2023-10-17 14:33:40,027 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,029 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=13, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 14:33:40,029 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,030 MultiCorpus: 6183 train + 680 dev + 2113 test sentences - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator 2023-10-17 14:33:40,030 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,030 Train: 6183 sentences 2023-10-17 14:33:40,030 (train_with_dev=False, train_with_test=False) 2023-10-17 14:33:40,030 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,030 Training Params: 2023-10-17 14:33:40,030 - learning_rate: "5e-05" 2023-10-17 14:33:40,030 - mini_batch_size: "8" 2023-10-17 14:33:40,030 - max_epochs: "10" 2023-10-17 14:33:40,030 - shuffle: "True" 2023-10-17 14:33:40,030 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,031 Plugins: 2023-10-17 14:33:40,031 - TensorboardLogger 2023-10-17 14:33:40,031 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 14:33:40,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,031 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 14:33:40,031 - metric: "('micro avg', 'f1-score')" 2023-10-17 14:33:40,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,031 Computation: 2023-10-17 14:33:40,031 - compute on device: cuda:0 2023-10-17 14:33:40,031 - embedding storage: none 2023-10-17 14:33:40,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,031 Model training base path: "hmbench-topres19th/en-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-17 14:33:40,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:33:40,032 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 14:33:47,292 epoch 1 - iter 77/773 - loss 2.50923587 - time (sec): 7.26 - samples/sec: 1831.85 - lr: 0.000005 - momentum: 0.000000 2023-10-17 14:33:54,411 epoch 1 - iter 154/773 - loss 1.42130164 - time (sec): 14.38 - samples/sec: 1820.77 - lr: 0.000010 - momentum: 0.000000 2023-10-17 14:34:01,440 epoch 1 - iter 231/773 - loss 1.00481350 - time (sec): 21.41 - samples/sec: 1826.16 - lr: 0.000015 - momentum: 0.000000 2023-10-17 14:34:08,979 epoch 1 - iter 308/773 - loss 0.80200716 - time (sec): 28.95 - samples/sec: 1752.52 - lr: 0.000020 - momentum: 0.000000 2023-10-17 14:34:16,018 epoch 1 - iter 385/773 - loss 0.68374915 - time (sec): 35.98 - samples/sec: 1715.41 - lr: 0.000025 - momentum: 0.000000 2023-10-17 14:34:22,978 epoch 1 - iter 462/773 - loss 0.58561188 - time (sec): 42.95 - samples/sec: 1737.12 - lr: 0.000030 - momentum: 0.000000 2023-10-17 14:34:29,816 epoch 1 - iter 539/773 - loss 0.52024904 - time (sec): 49.78 - samples/sec: 1741.94 - lr: 0.000035 - momentum: 0.000000 2023-10-17 14:34:36,668 epoch 1 - iter 616/773 - loss 0.46975073 - time (sec): 56.63 - samples/sec: 1747.71 - lr: 0.000040 - momentum: 0.000000 2023-10-17 14:34:43,744 epoch 1 - iter 693/773 - loss 0.42724592 - time (sec): 63.71 - samples/sec: 1754.87 - lr: 0.000045 - momentum: 0.000000 2023-10-17 14:34:50,680 epoch 1 - iter 770/773 - loss 0.39511649 - time (sec): 70.65 - samples/sec: 1750.92 - lr: 0.000050 - momentum: 0.000000 2023-10-17 14:34:50,952 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:34:50,952 EPOCH 1 done: loss 0.3936 - lr: 0.000050 2023-10-17 14:34:53,277 DEV : loss 0.05638180673122406 - f1-score (micro avg) 0.7427 2023-10-17 14:34:53,307 saving best model 2023-10-17 14:34:53,948 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:35:01,084 epoch 2 - iter 77/773 - loss 0.08450516 - time (sec): 7.13 - samples/sec: 1724.49 - lr: 0.000049 - momentum: 0.000000 2023-10-17 14:35:08,104 epoch 2 - iter 154/773 - loss 0.07623715 - time (sec): 14.15 - samples/sec: 1741.82 - lr: 0.000049 - momentum: 0.000000 2023-10-17 14:35:16,129 epoch 2 - iter 231/773 - loss 0.07797626 - time (sec): 22.18 - samples/sec: 1685.46 - lr: 0.000048 - momentum: 0.000000 2023-10-17 14:35:23,452 epoch 2 - iter 308/773 - loss 0.07829088 - time (sec): 29.50 - samples/sec: 1683.48 - lr: 0.000048 - momentum: 0.000000 2023-10-17 14:35:30,778 epoch 2 - iter 385/773 - loss 0.07642468 - time (sec): 36.83 - samples/sec: 1694.33 - lr: 0.000047 - momentum: 0.000000 2023-10-17 14:35:38,282 epoch 2 - iter 462/773 - loss 0.07853226 - time (sec): 44.33 - samples/sec: 1712.25 - lr: 0.000047 - momentum: 0.000000 2023-10-17 14:35:45,196 epoch 2 - iter 539/773 - loss 0.07797723 - time (sec): 51.25 - samples/sec: 1708.62 - lr: 0.000046 - momentum: 0.000000 2023-10-17 14:35:52,242 epoch 2 - iter 616/773 - loss 0.07775728 - time (sec): 58.29 - samples/sec: 1713.08 - lr: 0.000046 - momentum: 0.000000 2023-10-17 14:35:59,251 epoch 2 - iter 693/773 - loss 0.07783386 - time (sec): 65.30 - samples/sec: 1700.02 - lr: 0.000045 - momentum: 0.000000 2023-10-17 14:36:06,466 epoch 2 - iter 770/773 - loss 0.07655030 - time (sec): 72.52 - samples/sec: 1707.08 - lr: 0.000044 - momentum: 0.000000 2023-10-17 14:36:06,742 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:36:06,742 EPOCH 2 done: loss 0.0762 - lr: 0.000044 2023-10-17 14:36:09,756 DEV : loss 0.05624998360872269 - f1-score (micro avg) 0.7741 2023-10-17 14:36:09,787 saving best model 2023-10-17 14:36:11,251 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:36:18,549 epoch 3 - iter 77/773 - loss 0.04747565 - time (sec): 7.29 - samples/sec: 1682.24 - lr: 0.000044 - momentum: 0.000000 2023-10-17 14:36:26,038 epoch 3 - iter 154/773 - loss 0.05208446 - time (sec): 14.78 - samples/sec: 1713.20 - lr: 0.000043 - momentum: 0.000000 2023-10-17 14:36:33,264 epoch 3 - iter 231/773 - loss 0.05199616 - time (sec): 22.00 - samples/sec: 1689.36 - lr: 0.000043 - momentum: 0.000000 2023-10-17 14:36:40,604 epoch 3 - iter 308/773 - loss 0.04917980 - time (sec): 29.35 - samples/sec: 1690.54 - lr: 0.000042 - momentum: 0.000000 2023-10-17 14:36:47,941 epoch 3 - iter 385/773 - loss 0.04758071 - time (sec): 36.68 - samples/sec: 1678.00 - lr: 0.000042 - momentum: 0.000000 2023-10-17 14:36:55,193 epoch 3 - iter 462/773 - loss 0.04862057 - time (sec): 43.93 - samples/sec: 1685.83 - lr: 0.000041 - momentum: 0.000000 2023-10-17 14:37:02,584 epoch 3 - iter 539/773 - loss 0.04856681 - time (sec): 51.33 - samples/sec: 1684.53 - lr: 0.000041 - momentum: 0.000000 2023-10-17 14:37:09,641 epoch 3 - iter 616/773 - loss 0.05066774 - time (sec): 58.38 - samples/sec: 1694.99 - lr: 0.000040 - momentum: 0.000000 2023-10-17 14:37:16,730 epoch 3 - iter 693/773 - loss 0.05007386 - time (sec): 65.47 - samples/sec: 1706.62 - lr: 0.000039 - momentum: 0.000000 2023-10-17 14:37:23,872 epoch 3 - iter 770/773 - loss 0.05081763 - time (sec): 72.61 - samples/sec: 1704.59 - lr: 0.000039 - momentum: 0.000000 2023-10-17 14:37:24,152 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:37:24,152 EPOCH 3 done: loss 0.0507 - lr: 0.000039 2023-10-17 14:37:27,074 DEV : loss 0.0668470710515976 - f1-score (micro avg) 0.7938 2023-10-17 14:37:27,103 saving best model 2023-10-17 14:37:28,513 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:37:35,670 epoch 4 - iter 77/773 - loss 0.03373869 - time (sec): 7.15 - samples/sec: 1716.25 - lr: 0.000038 - momentum: 0.000000 2023-10-17 14:37:42,914 epoch 4 - iter 154/773 - loss 0.03223990 - time (sec): 14.40 - samples/sec: 1797.82 - lr: 0.000038 - momentum: 0.000000 2023-10-17 14:37:50,041 epoch 4 - iter 231/773 - loss 0.03664264 - time (sec): 21.52 - samples/sec: 1788.19 - lr: 0.000037 - momentum: 0.000000 2023-10-17 14:37:56,925 epoch 4 - iter 308/773 - loss 0.03580473 - time (sec): 28.41 - samples/sec: 1766.49 - lr: 0.000037 - momentum: 0.000000 2023-10-17 14:38:03,783 epoch 4 - iter 385/773 - loss 0.03747929 - time (sec): 35.27 - samples/sec: 1758.49 - lr: 0.000036 - momentum: 0.000000 2023-10-17 14:38:11,144 epoch 4 - iter 462/773 - loss 0.03752798 - time (sec): 42.63 - samples/sec: 1757.21 - lr: 0.000036 - momentum: 0.000000 2023-10-17 14:38:18,355 epoch 4 - iter 539/773 - loss 0.03661439 - time (sec): 49.84 - samples/sec: 1767.40 - lr: 0.000035 - momentum: 0.000000 2023-10-17 14:38:25,461 epoch 4 - iter 616/773 - loss 0.03508167 - time (sec): 56.94 - samples/sec: 1758.48 - lr: 0.000034 - momentum: 0.000000 2023-10-17 14:38:32,556 epoch 4 - iter 693/773 - loss 0.03524376 - time (sec): 64.04 - samples/sec: 1756.85 - lr: 0.000034 - momentum: 0.000000 2023-10-17 14:38:39,444 epoch 4 - iter 770/773 - loss 0.03569860 - time (sec): 70.93 - samples/sec: 1747.91 - lr: 0.000033 - momentum: 0.000000 2023-10-17 14:38:39,704 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:38:39,705 EPOCH 4 done: loss 0.0357 - lr: 0.000033 2023-10-17 14:38:42,665 DEV : loss 0.09208610653877258 - f1-score (micro avg) 0.7724 2023-10-17 14:38:42,696 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:38:49,903 epoch 5 - iter 77/773 - loss 0.03208987 - time (sec): 7.20 - samples/sec: 1819.01 - lr: 0.000033 - momentum: 0.000000 2023-10-17 14:38:57,068 epoch 5 - iter 154/773 - loss 0.02963635 - time (sec): 14.37 - samples/sec: 1790.88 - lr: 0.000032 - momentum: 0.000000 2023-10-17 14:39:04,021 epoch 5 - iter 231/773 - loss 0.03156884 - time (sec): 21.32 - samples/sec: 1782.65 - lr: 0.000032 - momentum: 0.000000 2023-10-17 14:39:10,992 epoch 5 - iter 308/773 - loss 0.02957247 - time (sec): 28.29 - samples/sec: 1779.80 - lr: 0.000031 - momentum: 0.000000 2023-10-17 14:39:18,021 epoch 5 - iter 385/773 - loss 0.03043304 - time (sec): 35.32 - samples/sec: 1777.02 - lr: 0.000031 - momentum: 0.000000 2023-10-17 14:39:25,200 epoch 5 - iter 462/773 - loss 0.03088270 - time (sec): 42.50 - samples/sec: 1764.76 - lr: 0.000030 - momentum: 0.000000 2023-10-17 14:39:31,906 epoch 5 - iter 539/773 - loss 0.02923464 - time (sec): 49.21 - samples/sec: 1779.74 - lr: 0.000029 - momentum: 0.000000 2023-10-17 14:39:38,445 epoch 5 - iter 616/773 - loss 0.02915810 - time (sec): 55.75 - samples/sec: 1797.13 - lr: 0.000029 - momentum: 0.000000 2023-10-17 14:39:44,773 epoch 5 - iter 693/773 - loss 0.02815671 - time (sec): 62.07 - samples/sec: 1802.51 - lr: 0.000028 - momentum: 0.000000 2023-10-17 14:39:51,103 epoch 5 - iter 770/773 - loss 0.02806962 - time (sec): 68.41 - samples/sec: 1810.07 - lr: 0.000028 - momentum: 0.000000 2023-10-17 14:39:51,338 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:39:51,339 EPOCH 5 done: loss 0.0281 - lr: 0.000028 2023-10-17 14:39:54,281 DEV : loss 0.09081842750310898 - f1-score (micro avg) 0.7808 2023-10-17 14:39:54,311 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:40:01,302 epoch 6 - iter 77/773 - loss 0.01833530 - time (sec): 6.99 - samples/sec: 1755.27 - lr: 0.000027 - momentum: 0.000000 2023-10-17 14:40:08,326 epoch 6 - iter 154/773 - loss 0.01654716 - time (sec): 14.01 - samples/sec: 1770.07 - lr: 0.000027 - momentum: 0.000000 2023-10-17 14:40:15,751 epoch 6 - iter 231/773 - loss 0.01693263 - time (sec): 21.44 - samples/sec: 1749.34 - lr: 0.000026 - momentum: 0.000000 2023-10-17 14:40:22,848 epoch 6 - iter 308/773 - loss 0.01631071 - time (sec): 28.54 - samples/sec: 1762.95 - lr: 0.000026 - momentum: 0.000000 2023-10-17 14:40:29,756 epoch 6 - iter 385/773 - loss 0.01560773 - time (sec): 35.44 - samples/sec: 1745.74 - lr: 0.000025 - momentum: 0.000000 2023-10-17 14:40:37,016 epoch 6 - iter 462/773 - loss 0.01553854 - time (sec): 42.70 - samples/sec: 1752.52 - lr: 0.000024 - momentum: 0.000000 2023-10-17 14:40:43,841 epoch 6 - iter 539/773 - loss 0.01650694 - time (sec): 49.53 - samples/sec: 1737.47 - lr: 0.000024 - momentum: 0.000000 2023-10-17 14:40:50,797 epoch 6 - iter 616/773 - loss 0.01698956 - time (sec): 56.48 - samples/sec: 1733.26 - lr: 0.000023 - momentum: 0.000000 2023-10-17 14:40:57,982 epoch 6 - iter 693/773 - loss 0.01685377 - time (sec): 63.67 - samples/sec: 1744.16 - lr: 0.000023 - momentum: 0.000000 2023-10-17 14:41:05,215 epoch 6 - iter 770/773 - loss 0.01627500 - time (sec): 70.90 - samples/sec: 1746.88 - lr: 0.000022 - momentum: 0.000000 2023-10-17 14:41:05,480 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:41:05,481 EPOCH 6 done: loss 0.0163 - lr: 0.000022 2023-10-17 14:41:08,499 DEV : loss 0.10279172658920288 - f1-score (micro avg) 0.7918 2023-10-17 14:41:08,530 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:41:15,513 epoch 7 - iter 77/773 - loss 0.00452528 - time (sec): 6.98 - samples/sec: 1685.35 - lr: 0.000022 - momentum: 0.000000 2023-10-17 14:41:22,501 epoch 7 - iter 154/773 - loss 0.00876548 - time (sec): 13.97 - samples/sec: 1722.63 - lr: 0.000021 - momentum: 0.000000 2023-10-17 14:41:30,027 epoch 7 - iter 231/773 - loss 0.01243303 - time (sec): 21.49 - samples/sec: 1687.99 - lr: 0.000021 - momentum: 0.000000 2023-10-17 14:41:37,202 epoch 7 - iter 308/773 - loss 0.01319413 - time (sec): 28.67 - samples/sec: 1701.70 - lr: 0.000020 - momentum: 0.000000 2023-10-17 14:41:44,698 epoch 7 - iter 385/773 - loss 0.01232171 - time (sec): 36.17 - samples/sec: 1714.09 - lr: 0.000019 - momentum: 0.000000 2023-10-17 14:41:51,565 epoch 7 - iter 462/773 - loss 0.01118046 - time (sec): 43.03 - samples/sec: 1726.55 - lr: 0.000019 - momentum: 0.000000 2023-10-17 14:41:58,599 epoch 7 - iter 539/773 - loss 0.01102460 - time (sec): 50.07 - samples/sec: 1731.55 - lr: 0.000018 - momentum: 0.000000 2023-10-17 14:42:05,563 epoch 7 - iter 616/773 - loss 0.01052311 - time (sec): 57.03 - samples/sec: 1742.46 - lr: 0.000018 - momentum: 0.000000 2023-10-17 14:42:12,767 epoch 7 - iter 693/773 - loss 0.01166359 - time (sec): 64.23 - samples/sec: 1755.31 - lr: 0.000017 - momentum: 0.000000 2023-10-17 14:42:19,919 epoch 7 - iter 770/773 - loss 0.01166227 - time (sec): 71.39 - samples/sec: 1735.49 - lr: 0.000017 - momentum: 0.000000 2023-10-17 14:42:20,202 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:42:20,203 EPOCH 7 done: loss 0.0118 - lr: 0.000017 2023-10-17 14:42:23,314 DEV : loss 0.12683075666427612 - f1-score (micro avg) 0.7672 2023-10-17 14:42:23,351 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:42:30,519 epoch 8 - iter 77/773 - loss 0.01092306 - time (sec): 7.17 - samples/sec: 1632.15 - lr: 0.000016 - momentum: 0.000000 2023-10-17 14:42:37,610 epoch 8 - iter 154/773 - loss 0.00834521 - time (sec): 14.26 - samples/sec: 1700.73 - lr: 0.000016 - momentum: 0.000000 2023-10-17 14:42:44,625 epoch 8 - iter 231/773 - loss 0.00763347 - time (sec): 21.27 - samples/sec: 1715.42 - lr: 0.000015 - momentum: 0.000000 2023-10-17 14:42:51,811 epoch 8 - iter 308/773 - loss 0.00734188 - time (sec): 28.46 - samples/sec: 1728.36 - lr: 0.000014 - momentum: 0.000000 2023-10-17 14:42:59,357 epoch 8 - iter 385/773 - loss 0.00782979 - time (sec): 36.00 - samples/sec: 1723.98 - lr: 0.000014 - momentum: 0.000000 2023-10-17 14:43:06,454 epoch 8 - iter 462/773 - loss 0.00716809 - time (sec): 43.10 - samples/sec: 1728.60 - lr: 0.000013 - momentum: 0.000000 2023-10-17 14:43:13,826 epoch 8 - iter 539/773 - loss 0.00773899 - time (sec): 50.47 - samples/sec: 1734.28 - lr: 0.000013 - momentum: 0.000000 2023-10-17 14:43:20,901 epoch 8 - iter 616/773 - loss 0.00783439 - time (sec): 57.55 - samples/sec: 1726.13 - lr: 0.000012 - momentum: 0.000000 2023-10-17 14:43:27,798 epoch 8 - iter 693/773 - loss 0.00774684 - time (sec): 64.45 - samples/sec: 1726.79 - lr: 0.000012 - momentum: 0.000000 2023-10-17 14:43:35,007 epoch 8 - iter 770/773 - loss 0.00791622 - time (sec): 71.65 - samples/sec: 1727.63 - lr: 0.000011 - momentum: 0.000000 2023-10-17 14:43:35,283 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:43:35,284 EPOCH 8 done: loss 0.0081 - lr: 0.000011 2023-10-17 14:43:38,140 DEV : loss 0.12362485378980637 - f1-score (micro avg) 0.7778 2023-10-17 14:43:38,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:43:45,185 epoch 9 - iter 77/773 - loss 0.00194071 - time (sec): 7.01 - samples/sec: 1862.43 - lr: 0.000011 - momentum: 0.000000 2023-10-17 14:43:52,369 epoch 9 - iter 154/773 - loss 0.00273045 - time (sec): 14.20 - samples/sec: 1830.87 - lr: 0.000010 - momentum: 0.000000 2023-10-17 14:43:59,729 epoch 9 - iter 231/773 - loss 0.00364150 - time (sec): 21.56 - samples/sec: 1778.00 - lr: 0.000009 - momentum: 0.000000 2023-10-17 14:44:06,692 epoch 9 - iter 308/773 - loss 0.00314935 - time (sec): 28.52 - samples/sec: 1747.14 - lr: 0.000009 - momentum: 0.000000 2023-10-17 14:44:13,912 epoch 9 - iter 385/773 - loss 0.00381506 - time (sec): 35.74 - samples/sec: 1759.68 - lr: 0.000008 - momentum: 0.000000 2023-10-17 14:44:21,090 epoch 9 - iter 462/773 - loss 0.00476997 - time (sec): 42.92 - samples/sec: 1763.78 - lr: 0.000008 - momentum: 0.000000 2023-10-17 14:44:28,137 epoch 9 - iter 539/773 - loss 0.00427351 - time (sec): 49.97 - samples/sec: 1762.97 - lr: 0.000007 - momentum: 0.000000 2023-10-17 14:44:35,251 epoch 9 - iter 616/773 - loss 0.00437576 - time (sec): 57.08 - samples/sec: 1741.96 - lr: 0.000007 - momentum: 0.000000 2023-10-17 14:44:42,591 epoch 9 - iter 693/773 - loss 0.00480221 - time (sec): 64.42 - samples/sec: 1737.41 - lr: 0.000006 - momentum: 0.000000 2023-10-17 14:44:49,550 epoch 9 - iter 770/773 - loss 0.00516866 - time (sec): 71.38 - samples/sec: 1732.98 - lr: 0.000006 - momentum: 0.000000 2023-10-17 14:44:49,828 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:44:49,828 EPOCH 9 done: loss 0.0051 - lr: 0.000006 2023-10-17 14:44:52,751 DEV : loss 0.12392386794090271 - f1-score (micro avg) 0.7699 2023-10-17 14:44:52,780 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:45:00,250 epoch 10 - iter 77/773 - loss 0.00532611 - time (sec): 7.47 - samples/sec: 1608.63 - lr: 0.000005 - momentum: 0.000000 2023-10-17 14:45:07,239 epoch 10 - iter 154/773 - loss 0.00378488 - time (sec): 14.46 - samples/sec: 1647.56 - lr: 0.000005 - momentum: 0.000000 2023-10-17 14:45:14,478 epoch 10 - iter 231/773 - loss 0.00382497 - time (sec): 21.70 - samples/sec: 1688.02 - lr: 0.000004 - momentum: 0.000000 2023-10-17 14:45:21,681 epoch 10 - iter 308/773 - loss 0.00350380 - time (sec): 28.90 - samples/sec: 1711.86 - lr: 0.000003 - momentum: 0.000000 2023-10-17 14:45:28,814 epoch 10 - iter 385/773 - loss 0.00387383 - time (sec): 36.03 - samples/sec: 1709.60 - lr: 0.000003 - momentum: 0.000000 2023-10-17 14:45:35,914 epoch 10 - iter 462/773 - loss 0.00390395 - time (sec): 43.13 - samples/sec: 1713.52 - lr: 0.000002 - momentum: 0.000000 2023-10-17 14:45:43,094 epoch 10 - iter 539/773 - loss 0.00380626 - time (sec): 50.31 - samples/sec: 1717.59 - lr: 0.000002 - momentum: 0.000000 2023-10-17 14:45:50,077 epoch 10 - iter 616/773 - loss 0.00372703 - time (sec): 57.29 - samples/sec: 1724.36 - lr: 0.000001 - momentum: 0.000000 2023-10-17 14:45:56,991 epoch 10 - iter 693/773 - loss 0.00367782 - time (sec): 64.21 - samples/sec: 1740.68 - lr: 0.000001 - momentum: 0.000000 2023-10-17 14:46:03,998 epoch 10 - iter 770/773 - loss 0.00357798 - time (sec): 71.22 - samples/sec: 1737.64 - lr: 0.000000 - momentum: 0.000000 2023-10-17 14:46:04,264 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:46:04,264 EPOCH 10 done: loss 0.0036 - lr: 0.000000 2023-10-17 14:46:07,181 DEV : loss 0.12464166432619095 - f1-score (micro avg) 0.7835 2023-10-17 14:46:07,879 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:46:07,881 Loading model from best epoch ... 2023-10-17 14:46:10,198 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET 2023-10-17 14:46:18,809 Results: - F-score (micro) 0.7858 - F-score (macro) 0.6784 - Accuracy 0.6705 By class: precision recall f1-score support LOC 0.8015 0.8795 0.8387 946 BUILDING 0.5374 0.6216 0.5764 185 STREET 0.5479 0.7143 0.6202 56 micro avg 0.7449 0.8315 0.7858 1187 macro avg 0.6290 0.7385 0.6784 1187 weighted avg 0.7484 0.8315 0.7875 1187 2023-10-17 14:46:18,809 ----------------------------------------------------------------------------------------------------