2023-10-19 23:51:49,700 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 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 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 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 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 Train: 1166 sentences 2023-10-19 23:51:49,701 (train_with_dev=False, train_with_test=False) 2023-10-19 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 Training Params: 2023-10-19 23:51:49,701 - learning_rate: "3e-05" 2023-10-19 23:51:49,701 - mini_batch_size: "8" 2023-10-19 23:51:49,701 - max_epochs: "10" 2023-10-19 23:51:49,701 - shuffle: "True" 2023-10-19 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 Plugins: 2023-10-19 23:51:49,701 - TensorboardLogger 2023-10-19 23:51:49,701 - LinearScheduler | warmup_fraction: '0.1' 2023-10-19 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 Final evaluation on model from best epoch (best-model.pt) 2023-10-19 23:51:49,701 - metric: "('micro avg', 'f1-score')" 2023-10-19 23:51:49,701 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,701 Computation: 2023-10-19 23:51:49,701 - compute on device: cuda:0 2023-10-19 23:51:49,701 - embedding storage: none 2023-10-19 23:51:49,702 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,702 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-19 23:51:49,702 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,702 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:49,702 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-19 23:51:50,088 epoch 1 - iter 14/146 - loss 3.34803276 - time (sec): 0.39 - samples/sec: 11886.51 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:51:50,441 epoch 1 - iter 28/146 - loss 3.24426997 - time (sec): 0.74 - samples/sec: 11746.87 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:51:50,828 epoch 1 - iter 42/146 - loss 3.17722726 - time (sec): 1.13 - samples/sec: 11334.14 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:51:51,227 epoch 1 - iter 56/146 - loss 3.06383245 - time (sec): 1.52 - samples/sec: 11127.79 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:51:51,611 epoch 1 - iter 70/146 - loss 2.97900869 - time (sec): 1.91 - samples/sec: 11251.57 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:51:51,985 epoch 1 - iter 84/146 - loss 2.86475164 - time (sec): 2.28 - samples/sec: 11411.19 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:51:52,374 epoch 1 - iter 98/146 - loss 2.76952224 - time (sec): 2.67 - samples/sec: 11378.82 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:51:52,748 epoch 1 - iter 112/146 - loss 2.62555563 - time (sec): 3.05 - samples/sec: 11482.65 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:51:53,129 epoch 1 - iter 126/146 - loss 2.50608976 - time (sec): 3.43 - samples/sec: 11324.46 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:51:53,511 epoch 1 - iter 140/146 - loss 2.38598195 - time (sec): 3.81 - samples/sec: 11288.10 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:51:53,672 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:53,672 EPOCH 1 done: loss 2.3402 - lr: 0.000029 2023-10-19 23:51:53,941 DEV : loss 0.4833422005176544 - f1-score (micro avg) 0.0 2023-10-19 23:51:53,945 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:54,358 epoch 2 - iter 14/146 - loss 1.00186629 - time (sec): 0.41 - samples/sec: 12089.20 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:51:54,720 epoch 2 - iter 28/146 - loss 0.89014949 - time (sec): 0.78 - samples/sec: 11314.02 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:51:55,079 epoch 2 - iter 42/146 - loss 0.85331323 - time (sec): 1.13 - samples/sec: 11572.81 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:51:55,473 epoch 2 - iter 56/146 - loss 0.82062153 - time (sec): 1.53 - samples/sec: 11530.13 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:51:55,826 epoch 2 - iter 70/146 - loss 0.80036944 - time (sec): 1.88 - samples/sec: 11591.03 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:51:56,200 epoch 2 - iter 84/146 - loss 0.78167558 - time (sec): 2.25 - samples/sec: 11607.64 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:51:56,541 epoch 2 - iter 98/146 - loss 0.73470966 - time (sec): 2.60 - samples/sec: 11570.72 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:51:56,922 epoch 2 - iter 112/146 - loss 0.71674782 - time (sec): 2.98 - samples/sec: 11688.35 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:51:57,290 epoch 2 - iter 126/146 - loss 0.70473681 - time (sec): 3.35 - samples/sec: 11606.83 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:51:57,656 epoch 2 - iter 140/146 - loss 0.70770530 - time (sec): 3.71 - samples/sec: 11598.03 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:51:57,796 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:57,796 EPOCH 2 done: loss 0.7028 - lr: 0.000027 2023-10-19 23:51:58,422 DEV : loss 0.44611138105392456 - f1-score (micro avg) 0.0 2023-10-19 23:51:58,426 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:51:58,949 epoch 3 - iter 14/146 - loss 0.56843240 - time (sec): 0.52 - samples/sec: 7685.20 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:51:59,330 epoch 3 - iter 28/146 - loss 0.55665083 - time (sec): 0.90 - samples/sec: 9273.02 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:51:59,705 epoch 3 - iter 42/146 - loss 0.56927226 - time (sec): 1.28 - samples/sec: 10481.34 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:52:00,049 epoch 3 - iter 56/146 - loss 0.56146026 - time (sec): 1.62 - samples/sec: 10990.27 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:52:00,407 epoch 3 - iter 70/146 - loss 0.56962488 - time (sec): 1.98 - samples/sec: 11026.51 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:52:00,760 epoch 3 - iter 84/146 - loss 0.55978929 - time (sec): 2.33 - samples/sec: 11177.29 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:52:01,117 epoch 3 - iter 98/146 - loss 0.55736095 - time (sec): 2.69 - samples/sec: 11279.49 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:52:01,491 epoch 3 - iter 112/146 - loss 0.57916592 - time (sec): 3.06 - samples/sec: 11199.25 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:52:01,868 epoch 3 - iter 126/146 - loss 0.60494417 - time (sec): 3.44 - samples/sec: 11332.47 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:52:02,213 epoch 3 - iter 140/146 - loss 0.59677716 - time (sec): 3.79 - samples/sec: 11354.76 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:52:02,351 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:02,351 EPOCH 3 done: loss 0.5947 - lr: 0.000024 2023-10-19 23:52:02,980 DEV : loss 0.3864370584487915 - f1-score (micro avg) 0.0 2023-10-19 23:52:02,984 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:03,349 epoch 4 - iter 14/146 - loss 0.51833400 - time (sec): 0.36 - samples/sec: 11745.60 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:52:03,714 epoch 4 - iter 28/146 - loss 0.54395629 - time (sec): 0.73 - samples/sec: 11621.06 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:52:04,082 epoch 4 - iter 42/146 - loss 0.56680138 - time (sec): 1.10 - samples/sec: 10967.22 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:52:04,447 epoch 4 - iter 56/146 - loss 0.57277620 - time (sec): 1.46 - samples/sec: 11339.24 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:52:04,825 epoch 4 - iter 70/146 - loss 0.63447119 - time (sec): 1.84 - samples/sec: 11379.23 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:52:05,194 epoch 4 - iter 84/146 - loss 0.61181656 - time (sec): 2.21 - samples/sec: 11408.00 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:52:05,552 epoch 4 - iter 98/146 - loss 0.58758215 - time (sec): 2.57 - samples/sec: 11328.25 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:52:05,957 epoch 4 - iter 112/146 - loss 0.57376561 - time (sec): 2.97 - samples/sec: 11463.68 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:52:06,331 epoch 4 - iter 126/146 - loss 0.57197538 - time (sec): 3.35 - samples/sec: 11366.94 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:52:06,689 epoch 4 - iter 140/146 - loss 0.57285088 - time (sec): 3.70 - samples/sec: 11470.39 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:52:06,850 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:06,850 EPOCH 4 done: loss 0.5641 - lr: 0.000020 2023-10-19 23:52:07,480 DEV : loss 0.35983359813690186 - f1-score (micro avg) 0.0 2023-10-19 23:52:07,485 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:07,886 epoch 5 - iter 14/146 - loss 0.72697613 - time (sec): 0.40 - samples/sec: 11787.78 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:52:08,229 epoch 5 - iter 28/146 - loss 0.67048227 - time (sec): 0.74 - samples/sec: 11342.21 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:52:08,606 epoch 5 - iter 42/146 - loss 0.60440180 - time (sec): 1.12 - samples/sec: 11690.40 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:52:08,982 epoch 5 - iter 56/146 - loss 0.56150800 - time (sec): 1.50 - samples/sec: 11649.36 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:52:09,373 epoch 5 - iter 70/146 - loss 0.52666893 - time (sec): 1.89 - samples/sec: 11755.06 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:52:09,725 epoch 5 - iter 84/146 - loss 0.51426781 - time (sec): 2.24 - samples/sec: 11594.14 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:52:10,084 epoch 5 - iter 98/146 - loss 0.50838649 - time (sec): 2.60 - samples/sec: 11665.32 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:52:10,429 epoch 5 - iter 112/146 - loss 0.50712580 - time (sec): 2.94 - samples/sec: 11427.86 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:52:10,808 epoch 5 - iter 126/146 - loss 0.52046347 - time (sec): 3.32 - samples/sec: 11439.33 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:52:11,153 epoch 5 - iter 140/146 - loss 0.51748259 - time (sec): 3.67 - samples/sec: 11606.10 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:52:11,300 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:11,300 EPOCH 5 done: loss 0.5165 - lr: 0.000017 2023-10-19 23:52:11,942 DEV : loss 0.3400147259235382 - f1-score (micro avg) 0.0239 2023-10-19 23:52:11,946 saving best model 2023-10-19 23:52:11,974 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:12,348 epoch 6 - iter 14/146 - loss 0.71859012 - time (sec): 0.37 - samples/sec: 11707.07 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:52:12,718 epoch 6 - iter 28/146 - loss 0.56899183 - time (sec): 0.74 - samples/sec: 11591.23 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:52:13,066 epoch 6 - iter 42/146 - loss 0.51990607 - time (sec): 1.09 - samples/sec: 11725.64 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:52:13,421 epoch 6 - iter 56/146 - loss 0.53360635 - time (sec): 1.45 - samples/sec: 11407.04 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:52:13,794 epoch 6 - iter 70/146 - loss 0.51135818 - time (sec): 1.82 - samples/sec: 11590.61 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:52:14,173 epoch 6 - iter 84/146 - loss 0.52944252 - time (sec): 2.20 - samples/sec: 11857.16 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:52:14,529 epoch 6 - iter 98/146 - loss 0.51191496 - time (sec): 2.55 - samples/sec: 11896.68 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:52:14,897 epoch 6 - iter 112/146 - loss 0.50006322 - time (sec): 2.92 - samples/sec: 11820.64 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:52:15,263 epoch 6 - iter 126/146 - loss 0.49173276 - time (sec): 3.29 - samples/sec: 11820.55 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:52:15,633 epoch 6 - iter 140/146 - loss 0.48245262 - time (sec): 3.66 - samples/sec: 11790.09 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:52:15,786 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:15,786 EPOCH 6 done: loss 0.4839 - lr: 0.000014 2023-10-19 23:52:16,429 DEV : loss 0.330739289522171 - f1-score (micro avg) 0.0578 2023-10-19 23:52:16,433 saving best model 2023-10-19 23:52:16,467 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:16,808 epoch 7 - iter 14/146 - loss 0.39481050 - time (sec): 0.34 - samples/sec: 10822.62 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:52:17,182 epoch 7 - iter 28/146 - loss 0.37652749 - time (sec): 0.71 - samples/sec: 10971.66 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:52:17,551 epoch 7 - iter 42/146 - loss 0.41835909 - time (sec): 1.08 - samples/sec: 11195.45 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:52:17,895 epoch 7 - iter 56/146 - loss 0.42637595 - time (sec): 1.43 - samples/sec: 10986.57 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:52:18,285 epoch 7 - iter 70/146 - loss 0.46759904 - time (sec): 1.82 - samples/sec: 11177.84 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:52:18,641 epoch 7 - iter 84/146 - loss 0.47208007 - time (sec): 2.17 - samples/sec: 11097.59 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:52:19,156 epoch 7 - iter 98/146 - loss 0.46177264 - time (sec): 2.69 - samples/sec: 10435.71 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:52:19,543 epoch 7 - iter 112/146 - loss 0.47139861 - time (sec): 3.07 - samples/sec: 10770.10 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:52:19,935 epoch 7 - iter 126/146 - loss 0.47595257 - time (sec): 3.47 - samples/sec: 10955.23 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:52:20,297 epoch 7 - iter 140/146 - loss 0.46725905 - time (sec): 3.83 - samples/sec: 11088.10 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:52:20,466 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:20,466 EPOCH 7 done: loss 0.4635 - lr: 0.000010 2023-10-19 23:52:21,114 DEV : loss 0.32605770230293274 - f1-score (micro avg) 0.0972 2023-10-19 23:52:21,118 saving best model 2023-10-19 23:52:21,151 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:21,533 epoch 8 - iter 14/146 - loss 0.39063923 - time (sec): 0.38 - samples/sec: 11350.79 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:52:21,890 epoch 8 - iter 28/146 - loss 0.52358403 - time (sec): 0.74 - samples/sec: 11999.88 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:52:22,256 epoch 8 - iter 42/146 - loss 0.47448311 - time (sec): 1.10 - samples/sec: 11965.72 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:52:22,629 epoch 8 - iter 56/146 - loss 0.44651128 - time (sec): 1.48 - samples/sec: 11768.99 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:52:23,000 epoch 8 - iter 70/146 - loss 0.43905400 - time (sec): 1.85 - samples/sec: 11734.69 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:52:23,336 epoch 8 - iter 84/146 - loss 0.43488104 - time (sec): 2.18 - samples/sec: 11814.12 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:52:23,679 epoch 8 - iter 98/146 - loss 0.44948982 - time (sec): 2.53 - samples/sec: 11595.87 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:52:24,064 epoch 8 - iter 112/146 - loss 0.45606613 - time (sec): 2.91 - samples/sec: 11562.77 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:52:24,437 epoch 8 - iter 126/146 - loss 0.44624813 - time (sec): 3.28 - samples/sec: 11655.29 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:52:24,792 epoch 8 - iter 140/146 - loss 0.44820969 - time (sec): 3.64 - samples/sec: 11694.03 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:52:24,948 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:24,948 EPOCH 8 done: loss 0.4477 - lr: 0.000007 2023-10-19 23:52:25,586 DEV : loss 0.3263406455516815 - f1-score (micro avg) 0.1153 2023-10-19 23:52:25,590 saving best model 2023-10-19 23:52:25,622 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:25,985 epoch 9 - iter 14/146 - loss 0.37820188 - time (sec): 0.36 - samples/sec: 10688.65 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:52:26,348 epoch 9 - iter 28/146 - loss 0.43671802 - time (sec): 0.73 - samples/sec: 10798.78 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:52:26,711 epoch 9 - iter 42/146 - loss 0.41517691 - time (sec): 1.09 - samples/sec: 11087.48 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:52:27,068 epoch 9 - iter 56/146 - loss 0.41215518 - time (sec): 1.44 - samples/sec: 11017.47 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:52:27,440 epoch 9 - iter 70/146 - loss 0.41827437 - time (sec): 1.82 - samples/sec: 11438.00 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:52:27,791 epoch 9 - iter 84/146 - loss 0.42593948 - time (sec): 2.17 - samples/sec: 11533.40 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:52:28,171 epoch 9 - iter 98/146 - loss 0.44034346 - time (sec): 2.55 - samples/sec: 11779.63 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:52:28,533 epoch 9 - iter 112/146 - loss 0.44311122 - time (sec): 2.91 - samples/sec: 11922.65 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:52:28,895 epoch 9 - iter 126/146 - loss 0.44155197 - time (sec): 3.27 - samples/sec: 12014.38 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:52:29,249 epoch 9 - iter 140/146 - loss 0.44005196 - time (sec): 3.63 - samples/sec: 11838.33 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:52:29,394 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:29,394 EPOCH 9 done: loss 0.4382 - lr: 0.000004 2023-10-19 23:52:30,032 DEV : loss 0.3212380111217499 - f1-score (micro avg) 0.1858 2023-10-19 23:52:30,036 saving best model 2023-10-19 23:52:30,068 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:30,452 epoch 10 - iter 14/146 - loss 0.32923291 - time (sec): 0.38 - samples/sec: 13011.39 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:52:30,810 epoch 10 - iter 28/146 - loss 0.38363662 - time (sec): 0.74 - samples/sec: 12147.27 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:52:31,181 epoch 10 - iter 42/146 - loss 0.38745870 - time (sec): 1.11 - samples/sec: 11796.33 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:52:31,543 epoch 10 - iter 56/146 - loss 0.37499813 - time (sec): 1.47 - samples/sec: 11874.41 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:52:31,922 epoch 10 - iter 70/146 - loss 0.39212077 - time (sec): 1.85 - samples/sec: 11639.66 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:52:32,302 epoch 10 - iter 84/146 - loss 0.41564761 - time (sec): 2.23 - samples/sec: 11571.15 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:52:32,647 epoch 10 - iter 98/146 - loss 0.42084198 - time (sec): 2.58 - samples/sec: 11389.64 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:52:33,018 epoch 10 - iter 112/146 - loss 0.42000229 - time (sec): 2.95 - samples/sec: 11351.89 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:52:33,380 epoch 10 - iter 126/146 - loss 0.43344724 - time (sec): 3.31 - samples/sec: 11581.27 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:52:33,752 epoch 10 - iter 140/146 - loss 0.43011787 - time (sec): 3.68 - samples/sec: 11638.03 - lr: 0.000000 - momentum: 0.000000 2023-10-19 23:52:33,905 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:33,906 EPOCH 10 done: loss 0.4317 - lr: 0.000000 2023-10-19 23:52:34,546 DEV : loss 0.32181745767593384 - f1-score (micro avg) 0.1801 2023-10-19 23:52:34,578 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:52:34,579 Loading model from best epoch ... 2023-10-19 23:52:34,653 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 23:52:35,708 Results: - F-score (micro) 0.1645 - F-score (macro) 0.0772 - Accuracy 0.0923 By class: precision recall f1-score support PER 0.2151 0.2126 0.2139 348 LOC 0.2727 0.0575 0.0949 261 ORG 0.0000 0.0000 0.0000 52 HumanProd 0.0000 0.0000 0.0000 22 micro avg 0.2231 0.1303 0.1645 683 macro avg 0.1220 0.0675 0.0772 683 weighted avg 0.2138 0.1303 0.1453 683 2023-10-19 23:52:35,708 ----------------------------------------------------------------------------------------------------