| 2023-10-13 13:36:06,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,214 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (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): 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-13 13:36:06,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,214 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-13 13:36:06,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,214 Train: 3575 sentences | |
| 2023-10-13 13:36:06,214 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 13:36:06,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,214 Training Params: | |
| 2023-10-13 13:36:06,214 - learning_rate: "5e-05" | |
| 2023-10-13 13:36:06,214 - mini_batch_size: "4" | |
| 2023-10-13 13:36:06,215 - max_epochs: "10" | |
| 2023-10-13 13:36:06,215 - shuffle: "True" | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,215 Plugins: | |
| 2023-10-13 13:36:06,215 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,215 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 13:36:06,215 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,215 Computation: | |
| 2023-10-13 13:36:06,215 - compute on device: cuda:0 | |
| 2023-10-13 13:36:06,215 - embedding storage: none | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,215 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:06,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:10,938 epoch 1 - iter 89/894 - loss 2.68748942 - time (sec): 4.72 - samples/sec: 1872.42 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 13:36:15,495 epoch 1 - iter 178/894 - loss 1.59012845 - time (sec): 9.28 - samples/sec: 1947.09 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 13:36:19,942 epoch 1 - iter 267/894 - loss 1.22746441 - time (sec): 13.73 - samples/sec: 1893.71 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 13:36:24,240 epoch 1 - iter 356/894 - loss 0.99377093 - time (sec): 18.02 - samples/sec: 1937.51 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 13:36:28,368 epoch 1 - iter 445/894 - loss 0.85393894 - time (sec): 22.15 - samples/sec: 1951.39 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 13:36:32,638 epoch 1 - iter 534/894 - loss 0.76142709 - time (sec): 26.42 - samples/sec: 1955.45 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 13:36:36,984 epoch 1 - iter 623/894 - loss 0.69553409 - time (sec): 30.77 - samples/sec: 1945.95 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 13:36:41,113 epoch 1 - iter 712/894 - loss 0.64037032 - time (sec): 34.90 - samples/sec: 1961.99 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 13:36:45,296 epoch 1 - iter 801/894 - loss 0.59367766 - time (sec): 39.08 - samples/sec: 1957.13 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 13:36:49,755 epoch 1 - iter 890/894 - loss 0.55614722 - time (sec): 43.54 - samples/sec: 1979.46 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-13 13:36:49,955 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:49,955 EPOCH 1 done: loss 0.5541 - lr: 0.000050 | |
| 2023-10-13 13:36:54,994 DEV : loss 0.25372514128685 - f1-score (micro avg) 0.5462 | |
| 2023-10-13 13:36:55,024 saving best model | |
| 2023-10-13 13:36:55,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:36:59,708 epoch 2 - iter 89/894 - loss 0.17468129 - time (sec): 4.32 - samples/sec: 2088.65 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 13:37:04,099 epoch 2 - iter 178/894 - loss 0.17014545 - time (sec): 8.71 - samples/sec: 2135.36 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 13:37:08,087 epoch 2 - iter 267/894 - loss 0.16084483 - time (sec): 12.70 - samples/sec: 2087.62 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 13:37:12,211 epoch 2 - iter 356/894 - loss 0.16855910 - time (sec): 16.82 - samples/sec: 2070.57 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 13:37:16,385 epoch 2 - iter 445/894 - loss 0.16531549 - time (sec): 21.00 - samples/sec: 2077.00 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 13:37:20,503 epoch 2 - iter 534/894 - loss 0.15775841 - time (sec): 25.11 - samples/sec: 2082.98 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 13:37:24,683 epoch 2 - iter 623/894 - loss 0.15772402 - time (sec): 29.30 - samples/sec: 2063.56 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 13:37:28,927 epoch 2 - iter 712/894 - loss 0.15883528 - time (sec): 33.54 - samples/sec: 2046.72 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 13:37:33,333 epoch 2 - iter 801/894 - loss 0.15729564 - time (sec): 37.95 - samples/sec: 2042.63 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 13:37:37,353 epoch 2 - iter 890/894 - loss 0.15659491 - time (sec): 41.97 - samples/sec: 2054.37 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 13:37:37,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:37:37,536 EPOCH 2 done: loss 0.1565 - lr: 0.000044 | |
| 2023-10-13 13:37:46,225 DEV : loss 0.146720752120018 - f1-score (micro avg) 0.6869 | |
| 2023-10-13 13:37:46,253 saving best model | |
| 2023-10-13 13:37:46,641 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:37:50,828 epoch 3 - iter 89/894 - loss 0.11101622 - time (sec): 4.19 - samples/sec: 2071.00 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 13:37:55,412 epoch 3 - iter 178/894 - loss 0.10493274 - time (sec): 8.77 - samples/sec: 2056.15 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 13:37:59,662 epoch 3 - iter 267/894 - loss 0.10198121 - time (sec): 13.02 - samples/sec: 2031.68 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 13:38:03,763 epoch 3 - iter 356/894 - loss 0.10072889 - time (sec): 17.12 - samples/sec: 2031.21 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 13:38:07,891 epoch 3 - iter 445/894 - loss 0.10004708 - time (sec): 21.25 - samples/sec: 2003.26 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 13:38:11,984 epoch 3 - iter 534/894 - loss 0.09936209 - time (sec): 25.34 - samples/sec: 2018.71 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 13:38:16,023 epoch 3 - iter 623/894 - loss 0.09825369 - time (sec): 29.38 - samples/sec: 2020.23 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 13:38:20,434 epoch 3 - iter 712/894 - loss 0.09475486 - time (sec): 33.79 - samples/sec: 2027.08 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 13:38:24,656 epoch 3 - iter 801/894 - loss 0.09884765 - time (sec): 38.01 - samples/sec: 2018.81 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 13:38:28,994 epoch 3 - iter 890/894 - loss 0.09665535 - time (sec): 42.35 - samples/sec: 2034.77 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 13:38:29,183 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:38:29,183 EPOCH 3 done: loss 0.0966 - lr: 0.000039 | |
| 2023-10-13 13:38:38,013 DEV : loss 0.1882152259349823 - f1-score (micro avg) 0.7134 | |
| 2023-10-13 13:38:38,040 saving best model | |
| 2023-10-13 13:38:38,468 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:38:42,765 epoch 4 - iter 89/894 - loss 0.05521601 - time (sec): 4.29 - samples/sec: 2010.24 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 13:38:46,774 epoch 4 - iter 178/894 - loss 0.06025113 - time (sec): 8.30 - samples/sec: 2000.44 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 13:38:50,728 epoch 4 - iter 267/894 - loss 0.06246618 - time (sec): 12.25 - samples/sec: 2061.29 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 13:38:54,961 epoch 4 - iter 356/894 - loss 0.05713263 - time (sec): 16.49 - samples/sec: 2066.43 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 13:38:59,367 epoch 4 - iter 445/894 - loss 0.05854806 - time (sec): 20.89 - samples/sec: 2093.48 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 13:39:03,669 epoch 4 - iter 534/894 - loss 0.05727048 - time (sec): 25.19 - samples/sec: 2083.68 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 13:39:07,689 epoch 4 - iter 623/894 - loss 0.05943191 - time (sec): 29.21 - samples/sec: 2067.43 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 13:39:11,950 epoch 4 - iter 712/894 - loss 0.05928586 - time (sec): 33.48 - samples/sec: 2074.11 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 13:39:16,241 epoch 4 - iter 801/894 - loss 0.06054469 - time (sec): 37.77 - samples/sec: 2068.73 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 13:39:20,667 epoch 4 - iter 890/894 - loss 0.05991357 - time (sec): 42.19 - samples/sec: 2042.27 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 13:39:20,844 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:39:20,844 EPOCH 4 done: loss 0.0601 - lr: 0.000033 | |
| 2023-10-13 13:39:29,758 DEV : loss 0.19933967292308807 - f1-score (micro avg) 0.7387 | |
| 2023-10-13 13:39:29,792 saving best model | |
| 2023-10-13 13:39:30,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:39:34,666 epoch 5 - iter 89/894 - loss 0.05581229 - time (sec): 4.37 - samples/sec: 2074.31 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 13:39:39,035 epoch 5 - iter 178/894 - loss 0.04722653 - time (sec): 8.74 - samples/sec: 1991.98 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 13:39:43,612 epoch 5 - iter 267/894 - loss 0.04585486 - time (sec): 13.31 - samples/sec: 1974.54 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 13:39:47,897 epoch 5 - iter 356/894 - loss 0.04522439 - time (sec): 17.60 - samples/sec: 1991.17 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 13:39:52,087 epoch 5 - iter 445/894 - loss 0.04771289 - time (sec): 21.79 - samples/sec: 1986.95 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 13:39:56,379 epoch 5 - iter 534/894 - loss 0.04810893 - time (sec): 26.08 - samples/sec: 1984.66 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 13:40:00,872 epoch 5 - iter 623/894 - loss 0.04557853 - time (sec): 30.57 - samples/sec: 2003.60 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 13:40:05,100 epoch 5 - iter 712/894 - loss 0.04568690 - time (sec): 34.80 - samples/sec: 1991.16 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 13:40:09,267 epoch 5 - iter 801/894 - loss 0.04528489 - time (sec): 38.97 - samples/sec: 1993.82 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 13:40:13,313 epoch 5 - iter 890/894 - loss 0.04320919 - time (sec): 43.01 - samples/sec: 2005.20 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 13:40:13,482 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:40:13,482 EPOCH 5 done: loss 0.0432 - lr: 0.000028 | |
| 2023-10-13 13:40:22,114 DEV : loss 0.22585448622703552 - f1-score (micro avg) 0.7412 | |
| 2023-10-13 13:40:22,142 saving best model | |
| 2023-10-13 13:40:22,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:40:27,061 epoch 6 - iter 89/894 - loss 0.02085790 - time (sec): 4.45 - samples/sec: 1968.09 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 13:40:31,364 epoch 6 - iter 178/894 - loss 0.02817642 - time (sec): 8.75 - samples/sec: 2031.27 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 13:40:35,396 epoch 6 - iter 267/894 - loss 0.02565474 - time (sec): 12.79 - samples/sec: 2051.52 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 13:40:39,892 epoch 6 - iter 356/894 - loss 0.02217424 - time (sec): 17.28 - samples/sec: 2095.95 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 13:40:44,068 epoch 6 - iter 445/894 - loss 0.02178014 - time (sec): 21.46 - samples/sec: 2037.88 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 13:40:48,065 epoch 6 - iter 534/894 - loss 0.02116497 - time (sec): 25.45 - samples/sec: 2044.48 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 13:40:52,279 epoch 6 - iter 623/894 - loss 0.02285682 - time (sec): 29.67 - samples/sec: 2040.62 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 13:40:56,435 epoch 6 - iter 712/894 - loss 0.02393454 - time (sec): 33.82 - samples/sec: 2029.42 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 13:41:00,740 epoch 6 - iter 801/894 - loss 0.02490852 - time (sec): 38.13 - samples/sec: 2034.66 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 13:41:04,960 epoch 6 - iter 890/894 - loss 0.02709514 - time (sec): 42.35 - samples/sec: 2036.01 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 13:41:05,130 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:41:05,130 EPOCH 6 done: loss 0.0271 - lr: 0.000022 | |
| 2023-10-13 13:41:13,883 DEV : loss 0.20660947263240814 - f1-score (micro avg) 0.7692 | |
| 2023-10-13 13:41:13,912 saving best model | |
| 2023-10-13 13:41:14,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:41:18,988 epoch 7 - iter 89/894 - loss 0.01441146 - time (sec): 4.61 - samples/sec: 2170.14 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 13:41:23,142 epoch 7 - iter 178/894 - loss 0.01336769 - time (sec): 8.77 - samples/sec: 2064.61 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 13:41:27,267 epoch 7 - iter 267/894 - loss 0.01184471 - time (sec): 12.89 - samples/sec: 2090.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 13:41:31,390 epoch 7 - iter 356/894 - loss 0.01381643 - time (sec): 17.02 - samples/sec: 2108.61 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 13:41:35,581 epoch 7 - iter 445/894 - loss 0.01343301 - time (sec): 21.21 - samples/sec: 2094.77 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 13:41:39,673 epoch 7 - iter 534/894 - loss 0.01496204 - time (sec): 25.30 - samples/sec: 2059.50 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 13:41:43,879 epoch 7 - iter 623/894 - loss 0.01637548 - time (sec): 29.51 - samples/sec: 2062.67 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 13:41:48,037 epoch 7 - iter 712/894 - loss 0.01538496 - time (sec): 33.66 - samples/sec: 2054.63 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 13:41:52,153 epoch 7 - iter 801/894 - loss 0.01717510 - time (sec): 37.78 - samples/sec: 2051.43 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 13:41:56,385 epoch 7 - iter 890/894 - loss 0.01693132 - time (sec): 42.01 - samples/sec: 2051.71 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 13:41:56,565 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:41:56,565 EPOCH 7 done: loss 0.0169 - lr: 0.000017 | |
| 2023-10-13 13:42:05,324 DEV : loss 0.2536468803882599 - f1-score (micro avg) 0.7769 | |
| 2023-10-13 13:42:05,352 saving best model | |
| 2023-10-13 13:42:05,779 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:42:10,163 epoch 8 - iter 89/894 - loss 0.00786799 - time (sec): 4.38 - samples/sec: 1996.79 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 13:42:14,442 epoch 8 - iter 178/894 - loss 0.00866875 - time (sec): 8.66 - samples/sec: 1994.51 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 13:42:18,591 epoch 8 - iter 267/894 - loss 0.01092078 - time (sec): 12.81 - samples/sec: 2002.69 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 13:42:22,760 epoch 8 - iter 356/894 - loss 0.01198771 - time (sec): 16.98 - samples/sec: 1994.23 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 13:42:26,964 epoch 8 - iter 445/894 - loss 0.01138557 - time (sec): 21.18 - samples/sec: 1994.40 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 13:42:31,193 epoch 8 - iter 534/894 - loss 0.01099923 - time (sec): 25.41 - samples/sec: 1991.11 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 13:42:35,348 epoch 8 - iter 623/894 - loss 0.01067929 - time (sec): 29.57 - samples/sec: 1999.99 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 13:42:39,827 epoch 8 - iter 712/894 - loss 0.01143117 - time (sec): 34.05 - samples/sec: 2006.75 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 13:42:44,083 epoch 8 - iter 801/894 - loss 0.01122106 - time (sec): 38.30 - samples/sec: 2025.04 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 13:42:48,301 epoch 8 - iter 890/894 - loss 0.01097617 - time (sec): 42.52 - samples/sec: 2029.05 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 13:42:48,491 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:42:48,492 EPOCH 8 done: loss 0.0109 - lr: 0.000011 | |
| 2023-10-13 13:42:57,409 DEV : loss 0.25275343656539917 - f1-score (micro avg) 0.7708 | |
| 2023-10-13 13:42:57,440 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:43:02,157 epoch 9 - iter 89/894 - loss 0.00495732 - time (sec): 4.72 - samples/sec: 1777.88 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 13:43:06,477 epoch 9 - iter 178/894 - loss 0.00486139 - time (sec): 9.04 - samples/sec: 1901.16 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 13:43:10,501 epoch 9 - iter 267/894 - loss 0.00630451 - time (sec): 13.06 - samples/sec: 1931.23 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 13:43:14,571 epoch 9 - iter 356/894 - loss 0.00739423 - time (sec): 17.13 - samples/sec: 1957.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 13:43:18,711 epoch 9 - iter 445/894 - loss 0.00718639 - time (sec): 21.27 - samples/sec: 2000.40 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 13:43:22,820 epoch 9 - iter 534/894 - loss 0.00649298 - time (sec): 25.38 - samples/sec: 2010.27 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 13:43:26,935 epoch 9 - iter 623/894 - loss 0.00722465 - time (sec): 29.49 - samples/sec: 2039.50 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 13:43:31,387 epoch 9 - iter 712/894 - loss 0.00773812 - time (sec): 33.95 - samples/sec: 2060.28 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 13:43:35,413 epoch 9 - iter 801/894 - loss 0.00726079 - time (sec): 37.97 - samples/sec: 2056.51 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 13:43:39,402 epoch 9 - iter 890/894 - loss 0.00690011 - time (sec): 41.96 - samples/sec: 2056.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 13:43:39,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:43:39,576 EPOCH 9 done: loss 0.0069 - lr: 0.000006 | |
| 2023-10-13 13:43:48,273 DEV : loss 0.2594471275806427 - f1-score (micro avg) 0.7778 | |
| 2023-10-13 13:43:48,300 saving best model | |
| 2023-10-13 13:43:48,726 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:43:53,074 epoch 10 - iter 89/894 - loss 0.00215822 - time (sec): 4.35 - samples/sec: 2283.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 13:43:57,281 epoch 10 - iter 178/894 - loss 0.00389851 - time (sec): 8.55 - samples/sec: 2190.38 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 13:44:01,325 epoch 10 - iter 267/894 - loss 0.00350003 - time (sec): 12.60 - samples/sec: 2146.14 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 13:44:05,445 epoch 10 - iter 356/894 - loss 0.00399930 - time (sec): 16.72 - samples/sec: 2102.62 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 13:44:09,795 epoch 10 - iter 445/894 - loss 0.00340014 - time (sec): 21.07 - samples/sec: 2080.76 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 13:44:14,542 epoch 10 - iter 534/894 - loss 0.00358239 - time (sec): 25.82 - samples/sec: 2011.27 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 13:44:19,279 epoch 10 - iter 623/894 - loss 0.00371600 - time (sec): 30.55 - samples/sec: 1968.33 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 13:44:23,736 epoch 10 - iter 712/894 - loss 0.00366171 - time (sec): 35.01 - samples/sec: 1968.68 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 13:44:28,034 epoch 10 - iter 801/894 - loss 0.00355658 - time (sec): 39.31 - samples/sec: 1972.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 13:44:32,317 epoch 10 - iter 890/894 - loss 0.00415920 - time (sec): 43.59 - samples/sec: 1977.84 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 13:44:32,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:44:32,511 EPOCH 10 done: loss 0.0041 - lr: 0.000000 | |
| 2023-10-13 13:44:41,095 DEV : loss 0.26341870427131653 - f1-score (micro avg) 0.7824 | |
| 2023-10-13 13:44:41,123 saving best model | |
| 2023-10-13 13:44:41,945 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 13:44:41,946 Loading model from best epoch ... | |
| 2023-10-13 13:44:43,435 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-13 13:44:48,077 | |
| Results: | |
| - F-score (micro) 0.7298 | |
| - F-score (macro) 0.658 | |
| - Accuracy 0.5973 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8023 0.8238 0.8129 596 | |
| pers 0.6329 0.7508 0.6868 333 | |
| org 0.5833 0.5303 0.5556 132 | |
| prod 0.6087 0.4242 0.5000 66 | |
| time 0.7347 0.7347 0.7347 49 | |
| micro avg 0.7160 0.7440 0.7298 1176 | |
| macro avg 0.6724 0.6528 0.6580 1176 | |
| weighted avg 0.7161 0.7440 0.7275 1176 | |
| 2023-10-13 13:44:48,078 ---------------------------------------------------------------------------------------------------- | |