2023-10-25 21:22:49,010 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,011 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 21:22:49,011 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 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 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Train: 1166 sentences 2023-10-25 21:22:49,012 (train_with_dev=False, train_with_test=False) 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Training Params: 2023-10-25 21:22:49,012 - learning_rate: "5e-05" 2023-10-25 21:22:49,012 - mini_batch_size: "4" 2023-10-25 21:22:49,012 - max_epochs: "10" 2023-10-25 21:22:49,012 - shuffle: "True" 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Plugins: 2023-10-25 21:22:49,012 - TensorboardLogger 2023-10-25 21:22:49,012 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:22:49,012 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Computation: 2023-10-25 21:22:49,012 - compute on device: cuda:0 2023-10-25 21:22:49,012 - embedding storage: none 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:49,012 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:22:50,365 epoch 1 - iter 29/292 - loss 3.04468690 - time (sec): 1.35 - samples/sec: 3544.24 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:22:51,616 epoch 1 - iter 58/292 - loss 2.08228056 - time (sec): 2.60 - samples/sec: 3418.55 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:22:52,870 epoch 1 - iter 87/292 - loss 1.67391242 - time (sec): 3.86 - samples/sec: 3380.18 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:22:54,119 epoch 1 - iter 116/292 - loss 1.39271840 - time (sec): 5.11 - samples/sec: 3361.81 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:22:55,408 epoch 1 - iter 145/292 - loss 1.19734159 - time (sec): 6.39 - samples/sec: 3286.22 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:22:56,810 epoch 1 - iter 174/292 - loss 1.01730119 - time (sec): 7.80 - samples/sec: 3367.82 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:22:58,079 epoch 1 - iter 203/292 - loss 0.91202992 - time (sec): 9.07 - samples/sec: 3355.88 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:22:59,525 epoch 1 - iter 232/292 - loss 0.82288451 - time (sec): 10.51 - samples/sec: 3320.22 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:23:00,832 epoch 1 - iter 261/292 - loss 0.74308263 - time (sec): 11.82 - samples/sec: 3348.87 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:23:02,179 epoch 1 - iter 290/292 - loss 0.68034745 - time (sec): 13.17 - samples/sec: 3354.10 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:23:02,263 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:02,263 EPOCH 1 done: loss 0.6780 - lr: 0.000049 2023-10-25 21:23:02,769 DEV : loss 0.15992717444896698 - f1-score (micro avg) 0.5378 2023-10-25 21:23:02,773 saving best model 2023-10-25 21:23:03,304 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:04,601 epoch 2 - iter 29/292 - loss 0.21214502 - time (sec): 1.30 - samples/sec: 3350.43 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:23:05,969 epoch 2 - iter 58/292 - loss 0.16803234 - time (sec): 2.66 - samples/sec: 3478.53 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:23:07,229 epoch 2 - iter 87/292 - loss 0.16062619 - time (sec): 3.92 - samples/sec: 3417.74 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:23:08,555 epoch 2 - iter 116/292 - loss 0.17011069 - time (sec): 5.25 - samples/sec: 3419.64 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:23:09,852 epoch 2 - iter 145/292 - loss 0.16743668 - time (sec): 6.55 - samples/sec: 3382.00 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:23:11,093 epoch 2 - iter 174/292 - loss 0.16331818 - time (sec): 7.79 - samples/sec: 3318.18 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:23:12,390 epoch 2 - iter 203/292 - loss 0.16521386 - time (sec): 9.08 - samples/sec: 3293.04 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:23:13,727 epoch 2 - iter 232/292 - loss 0.16386177 - time (sec): 10.42 - samples/sec: 3308.08 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:23:15,077 epoch 2 - iter 261/292 - loss 0.15723361 - time (sec): 11.77 - samples/sec: 3350.27 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:23:16,379 epoch 2 - iter 290/292 - loss 0.15379255 - time (sec): 13.07 - samples/sec: 3390.10 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:23:16,458 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:16,458 EPOCH 2 done: loss 0.1536 - lr: 0.000045 2023-10-25 21:23:17,366 DEV : loss 0.12357047200202942 - f1-score (micro avg) 0.7236 2023-10-25 21:23:17,370 saving best model 2023-10-25 21:23:17,907 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:19,208 epoch 3 - iter 29/292 - loss 0.08209900 - time (sec): 1.30 - samples/sec: 3698.78 - lr: 0.000044 - momentum: 0.000000 2023-10-25 21:23:20,480 epoch 3 - iter 58/292 - loss 0.08954013 - time (sec): 2.57 - samples/sec: 3585.69 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:23:21,942 epoch 3 - iter 87/292 - loss 0.09024601 - time (sec): 4.03 - samples/sec: 3363.73 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:23:23,235 epoch 3 - iter 116/292 - loss 0.09815526 - time (sec): 5.32 - samples/sec: 3316.48 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:23:24,526 epoch 3 - iter 145/292 - loss 0.10736630 - time (sec): 6.61 - samples/sec: 3329.89 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:23:25,765 epoch 3 - iter 174/292 - loss 0.10295479 - time (sec): 7.85 - samples/sec: 3267.84 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:23:27,043 epoch 3 - iter 203/292 - loss 0.09578494 - time (sec): 9.13 - samples/sec: 3300.02 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:23:28,435 epoch 3 - iter 232/292 - loss 0.09515875 - time (sec): 10.52 - samples/sec: 3296.33 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:23:29,808 epoch 3 - iter 261/292 - loss 0.09502063 - time (sec): 11.90 - samples/sec: 3318.84 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:23:31,136 epoch 3 - iter 290/292 - loss 0.09090155 - time (sec): 13.22 - samples/sec: 3350.86 - lr: 0.000039 - momentum: 0.000000 2023-10-25 21:23:31,223 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:31,223 EPOCH 3 done: loss 0.0908 - lr: 0.000039 2023-10-25 21:23:32,135 DEV : loss 0.11771436035633087 - f1-score (micro avg) 0.7456 2023-10-25 21:23:32,140 saving best model 2023-10-25 21:23:32,814 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:34,120 epoch 4 - iter 29/292 - loss 0.04447974 - time (sec): 1.30 - samples/sec: 3415.97 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:23:35,447 epoch 4 - iter 58/292 - loss 0.05748043 - time (sec): 2.63 - samples/sec: 3591.72 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:23:36,803 epoch 4 - iter 87/292 - loss 0.05839321 - time (sec): 3.99 - samples/sec: 3601.72 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:23:38,071 epoch 4 - iter 116/292 - loss 0.05373818 - time (sec): 5.25 - samples/sec: 3569.23 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:23:39,367 epoch 4 - iter 145/292 - loss 0.06079832 - time (sec): 6.55 - samples/sec: 3529.73 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:23:40,548 epoch 4 - iter 174/292 - loss 0.05840615 - time (sec): 7.73 - samples/sec: 3460.91 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:23:41,735 epoch 4 - iter 203/292 - loss 0.05922118 - time (sec): 8.92 - samples/sec: 3457.73 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:23:43,026 epoch 4 - iter 232/292 - loss 0.05817814 - time (sec): 10.21 - samples/sec: 3490.62 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:23:44,270 epoch 4 - iter 261/292 - loss 0.05811754 - time (sec): 11.45 - samples/sec: 3463.49 - lr: 0.000034 - momentum: 0.000000 2023-10-25 21:23:45,618 epoch 4 - iter 290/292 - loss 0.05637850 - time (sec): 12.80 - samples/sec: 3456.42 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:23:45,698 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:45,698 EPOCH 4 done: loss 0.0563 - lr: 0.000033 2023-10-25 21:23:46,613 DEV : loss 0.16891229152679443 - f1-score (micro avg) 0.7172 2023-10-25 21:23:46,618 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:48,047 epoch 5 - iter 29/292 - loss 0.01793138 - time (sec): 1.43 - samples/sec: 3282.09 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:23:49,387 epoch 5 - iter 58/292 - loss 0.03776489 - time (sec): 2.77 - samples/sec: 3374.60 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:23:50,675 epoch 5 - iter 87/292 - loss 0.03871292 - time (sec): 4.06 - samples/sec: 3416.95 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:23:51,995 epoch 5 - iter 116/292 - loss 0.03671836 - time (sec): 5.38 - samples/sec: 3461.52 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:23:53,267 epoch 5 - iter 145/292 - loss 0.03345817 - time (sec): 6.65 - samples/sec: 3532.80 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:23:54,488 epoch 5 - iter 174/292 - loss 0.03604099 - time (sec): 7.87 - samples/sec: 3450.29 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:23:55,717 epoch 5 - iter 203/292 - loss 0.03563773 - time (sec): 9.10 - samples/sec: 3475.36 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:23:56,883 epoch 5 - iter 232/292 - loss 0.03978405 - time (sec): 10.26 - samples/sec: 3450.93 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:23:58,127 epoch 5 - iter 261/292 - loss 0.03922902 - time (sec): 11.51 - samples/sec: 3449.17 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:23:59,426 epoch 5 - iter 290/292 - loss 0.04000375 - time (sec): 12.81 - samples/sec: 3454.07 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:23:59,515 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:23:59,515 EPOCH 5 done: loss 0.0398 - lr: 0.000028 2023-10-25 21:24:00,428 DEV : loss 0.12579147517681122 - f1-score (micro avg) 0.7352 2023-10-25 21:24:00,433 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:01,711 epoch 6 - iter 29/292 - loss 0.02611874 - time (sec): 1.28 - samples/sec: 3400.46 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:24:02,992 epoch 6 - iter 58/292 - loss 0.03086291 - time (sec): 2.56 - samples/sec: 3281.23 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:24:04,290 epoch 6 - iter 87/292 - loss 0.02541001 - time (sec): 3.86 - samples/sec: 3282.22 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:24:05,568 epoch 6 - iter 116/292 - loss 0.02774603 - time (sec): 5.13 - samples/sec: 3237.20 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:24:06,856 epoch 6 - iter 145/292 - loss 0.02771761 - time (sec): 6.42 - samples/sec: 3299.67 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:24:08,149 epoch 6 - iter 174/292 - loss 0.02765889 - time (sec): 7.71 - samples/sec: 3353.44 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:24:09,408 epoch 6 - iter 203/292 - loss 0.02925281 - time (sec): 8.97 - samples/sec: 3370.19 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:24:10,826 epoch 6 - iter 232/292 - loss 0.02864905 - time (sec): 10.39 - samples/sec: 3431.12 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:24:12,058 epoch 6 - iter 261/292 - loss 0.02763788 - time (sec): 11.62 - samples/sec: 3413.92 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:24:13,367 epoch 6 - iter 290/292 - loss 0.02581966 - time (sec): 12.93 - samples/sec: 3424.87 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:24:13,446 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:13,446 EPOCH 6 done: loss 0.0257 - lr: 0.000022 2023-10-25 21:24:14,365 DEV : loss 0.1791224181652069 - f1-score (micro avg) 0.7289 2023-10-25 21:24:14,370 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:15,661 epoch 7 - iter 29/292 - loss 0.01525348 - time (sec): 1.29 - samples/sec: 2948.18 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:24:16,980 epoch 7 - iter 58/292 - loss 0.02610841 - time (sec): 2.61 - samples/sec: 3107.31 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:24:18,373 epoch 7 - iter 87/292 - loss 0.02233332 - time (sec): 4.00 - samples/sec: 3326.21 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:24:19,793 epoch 7 - iter 116/292 - loss 0.01975879 - time (sec): 5.42 - samples/sec: 3136.62 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:24:21,105 epoch 7 - iter 145/292 - loss 0.02079285 - time (sec): 6.73 - samples/sec: 3140.38 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:24:22,435 epoch 7 - iter 174/292 - loss 0.01893185 - time (sec): 8.06 - samples/sec: 3231.57 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:24:23,760 epoch 7 - iter 203/292 - loss 0.01874262 - time (sec): 9.39 - samples/sec: 3280.58 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:24:25,035 epoch 7 - iter 232/292 - loss 0.01913688 - time (sec): 10.66 - samples/sec: 3308.42 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:24:26,341 epoch 7 - iter 261/292 - loss 0.01811495 - time (sec): 11.97 - samples/sec: 3278.83 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:24:27,679 epoch 7 - iter 290/292 - loss 0.01871243 - time (sec): 13.31 - samples/sec: 3314.90 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:24:27,767 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:27,768 EPOCH 7 done: loss 0.0196 - lr: 0.000017 2023-10-25 21:24:28,684 DEV : loss 0.18422643840312958 - f1-score (micro avg) 0.6875 2023-10-25 21:24:28,688 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:29,929 epoch 8 - iter 29/292 - loss 0.00351023 - time (sec): 1.24 - samples/sec: 3412.68 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:24:31,209 epoch 8 - iter 58/292 - loss 0.00912950 - time (sec): 2.52 - samples/sec: 3786.95 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:24:32,409 epoch 8 - iter 87/292 - loss 0.00811109 - time (sec): 3.72 - samples/sec: 3672.28 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:24:33,594 epoch 8 - iter 116/292 - loss 0.00685205 - time (sec): 4.90 - samples/sec: 3593.20 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:24:34,855 epoch 8 - iter 145/292 - loss 0.00786036 - time (sec): 6.17 - samples/sec: 3596.15 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:24:36,191 epoch 8 - iter 174/292 - loss 0.01019612 - time (sec): 7.50 - samples/sec: 3593.87 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:24:37,508 epoch 8 - iter 203/292 - loss 0.00968103 - time (sec): 8.82 - samples/sec: 3519.18 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:24:38,796 epoch 8 - iter 232/292 - loss 0.00998358 - time (sec): 10.11 - samples/sec: 3443.22 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:24:40,122 epoch 8 - iter 261/292 - loss 0.00986264 - time (sec): 11.43 - samples/sec: 3449.32 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:24:41,512 epoch 8 - iter 290/292 - loss 0.01018475 - time (sec): 12.82 - samples/sec: 3452.18 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:24:41,591 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:41,591 EPOCH 8 done: loss 0.0104 - lr: 0.000011 2023-10-25 21:24:42,498 DEV : loss 0.19869066774845123 - f1-score (micro avg) 0.7532 2023-10-25 21:24:42,503 saving best model 2023-10-25 21:24:43,185 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:44,510 epoch 9 - iter 29/292 - loss 0.00300745 - time (sec): 1.32 - samples/sec: 3463.47 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:24:45,815 epoch 9 - iter 58/292 - loss 0.00560549 - time (sec): 2.63 - samples/sec: 3327.56 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:24:47,124 epoch 9 - iter 87/292 - loss 0.00597532 - time (sec): 3.94 - samples/sec: 3373.84 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:24:48,472 epoch 9 - iter 116/292 - loss 0.00660099 - time (sec): 5.28 - samples/sec: 3450.68 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:24:49,731 epoch 9 - iter 145/292 - loss 0.00583953 - time (sec): 6.54 - samples/sec: 3382.80 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:24:51,039 epoch 9 - iter 174/292 - loss 0.00673963 - time (sec): 7.85 - samples/sec: 3371.39 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:24:52,313 epoch 9 - iter 203/292 - loss 0.00632106 - time (sec): 9.13 - samples/sec: 3357.34 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:24:53,579 epoch 9 - iter 232/292 - loss 0.00585454 - time (sec): 10.39 - samples/sec: 3307.81 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:24:54,953 epoch 9 - iter 261/292 - loss 0.00520285 - time (sec): 11.77 - samples/sec: 3336.98 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:24:56,314 epoch 9 - iter 290/292 - loss 0.00729847 - time (sec): 13.13 - samples/sec: 3355.06 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:24:56,404 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:56,404 EPOCH 9 done: loss 0.0072 - lr: 0.000006 2023-10-25 21:24:57,331 DEV : loss 0.207131028175354 - f1-score (micro avg) 0.7122 2023-10-25 21:24:57,336 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:24:58,656 epoch 10 - iter 29/292 - loss 0.00724381 - time (sec): 1.32 - samples/sec: 3476.36 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:24:59,897 epoch 10 - iter 58/292 - loss 0.00640674 - time (sec): 2.56 - samples/sec: 3323.92 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:25:01,158 epoch 10 - iter 87/292 - loss 0.00503092 - time (sec): 3.82 - samples/sec: 3221.06 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:25:02,538 epoch 10 - iter 116/292 - loss 0.00775827 - time (sec): 5.20 - samples/sec: 3346.98 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:25:03,822 epoch 10 - iter 145/292 - loss 0.00633399 - time (sec): 6.48 - samples/sec: 3367.76 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:25:05,151 epoch 10 - iter 174/292 - loss 0.00539255 - time (sec): 7.81 - samples/sec: 3425.52 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:25:06,458 epoch 10 - iter 203/292 - loss 0.00516222 - time (sec): 9.12 - samples/sec: 3487.33 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:25:07,712 epoch 10 - iter 232/292 - loss 0.00511528 - time (sec): 10.38 - samples/sec: 3432.05 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:25:09,027 epoch 10 - iter 261/292 - loss 0.00467370 - time (sec): 11.69 - samples/sec: 3408.74 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:25:10,287 epoch 10 - iter 290/292 - loss 0.00471642 - time (sec): 12.95 - samples/sec: 3410.43 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:25:10,370 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:25:10,370 EPOCH 10 done: loss 0.0047 - lr: 0.000000 2023-10-25 21:25:11,373 DEV : loss 0.20934493839740753 - f1-score (micro avg) 0.7235 2023-10-25 21:25:11,898 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:25:11,899 Loading model from best epoch ... 2023-10-25 21:25:13,646 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 21:25:15,364 Results: - F-score (micro) 0.7502 - F-score (macro) 0.6687 - Accuracy 0.6236 By class: precision recall f1-score support PER 0.7936 0.8506 0.8211 348 LOC 0.6594 0.8084 0.7263 261 ORG 0.4038 0.4038 0.4038 52 HumanProd 0.6800 0.7727 0.7234 22 micro avg 0.7078 0.7980 0.7502 683 macro avg 0.6342 0.7089 0.6687 683 weighted avg 0.7090 0.7980 0.7500 683 2023-10-25 21:25:15,364 ----------------------------------------------------------------------------------------------------