2023-10-25 21:32:57,504 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,504 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(64001, 768) (position_embeddings): Embedding(512, 768) (token_type_embeddings): Embedding(2, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): BertSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 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 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Train: 1166 sentences 2023-10-25 21:32:57,505 (train_with_dev=False, train_with_test=False) 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Training Params: 2023-10-25 21:32:57,505 - learning_rate: "5e-05" 2023-10-25 21:32:57,505 - mini_batch_size: "4" 2023-10-25 21:32:57,505 - max_epochs: "10" 2023-10-25 21:32:57,505 - shuffle: "True" 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Plugins: 2023-10-25 21:32:57,505 - TensorboardLogger 2023-10-25 21:32:57,505 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:32:57,505 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Computation: 2023-10-25 21:32:57,505 - compute on device: cuda:0 2023-10-25 21:32:57,505 - embedding storage: none 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:57,505 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:32:58,806 epoch 1 - iter 29/292 - loss 2.45137787 - time (sec): 1.30 - samples/sec: 3120.17 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:33:00,122 epoch 1 - iter 58/292 - loss 1.70444850 - time (sec): 2.62 - samples/sec: 2993.17 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:33:01,467 epoch 1 - iter 87/292 - loss 1.36569673 - time (sec): 3.96 - samples/sec: 3159.08 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:33:02,798 epoch 1 - iter 116/292 - loss 1.13542738 - time (sec): 5.29 - samples/sec: 3233.59 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:33:04,065 epoch 1 - iter 145/292 - loss 0.95947046 - time (sec): 6.56 - samples/sec: 3311.90 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:33:05,349 epoch 1 - iter 174/292 - loss 0.86059002 - time (sec): 7.84 - samples/sec: 3267.81 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:33:06,715 epoch 1 - iter 203/292 - loss 0.75774356 - time (sec): 9.21 - samples/sec: 3338.69 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:33:08,059 epoch 1 - iter 232/292 - loss 0.68013281 - time (sec): 10.55 - samples/sec: 3389.51 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:33:09,369 epoch 1 - iter 261/292 - loss 0.63213092 - time (sec): 11.86 - samples/sec: 3397.16 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:33:10,649 epoch 1 - iter 290/292 - loss 0.59913023 - time (sec): 13.14 - samples/sec: 3363.80 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:33:10,733 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:10,733 EPOCH 1 done: loss 0.5985 - lr: 0.000049 2023-10-25 21:33:11,405 DEV : loss 0.12858878076076508 - f1-score (micro avg) 0.6058 2023-10-25 21:33:11,409 saving best model 2023-10-25 21:33:11,920 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:13,209 epoch 2 - iter 29/292 - loss 0.15207670 - time (sec): 1.29 - samples/sec: 3462.10 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:33:14,531 epoch 2 - iter 58/292 - loss 0.17254937 - time (sec): 2.61 - samples/sec: 3369.96 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:33:15,837 epoch 2 - iter 87/292 - loss 0.16515785 - time (sec): 3.92 - samples/sec: 3320.56 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:33:17,171 epoch 2 - iter 116/292 - loss 0.15565784 - time (sec): 5.25 - samples/sec: 3367.25 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:33:18,426 epoch 2 - iter 145/292 - loss 0.15034919 - time (sec): 6.51 - samples/sec: 3346.07 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:33:19,663 epoch 2 - iter 174/292 - loss 0.15226906 - time (sec): 7.74 - samples/sec: 3387.64 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:33:20,920 epoch 2 - iter 203/292 - loss 0.15082330 - time (sec): 9.00 - samples/sec: 3375.79 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:33:22,195 epoch 2 - iter 232/292 - loss 0.15194885 - time (sec): 10.27 - samples/sec: 3383.93 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:33:23,556 epoch 2 - iter 261/292 - loss 0.15456539 - time (sec): 11.63 - samples/sec: 3380.94 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:33:24,901 epoch 2 - iter 290/292 - loss 0.14927010 - time (sec): 12.98 - samples/sec: 3393.23 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:33:24,981 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:24,981 EPOCH 2 done: loss 0.1483 - lr: 0.000045 2023-10-25 21:33:25,896 DEV : loss 0.1477406919002533 - f1-score (micro avg) 0.6391 2023-10-25 21:33:25,900 saving best model 2023-10-25 21:33:26,570 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:28,092 epoch 3 - iter 29/292 - loss 0.09222681 - time (sec): 1.52 - samples/sec: 3853.44 - lr: 0.000044 - momentum: 0.000000 2023-10-25 21:33:29,401 epoch 3 - iter 58/292 - loss 0.09581570 - time (sec): 2.83 - samples/sec: 3688.13 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:33:30,640 epoch 3 - iter 87/292 - loss 0.09699714 - time (sec): 4.07 - samples/sec: 3597.96 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:33:31,923 epoch 3 - iter 116/292 - loss 0.09432914 - time (sec): 5.35 - samples/sec: 3493.39 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:33:33,252 epoch 3 - iter 145/292 - loss 0.09100948 - time (sec): 6.68 - samples/sec: 3462.50 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:33:34,541 epoch 3 - iter 174/292 - loss 0.08813279 - time (sec): 7.97 - samples/sec: 3403.92 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:33:35,854 epoch 3 - iter 203/292 - loss 0.08542829 - time (sec): 9.28 - samples/sec: 3409.01 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:33:37,116 epoch 3 - iter 232/292 - loss 0.08503915 - time (sec): 10.54 - samples/sec: 3326.93 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:33:38,435 epoch 3 - iter 261/292 - loss 0.08523882 - time (sec): 11.86 - samples/sec: 3379.59 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:33:39,681 epoch 3 - iter 290/292 - loss 0.08483685 - time (sec): 13.11 - samples/sec: 3373.62 - lr: 0.000039 - momentum: 0.000000 2023-10-25 21:33:39,767 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:39,768 EPOCH 3 done: loss 0.0858 - lr: 0.000039 2023-10-25 21:33:40,839 DEV : loss 0.1286671906709671 - f1-score (micro avg) 0.7152 2023-10-25 21:33:40,843 saving best model 2023-10-25 21:33:41,512 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:42,842 epoch 4 - iter 29/292 - loss 0.06579822 - time (sec): 1.33 - samples/sec: 3197.68 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:33:44,181 epoch 4 - iter 58/292 - loss 0.05383181 - time (sec): 2.67 - samples/sec: 3158.85 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:33:45,500 epoch 4 - iter 87/292 - loss 0.04876507 - time (sec): 3.98 - samples/sec: 3274.58 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:33:46,811 epoch 4 - iter 116/292 - loss 0.04823903 - time (sec): 5.29 - samples/sec: 3210.16 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:33:48,194 epoch 4 - iter 145/292 - loss 0.05376063 - time (sec): 6.68 - samples/sec: 3382.61 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:33:49,494 epoch 4 - iter 174/292 - loss 0.05346591 - time (sec): 7.98 - samples/sec: 3433.92 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:33:50,743 epoch 4 - iter 203/292 - loss 0.05630322 - time (sec): 9.23 - samples/sec: 3443.19 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:33:52,047 epoch 4 - iter 232/292 - loss 0.05797129 - time (sec): 10.53 - samples/sec: 3396.68 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:33:53,474 epoch 4 - iter 261/292 - loss 0.05843650 - time (sec): 11.96 - samples/sec: 3381.69 - lr: 0.000034 - momentum: 0.000000 2023-10-25 21:33:54,735 epoch 4 - iter 290/292 - loss 0.05750520 - time (sec): 13.22 - samples/sec: 3343.54 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:33:54,814 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:54,814 EPOCH 4 done: loss 0.0572 - lr: 0.000033 2023-10-25 21:33:55,722 DEV : loss 0.1722760796546936 - f1-score (micro avg) 0.7025 2023-10-25 21:33:55,726 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:56,988 epoch 5 - iter 29/292 - loss 0.04342491 - time (sec): 1.26 - samples/sec: 3606.54 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:33:58,245 epoch 5 - iter 58/292 - loss 0.04319897 - time (sec): 2.52 - samples/sec: 3469.22 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:33:59,571 epoch 5 - iter 87/292 - loss 0.03827778 - time (sec): 3.84 - samples/sec: 3389.04 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:34:00,840 epoch 5 - iter 116/292 - loss 0.03386059 - time (sec): 5.11 - samples/sec: 3404.01 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:34:02,129 epoch 5 - iter 145/292 - loss 0.03593760 - time (sec): 6.40 - samples/sec: 3414.83 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:34:03,401 epoch 5 - iter 174/292 - loss 0.03846183 - time (sec): 7.67 - samples/sec: 3360.64 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:34:04,755 epoch 5 - iter 203/292 - loss 0.03960139 - time (sec): 9.03 - samples/sec: 3365.46 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:34:06,006 epoch 5 - iter 232/292 - loss 0.03978996 - time (sec): 10.28 - samples/sec: 3462.51 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:34:07,231 epoch 5 - iter 261/292 - loss 0.04007028 - time (sec): 11.50 - samples/sec: 3481.69 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:34:08,469 epoch 5 - iter 290/292 - loss 0.03905369 - time (sec): 12.74 - samples/sec: 3476.05 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:34:08,549 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:08,550 EPOCH 5 done: loss 0.0390 - lr: 0.000028 2023-10-25 21:34:09,457 DEV : loss 0.16055038571357727 - f1-score (micro avg) 0.6835 2023-10-25 21:34:09,462 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:10,800 epoch 6 - iter 29/292 - loss 0.03141562 - time (sec): 1.34 - samples/sec: 3701.70 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:34:12,095 epoch 6 - iter 58/292 - loss 0.03968166 - time (sec): 2.63 - samples/sec: 3404.87 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:34:13,387 epoch 6 - iter 87/292 - loss 0.03196566 - time (sec): 3.92 - samples/sec: 3450.89 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:34:14,722 epoch 6 - iter 116/292 - loss 0.03582229 - time (sec): 5.26 - samples/sec: 3465.57 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:34:15,994 epoch 6 - iter 145/292 - loss 0.03410517 - time (sec): 6.53 - samples/sec: 3474.12 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:34:17,304 epoch 6 - iter 174/292 - loss 0.03262458 - time (sec): 7.84 - samples/sec: 3455.30 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:34:18,567 epoch 6 - iter 203/292 - loss 0.03056044 - time (sec): 9.10 - samples/sec: 3418.19 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:34:19,863 epoch 6 - iter 232/292 - loss 0.03001793 - time (sec): 10.40 - samples/sec: 3390.09 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:34:21,193 epoch 6 - iter 261/292 - loss 0.03043669 - time (sec): 11.73 - samples/sec: 3399.43 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:34:22,499 epoch 6 - iter 290/292 - loss 0.03080981 - time (sec): 13.04 - samples/sec: 3371.72 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:34:22,589 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:22,589 EPOCH 6 done: loss 0.0306 - lr: 0.000022 2023-10-25 21:34:23,501 DEV : loss 0.19378620386123657 - f1-score (micro avg) 0.7133 2023-10-25 21:34:23,506 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:24,816 epoch 7 - iter 29/292 - loss 0.02249619 - time (sec): 1.31 - samples/sec: 3713.89 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:34:26,141 epoch 7 - iter 58/292 - loss 0.03051413 - time (sec): 2.63 - samples/sec: 3714.66 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:34:27,389 epoch 7 - iter 87/292 - loss 0.03401934 - time (sec): 3.88 - samples/sec: 3562.14 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:34:28,671 epoch 7 - iter 116/292 - loss 0.03101955 - time (sec): 5.16 - samples/sec: 3443.23 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:34:29,951 epoch 7 - iter 145/292 - loss 0.02682969 - time (sec): 6.44 - samples/sec: 3368.08 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:34:31,346 epoch 7 - iter 174/292 - loss 0.02528320 - time (sec): 7.84 - samples/sec: 3392.08 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:34:32,684 epoch 7 - iter 203/292 - loss 0.02397947 - time (sec): 9.18 - samples/sec: 3398.50 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:34:33,987 epoch 7 - iter 232/292 - loss 0.02354003 - time (sec): 10.48 - samples/sec: 3367.45 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:34:35,297 epoch 7 - iter 261/292 - loss 0.02151238 - time (sec): 11.79 - samples/sec: 3361.83 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:34:36,578 epoch 7 - iter 290/292 - loss 0.02098365 - time (sec): 13.07 - samples/sec: 3389.04 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:34:36,653 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:36,654 EPOCH 7 done: loss 0.0209 - lr: 0.000017 2023-10-25 21:34:37,749 DEV : loss 0.1828424036502838 - f1-score (micro avg) 0.7832 2023-10-25 21:34:37,754 saving best model 2023-10-25 21:34:38,425 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:39,867 epoch 8 - iter 29/292 - loss 0.02744473 - time (sec): 1.44 - samples/sec: 3042.64 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:34:41,255 epoch 8 - iter 58/292 - loss 0.02406253 - time (sec): 2.83 - samples/sec: 3124.97 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:34:42,541 epoch 8 - iter 87/292 - loss 0.01768261 - time (sec): 4.11 - samples/sec: 3273.21 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:34:43,782 epoch 8 - iter 116/292 - loss 0.01689601 - time (sec): 5.35 - samples/sec: 3291.07 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:34:45,038 epoch 8 - iter 145/292 - loss 0.01534873 - time (sec): 6.61 - samples/sec: 3295.91 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:34:46,352 epoch 8 - iter 174/292 - loss 0.01693279 - time (sec): 7.92 - samples/sec: 3280.78 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:34:47,614 epoch 8 - iter 203/292 - loss 0.01577629 - time (sec): 9.19 - samples/sec: 3233.29 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:34:48,896 epoch 8 - iter 232/292 - loss 0.01567376 - time (sec): 10.47 - samples/sec: 3264.57 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:34:50,171 epoch 8 - iter 261/292 - loss 0.01480935 - time (sec): 11.74 - samples/sec: 3318.43 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:34:51,559 epoch 8 - iter 290/292 - loss 0.01450321 - time (sec): 13.13 - samples/sec: 3369.14 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:34:51,643 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:51,643 EPOCH 8 done: loss 0.0144 - lr: 0.000011 2023-10-25 21:34:52,565 DEV : loss 0.2024029940366745 - f1-score (micro avg) 0.7134 2023-10-25 21:34:52,569 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:34:53,951 epoch 9 - iter 29/292 - loss 0.00639943 - time (sec): 1.38 - samples/sec: 3617.05 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:34:55,179 epoch 9 - iter 58/292 - loss 0.00947452 - time (sec): 2.61 - samples/sec: 3552.62 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:34:56,462 epoch 9 - iter 87/292 - loss 0.00782213 - time (sec): 3.89 - samples/sec: 3553.60 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:34:57,797 epoch 9 - iter 116/292 - loss 0.01172703 - time (sec): 5.23 - samples/sec: 3543.78 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:34:59,111 epoch 9 - iter 145/292 - loss 0.01086021 - time (sec): 6.54 - samples/sec: 3507.32 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:35:00,406 epoch 9 - iter 174/292 - loss 0.01055746 - time (sec): 7.84 - samples/sec: 3482.07 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:35:01,686 epoch 9 - iter 203/292 - loss 0.00948365 - time (sec): 9.12 - samples/sec: 3480.90 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:35:02,926 epoch 9 - iter 232/292 - loss 0.00922094 - time (sec): 10.36 - samples/sec: 3441.15 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:35:04,220 epoch 9 - iter 261/292 - loss 0.00941786 - time (sec): 11.65 - samples/sec: 3399.49 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:35:05,542 epoch 9 - iter 290/292 - loss 0.00868448 - time (sec): 12.97 - samples/sec: 3404.17 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:35:05,627 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:35:05,627 EPOCH 9 done: loss 0.0086 - lr: 0.000006 2023-10-25 21:35:06,545 DEV : loss 0.21211808919906616 - f1-score (micro avg) 0.7403 2023-10-25 21:35:06,549 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:35:07,830 epoch 10 - iter 29/292 - loss 0.00154113 - time (sec): 1.28 - samples/sec: 3413.30 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:35:09,139 epoch 10 - iter 58/292 - loss 0.00087880 - time (sec): 2.59 - samples/sec: 3179.05 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:35:10,428 epoch 10 - iter 87/292 - loss 0.00742925 - time (sec): 3.88 - samples/sec: 3189.66 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:35:11,675 epoch 10 - iter 116/292 - loss 0.00728705 - time (sec): 5.12 - samples/sec: 3255.16 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:35:13,053 epoch 10 - iter 145/292 - loss 0.00611792 - time (sec): 6.50 - samples/sec: 3311.10 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:35:14,289 epoch 10 - iter 174/292 - loss 0.00635455 - time (sec): 7.74 - samples/sec: 3345.65 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:35:15,631 epoch 10 - iter 203/292 - loss 0.00623399 - time (sec): 9.08 - samples/sec: 3401.46 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:35:16,944 epoch 10 - iter 232/292 - loss 0.00631900 - time (sec): 10.39 - samples/sec: 3381.05 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:35:18,296 epoch 10 - iter 261/292 - loss 0.00618350 - time (sec): 11.75 - samples/sec: 3378.37 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:35:19,587 epoch 10 - iter 290/292 - loss 0.00631463 - time (sec): 13.04 - samples/sec: 3395.56 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:35:19,663 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:35:19,663 EPOCH 10 done: loss 0.0063 - lr: 0.000000 2023-10-25 21:35:20,570 DEV : loss 0.21458660066127777 - f1-score (micro avg) 0.7179 2023-10-25 21:35:21,093 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:35:21,094 Loading model from best epoch ... 2023-10-25 21:35:22,805 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 2023-10-25 21:35:24,351 Results: - F-score (micro) 0.7601 - F-score (macro) 0.6983 - Accuracy 0.6367 By class: precision recall f1-score support PER 0.8000 0.8391 0.8191 348 LOC 0.6709 0.8123 0.7348 261 ORG 0.5102 0.4808 0.4950 52 HumanProd 0.7619 0.7273 0.7442 22 micro avg 0.7257 0.7980 0.7601 683 macro avg 0.6857 0.7148 0.6983 683 weighted avg 0.7274 0.7980 0.7598 683 2023-10-25 21:35:24,351 ----------------------------------------------------------------------------------------------------