,262 epoch 6 - iter 1246/1786 - loss 0.03178910 - time (sec): 65.97 - samples/sec: 2655.85 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 14:42:29,099 epoch 6 - iter 1424/1786 - loss 0.03207149 - time (sec): 74.81 - samples/sec: 2668.25 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 14:42:37,964 epoch 6 - iter 1602/1786 - loss 0.03149622 - time (sec): 83.67 - samples/sec: 2688.13 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 14:42:46,897 epoch 6 - iter 1780/1786 - loss 0.03192675 - time (sec): 92.61 - samples/sec: 2677.94 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 14:42:47,185 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:42:47,186 EPOCH 6 done: loss 0.0318 - lr: 0.000013 | |
| 2023-10-25 14:42:51,967 DEV : loss 0.20672442018985748 - f1-score (micro avg) 0.7962 | |
| 2023-10-25 14:42:51,988 saving best model | |
| 2023-10-25 14:42:52,693 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:43:01,533 epoch 7 - iter 178/1786 - loss 0.01719752 - time (sec): 8.84 - samples/sec: 2600.24 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 14:43:10,125 epoch 7 - iter 356/1786 - loss 0.02135005 - time (sec): 17.43 - samples/sec: 2746.42 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 14:43:19,192 epoch 7 - iter 534/1786 - loss 0.02318318 - time (sec): 26.50 - samples/sec: 2854.55 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 14:43:28,579 epoch 7 - iter 712/1786 - loss 0.02312462 - time (sec): 35.88 - samples/sec: 2842.16 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 14:43:37,817 epoch 7 - iter 890/1786 - loss 0.02250943 - time (sec): 45.12 - samples/sec: 2758.16 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 14:43:46,912 epoch 7 - iter 1068/1786 - loss 0.02128871 - time (sec): 54.22 - samples/sec: 2738.00 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 14:43:56,071 epoch 7 - iter 1246/1786 - loss 0.02132723 - time (sec): 63.38 - samples/sec: 2735.65 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 14:44:05,300 epoch 7 - iter 1424/1786 - loss 0.02185820 - time (sec): 72.61 - samples/sec: 2731.09 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 14:44:14,347 epoch 7 - iter 1602/1786 - loss 0.02218104 - time (sec): 81.65 - samples/sec: 2724.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 14:44:23,204 epoch 7 - iter 1780/1786 - loss 0.02222713 - time (sec): 90.51 - samples/sec: 2740.75 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 14:44:23,491 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:44:23,491 EPOCH 7 done: loss 0.0223 - lr: 0.000010 | |
| 2023-10-25 14:44:27,321 DEV : loss 0.22337248921394348 - f1-score (micro avg) 0.7964 | |
| 2023-10-25 14:44:27,339 saving best model | |
| 2023-10-25 14:44:28,025 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:44:37,591 epoch 8 - iter 178/1786 - loss 0.01779272 - time (sec): 9.56 - samples/sec: 2588.34 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 14:44:47,021 epoch 8 - iter 356/1786 - loss 0.01894142 - time (sec): 18.99 - samples/sec: 2700.71 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 14:44:56,629 epoch 8 - iter 534/1786 - loss 0.01605388 - time (sec): 28.60 - samples/sec: 2696.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 14:45:06,337 epoch 8 - iter 712/1786 - loss 0.01635096 - time (sec): 38.31 - samples/sec: 2688.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 14:45:15,994 epoch 8 - iter 890/1786 - loss 0.01715962 - time (sec): 47.96 - samples/sec: 2632.09 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 14:45:25,422 epoch 8 - iter 1068/1786 - loss 0.01852086 - time (sec): 57.39 - samples/sec: 2616.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 14:45:34,422 epoch 8 - iter 1246/1786 - loss 0.01764650 - time (sec): 66.39 - samples/sec: 2636.24 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 14:45:44,111 epoch 8 - iter 1424/1786 - loss 0.01697131 - time (sec): 76.08 - samples/sec: 2625.83 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 14:45:53,686 epoch 8 - iter 1602/1786 - loss 0.01660441 - time (sec): 85.66 - samples/sec: 2623.06 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 14:46:03,240 epoch 8 - iter 1780/1786 - loss 0.01626775 - time (sec): 95.21 - samples/sec: 2604.67 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 14:46:03,553 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:46:03,553 EPOCH 8 done: loss 0.0162 - lr: 0.000007 | |
| 2023-10-25 14:46:08,504 DEV : loss 0.22934271395206451 - f1-score (micro avg) 0.7997 | |
| 2023-10-25 14:46:08,526 saving best model | |
| 2023-10-25 14:46:09,250 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:46:18,809 epoch 9 - iter 178/1786 - loss 0.01295900 - time (sec): 9.56 - samples/sec: 2559.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 14:46:28,369 epoch 9 - iter 356/1786 - loss 0.01695431 - time (sec): 19.12 - samples/sec: 2630.20 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 14:46:37,819 epoch 9 - iter 534/1786 - loss 0.01347445 - time (sec): 28.57 - samples/sec: 2666.73 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 14:46:47,103 epoch 9 - iter 712/1786 - loss 0.01503886 - time (sec): 37.85 - samples/sec: 2644.36 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 14:46:56,001 epoch 9 - iter 890/1786 - loss 0.01306635 - time (sec): 46.75 - samples/sec: 2693.10 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 14:47:05,076 epoch 9 - iter 1068/1786 - loss 0.01204591 - time (sec): 55.82 - samples/sec: 2692.47 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 14:47:14,461 epoch 9 - iter 1246/1786 - loss 0.01146321 - time (sec): 65.21 - samples/sec: 2690.78 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 14:47:23,721 epoch 9 - iter 1424/1786 - loss 0.01130831 - time (sec): 74.47 - samples/sec: 2677.47 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 14:47:33,098 epoch 9 - iter 1602/1786 - loss 0.01112742 - time (sec): 83.85 - samples/sec: 2675.96 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 14:47:42,454 epoch 9 - iter 1780/1786 - loss 0.01140774 - time (sec): 93.20 - samples/sec: 2661.17 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 14:47:42,751 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:47:42,751 EPOCH 9 done: loss 0.0114 - lr: 0.000003 | |
| 2023-10-25 14:47:46,674 DEV : loss 0.2408183217048645 - f1-score (micro avg) 0.7965 | |
| 2023-10-25 14:47:46,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:47:56,117 epoch 10 - iter 178/1786 - loss 0.00749371 - time (sec): 9.42 - samples/sec: 2742.95 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 14:48:05,390 epoch 10 - iter 356/1786 - loss 0.00521229 - time (sec): 18.69 - samples/sec: 2747.16 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 14:48:14,524 epoch 10 - iter 534/1786 - loss 0.00725197 - time (sec): 27.82 - samples/sec: 2703.18 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 14:48:23,669 epoch 10 - iter 712/1786 - loss 0.00808463 - time (sec): 36.97 - samples/sec: 2718.18 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 14:48:32,464 epoch 10 - iter 890/1786 - loss 0.00808605 - time (sec): 45.76 - samples/sec: 2711.31 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 14:48:41,419 epoch 10 - iter 1068/1786 - loss 0.00815421 - time (sec): 54.72 - samples/sec: 2706.54 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 14:48:50,504 epoch 10 - iter 1246/1786 - loss 0.00802142 - time (sec): 63.80 - samples/sec: 2718.32 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 14:48:59,792 epoch 10 - iter 1424/1786 - loss 0.00776468 - time (sec): 73.09 - samples/sec: 2721.60 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 14:49:09,176 epoch 10 - iter 1602/1786 - loss 0.00740460 - time (sec): 82.48 - samples/sec: 2707.01 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 14:49:18,632 epoch 10 - iter 1780/1786 - loss 0.00732665 - time (sec): 91.93 - samples/sec: 2695.35 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 14:49:18,972 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:49:18,973 EPOCH 10 done: loss 0.0073 - lr: 0.000000 | |
| 2023-10-25 14:49:24,029 DEV : loss 0.244009330868721 - f1-score (micro avg) 0.7973 | |
| 2023-10-25 14:49:24,566 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 14:49:24,567 Loading model from best epoch ... | |
| 2023-10-25 14:49:26,591 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-25 14:49:38,665 | |
| Results: | |
| - F-score (micro) 0.6933 | |
| - F-score (macro) 0.619 | |
| - Accuracy 0.5461 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.6972 0.6667 0.6816 1095 | |
| PER 0.7832 0.7816 0.7824 1012 | |
| ORG 0.4733 0.5714 0.5178 357 | |
| HumanProd 0.4038 0.6364 0.4941 33 | |
| micro avg 0.6874 0.6992 0.6933 2497 | |
| macro avg 0.5894 0.6640 0.6190 2497 | |
| weighted avg 0.6962 0.6992 0.6966 2497 | |
| 2023-10-25 14:49:38,666 ---------------------------------------------------------------------------------------------------- | |