2023-10-25 21:19:59,894 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 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 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 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 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 Train: 1166 sentences 2023-10-25 21:19:59,895 (train_with_dev=False, train_with_test=False) 2023-10-25 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 Training Params: 2023-10-25 21:19:59,895 - learning_rate: "3e-05" 2023-10-25 21:19:59,895 - mini_batch_size: "4" 2023-10-25 21:19:59,895 - max_epochs: "10" 2023-10-25 21:19:59,895 - shuffle: "True" 2023-10-25 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 Plugins: 2023-10-25 21:19:59,895 - TensorboardLogger 2023-10-25 21:19:59,895 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:19:59,895 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,895 Computation: 2023-10-25 21:19:59,895 - compute on device: cuda:0 2023-10-25 21:19:59,895 - embedding storage: none 2023-10-25 21:19:59,895 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,896 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-25 21:19:59,896 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,896 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:19:59,896 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:20:01,315 epoch 1 - iter 29/292 - loss 3.17590895 - time (sec): 1.42 - samples/sec: 3376.53 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:20:02,583 epoch 1 - iter 58/292 - loss 2.43702185 - time (sec): 2.69 - samples/sec: 3311.36 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:20:03,832 epoch 1 - iter 87/292 - loss 1.95169503 - time (sec): 3.94 - samples/sec: 3312.69 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:20:05,105 epoch 1 - iter 116/292 - loss 1.62169131 - time (sec): 5.21 - samples/sec: 3296.01 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:20:06,393 epoch 1 - iter 145/292 - loss 1.40877887 - time (sec): 6.50 - samples/sec: 3234.73 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:20:07,807 epoch 1 - iter 174/292 - loss 1.20206482 - time (sec): 7.91 - samples/sec: 3319.44 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:20:09,100 epoch 1 - iter 203/292 - loss 1.07963154 - time (sec): 9.20 - samples/sec: 3305.80 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:20:10,469 epoch 1 - iter 232/292 - loss 0.97153816 - time (sec): 10.57 - samples/sec: 3301.30 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:20:11,772 epoch 1 - iter 261/292 - loss 0.87789158 - time (sec): 11.88 - samples/sec: 3333.01 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:20:13,122 epoch 1 - iter 290/292 - loss 0.80297568 - time (sec): 13.23 - samples/sec: 3338.93 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:20:13,206 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:13,207 EPOCH 1 done: loss 0.8001 - lr: 0.000030 2023-10-25 21:20:13,864 DEV : loss 0.16615526378154755 - f1-score (micro avg) 0.5011 2023-10-25 21:20:13,868 saving best model 2023-10-25 21:20:14,344 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:15,649 epoch 2 - iter 29/292 - loss 0.22299871 - time (sec): 1.30 - samples/sec: 3330.56 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:20:16,981 epoch 2 - iter 58/292 - loss 0.17875882 - time (sec): 2.64 - samples/sec: 3515.59 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:20:18,227 epoch 2 - iter 87/292 - loss 0.17193383 - time (sec): 3.88 - samples/sec: 3453.99 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:20:19,545 epoch 2 - iter 116/292 - loss 0.18206582 - time (sec): 5.20 - samples/sec: 3451.77 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:20:20,848 epoch 2 - iter 145/292 - loss 0.17741981 - time (sec): 6.50 - samples/sec: 3404.44 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:20:22,094 epoch 2 - iter 174/292 - loss 0.17506302 - time (sec): 7.75 - samples/sec: 3334.92 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:20:23,379 epoch 2 - iter 203/292 - loss 0.17541687 - time (sec): 9.03 - samples/sec: 3311.77 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:20:24,707 epoch 2 - iter 232/292 - loss 0.17510377 - time (sec): 10.36 - samples/sec: 3327.47 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:20:26,046 epoch 2 - iter 261/292 - loss 0.16765312 - time (sec): 11.70 - samples/sec: 3370.33 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:20:27,363 epoch 2 - iter 290/292 - loss 0.16482145 - time (sec): 13.02 - samples/sec: 3404.67 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:20:27,452 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:27,452 EPOCH 2 done: loss 0.1647 - lr: 0.000027 2023-10-25 21:20:28,362 DEV : loss 0.11898940056562424 - f1-score (micro avg) 0.7314 2023-10-25 21:20:28,366 saving best model 2023-10-25 21:20:28,978 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:30,260 epoch 3 - iter 29/292 - loss 0.08120991 - time (sec): 1.28 - samples/sec: 3746.82 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:20:31,528 epoch 3 - iter 58/292 - loss 0.08860077 - time (sec): 2.55 - samples/sec: 3614.53 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:20:32,824 epoch 3 - iter 87/292 - loss 0.09344842 - time (sec): 3.84 - samples/sec: 3526.47 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:20:34,123 epoch 3 - iter 116/292 - loss 0.10393542 - time (sec): 5.14 - samples/sec: 3433.06 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:20:35,428 epoch 3 - iter 145/292 - loss 0.11337875 - time (sec): 6.45 - samples/sec: 3415.71 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:20:36,671 epoch 3 - iter 174/292 - loss 0.10761336 - time (sec): 7.69 - samples/sec: 3336.96 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:20:37,957 epoch 3 - iter 203/292 - loss 0.10181384 - time (sec): 8.98 - samples/sec: 3356.72 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:20:39,290 epoch 3 - iter 232/292 - loss 0.10275434 - time (sec): 10.31 - samples/sec: 3364.72 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:20:40,687 epoch 3 - iter 261/292 - loss 0.10297989 - time (sec): 11.71 - samples/sec: 3372.52 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:20:41,981 epoch 3 - iter 290/292 - loss 0.09953734 - time (sec): 13.00 - samples/sec: 3408.36 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:20:42,060 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:42,060 EPOCH 3 done: loss 0.0995 - lr: 0.000023 2023-10-25 21:20:43,120 DEV : loss 0.11886752396821976 - f1-score (micro avg) 0.7387 2023-10-25 21:20:43,124 saving best model 2023-10-25 21:20:43,739 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:45,076 epoch 4 - iter 29/292 - loss 0.06595635 - time (sec): 1.34 - samples/sec: 3335.83 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:20:46,414 epoch 4 - iter 58/292 - loss 0.07118520 - time (sec): 2.67 - samples/sec: 3534.73 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:20:47,757 epoch 4 - iter 87/292 - loss 0.06789459 - time (sec): 4.02 - samples/sec: 3575.75 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:20:49,027 epoch 4 - iter 116/292 - loss 0.06211278 - time (sec): 5.29 - samples/sec: 3547.81 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:20:50,305 epoch 4 - iter 145/292 - loss 0.06537711 - time (sec): 6.56 - samples/sec: 3522.30 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:20:51,507 epoch 4 - iter 174/292 - loss 0.06560146 - time (sec): 7.77 - samples/sec: 3445.44 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:20:52,761 epoch 4 - iter 203/292 - loss 0.06457142 - time (sec): 9.02 - samples/sec: 3419.07 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:20:54,091 epoch 4 - iter 232/292 - loss 0.06534614 - time (sec): 10.35 - samples/sec: 3443.05 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:20:55,340 epoch 4 - iter 261/292 - loss 0.06405753 - time (sec): 11.60 - samples/sec: 3419.94 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:20:56,667 epoch 4 - iter 290/292 - loss 0.06209047 - time (sec): 12.93 - samples/sec: 3423.10 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:20:56,757 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:56,757 EPOCH 4 done: loss 0.0619 - lr: 0.000020 2023-10-25 21:20:57,676 DEV : loss 0.11910221725702286 - f1-score (micro avg) 0.7722 2023-10-25 21:20:57,680 saving best model 2023-10-25 21:20:58,296 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:20:59,656 epoch 5 - iter 29/292 - loss 0.02417236 - time (sec): 1.36 - samples/sec: 3453.26 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:21:00,977 epoch 5 - iter 58/292 - loss 0.04141239 - time (sec): 2.68 - samples/sec: 3487.81 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:21:02,248 epoch 5 - iter 87/292 - loss 0.03995571 - time (sec): 3.95 - samples/sec: 3508.83 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:21:03,535 epoch 5 - iter 116/292 - loss 0.04020180 - time (sec): 5.24 - samples/sec: 3553.70 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:21:04,810 epoch 5 - iter 145/292 - loss 0.03664786 - time (sec): 6.51 - samples/sec: 3607.13 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:21:06,022 epoch 5 - iter 174/292 - loss 0.03846683 - time (sec): 7.72 - samples/sec: 3515.50 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:21:07,249 epoch 5 - iter 203/292 - loss 0.03939697 - time (sec): 8.95 - samples/sec: 3532.53 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:21:08,412 epoch 5 - iter 232/292 - loss 0.04260414 - time (sec): 10.11 - samples/sec: 3502.45 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:21:09,613 epoch 5 - iter 261/292 - loss 0.04150922 - time (sec): 11.31 - samples/sec: 3508.40 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:21:10,816 epoch 5 - iter 290/292 - loss 0.04161576 - time (sec): 12.52 - samples/sec: 3534.13 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:21:10,893 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:10,893 EPOCH 5 done: loss 0.0415 - lr: 0.000017 2023-10-25 21:21:11,809 DEV : loss 0.13558463752269745 - f1-score (micro avg) 0.7706 2023-10-25 21:21:11,814 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:13,067 epoch 6 - iter 29/292 - loss 0.02684862 - time (sec): 1.25 - samples/sec: 3466.34 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:21:14,380 epoch 6 - iter 58/292 - loss 0.02943289 - time (sec): 2.57 - samples/sec: 3272.73 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:21:15,709 epoch 6 - iter 87/292 - loss 0.02812073 - time (sec): 3.89 - samples/sec: 3249.93 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:21:16,969 epoch 6 - iter 116/292 - loss 0.03204096 - time (sec): 5.15 - samples/sec: 3224.49 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:21:18,298 epoch 6 - iter 145/292 - loss 0.02999566 - time (sec): 6.48 - samples/sec: 3268.79 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:21:19,687 epoch 6 - iter 174/292 - loss 0.03172843 - time (sec): 7.87 - samples/sec: 3286.22 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:21:20,979 epoch 6 - iter 203/292 - loss 0.03002027 - time (sec): 9.16 - samples/sec: 3300.22 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:21:22,397 epoch 6 - iter 232/292 - loss 0.03059791 - time (sec): 10.58 - samples/sec: 3369.61 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:21:23,678 epoch 6 - iter 261/292 - loss 0.02908626 - time (sec): 11.86 - samples/sec: 3344.93 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:21:25,027 epoch 6 - iter 290/292 - loss 0.02740269 - time (sec): 13.21 - samples/sec: 3352.52 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:21:25,113 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:25,113 EPOCH 6 done: loss 0.0274 - lr: 0.000013 2023-10-25 21:21:26,037 DEV : loss 0.15638913214206696 - f1-score (micro avg) 0.7679 2023-10-25 21:21:26,042 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:27,313 epoch 7 - iter 29/292 - loss 0.01451795 - time (sec): 1.27 - samples/sec: 2997.89 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:21:28,737 epoch 7 - iter 58/292 - loss 0.03043042 - time (sec): 2.69 - samples/sec: 3010.82 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:21:30,145 epoch 7 - iter 87/292 - loss 0.02516600 - time (sec): 4.10 - samples/sec: 3245.65 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:21:31,430 epoch 7 - iter 116/292 - loss 0.02158147 - time (sec): 5.39 - samples/sec: 3157.27 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:21:32,717 epoch 7 - iter 145/292 - loss 0.02062496 - time (sec): 6.67 - samples/sec: 3169.32 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:21:34,061 epoch 7 - iter 174/292 - loss 0.01787927 - time (sec): 8.02 - samples/sec: 3250.37 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:21:35,385 epoch 7 - iter 203/292 - loss 0.01848142 - time (sec): 9.34 - samples/sec: 3297.63 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:21:36,709 epoch 7 - iter 232/292 - loss 0.01855890 - time (sec): 10.67 - samples/sec: 3308.28 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:21:38,062 epoch 7 - iter 261/292 - loss 0.01791828 - time (sec): 12.02 - samples/sec: 3265.53 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:21:39,423 epoch 7 - iter 290/292 - loss 0.01785400 - time (sec): 13.38 - samples/sec: 3297.27 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:21:39,515 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:39,516 EPOCH 7 done: loss 0.0180 - lr: 0.000010 2023-10-25 21:21:40,597 DEV : loss 0.18467850983142853 - f1-score (micro avg) 0.7632 2023-10-25 21:21:40,601 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:41,860 epoch 8 - iter 29/292 - loss 0.00890727 - time (sec): 1.26 - samples/sec: 3364.75 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:21:43,217 epoch 8 - iter 58/292 - loss 0.01626205 - time (sec): 2.61 - samples/sec: 3650.22 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:21:44,484 epoch 8 - iter 87/292 - loss 0.01503426 - time (sec): 3.88 - samples/sec: 3519.28 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:21:45,740 epoch 8 - iter 116/292 - loss 0.01367778 - time (sec): 5.14 - samples/sec: 3430.14 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:21:47,040 epoch 8 - iter 145/292 - loss 0.01407450 - time (sec): 6.44 - samples/sec: 3444.56 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:21:48,396 epoch 8 - iter 174/292 - loss 0.01584846 - time (sec): 7.79 - samples/sec: 3459.37 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:21:49,716 epoch 8 - iter 203/292 - loss 0.01528952 - time (sec): 9.11 - samples/sec: 3405.25 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:21:51,000 epoch 8 - iter 232/292 - loss 0.01505405 - time (sec): 10.40 - samples/sec: 3346.87 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:21:52,312 epoch 8 - iter 261/292 - loss 0.01625469 - time (sec): 11.71 - samples/sec: 3367.76 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:21:53,621 epoch 8 - iter 290/292 - loss 0.01598943 - time (sec): 13.02 - samples/sec: 3400.48 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:21:53,697 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:53,697 EPOCH 8 done: loss 0.0160 - lr: 0.000007 2023-10-25 21:21:54,623 DEV : loss 0.18894101679325104 - f1-score (micro avg) 0.7505 2023-10-25 21:21:54,628 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:21:55,912 epoch 9 - iter 29/292 - loss 0.00813305 - time (sec): 1.28 - samples/sec: 3571.13 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:21:57,150 epoch 9 - iter 58/292 - loss 0.00977612 - time (sec): 2.52 - samples/sec: 3468.56 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:21:58,365 epoch 9 - iter 87/292 - loss 0.01322378 - time (sec): 3.74 - samples/sec: 3555.01 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:21:59,642 epoch 9 - iter 116/292 - loss 0.01295467 - time (sec): 5.01 - samples/sec: 3637.29 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:22:00,834 epoch 9 - iter 145/292 - loss 0.01203134 - time (sec): 6.20 - samples/sec: 3567.96 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:22:02,159 epoch 9 - iter 174/292 - loss 0.01179165 - time (sec): 7.53 - samples/sec: 3515.78 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:22:03,457 epoch 9 - iter 203/292 - loss 0.01078956 - time (sec): 8.83 - samples/sec: 3470.82 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:22:04,698 epoch 9 - iter 232/292 - loss 0.00998269 - time (sec): 10.07 - samples/sec: 3414.02 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:22:06,032 epoch 9 - iter 261/292 - loss 0.00887687 - time (sec): 11.40 - samples/sec: 3443.18 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:22:07,378 epoch 9 - iter 290/292 - loss 0.01054438 - time (sec): 12.75 - samples/sec: 3454.51 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:22:07,467 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:07,467 EPOCH 9 done: loss 0.0105 - lr: 0.000003 2023-10-25 21:22:08,374 DEV : loss 0.19431500136852264 - f1-score (micro avg) 0.757 2023-10-25 21:22:08,379 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:09,708 epoch 10 - iter 29/292 - loss 0.01082939 - time (sec): 1.33 - samples/sec: 3453.25 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:22:10,945 epoch 10 - iter 58/292 - loss 0.00934277 - time (sec): 2.57 - samples/sec: 3316.40 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:22:12,197 epoch 10 - iter 87/292 - loss 0.00832350 - time (sec): 3.82 - samples/sec: 3224.24 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:22:13,561 epoch 10 - iter 116/292 - loss 0.01106584 - time (sec): 5.18 - samples/sec: 3359.73 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:22:14,806 epoch 10 - iter 145/292 - loss 0.00926850 - time (sec): 6.43 - samples/sec: 3398.47 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:22:16,184 epoch 10 - iter 174/292 - loss 0.00795886 - time (sec): 7.80 - samples/sec: 3429.82 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:22:17,554 epoch 10 - iter 203/292 - loss 0.00803485 - time (sec): 9.17 - samples/sec: 3467.14 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:22:18,867 epoch 10 - iter 232/292 - loss 0.00888351 - time (sec): 10.49 - samples/sec: 3395.29 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:22:20,193 epoch 10 - iter 261/292 - loss 0.00841492 - time (sec): 11.81 - samples/sec: 3373.34 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:22:21,478 epoch 10 - iter 290/292 - loss 0.00810355 - time (sec): 13.10 - samples/sec: 3371.86 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:22:21,573 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:21,573 EPOCH 10 done: loss 0.0081 - lr: 0.000000 2023-10-25 21:22:22,489 DEV : loss 0.19873516261577606 - f1-score (micro avg) 0.7592 2023-10-25 21:22:22,963 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:22:22,964 Loading model from best epoch ... 2023-10-25 21:22:24,545 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 21:22:26,090 Results: - F-score (micro) 0.7596 - F-score (macro) 0.6635 - Accuracy 0.6407 By class: precision recall f1-score support PER 0.8050 0.8305 0.8175 348 LOC 0.7096 0.8238 0.7624 261 ORG 0.3929 0.4231 0.4074 52 HumanProd 0.6154 0.7273 0.6667 22 micro avg 0.7285 0.7936 0.7596 683 macro avg 0.6307 0.7011 0.6635 683 weighted avg 0.7311 0.7936 0.7604 683 2023-10-25 21:22:26,090 ----------------------------------------------------------------------------------------------------