| 2023-10-19 20:02:41,370 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,370 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-19 20:02:41,370 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,370 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 | |
| 2023-10-19 20:02:41,370 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,370 Train: 7142 sentences | |
| 2023-10-19 20:02:41,370 (train_with_dev=False, train_with_test=False) | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Training Params: | |
| 2023-10-19 20:02:41,371 - learning_rate: "3e-05" | |
| 2023-10-19 20:02:41,371 - mini_batch_size: "8" | |
| 2023-10-19 20:02:41,371 - max_epochs: "10" | |
| 2023-10-19 20:02:41,371 - shuffle: "True" | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Plugins: | |
| 2023-10-19 20:02:41,371 - TensorboardLogger | |
| 2023-10-19 20:02:41,371 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-19 20:02:41,371 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Computation: | |
| 2023-10-19 20:02:41,371 - compute on device: cuda:0 | |
| 2023-10-19 20:02:41,371 - embedding storage: none | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Model training base path: "hmbench-newseye/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:02:41,371 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-19 20:02:43,725 epoch 1 - iter 89/893 - loss 2.79188490 - time (sec): 2.35 - samples/sec: 11352.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:02:46,036 epoch 1 - iter 178/893 - loss 2.61515556 - time (sec): 4.66 - samples/sec: 10906.94 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:02:48,288 epoch 1 - iter 267/893 - loss 2.34054331 - time (sec): 6.92 - samples/sec: 10747.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:02:50,551 epoch 1 - iter 356/893 - loss 2.03989423 - time (sec): 9.18 - samples/sec: 10817.11 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:02:52,789 epoch 1 - iter 445/893 - loss 1.80785549 - time (sec): 11.42 - samples/sec: 10771.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:02:54,975 epoch 1 - iter 534/893 - loss 1.64636165 - time (sec): 13.60 - samples/sec: 10816.29 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:02:57,307 epoch 1 - iter 623/893 - loss 1.49893188 - time (sec): 15.94 - samples/sec: 10849.48 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:02:59,556 epoch 1 - iter 712/893 - loss 1.39030658 - time (sec): 18.18 - samples/sec: 10811.44 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:03:01,862 epoch 1 - iter 801/893 - loss 1.30158560 - time (sec): 20.49 - samples/sec: 10831.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:03:04,146 epoch 1 - iter 890/893 - loss 1.22337235 - time (sec): 22.77 - samples/sec: 10892.98 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 20:03:04,227 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:04,227 EPOCH 1 done: loss 1.2217 - lr: 0.000030 | |
| 2023-10-19 20:03:05,672 DEV : loss 0.3446877598762512 - f1-score (micro avg) 0.0378 | |
| 2023-10-19 20:03:05,686 saving best model | |
| 2023-10-19 20:03:05,721 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:07,724 epoch 2 - iter 89/893 - loss 0.55265620 - time (sec): 2.00 - samples/sec: 11812.70 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 20:03:09,989 epoch 2 - iter 178/893 - loss 0.50626466 - time (sec): 4.27 - samples/sec: 11382.89 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:03:12,173 epoch 2 - iter 267/893 - loss 0.50045584 - time (sec): 6.45 - samples/sec: 11059.55 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:03:14,417 epoch 2 - iter 356/893 - loss 0.49013333 - time (sec): 8.70 - samples/sec: 11043.35 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:03:16,658 epoch 2 - iter 445/893 - loss 0.49176159 - time (sec): 10.94 - samples/sec: 11102.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:03:18,956 epoch 2 - iter 534/893 - loss 0.48647694 - time (sec): 13.24 - samples/sec: 11113.66 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:03:21,023 epoch 2 - iter 623/893 - loss 0.47781561 - time (sec): 15.30 - samples/sec: 11386.80 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:03:23,292 epoch 2 - iter 712/893 - loss 0.47306629 - time (sec): 17.57 - samples/sec: 11350.70 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:03:25,506 epoch 2 - iter 801/893 - loss 0.47156156 - time (sec): 19.78 - samples/sec: 11325.69 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:03:27,763 epoch 2 - iter 890/893 - loss 0.46923210 - time (sec): 22.04 - samples/sec: 11261.08 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:03:27,837 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:27,838 EPOCH 2 done: loss 0.4691 - lr: 0.000027 | |
| 2023-10-19 20:03:30,630 DEV : loss 0.279310941696167 - f1-score (micro avg) 0.2653 | |
| 2023-10-19 20:03:30,644 saving best model | |
| 2023-10-19 20:03:30,676 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:32,903 epoch 3 - iter 89/893 - loss 0.40506812 - time (sec): 2.23 - samples/sec: 10690.15 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:03:35,235 epoch 3 - iter 178/893 - loss 0.38010385 - time (sec): 4.56 - samples/sec: 11115.43 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:03:37,501 epoch 3 - iter 267/893 - loss 0.37662633 - time (sec): 6.82 - samples/sec: 11073.04 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:03:39,721 epoch 3 - iter 356/893 - loss 0.38495631 - time (sec): 9.04 - samples/sec: 11045.67 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:03:41,991 epoch 3 - iter 445/893 - loss 0.38828927 - time (sec): 11.31 - samples/sec: 11129.43 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:03:44,287 epoch 3 - iter 534/893 - loss 0.39211636 - time (sec): 13.61 - samples/sec: 11133.36 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:03:46,507 epoch 3 - iter 623/893 - loss 0.39046621 - time (sec): 15.83 - samples/sec: 11032.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:03:48,760 epoch 3 - iter 712/893 - loss 0.39250884 - time (sec): 18.08 - samples/sec: 11020.44 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:03:51,013 epoch 3 - iter 801/893 - loss 0.39203862 - time (sec): 20.34 - samples/sec: 11038.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:03:53,262 epoch 3 - iter 890/893 - loss 0.38941708 - time (sec): 22.59 - samples/sec: 10979.59 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:03:53,342 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:53,342 EPOCH 3 done: loss 0.3895 - lr: 0.000023 | |
| 2023-10-19 20:03:55,699 DEV : loss 0.24555543065071106 - f1-score (micro avg) 0.3492 | |
| 2023-10-19 20:03:55,714 saving best model | |
| 2023-10-19 20:03:55,750 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:03:58,025 epoch 4 - iter 89/893 - loss 0.36113360 - time (sec): 2.27 - samples/sec: 11397.77 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:04:00,247 epoch 4 - iter 178/893 - loss 0.37535560 - time (sec): 4.50 - samples/sec: 11055.72 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:04:02,497 epoch 4 - iter 267/893 - loss 0.38798410 - time (sec): 6.75 - samples/sec: 10954.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:04:04,814 epoch 4 - iter 356/893 - loss 0.36743176 - time (sec): 9.06 - samples/sec: 10987.50 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:04:07,053 epoch 4 - iter 445/893 - loss 0.36072597 - time (sec): 11.30 - samples/sec: 11008.14 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:04:09,282 epoch 4 - iter 534/893 - loss 0.35634201 - time (sec): 13.53 - samples/sec: 10966.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:04:11,544 epoch 4 - iter 623/893 - loss 0.35741415 - time (sec): 15.79 - samples/sec: 10900.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:04:13,740 epoch 4 - iter 712/893 - loss 0.35551333 - time (sec): 17.99 - samples/sec: 10928.84 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:04:16,072 epoch 4 - iter 801/893 - loss 0.35441138 - time (sec): 20.32 - samples/sec: 10943.74 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:04:18,390 epoch 4 - iter 890/893 - loss 0.35047145 - time (sec): 22.64 - samples/sec: 10963.62 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:04:18,455 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:04:18,455 EPOCH 4 done: loss 0.3506 - lr: 0.000020 | |
| 2023-10-19 20:04:21,307 DEV : loss 0.23053158819675446 - f1-score (micro avg) 0.4164 | |
| 2023-10-19 20:04:21,320 saving best model | |
| 2023-10-19 20:04:21,354 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:04:23,584 epoch 5 - iter 89/893 - loss 0.36360822 - time (sec): 2.23 - samples/sec: 11218.46 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:04:25,876 epoch 5 - iter 178/893 - loss 0.34953845 - time (sec): 4.52 - samples/sec: 11330.46 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:04:28,191 epoch 5 - iter 267/893 - loss 0.33640113 - time (sec): 6.84 - samples/sec: 11092.39 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:04:30,437 epoch 5 - iter 356/893 - loss 0.33695372 - time (sec): 9.08 - samples/sec: 10958.27 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:04:32,684 epoch 5 - iter 445/893 - loss 0.33502067 - time (sec): 11.33 - samples/sec: 10796.79 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:04:34,983 epoch 5 - iter 534/893 - loss 0.32633282 - time (sec): 13.63 - samples/sec: 10838.27 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:04:37,208 epoch 5 - iter 623/893 - loss 0.32930044 - time (sec): 15.85 - samples/sec: 10786.98 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:04:39,526 epoch 5 - iter 712/893 - loss 0.32599754 - time (sec): 18.17 - samples/sec: 10806.95 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:04:41,815 epoch 5 - iter 801/893 - loss 0.32412592 - time (sec): 20.46 - samples/sec: 10882.52 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:04:44,085 epoch 5 - iter 890/893 - loss 0.32457590 - time (sec): 22.73 - samples/sec: 10907.25 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:04:44,171 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:04:44,171 EPOCH 5 done: loss 0.3245 - lr: 0.000017 | |
| 2023-10-19 20:04:46,562 DEV : loss 0.22031265497207642 - f1-score (micro avg) 0.4319 | |
| 2023-10-19 20:04:46,578 saving best model | |
| 2023-10-19 20:04:46,612 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:04:49,412 epoch 6 - iter 89/893 - loss 0.29917674 - time (sec): 2.80 - samples/sec: 8970.24 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:04:51,611 epoch 6 - iter 178/893 - loss 0.30090357 - time (sec): 5.00 - samples/sec: 9705.99 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:04:53,798 epoch 6 - iter 267/893 - loss 0.30335158 - time (sec): 7.19 - samples/sec: 10058.54 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:04:56,069 epoch 6 - iter 356/893 - loss 0.29977449 - time (sec): 9.46 - samples/sec: 10419.04 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:04:58,350 epoch 6 - iter 445/893 - loss 0.29912670 - time (sec): 11.74 - samples/sec: 10649.72 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:05:00,578 epoch 6 - iter 534/893 - loss 0.29972497 - time (sec): 13.97 - samples/sec: 10682.42 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:05:02,836 epoch 6 - iter 623/893 - loss 0.30160090 - time (sec): 16.22 - samples/sec: 10660.06 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:05:05,114 epoch 6 - iter 712/893 - loss 0.30329819 - time (sec): 18.50 - samples/sec: 10674.37 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:05:07,353 epoch 6 - iter 801/893 - loss 0.30226174 - time (sec): 20.74 - samples/sec: 10770.24 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:05:09,610 epoch 6 - iter 890/893 - loss 0.30273390 - time (sec): 23.00 - samples/sec: 10787.39 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:05:09,681 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:05:09,681 EPOCH 6 done: loss 0.3027 - lr: 0.000013 | |
| 2023-10-19 20:05:12,048 DEV : loss 0.21030142903327942 - f1-score (micro avg) 0.4508 | |
| 2023-10-19 20:05:12,062 saving best model | |
| 2023-10-19 20:05:12,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:05:14,410 epoch 7 - iter 89/893 - loss 0.27586402 - time (sec): 2.31 - samples/sec: 11425.48 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:05:16,516 epoch 7 - iter 178/893 - loss 0.29185307 - time (sec): 4.42 - samples/sec: 11712.87 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:05:18,743 epoch 7 - iter 267/893 - loss 0.28935607 - time (sec): 6.64 - samples/sec: 11312.02 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:05:21,023 epoch 7 - iter 356/893 - loss 0.29203548 - time (sec): 8.92 - samples/sec: 11033.42 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:05:23,248 epoch 7 - iter 445/893 - loss 0.29379774 - time (sec): 11.15 - samples/sec: 11063.54 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:05:25,531 epoch 7 - iter 534/893 - loss 0.29301504 - time (sec): 13.43 - samples/sec: 11023.25 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:05:27,819 epoch 7 - iter 623/893 - loss 0.29205510 - time (sec): 15.72 - samples/sec: 11044.37 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:05:30,143 epoch 7 - iter 712/893 - loss 0.29058991 - time (sec): 18.04 - samples/sec: 11110.85 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:05:32,363 epoch 7 - iter 801/893 - loss 0.29245337 - time (sec): 20.26 - samples/sec: 11065.63 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:05:34,600 epoch 7 - iter 890/893 - loss 0.29089580 - time (sec): 22.50 - samples/sec: 11036.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:05:34,670 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:05:34,671 EPOCH 7 done: loss 0.2911 - lr: 0.000010 | |
| 2023-10-19 20:05:37,489 DEV : loss 0.20720338821411133 - f1-score (micro avg) 0.4672 | |
| 2023-10-19 20:05:37,502 saving best model | |
| 2023-10-19 20:05:37,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:05:39,794 epoch 8 - iter 89/893 - loss 0.27774907 - time (sec): 2.26 - samples/sec: 11112.16 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:05:42,014 epoch 8 - iter 178/893 - loss 0.26957585 - time (sec): 4.48 - samples/sec: 11162.38 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:05:44,238 epoch 8 - iter 267/893 - loss 0.28147536 - time (sec): 6.70 - samples/sec: 11015.63 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:05:46,501 epoch 8 - iter 356/893 - loss 0.28289854 - time (sec): 8.96 - samples/sec: 11009.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:05:48,711 epoch 8 - iter 445/893 - loss 0.28117295 - time (sec): 11.17 - samples/sec: 11071.86 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:05:50,984 epoch 8 - iter 534/893 - loss 0.28021332 - time (sec): 13.45 - samples/sec: 11099.17 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:05:53,200 epoch 8 - iter 623/893 - loss 0.28009769 - time (sec): 15.66 - samples/sec: 11108.29 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:05:55,483 epoch 8 - iter 712/893 - loss 0.27850109 - time (sec): 17.95 - samples/sec: 11093.56 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:05:57,728 epoch 8 - iter 801/893 - loss 0.28167039 - time (sec): 20.19 - samples/sec: 11062.97 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:05:59,979 epoch 8 - iter 890/893 - loss 0.28144169 - time (sec): 22.44 - samples/sec: 11048.66 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:06:00,053 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:00,053 EPOCH 8 done: loss 0.2812 - lr: 0.000007 | |
| 2023-10-19 20:06:02,455 DEV : loss 0.20476743578910828 - f1-score (micro avg) 0.4805 | |
| 2023-10-19 20:06:02,469 saving best model | |
| 2023-10-19 20:06:02,504 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:04,834 epoch 9 - iter 89/893 - loss 0.27170126 - time (sec): 2.33 - samples/sec: 11367.49 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:06:07,090 epoch 9 - iter 178/893 - loss 0.26530562 - time (sec): 4.59 - samples/sec: 11293.74 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:06:09,087 epoch 9 - iter 267/893 - loss 0.26261891 - time (sec): 6.58 - samples/sec: 11573.45 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:06:11,314 epoch 9 - iter 356/893 - loss 0.26838652 - time (sec): 8.81 - samples/sec: 11293.47 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:06:13,535 epoch 9 - iter 445/893 - loss 0.27202370 - time (sec): 11.03 - samples/sec: 11166.55 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:06:15,784 epoch 9 - iter 534/893 - loss 0.27221890 - time (sec): 13.28 - samples/sec: 11209.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:06:18,056 epoch 9 - iter 623/893 - loss 0.27510528 - time (sec): 15.55 - samples/sec: 11191.69 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:06:20,253 epoch 9 - iter 712/893 - loss 0.27406065 - time (sec): 17.75 - samples/sec: 11176.26 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:06:22,509 epoch 9 - iter 801/893 - loss 0.27418893 - time (sec): 20.00 - samples/sec: 11185.83 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:06:24,749 epoch 9 - iter 890/893 - loss 0.27283631 - time (sec): 22.24 - samples/sec: 11150.60 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:06:24,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:24,823 EPOCH 9 done: loss 0.2724 - lr: 0.000003 | |
| 2023-10-19 20:06:27,630 DEV : loss 0.20394523441791534 - f1-score (micro avg) 0.4875 | |
| 2023-10-19 20:06:27,643 saving best model | |
| 2023-10-19 20:06:27,678 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:29,876 epoch 10 - iter 89/893 - loss 0.27186045 - time (sec): 2.20 - samples/sec: 10565.18 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:06:32,140 epoch 10 - iter 178/893 - loss 0.28325566 - time (sec): 4.46 - samples/sec: 10724.49 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:06:34,426 epoch 10 - iter 267/893 - loss 0.28330112 - time (sec): 6.75 - samples/sec: 10745.16 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:06:36,681 epoch 10 - iter 356/893 - loss 0.28151126 - time (sec): 9.00 - samples/sec: 10845.21 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:06:38,903 epoch 10 - iter 445/893 - loss 0.27886107 - time (sec): 11.22 - samples/sec: 10819.44 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:06:41,070 epoch 10 - iter 534/893 - loss 0.27309122 - time (sec): 13.39 - samples/sec: 10915.88 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:06:43,380 epoch 10 - iter 623/893 - loss 0.26808545 - time (sec): 15.70 - samples/sec: 10969.00 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:06:45,637 epoch 10 - iter 712/893 - loss 0.26343191 - time (sec): 17.96 - samples/sec: 11030.06 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:06:47,913 epoch 10 - iter 801/893 - loss 0.26658732 - time (sec): 20.23 - samples/sec: 11041.20 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-19 20:06:50,173 epoch 10 - iter 890/893 - loss 0.26998091 - time (sec): 22.49 - samples/sec: 11032.32 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-19 20:06:50,245 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:50,246 EPOCH 10 done: loss 0.2707 - lr: 0.000000 | |
| 2023-10-19 20:06:53,057 DEV : loss 0.20230604708194733 - f1-score (micro avg) 0.4879 | |
| 2023-10-19 20:06:53,070 saving best model | |
| 2023-10-19 20:06:53,132 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:06:53,132 Loading model from best epoch ... | |
| 2023-10-19 20:06:53,211 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 | |
| 2023-10-19 20:06:57,772 | |
| Results: | |
| - F-score (micro) 0.373 | |
| - F-score (macro) 0.2137 | |
| - Accuracy 0.2375 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.3794 0.4612 0.4163 1095 | |
| PER 0.3723 0.4595 0.4113 1012 | |
| ORG 0.0435 0.0196 0.0270 357 | |
| HumanProd 0.0000 0.0000 0.0000 33 | |
| micro avg 0.3564 0.3913 0.3730 2497 | |
| macro avg 0.1988 0.2351 0.2137 2497 | |
| weighted avg 0.3235 0.3913 0.3531 2497 | |
| 2023-10-19 20:06:57,772 ---------------------------------------------------------------------------------------------------- | |