2023-10-17 17:58:07,427 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,428 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 17:58:07,428 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,428 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 17:58:07,428 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,428 Train: 1166 sentences 2023-10-17 17:58:07,428 (train_with_dev=False, train_with_test=False) 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Training Params: 2023-10-17 17:58:07,429 - learning_rate: "5e-05" 2023-10-17 17:58:07,429 - mini_batch_size: "4" 2023-10-17 17:58:07,429 - max_epochs: "10" 2023-10-17 17:58:07,429 - shuffle: "True" 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Plugins: 2023-10-17 17:58:07,429 - TensorboardLogger 2023-10-17 17:58:07,429 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 17:58:07,429 - metric: "('micro avg', 'f1-score')" 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Computation: 2023-10-17 17:58:07,429 - compute on device: cuda:0 2023-10-17 17:58:07,429 - embedding storage: none 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:07,429 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 17:58:08,948 epoch 1 - iter 29/292 - loss 3.35693242 - time (sec): 1.52 - samples/sec: 2481.07 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:58:10,706 epoch 1 - iter 58/292 - loss 2.40158772 - time (sec): 3.28 - samples/sec: 2746.46 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:58:12,378 epoch 1 - iter 87/292 - loss 1.81703963 - time (sec): 4.95 - samples/sec: 2780.63 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:58:14,242 epoch 1 - iter 116/292 - loss 1.50647114 - time (sec): 6.81 - samples/sec: 2755.93 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:58:15,845 epoch 1 - iter 145/292 - loss 1.30749839 - time (sec): 8.41 - samples/sec: 2710.21 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:58:17,535 epoch 1 - iter 174/292 - loss 1.14398900 - time (sec): 10.10 - samples/sec: 2704.56 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:58:19,202 epoch 1 - iter 203/292 - loss 1.02388352 - time (sec): 11.77 - samples/sec: 2705.79 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:58:20,739 epoch 1 - iter 232/292 - loss 0.95215720 - time (sec): 13.31 - samples/sec: 2692.50 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:58:22,437 epoch 1 - iter 261/292 - loss 0.87431897 - time (sec): 15.01 - samples/sec: 2663.32 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:58:24,018 epoch 1 - iter 290/292 - loss 0.81843563 - time (sec): 16.59 - samples/sec: 2663.35 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:58:24,125 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:24,125 EPOCH 1 done: loss 0.8153 - lr: 0.000049 2023-10-17 17:58:24,983 DEV : loss 0.16816182434558868 - f1-score (micro avg) 0.4943 2023-10-17 17:58:24,997 saving best model 2023-10-17 17:58:25,403 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:27,070 epoch 2 - iter 29/292 - loss 0.20843227 - time (sec): 1.66 - samples/sec: 2647.59 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:58:28,672 epoch 2 - iter 58/292 - loss 0.18562051 - time (sec): 3.27 - samples/sec: 2576.35 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:58:30,295 epoch 2 - iter 87/292 - loss 0.18807184 - time (sec): 4.89 - samples/sec: 2638.19 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:58:32,156 epoch 2 - iter 116/292 - loss 0.19178363 - time (sec): 6.75 - samples/sec: 2679.90 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:58:33,681 epoch 2 - iter 145/292 - loss 0.19660908 - time (sec): 8.28 - samples/sec: 2649.53 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:58:35,401 epoch 2 - iter 174/292 - loss 0.18834867 - time (sec): 10.00 - samples/sec: 2642.70 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:58:37,236 epoch 2 - iter 203/292 - loss 0.18795088 - time (sec): 11.83 - samples/sec: 2676.70 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:58:39,005 epoch 2 - iter 232/292 - loss 0.18476687 - time (sec): 13.60 - samples/sec: 2698.36 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:58:40,512 epoch 2 - iter 261/292 - loss 0.18398307 - time (sec): 15.11 - samples/sec: 2659.83 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:58:42,146 epoch 2 - iter 290/292 - loss 0.18080703 - time (sec): 16.74 - samples/sec: 2645.78 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:58:42,237 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:42,238 EPOCH 2 done: loss 0.1807 - lr: 0.000045 2023-10-17 17:58:43,941 DEV : loss 0.15552328526973724 - f1-score (micro avg) 0.6562 2023-10-17 17:58:43,947 saving best model 2023-10-17 17:58:44,403 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:58:46,086 epoch 3 - iter 29/292 - loss 0.10474185 - time (sec): 1.68 - samples/sec: 2898.39 - lr: 0.000044 - momentum: 0.000000 2023-10-17 17:58:47,922 epoch 3 - iter 58/292 - loss 0.10398762 - time (sec): 3.52 - samples/sec: 2759.49 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:58:49,548 epoch 3 - iter 87/292 - loss 0.12767526 - time (sec): 5.14 - samples/sec: 2718.62 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:58:51,123 epoch 3 - iter 116/292 - loss 0.12096457 - time (sec): 6.72 - samples/sec: 2666.56 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:58:52,826 epoch 3 - iter 145/292 - loss 0.11567654 - time (sec): 8.42 - samples/sec: 2657.83 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:58:54,601 epoch 3 - iter 174/292 - loss 0.11268765 - time (sec): 10.20 - samples/sec: 2654.12 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:58:56,170 epoch 3 - iter 203/292 - loss 0.10757754 - time (sec): 11.76 - samples/sec: 2657.91 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:58:57,967 epoch 3 - iter 232/292 - loss 0.10369889 - time (sec): 13.56 - samples/sec: 2639.60 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:58:59,651 epoch 3 - iter 261/292 - loss 0.10296987 - time (sec): 15.25 - samples/sec: 2626.33 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:59:01,340 epoch 3 - iter 290/292 - loss 0.10510734 - time (sec): 16.93 - samples/sec: 2614.92 - lr: 0.000039 - momentum: 0.000000 2023-10-17 17:59:01,427 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:01,428 EPOCH 3 done: loss 0.1050 - lr: 0.000039 2023-10-17 17:59:02,790 DEV : loss 0.10585162043571472 - f1-score (micro avg) 0.7419 2023-10-17 17:59:02,798 saving best model 2023-10-17 17:59:03,250 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:04,919 epoch 4 - iter 29/292 - loss 0.05183600 - time (sec): 1.66 - samples/sec: 2769.70 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:59:06,661 epoch 4 - iter 58/292 - loss 0.05491146 - time (sec): 3.41 - samples/sec: 2750.09 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:59:08,204 epoch 4 - iter 87/292 - loss 0.05566885 - time (sec): 4.95 - samples/sec: 2676.73 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:59:10,045 epoch 4 - iter 116/292 - loss 0.05537419 - time (sec): 6.79 - samples/sec: 2710.16 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:59:11,681 epoch 4 - iter 145/292 - loss 0.06564170 - time (sec): 8.43 - samples/sec: 2711.35 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:59:13,443 epoch 4 - iter 174/292 - loss 0.07091282 - time (sec): 10.19 - samples/sec: 2697.24 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:59:15,062 epoch 4 - iter 203/292 - loss 0.06947365 - time (sec): 11.81 - samples/sec: 2665.38 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:59:16,819 epoch 4 - iter 232/292 - loss 0.07485098 - time (sec): 13.56 - samples/sec: 2647.81 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:59:18,435 epoch 4 - iter 261/292 - loss 0.07325834 - time (sec): 15.18 - samples/sec: 2646.67 - lr: 0.000034 - momentum: 0.000000 2023-10-17 17:59:20,007 epoch 4 - iter 290/292 - loss 0.07071229 - time (sec): 16.75 - samples/sec: 2644.73 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:59:20,091 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:20,092 EPOCH 4 done: loss 0.0705 - lr: 0.000033 2023-10-17 17:59:21,397 DEV : loss 0.15273110568523407 - f1-score (micro avg) 0.7775 2023-10-17 17:59:21,403 saving best model 2023-10-17 17:59:21,837 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:23,539 epoch 5 - iter 29/292 - loss 0.03385877 - time (sec): 1.70 - samples/sec: 2504.93 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:59:25,093 epoch 5 - iter 58/292 - loss 0.04827007 - time (sec): 3.25 - samples/sec: 2622.66 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:59:26,808 epoch 5 - iter 87/292 - loss 0.04812479 - time (sec): 4.97 - samples/sec: 2736.37 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:59:28,532 epoch 5 - iter 116/292 - loss 0.04989877 - time (sec): 6.69 - samples/sec: 2676.73 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:59:30,292 epoch 5 - iter 145/292 - loss 0.05178593 - time (sec): 8.45 - samples/sec: 2646.29 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:59:31,921 epoch 5 - iter 174/292 - loss 0.04817322 - time (sec): 10.08 - samples/sec: 2640.85 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:59:33,512 epoch 5 - iter 203/292 - loss 0.04781243 - time (sec): 11.67 - samples/sec: 2643.03 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:59:35,227 epoch 5 - iter 232/292 - loss 0.04594962 - time (sec): 13.39 - samples/sec: 2631.40 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:59:36,905 epoch 5 - iter 261/292 - loss 0.04519214 - time (sec): 15.07 - samples/sec: 2644.65 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:59:38,544 epoch 5 - iter 290/292 - loss 0.04462130 - time (sec): 16.71 - samples/sec: 2652.22 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:59:38,636 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:38,637 EPOCH 5 done: loss 0.0446 - lr: 0.000028 2023-10-17 17:59:39,971 DEV : loss 0.1602601408958435 - f1-score (micro avg) 0.7296 2023-10-17 17:59:39,978 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:41,745 epoch 6 - iter 29/292 - loss 0.03117945 - time (sec): 1.77 - samples/sec: 2448.91 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:59:43,627 epoch 6 - iter 58/292 - loss 0.02884635 - time (sec): 3.65 - samples/sec: 2482.68 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:59:45,431 epoch 6 - iter 87/292 - loss 0.02959983 - time (sec): 5.45 - samples/sec: 2387.97 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:59:47,014 epoch 6 - iter 116/292 - loss 0.03130694 - time (sec): 7.03 - samples/sec: 2332.69 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:59:48,803 epoch 6 - iter 145/292 - loss 0.02949162 - time (sec): 8.82 - samples/sec: 2410.79 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:59:50,550 epoch 6 - iter 174/292 - loss 0.03282502 - time (sec): 10.57 - samples/sec: 2485.60 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:59:52,093 epoch 6 - iter 203/292 - loss 0.03369730 - time (sec): 12.11 - samples/sec: 2487.82 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:59:53,748 epoch 6 - iter 232/292 - loss 0.03273151 - time (sec): 13.77 - samples/sec: 2494.63 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:59:55,348 epoch 6 - iter 261/292 - loss 0.03486864 - time (sec): 15.37 - samples/sec: 2521.05 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:59:57,157 epoch 6 - iter 290/292 - loss 0.03165586 - time (sec): 17.18 - samples/sec: 2573.35 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:59:57,250 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:59:57,250 EPOCH 6 done: loss 0.0319 - lr: 0.000022 2023-10-17 17:59:58,554 DEV : loss 0.1713484823703766 - f1-score (micro avg) 0.773 2023-10-17 17:59:58,561 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:00,155 epoch 7 - iter 29/292 - loss 0.02059682 - time (sec): 1.59 - samples/sec: 2614.99 - lr: 0.000022 - momentum: 0.000000 2023-10-17 18:00:01,684 epoch 7 - iter 58/292 - loss 0.02743531 - time (sec): 3.12 - samples/sec: 2516.97 - lr: 0.000021 - momentum: 0.000000 2023-10-17 18:00:03,380 epoch 7 - iter 87/292 - loss 0.02412808 - time (sec): 4.82 - samples/sec: 2563.43 - lr: 0.000021 - momentum: 0.000000 2023-10-17 18:00:04,976 epoch 7 - iter 116/292 - loss 0.02556567 - time (sec): 6.41 - samples/sec: 2576.34 - lr: 0.000020 - momentum: 0.000000 2023-10-17 18:00:06,649 epoch 7 - iter 145/292 - loss 0.03034182 - time (sec): 8.09 - samples/sec: 2638.95 - lr: 0.000020 - momentum: 0.000000 2023-10-17 18:00:08,341 epoch 7 - iter 174/292 - loss 0.02823755 - time (sec): 9.78 - samples/sec: 2600.27 - lr: 0.000019 - momentum: 0.000000 2023-10-17 18:00:10,116 epoch 7 - iter 203/292 - loss 0.02560592 - time (sec): 11.55 - samples/sec: 2602.05 - lr: 0.000018 - momentum: 0.000000 2023-10-17 18:00:11,803 epoch 7 - iter 232/292 - loss 0.02413585 - time (sec): 13.24 - samples/sec: 2583.25 - lr: 0.000018 - momentum: 0.000000 2023-10-17 18:00:13,524 epoch 7 - iter 261/292 - loss 0.02391633 - time (sec): 14.96 - samples/sec: 2594.87 - lr: 0.000017 - momentum: 0.000000 2023-10-17 18:00:15,255 epoch 7 - iter 290/292 - loss 0.02352649 - time (sec): 16.69 - samples/sec: 2626.34 - lr: 0.000017 - momentum: 0.000000 2023-10-17 18:00:15,455 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:15,456 EPOCH 7 done: loss 0.0234 - lr: 0.000017 2023-10-17 18:00:16,783 DEV : loss 0.1889658421278 - f1-score (micro avg) 0.756 2023-10-17 18:00:16,790 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:18,494 epoch 8 - iter 29/292 - loss 0.01156358 - time (sec): 1.70 - samples/sec: 2576.80 - lr: 0.000016 - momentum: 0.000000 2023-10-17 18:00:20,203 epoch 8 - iter 58/292 - loss 0.01363486 - time (sec): 3.41 - samples/sec: 2579.01 - lr: 0.000016 - momentum: 0.000000 2023-10-17 18:00:21,863 epoch 8 - iter 87/292 - loss 0.01449766 - time (sec): 5.07 - samples/sec: 2619.98 - lr: 0.000015 - momentum: 0.000000 2023-10-17 18:00:23,775 epoch 8 - iter 116/292 - loss 0.01864699 - time (sec): 6.98 - samples/sec: 2550.16 - lr: 0.000015 - momentum: 0.000000 2023-10-17 18:00:25,440 epoch 8 - iter 145/292 - loss 0.01972188 - time (sec): 8.65 - samples/sec: 2588.01 - lr: 0.000014 - momentum: 0.000000 2023-10-17 18:00:27,084 epoch 8 - iter 174/292 - loss 0.01866095 - time (sec): 10.29 - samples/sec: 2627.52 - lr: 0.000013 - momentum: 0.000000 2023-10-17 18:00:28,834 epoch 8 - iter 203/292 - loss 0.01727761 - time (sec): 12.04 - samples/sec: 2658.79 - lr: 0.000013 - momentum: 0.000000 2023-10-17 18:00:30,336 epoch 8 - iter 232/292 - loss 0.01740192 - time (sec): 13.54 - samples/sec: 2627.55 - lr: 0.000012 - momentum: 0.000000 2023-10-17 18:00:32,062 epoch 8 - iter 261/292 - loss 0.01627368 - time (sec): 15.27 - samples/sec: 2641.10 - lr: 0.000012 - momentum: 0.000000 2023-10-17 18:00:33,679 epoch 8 - iter 290/292 - loss 0.01606708 - time (sec): 16.89 - samples/sec: 2620.90 - lr: 0.000011 - momentum: 0.000000 2023-10-17 18:00:33,770 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:33,770 EPOCH 8 done: loss 0.0160 - lr: 0.000011 2023-10-17 18:00:35,012 DEV : loss 0.20527206361293793 - f1-score (micro avg) 0.7478 2023-10-17 18:00:35,018 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:36,610 epoch 9 - iter 29/292 - loss 0.01233241 - time (sec): 1.59 - samples/sec: 2518.86 - lr: 0.000011 - momentum: 0.000000 2023-10-17 18:00:38,511 epoch 9 - iter 58/292 - loss 0.01637592 - time (sec): 3.49 - samples/sec: 2727.71 - lr: 0.000010 - momentum: 0.000000 2023-10-17 18:00:40,332 epoch 9 - iter 87/292 - loss 0.02791061 - time (sec): 5.31 - samples/sec: 2765.82 - lr: 0.000010 - momentum: 0.000000 2023-10-17 18:00:41,916 epoch 9 - iter 116/292 - loss 0.02442203 - time (sec): 6.90 - samples/sec: 2697.63 - lr: 0.000009 - momentum: 0.000000 2023-10-17 18:00:43,406 epoch 9 - iter 145/292 - loss 0.02208196 - time (sec): 8.39 - samples/sec: 2646.99 - lr: 0.000008 - momentum: 0.000000 2023-10-17 18:00:45,075 epoch 9 - iter 174/292 - loss 0.01999989 - time (sec): 10.06 - samples/sec: 2666.89 - lr: 0.000008 - momentum: 0.000000 2023-10-17 18:00:46,681 epoch 9 - iter 203/292 - loss 0.01804618 - time (sec): 11.66 - samples/sec: 2648.58 - lr: 0.000007 - momentum: 0.000000 2023-10-17 18:00:48,397 epoch 9 - iter 232/292 - loss 0.01685413 - time (sec): 13.38 - samples/sec: 2684.23 - lr: 0.000007 - momentum: 0.000000 2023-10-17 18:00:49,945 epoch 9 - iter 261/292 - loss 0.01630731 - time (sec): 14.93 - samples/sec: 2653.53 - lr: 0.000006 - momentum: 0.000000 2023-10-17 18:00:51,498 epoch 9 - iter 290/292 - loss 0.01472446 - time (sec): 16.48 - samples/sec: 2667.85 - lr: 0.000006 - momentum: 0.000000 2023-10-17 18:00:51,635 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:51,635 EPOCH 9 done: loss 0.0146 - lr: 0.000006 2023-10-17 18:00:52,961 DEV : loss 0.19456231594085693 - f1-score (micro avg) 0.7682 2023-10-17 18:00:52,968 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:00:54,993 epoch 10 - iter 29/292 - loss 0.01092397 - time (sec): 2.02 - samples/sec: 2646.57 - lr: 0.000005 - momentum: 0.000000 2023-10-17 18:00:56,816 epoch 10 - iter 58/292 - loss 0.00845707 - time (sec): 3.85 - samples/sec: 2558.88 - lr: 0.000005 - momentum: 0.000000 2023-10-17 18:00:58,489 epoch 10 - iter 87/292 - loss 0.00773468 - time (sec): 5.52 - samples/sec: 2551.82 - lr: 0.000004 - momentum: 0.000000 2023-10-17 18:01:00,138 epoch 10 - iter 116/292 - loss 0.00801451 - time (sec): 7.17 - samples/sec: 2554.52 - lr: 0.000003 - momentum: 0.000000 2023-10-17 18:01:01,812 epoch 10 - iter 145/292 - loss 0.00771078 - time (sec): 8.84 - samples/sec: 2498.95 - lr: 0.000003 - momentum: 0.000000 2023-10-17 18:01:03,554 epoch 10 - iter 174/292 - loss 0.00748683 - time (sec): 10.58 - samples/sec: 2490.12 - lr: 0.000002 - momentum: 0.000000 2023-10-17 18:01:05,404 epoch 10 - iter 203/292 - loss 0.00738807 - time (sec): 12.43 - samples/sec: 2525.12 - lr: 0.000002 - momentum: 0.000000 2023-10-17 18:01:07,056 epoch 10 - iter 232/292 - loss 0.00744920 - time (sec): 14.09 - samples/sec: 2533.47 - lr: 0.000001 - momentum: 0.000000 2023-10-17 18:01:08,664 epoch 10 - iter 261/292 - loss 0.00703627 - time (sec): 15.69 - samples/sec: 2522.98 - lr: 0.000001 - momentum: 0.000000 2023-10-17 18:01:10,405 epoch 10 - iter 290/292 - loss 0.00754299 - time (sec): 17.44 - samples/sec: 2529.90 - lr: 0.000000 - momentum: 0.000000 2023-10-17 18:01:10,507 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:01:10,507 EPOCH 10 done: loss 0.0075 - lr: 0.000000 2023-10-17 18:01:11,756 DEV : loss 0.20955659449100494 - f1-score (micro avg) 0.7639 2023-10-17 18:01:12,085 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:01:12,086 Loading model from best epoch ... 2023-10-17 18:01:13,492 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 18:01:15,926 Results: - F-score (micro) 0.7333 - F-score (macro) 0.6735 - Accuracy 0.6027 By class: precision recall f1-score support PER 0.7995 0.8362 0.8174 348 LOC 0.6030 0.7739 0.6779 261 ORG 0.4884 0.4038 0.4421 52 HumanProd 0.9333 0.6364 0.7568 22 micro avg 0.6975 0.7731 0.7333 683 macro avg 0.7060 0.6626 0.6735 683 weighted avg 0.7050 0.7731 0.7336 683 2023-10-17 18:01:15,926 ----------------------------------------------------------------------------------------------------