2023-10-17 17:40:53,736 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,737 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=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 17:40:53,737 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 MultiCorpus: 1166 train + 165 dev + 415 test sentences - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Train: 1166 sentences 2023-10-17 17:40:53,738 (train_with_dev=False, train_with_test=False) 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Training Params: 2023-10-17 17:40:53,738 - learning_rate: "3e-05" 2023-10-17 17:40:53,738 - mini_batch_size: "4" 2023-10-17 17:40:53,738 - max_epochs: "10" 2023-10-17 17:40:53,738 - shuffle: "True" 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Plugins: 2023-10-17 17:40:53,738 - TensorboardLogger 2023-10-17 17:40:53,738 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 17:40:53,738 - metric: "('micro avg', 'f1-score')" 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Computation: 2023-10-17 17:40:53,738 - compute on device: cuda:0 2023-10-17 17:40:53,738 - embedding storage: none 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,738 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:40:53,739 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 17:40:55,392 epoch 1 - iter 29/292 - loss 3.68250305 - time (sec): 1.65 - samples/sec: 2700.70 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:40:57,068 epoch 1 - iter 58/292 - loss 3.14319074 - time (sec): 3.33 - samples/sec: 2759.47 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:40:58,833 epoch 1 - iter 87/292 - loss 2.40373810 - time (sec): 5.09 - samples/sec: 2632.37 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:41:00,337 epoch 1 - iter 116/292 - loss 1.99462913 - time (sec): 6.60 - samples/sec: 2597.35 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:41:01,905 epoch 1 - iter 145/292 - loss 1.71324812 - time (sec): 8.17 - samples/sec: 2605.46 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:41:03,463 epoch 1 - iter 174/292 - loss 1.49452360 - time (sec): 9.72 - samples/sec: 2614.47 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:41:05,137 epoch 1 - iter 203/292 - loss 1.32945702 - time (sec): 11.40 - samples/sec: 2608.52 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:41:06,708 epoch 1 - iter 232/292 - loss 1.21768316 - time (sec): 12.97 - samples/sec: 2597.01 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:41:08,391 epoch 1 - iter 261/292 - loss 1.10270361 - time (sec): 14.65 - samples/sec: 2622.03 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:41:10,413 epoch 1 - iter 290/292 - loss 1.00803344 - time (sec): 16.67 - samples/sec: 2653.62 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:41:10,509 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:10,509 EPOCH 1 done: loss 1.0055 - lr: 0.000030 2023-10-17 17:41:11,541 DEV : loss 0.18136057257652283 - f1-score (micro avg) 0.476 2023-10-17 17:41:11,546 saving best model 2023-10-17 17:41:11,880 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:13,724 epoch 2 - iter 29/292 - loss 0.27089229 - time (sec): 1.84 - samples/sec: 2733.99 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:41:15,282 epoch 2 - iter 58/292 - loss 0.26909781 - time (sec): 3.40 - samples/sec: 2563.95 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:41:16,787 epoch 2 - iter 87/292 - loss 0.25031740 - time (sec): 4.91 - samples/sec: 2554.96 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:41:18,259 epoch 2 - iter 116/292 - loss 0.23780745 - time (sec): 6.38 - samples/sec: 2539.34 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:41:20,070 epoch 2 - iter 145/292 - loss 0.24363146 - time (sec): 8.19 - samples/sec: 2617.92 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:41:21,741 epoch 2 - iter 174/292 - loss 0.22791139 - time (sec): 9.86 - samples/sec: 2566.47 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:41:23,404 epoch 2 - iter 203/292 - loss 0.21320925 - time (sec): 11.52 - samples/sec: 2565.02 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:41:25,029 epoch 2 - iter 232/292 - loss 0.20829472 - time (sec): 13.15 - samples/sec: 2566.07 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:41:26,841 epoch 2 - iter 261/292 - loss 0.19624855 - time (sec): 14.96 - samples/sec: 2612.33 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:41:28,696 epoch 2 - iter 290/292 - loss 0.19564262 - time (sec): 16.81 - samples/sec: 2633.34 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:41:28,790 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:28,791 EPOCH 2 done: loss 0.1950 - lr: 0.000027 2023-10-17 17:41:30,017 DEV : loss 0.11772378534078598 - f1-score (micro avg) 0.6652 2023-10-17 17:41:30,022 saving best model 2023-10-17 17:41:30,470 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:31,956 epoch 3 - iter 29/292 - loss 0.12437244 - time (sec): 1.48 - samples/sec: 2385.06 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:41:33,783 epoch 3 - iter 58/292 - loss 0.11415926 - time (sec): 3.31 - samples/sec: 2643.48 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:41:35,552 epoch 3 - iter 87/292 - loss 0.10815903 - time (sec): 5.08 - samples/sec: 2660.89 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:41:37,274 epoch 3 - iter 116/292 - loss 0.10540997 - time (sec): 6.80 - samples/sec: 2621.18 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:41:38,909 epoch 3 - iter 145/292 - loss 0.11397380 - time (sec): 8.43 - samples/sec: 2586.10 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:41:40,496 epoch 3 - iter 174/292 - loss 0.11201308 - time (sec): 10.02 - samples/sec: 2602.24 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:41:42,105 epoch 3 - iter 203/292 - loss 0.11590502 - time (sec): 11.63 - samples/sec: 2571.47 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:41:43,904 epoch 3 - iter 232/292 - loss 0.11396581 - time (sec): 13.43 - samples/sec: 2609.79 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:41:45,647 epoch 3 - iter 261/292 - loss 0.11202885 - time (sec): 15.17 - samples/sec: 2616.01 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:41:47,313 epoch 3 - iter 290/292 - loss 0.11160831 - time (sec): 16.84 - samples/sec: 2630.43 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:41:47,395 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:47,395 EPOCH 3 done: loss 0.1113 - lr: 0.000023 2023-10-17 17:41:48,677 DEV : loss 0.1223890632390976 - f1-score (micro avg) 0.7442 2023-10-17 17:41:48,682 saving best model 2023-10-17 17:41:49,156 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:41:50,842 epoch 4 - iter 29/292 - loss 0.06652164 - time (sec): 1.68 - samples/sec: 2930.17 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:41:52,443 epoch 4 - iter 58/292 - loss 0.07721451 - time (sec): 3.29 - samples/sec: 2823.05 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:41:54,122 epoch 4 - iter 87/292 - loss 0.09464470 - time (sec): 4.96 - samples/sec: 2769.06 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:41:55,600 epoch 4 - iter 116/292 - loss 0.08942417 - time (sec): 6.44 - samples/sec: 2674.86 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:41:57,265 epoch 4 - iter 145/292 - loss 0.08297407 - time (sec): 8.11 - samples/sec: 2674.26 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:41:59,057 epoch 4 - iter 174/292 - loss 0.08430332 - time (sec): 9.90 - samples/sec: 2704.79 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:42:00,597 epoch 4 - iter 203/292 - loss 0.08242476 - time (sec): 11.44 - samples/sec: 2670.17 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:42:02,247 epoch 4 - iter 232/292 - loss 0.08006731 - time (sec): 13.09 - samples/sec: 2644.82 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:42:03,920 epoch 4 - iter 261/292 - loss 0.07525678 - time (sec): 14.76 - samples/sec: 2651.25 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:42:05,625 epoch 4 - iter 290/292 - loss 0.07416172 - time (sec): 16.47 - samples/sec: 2691.57 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:42:05,708 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:05,708 EPOCH 4 done: loss 0.0740 - lr: 0.000020 2023-10-17 17:42:07,158 DEV : loss 0.13055771589279175 - f1-score (micro avg) 0.7602 2023-10-17 17:42:07,163 saving best model 2023-10-17 17:42:07,621 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:09,233 epoch 5 - iter 29/292 - loss 0.05571383 - time (sec): 1.61 - samples/sec: 2424.35 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:42:10,958 epoch 5 - iter 58/292 - loss 0.06187539 - time (sec): 3.33 - samples/sec: 2621.87 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:42:12,602 epoch 5 - iter 87/292 - loss 0.05527628 - time (sec): 4.98 - samples/sec: 2716.85 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:42:14,400 epoch 5 - iter 116/292 - loss 0.05682208 - time (sec): 6.77 - samples/sec: 2692.02 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:42:15,955 epoch 5 - iter 145/292 - loss 0.05460577 - time (sec): 8.33 - samples/sec: 2649.83 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:42:17,518 epoch 5 - iter 174/292 - loss 0.05178654 - time (sec): 9.89 - samples/sec: 2646.78 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:42:19,227 epoch 5 - iter 203/292 - loss 0.05084122 - time (sec): 11.60 - samples/sec: 2652.93 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:42:20,796 epoch 5 - iter 232/292 - loss 0.04985321 - time (sec): 13.17 - samples/sec: 2667.06 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:42:22,639 epoch 5 - iter 261/292 - loss 0.05230871 - time (sec): 15.01 - samples/sec: 2661.45 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:42:24,268 epoch 5 - iter 290/292 - loss 0.05658315 - time (sec): 16.64 - samples/sec: 2649.21 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:42:24,391 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:24,391 EPOCH 5 done: loss 0.0566 - lr: 0.000017 2023-10-17 17:42:25,637 DEV : loss 0.13382023572921753 - f1-score (micro avg) 0.7511 2023-10-17 17:42:25,642 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:27,192 epoch 6 - iter 29/292 - loss 0.02881444 - time (sec): 1.55 - samples/sec: 2584.46 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:42:29,029 epoch 6 - iter 58/292 - loss 0.04281959 - time (sec): 3.38 - samples/sec: 2679.47 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:42:30,557 epoch 6 - iter 87/292 - loss 0.03964120 - time (sec): 4.91 - samples/sec: 2585.43 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:42:32,359 epoch 6 - iter 116/292 - loss 0.03670832 - time (sec): 6.71 - samples/sec: 2583.43 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:42:34,249 epoch 6 - iter 145/292 - loss 0.03902949 - time (sec): 8.61 - samples/sec: 2586.32 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:42:35,947 epoch 6 - iter 174/292 - loss 0.03725768 - time (sec): 10.30 - samples/sec: 2631.61 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:42:37,562 epoch 6 - iter 203/292 - loss 0.03855395 - time (sec): 11.92 - samples/sec: 2622.30 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:42:39,209 epoch 6 - iter 232/292 - loss 0.03648586 - time (sec): 13.56 - samples/sec: 2603.71 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:42:40,834 epoch 6 - iter 261/292 - loss 0.03780658 - time (sec): 15.19 - samples/sec: 2607.88 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:42:42,380 epoch 6 - iter 290/292 - loss 0.03828100 - time (sec): 16.74 - samples/sec: 2650.48 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:42:42,461 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:42,461 EPOCH 6 done: loss 0.0382 - lr: 0.000013 2023-10-17 17:42:43,729 DEV : loss 0.1387849748134613 - f1-score (micro avg) 0.7562 2023-10-17 17:42:43,734 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:42:45,307 epoch 7 - iter 29/292 - loss 0.01361842 - time (sec): 1.57 - samples/sec: 2431.67 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:42:46,981 epoch 7 - iter 58/292 - loss 0.02741036 - time (sec): 3.25 - samples/sec: 2667.70 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:42:48,715 epoch 7 - iter 87/292 - loss 0.02358511 - time (sec): 4.98 - samples/sec: 2705.00 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:42:50,390 epoch 7 - iter 116/292 - loss 0.03159564 - time (sec): 6.65 - samples/sec: 2673.57 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:42:52,053 epoch 7 - iter 145/292 - loss 0.02732421 - time (sec): 8.32 - samples/sec: 2697.29 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:42:53,652 epoch 7 - iter 174/292 - loss 0.02603176 - time (sec): 9.92 - samples/sec: 2630.63 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:42:55,324 epoch 7 - iter 203/292 - loss 0.02704455 - time (sec): 11.59 - samples/sec: 2680.50 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:42:56,986 epoch 7 - iter 232/292 - loss 0.02861640 - time (sec): 13.25 - samples/sec: 2672.23 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:42:58,689 epoch 7 - iter 261/292 - loss 0.02783647 - time (sec): 14.95 - samples/sec: 2679.23 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:43:00,300 epoch 7 - iter 290/292 - loss 0.02793728 - time (sec): 16.57 - samples/sec: 2671.21 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:43:00,399 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:00,399 EPOCH 7 done: loss 0.0278 - lr: 0.000010 2023-10-17 17:43:01,670 DEV : loss 0.15122058987617493 - f1-score (micro avg) 0.7865 2023-10-17 17:43:01,676 saving best model 2023-10-17 17:43:02,074 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:03,652 epoch 8 - iter 29/292 - loss 0.03474470 - time (sec): 1.58 - samples/sec: 2548.38 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:43:05,374 epoch 8 - iter 58/292 - loss 0.03005709 - time (sec): 3.30 - samples/sec: 2550.78 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:43:07,042 epoch 8 - iter 87/292 - loss 0.02472687 - time (sec): 4.97 - samples/sec: 2531.31 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:43:08,591 epoch 8 - iter 116/292 - loss 0.02387951 - time (sec): 6.52 - samples/sec: 2547.94 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:43:10,241 epoch 8 - iter 145/292 - loss 0.02389223 - time (sec): 8.17 - samples/sec: 2591.36 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:43:11,927 epoch 8 - iter 174/292 - loss 0.02420953 - time (sec): 9.85 - samples/sec: 2622.08 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:43:13,437 epoch 8 - iter 203/292 - loss 0.02291096 - time (sec): 11.36 - samples/sec: 2610.71 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:43:15,274 epoch 8 - iter 232/292 - loss 0.02169136 - time (sec): 13.20 - samples/sec: 2650.27 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:43:16,993 epoch 8 - iter 261/292 - loss 0.02098081 - time (sec): 14.92 - samples/sec: 2627.87 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:43:18,843 epoch 8 - iter 290/292 - loss 0.02082531 - time (sec): 16.77 - samples/sec: 2642.30 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:43:18,932 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:18,932 EPOCH 8 done: loss 0.0208 - lr: 0.000007 2023-10-17 17:43:20,229 DEV : loss 0.1585906744003296 - f1-score (micro avg) 0.7679 2023-10-17 17:43:20,234 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:21,892 epoch 9 - iter 29/292 - loss 0.01213194 - time (sec): 1.66 - samples/sec: 2813.91 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:43:23,564 epoch 9 - iter 58/292 - loss 0.01599530 - time (sec): 3.33 - samples/sec: 2657.07 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:43:25,343 epoch 9 - iter 87/292 - loss 0.02053743 - time (sec): 5.11 - samples/sec: 2697.30 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:43:27,166 epoch 9 - iter 116/292 - loss 0.02114353 - time (sec): 6.93 - samples/sec: 2673.31 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:43:28,962 epoch 9 - iter 145/292 - loss 0.01954370 - time (sec): 8.73 - samples/sec: 2678.43 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:43:30,574 epoch 9 - iter 174/292 - loss 0.01808923 - time (sec): 10.34 - samples/sec: 2665.74 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:43:32,169 epoch 9 - iter 203/292 - loss 0.01813334 - time (sec): 11.93 - samples/sec: 2656.85 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:43:33,777 epoch 9 - iter 232/292 - loss 0.01754142 - time (sec): 13.54 - samples/sec: 2650.16 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:43:35,257 epoch 9 - iter 261/292 - loss 0.01772635 - time (sec): 15.02 - samples/sec: 2616.40 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:43:36,993 epoch 9 - iter 290/292 - loss 0.01726453 - time (sec): 16.76 - samples/sec: 2632.97 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:43:37,089 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:37,089 EPOCH 9 done: loss 0.0174 - lr: 0.000003 2023-10-17 17:43:38,331 DEV : loss 0.16505198180675507 - f1-score (micro avg) 0.7753 2023-10-17 17:43:38,336 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:39,887 epoch 10 - iter 29/292 - loss 0.00544103 - time (sec): 1.55 - samples/sec: 2830.15 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:43:41,491 epoch 10 - iter 58/292 - loss 0.01290303 - time (sec): 3.15 - samples/sec: 2692.45 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:43:43,394 epoch 10 - iter 87/292 - loss 0.01829305 - time (sec): 5.06 - samples/sec: 2546.21 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:43:45,078 epoch 10 - iter 116/292 - loss 0.01848904 - time (sec): 6.74 - samples/sec: 2661.73 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:43:46,711 epoch 10 - iter 145/292 - loss 0.01710130 - time (sec): 8.37 - samples/sec: 2698.38 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:43:48,242 epoch 10 - iter 174/292 - loss 0.01481307 - time (sec): 9.90 - samples/sec: 2677.18 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:43:50,174 epoch 10 - iter 203/292 - loss 0.01532186 - time (sec): 11.84 - samples/sec: 2663.93 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:43:51,882 epoch 10 - iter 232/292 - loss 0.01400894 - time (sec): 13.55 - samples/sec: 2675.56 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:43:53,457 epoch 10 - iter 261/292 - loss 0.01527717 - time (sec): 15.12 - samples/sec: 2665.48 - lr: 0.000000 - momentum: 0.000000 2023-10-17 17:43:55,002 epoch 10 - iter 290/292 - loss 0.01471316 - time (sec): 16.67 - samples/sec: 2654.31 - lr: 0.000000 - momentum: 0.000000 2023-10-17 17:43:55,093 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:55,093 EPOCH 10 done: loss 0.0146 - lr: 0.000000 2023-10-17 17:43:56,439 DEV : loss 0.16691839694976807 - f1-score (micro avg) 0.7648 2023-10-17 17:43:56,829 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:43:56,831 Loading model from best epoch ... 2023-10-17 17:43:58,309 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-17 17:44:01,099 Results: - F-score (micro) 0.7634 - F-score (macro) 0.6822 - Accuracy 0.6295 By class: precision recall f1-score support PER 0.8366 0.8534 0.8450 348 LOC 0.6485 0.8199 0.7242 261 ORG 0.4524 0.3654 0.4043 52 HumanProd 0.7391 0.7727 0.7556 22 micro avg 0.7293 0.8009 0.7634 683 macro avg 0.6692 0.7029 0.6822 683 weighted avg 0.7323 0.8009 0.7624 683 2023-10-17 17:44:01,099 ----------------------------------------------------------------------------------------------------