2023-10-19 23:49:44,654 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,654 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(32001, 128) (position_embeddings): Embedding(512, 128) (token_type_embeddings): Embedding(2, 128) (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): BertEncoder( (layer): ModuleList( (0-1): 2 x BertLayer( (attention): BertAttention( (self): BertSelfAttention( (query): Linear(in_features=128, out_features=128, bias=True) (key): Linear(in_features=128, out_features=128, bias=True) (value): Linear(in_features=128, out_features=128, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): BertSelfOutput( (dense): Linear(in_features=128, out_features=128, bias=True) (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): BertIntermediate( (dense): Linear(in_features=128, out_features=512, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (dense): Linear(in_features=512, out_features=128, bias=True) (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=128, out_features=128, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=128, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-19 23:49:44,654 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,654 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 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Train: 1166 sentences 2023-10-19 23:49:44,655 (train_with_dev=False, train_with_test=False) 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Training Params: 2023-10-19 23:49:44,655 - learning_rate: "3e-05" 2023-10-19 23:49:44,655 - mini_batch_size: "4" 2023-10-19 23:49:44,655 - max_epochs: "10" 2023-10-19 23:49:44,655 - shuffle: "True" 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Plugins: 2023-10-19 23:49:44,655 - TensorboardLogger 2023-10-19 23:49:44,655 - LinearScheduler | warmup_fraction: '0.1' 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Final evaluation on model from best epoch (best-model.pt) 2023-10-19 23:49:44,655 - metric: "('micro avg', 'f1-score')" 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Computation: 2023-10-19 23:49:44,655 - compute on device: cuda:0 2023-10-19 23:49:44,655 - embedding storage: none 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:44,655 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-19 23:49:45,171 epoch 1 - iter 29/292 - loss 3.23366766 - time (sec): 0.52 - samples/sec: 9308.03 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:49:45,672 epoch 1 - iter 58/292 - loss 3.25275791 - time (sec): 1.02 - samples/sec: 8780.75 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:49:46,209 epoch 1 - iter 87/292 - loss 3.09522052 - time (sec): 1.55 - samples/sec: 8385.87 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:49:46,752 epoch 1 - iter 116/292 - loss 2.96850491 - time (sec): 2.10 - samples/sec: 8369.71 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:49:47,307 epoch 1 - iter 145/292 - loss 2.77725528 - time (sec): 2.65 - samples/sec: 8488.65 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:49:47,849 epoch 1 - iter 174/292 - loss 2.58029420 - time (sec): 3.19 - samples/sec: 8553.64 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:49:48,361 epoch 1 - iter 203/292 - loss 2.39676813 - time (sec): 3.70 - samples/sec: 8574.16 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:49:48,846 epoch 1 - iter 232/292 - loss 2.23157178 - time (sec): 4.19 - samples/sec: 8552.98 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:49:49,383 epoch 1 - iter 261/292 - loss 2.09117800 - time (sec): 4.73 - samples/sec: 8454.45 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:49:49,865 epoch 1 - iter 290/292 - loss 1.99194641 - time (sec): 5.21 - samples/sec: 8489.62 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:49:49,893 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:49,893 EPOCH 1 done: loss 1.9855 - lr: 0.000030 2023-10-19 23:49:50,154 DEV : loss 0.45264244079589844 - f1-score (micro avg) 0.0 2023-10-19 23:49:50,158 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:50,701 epoch 2 - iter 29/292 - loss 0.92771541 - time (sec): 0.54 - samples/sec: 9419.62 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:49:51,190 epoch 2 - iter 58/292 - loss 0.79135239 - time (sec): 1.03 - samples/sec: 8802.41 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:49:51,708 epoch 2 - iter 87/292 - loss 0.76416654 - time (sec): 1.55 - samples/sec: 8865.95 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:49:52,232 epoch 2 - iter 116/292 - loss 0.75800533 - time (sec): 2.07 - samples/sec: 8888.41 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:49:52,749 epoch 2 - iter 145/292 - loss 0.74324513 - time (sec): 2.59 - samples/sec: 8725.33 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:49:53,239 epoch 2 - iter 174/292 - loss 0.72235129 - time (sec): 3.08 - samples/sec: 8666.19 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:49:53,750 epoch 2 - iter 203/292 - loss 0.68411345 - time (sec): 3.59 - samples/sec: 8684.86 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:49:54,296 epoch 2 - iter 232/292 - loss 0.66363694 - time (sec): 4.14 - samples/sec: 8702.86 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:49:54,805 epoch 2 - iter 261/292 - loss 0.65749594 - time (sec): 4.65 - samples/sec: 8595.78 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:49:55,316 epoch 2 - iter 290/292 - loss 0.64381828 - time (sec): 5.16 - samples/sec: 8537.64 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:49:55,353 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:55,353 EPOCH 2 done: loss 0.6399 - lr: 0.000027 2023-10-19 23:49:55,987 DEV : loss 0.4109416902065277 - f1-score (micro avg) 0.0 2023-10-19 23:49:55,991 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:49:56,511 epoch 3 - iter 29/292 - loss 0.56836488 - time (sec): 0.52 - samples/sec: 8126.62 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:49:57,065 epoch 3 - iter 58/292 - loss 0.52701593 - time (sec): 1.07 - samples/sec: 8165.60 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:49:57,621 epoch 3 - iter 87/292 - loss 0.53413707 - time (sec): 1.63 - samples/sec: 8445.86 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:49:58,141 epoch 3 - iter 116/292 - loss 0.53704706 - time (sec): 2.15 - samples/sec: 8606.37 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:49:58,652 epoch 3 - iter 145/292 - loss 0.53492671 - time (sec): 2.66 - samples/sec: 8476.20 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:49:59,173 epoch 3 - iter 174/292 - loss 0.52807808 - time (sec): 3.18 - samples/sec: 8499.75 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:49:59,678 epoch 3 - iter 203/292 - loss 0.52293822 - time (sec): 3.69 - samples/sec: 8483.35 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:50:00,319 epoch 3 - iter 232/292 - loss 0.53248911 - time (sec): 4.33 - samples/sec: 8196.29 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:50:00,857 epoch 3 - iter 261/292 - loss 0.55584902 - time (sec): 4.87 - samples/sec: 8346.87 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:50:01,356 epoch 3 - iter 290/292 - loss 0.54349142 - time (sec): 5.36 - samples/sec: 8243.27 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:50:01,385 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:01,386 EPOCH 3 done: loss 0.5425 - lr: 0.000023 2023-10-19 23:50:02,033 DEV : loss 0.3629387617111206 - f1-score (micro avg) 0.0 2023-10-19 23:50:02,037 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:02,583 epoch 4 - iter 29/292 - loss 0.44234018 - time (sec): 0.55 - samples/sec: 8145.45 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:50:03,112 epoch 4 - iter 58/292 - loss 0.47095915 - time (sec): 1.08 - samples/sec: 8028.67 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:50:03,606 epoch 4 - iter 87/292 - loss 0.48713525 - time (sec): 1.57 - samples/sec: 8091.97 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:50:04,084 epoch 4 - iter 116/292 - loss 0.54057413 - time (sec): 2.05 - samples/sec: 8646.72 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:50:04,597 epoch 4 - iter 145/292 - loss 0.54157699 - time (sec): 2.56 - samples/sec: 8471.16 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:50:05,106 epoch 4 - iter 174/292 - loss 0.52419907 - time (sec): 3.07 - samples/sec: 8467.18 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:50:05,603 epoch 4 - iter 203/292 - loss 0.50823803 - time (sec): 3.57 - samples/sec: 8393.88 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:50:06,145 epoch 4 - iter 232/292 - loss 0.49738370 - time (sec): 4.11 - samples/sec: 8590.14 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:50:06,650 epoch 4 - iter 261/292 - loss 0.48959920 - time (sec): 4.61 - samples/sec: 8553.94 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:50:07,166 epoch 4 - iter 290/292 - loss 0.48932254 - time (sec): 5.13 - samples/sec: 8567.77 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:50:07,205 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:07,205 EPOCH 4 done: loss 0.4862 - lr: 0.000020 2023-10-19 23:50:07,841 DEV : loss 0.3369694650173187 - f1-score (micro avg) 0.0522 2023-10-19 23:50:07,845 saving best model 2023-10-19 23:50:07,873 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:08,389 epoch 5 - iter 29/292 - loss 0.59986532 - time (sec): 0.52 - samples/sec: 9669.90 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:50:08,890 epoch 5 - iter 58/292 - loss 0.54446958 - time (sec): 1.02 - samples/sec: 8851.61 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:50:09,415 epoch 5 - iter 87/292 - loss 0.52382245 - time (sec): 1.54 - samples/sec: 8780.25 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:50:09,958 epoch 5 - iter 116/292 - loss 0.49345204 - time (sec): 2.08 - samples/sec: 8805.88 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:50:10,521 epoch 5 - iter 145/292 - loss 0.46446324 - time (sec): 2.65 - samples/sec: 8647.69 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:50:10,998 epoch 5 - iter 174/292 - loss 0.45495738 - time (sec): 3.12 - samples/sec: 8585.51 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:50:11,506 epoch 5 - iter 203/292 - loss 0.44868989 - time (sec): 3.63 - samples/sec: 8651.19 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:50:12,002 epoch 5 - iter 232/292 - loss 0.45470579 - time (sec): 4.13 - samples/sec: 8429.60 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:50:12,488 epoch 5 - iter 261/292 - loss 0.45728633 - time (sec): 4.61 - samples/sec: 8503.52 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:50:12,998 epoch 5 - iter 290/292 - loss 0.45813778 - time (sec): 5.12 - samples/sec: 8626.62 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:50:13,028 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:13,029 EPOCH 5 done: loss 0.4589 - lr: 0.000017 2023-10-19 23:50:13,664 DEV : loss 0.3155231177806854 - f1-score (micro avg) 0.2 2023-10-19 23:50:13,668 saving best model 2023-10-19 23:50:13,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:14,204 epoch 6 - iter 29/292 - loss 0.53462839 - time (sec): 0.50 - samples/sec: 8790.02 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:50:14,710 epoch 6 - iter 58/292 - loss 0.45387607 - time (sec): 1.01 - samples/sec: 8763.56 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:50:15,202 epoch 6 - iter 87/292 - loss 0.43858593 - time (sec): 1.50 - samples/sec: 8859.98 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:50:15,682 epoch 6 - iter 116/292 - loss 0.44130740 - time (sec): 1.98 - samples/sec: 8591.37 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:50:16,206 epoch 6 - iter 145/292 - loss 0.43534614 - time (sec): 2.50 - samples/sec: 8722.92 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:50:16,721 epoch 6 - iter 174/292 - loss 0.45146060 - time (sec): 3.02 - samples/sec: 8892.81 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:50:17,227 epoch 6 - iter 203/292 - loss 0.43994146 - time (sec): 3.53 - samples/sec: 8858.23 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:50:17,738 epoch 6 - iter 232/292 - loss 0.43069230 - time (sec): 4.04 - samples/sec: 8776.63 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:50:18,259 epoch 6 - iter 261/292 - loss 0.42140208 - time (sec): 4.56 - samples/sec: 8859.96 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:50:18,773 epoch 6 - iter 290/292 - loss 0.42268096 - time (sec): 5.07 - samples/sec: 8732.95 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:50:18,802 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:18,802 EPOCH 6 done: loss 0.4225 - lr: 0.000013 2023-10-19 23:50:19,452 DEV : loss 0.3091878592967987 - f1-score (micro avg) 0.2337 2023-10-19 23:50:19,457 saving best model 2023-10-19 23:50:19,488 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:19,962 epoch 7 - iter 29/292 - loss 0.36939978 - time (sec): 0.47 - samples/sec: 8508.54 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:50:20,469 epoch 7 - iter 58/292 - loss 0.34863665 - time (sec): 0.98 - samples/sec: 8253.29 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:50:20,967 epoch 7 - iter 87/292 - loss 0.37735444 - time (sec): 1.48 - samples/sec: 8488.20 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:50:21,461 epoch 7 - iter 116/292 - loss 0.42584412 - time (sec): 1.97 - samples/sec: 8521.83 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:50:21,956 epoch 7 - iter 145/292 - loss 0.41926330 - time (sec): 2.47 - samples/sec: 8485.20 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:50:22,465 epoch 7 - iter 174/292 - loss 0.41470611 - time (sec): 2.98 - samples/sec: 8410.67 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:50:22,985 epoch 7 - iter 203/292 - loss 0.41112570 - time (sec): 3.50 - samples/sec: 8532.31 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:50:23,524 epoch 7 - iter 232/292 - loss 0.41695875 - time (sec): 4.04 - samples/sec: 8494.03 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:50:24,066 epoch 7 - iter 261/292 - loss 0.41595517 - time (sec): 4.58 - samples/sec: 8616.91 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:50:24,614 epoch 7 - iter 290/292 - loss 0.40657648 - time (sec): 5.13 - samples/sec: 8630.87 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:50:24,651 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:24,651 EPOCH 7 done: loss 0.4063 - lr: 0.000010 2023-10-19 23:50:25,299 DEV : loss 0.30544406175613403 - f1-score (micro avg) 0.2442 2023-10-19 23:50:25,304 saving best model 2023-10-19 23:50:25,335 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:25,862 epoch 8 - iter 29/292 - loss 0.46693410 - time (sec): 0.53 - samples/sec: 9430.55 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:50:26,374 epoch 8 - iter 58/292 - loss 0.45223574 - time (sec): 1.04 - samples/sec: 8889.98 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:50:26,919 epoch 8 - iter 87/292 - loss 0.41985147 - time (sec): 1.58 - samples/sec: 8638.02 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:50:27,500 epoch 8 - iter 116/292 - loss 0.39639438 - time (sec): 2.16 - samples/sec: 8397.44 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:50:27,950 epoch 8 - iter 145/292 - loss 0.38044177 - time (sec): 2.61 - samples/sec: 8685.66 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:50:28,444 epoch 8 - iter 174/292 - loss 0.39141118 - time (sec): 3.11 - samples/sec: 8534.62 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:50:28,981 epoch 8 - iter 203/292 - loss 0.38177708 - time (sec): 3.65 - samples/sec: 8433.50 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:50:29,486 epoch 8 - iter 232/292 - loss 0.39149494 - time (sec): 4.15 - samples/sec: 8434.27 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:50:30,009 epoch 8 - iter 261/292 - loss 0.38697211 - time (sec): 4.67 - samples/sec: 8473.81 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:50:30,523 epoch 8 - iter 290/292 - loss 0.38508142 - time (sec): 5.19 - samples/sec: 8518.94 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:50:30,554 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:30,554 EPOCH 8 done: loss 0.3861 - lr: 0.000007 2023-10-19 23:50:31,188 DEV : loss 0.306864857673645 - f1-score (micro avg) 0.2274 2023-10-19 23:50:31,192 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:31,687 epoch 9 - iter 29/292 - loss 0.34080573 - time (sec): 0.49 - samples/sec: 8069.80 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:50:32,174 epoch 9 - iter 58/292 - loss 0.39740699 - time (sec): 0.98 - samples/sec: 8275.65 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:50:32,672 epoch 9 - iter 87/292 - loss 0.38941554 - time (sec): 1.48 - samples/sec: 8329.76 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:50:33,175 epoch 9 - iter 116/292 - loss 0.37411188 - time (sec): 1.98 - samples/sec: 8364.62 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:50:33,678 epoch 9 - iter 145/292 - loss 0.37705396 - time (sec): 2.49 - samples/sec: 8584.38 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:50:34,207 epoch 9 - iter 174/292 - loss 0.37556133 - time (sec): 3.01 - samples/sec: 8673.00 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:50:34,741 epoch 9 - iter 203/292 - loss 0.38081345 - time (sec): 3.55 - samples/sec: 8845.59 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:50:35,256 epoch 9 - iter 232/292 - loss 0.38515839 - time (sec): 4.06 - samples/sec: 8916.11 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:50:35,754 epoch 9 - iter 261/292 - loss 0.38318305 - time (sec): 4.56 - samples/sec: 8878.53 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:50:36,245 epoch 9 - iter 290/292 - loss 0.38427222 - time (sec): 5.05 - samples/sec: 8745.25 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:50:36,279 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:36,279 EPOCH 9 done: loss 0.3833 - lr: 0.000003 2023-10-19 23:50:37,074 DEV : loss 0.306318461894989 - f1-score (micro avg) 0.2234 2023-10-19 23:50:37,078 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:37,653 epoch 10 - iter 29/292 - loss 0.30956639 - time (sec): 0.58 - samples/sec: 8756.50 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:50:38,195 epoch 10 - iter 58/292 - loss 0.35087803 - time (sec): 1.12 - samples/sec: 8239.31 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:50:38,681 epoch 10 - iter 87/292 - loss 0.35546959 - time (sec): 1.60 - samples/sec: 8456.65 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:50:39,183 epoch 10 - iter 116/292 - loss 0.34859194 - time (sec): 2.10 - samples/sec: 8631.38 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:50:39,649 epoch 10 - iter 145/292 - loss 0.37253886 - time (sec): 2.57 - samples/sec: 8795.86 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:50:40,139 epoch 10 - iter 174/292 - loss 0.37750606 - time (sec): 3.06 - samples/sec: 8752.59 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:50:40,599 epoch 10 - iter 203/292 - loss 0.38037581 - time (sec): 3.52 - samples/sec: 8598.64 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:50:41,069 epoch 10 - iter 232/292 - loss 0.37226905 - time (sec): 3.99 - samples/sec: 8751.82 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:50:41,578 epoch 10 - iter 261/292 - loss 0.37712323 - time (sec): 4.50 - samples/sec: 8867.59 - lr: 0.000000 - momentum: 0.000000 2023-10-19 23:50:42,056 epoch 10 - iter 290/292 - loss 0.37760770 - time (sec): 4.98 - samples/sec: 8879.88 - lr: 0.000000 - momentum: 0.000000 2023-10-19 23:50:42,079 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:42,080 EPOCH 10 done: loss 0.3783 - lr: 0.000000 2023-10-19 23:50:42,723 DEV : loss 0.308378130197525 - f1-score (micro avg) 0.2222 2023-10-19 23:50:42,755 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:50:42,756 Loading model from best epoch ... 2023-10-19 23:50:42,833 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 2023-10-19 23:50:43,726 Results: - F-score (micro) 0.2325 - F-score (macro) 0.1217 - Accuracy 0.137 By class: precision recall f1-score support PER 0.2661 0.2615 0.2638 348 LOC 0.2537 0.1992 0.2232 261 ORG 0.0000 0.0000 0.0000 52 HumanProd 0.0000 0.0000 0.0000 22 micro avg 0.2614 0.2094 0.2325 683 macro avg 0.1299 0.1152 0.1217 683 weighted avg 0.2325 0.2094 0.2197 683 2023-10-19 23:50:43,726 ----------------------------------------------------------------------------------------------------