2023-10-19 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,265 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 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,265 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 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,265 Train: 1166 sentences 2023-10-19 23:54:46,265 (train_with_dev=False, train_with_test=False) 2023-10-19 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,265 Training Params: 2023-10-19 23:54:46,265 - learning_rate: "5e-05" 2023-10-19 23:54:46,265 - mini_batch_size: "4" 2023-10-19 23:54:46,265 - max_epochs: "10" 2023-10-19 23:54:46,265 - shuffle: "True" 2023-10-19 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,265 Plugins: 2023-10-19 23:54:46,265 - TensorboardLogger 2023-10-19 23:54:46,265 - LinearScheduler | warmup_fraction: '0.1' 2023-10-19 23:54:46,265 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,266 Final evaluation on model from best epoch (best-model.pt) 2023-10-19 23:54:46,266 - metric: "('micro avg', 'f1-score')" 2023-10-19 23:54:46,266 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,266 Computation: 2023-10-19 23:54:46,266 - compute on device: cuda:0 2023-10-19 23:54:46,266 - embedding storage: none 2023-10-19 23:54:46,266 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,266 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-19 23:54:46,266 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,266 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:46,266 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-19 23:54:46,793 epoch 1 - iter 29/292 - loss 3.55752914 - time (sec): 0.53 - samples/sec: 7908.79 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:54:47,324 epoch 1 - iter 58/292 - loss 3.51797914 - time (sec): 1.06 - samples/sec: 8808.85 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:54:47,833 epoch 1 - iter 87/292 - loss 3.38770600 - time (sec): 1.57 - samples/sec: 8612.55 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:54:48,346 epoch 1 - iter 116/292 - loss 3.15720938 - time (sec): 2.08 - samples/sec: 8491.67 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:54:48,870 epoch 1 - iter 145/292 - loss 2.91319087 - time (sec): 2.60 - samples/sec: 8456.38 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:54:49,365 epoch 1 - iter 174/292 - loss 2.68788876 - time (sec): 3.10 - samples/sec: 8374.19 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:54:49,915 epoch 1 - iter 203/292 - loss 2.45249775 - time (sec): 3.65 - samples/sec: 8479.75 - lr: 0.000035 - momentum: 0.000000 2023-10-19 23:54:50,473 epoch 1 - iter 232/292 - loss 2.21945254 - time (sec): 4.21 - samples/sec: 8501.77 - lr: 0.000040 - momentum: 0.000000 2023-10-19 23:54:50,953 epoch 1 - iter 261/292 - loss 2.05466586 - time (sec): 4.69 - samples/sec: 8518.18 - lr: 0.000045 - momentum: 0.000000 2023-10-19 23:54:51,428 epoch 1 - iter 290/292 - loss 1.91851237 - time (sec): 5.16 - samples/sec: 8529.52 - lr: 0.000049 - momentum: 0.000000 2023-10-19 23:54:51,462 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:51,462 EPOCH 1 done: loss 1.9040 - lr: 0.000049 2023-10-19 23:54:51,728 DEV : loss 0.45997393131256104 - f1-score (micro avg) 0.0 2023-10-19 23:54:51,732 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:52,162 epoch 2 - iter 29/292 - loss 0.58656023 - time (sec): 0.43 - samples/sec: 7909.71 - lr: 0.000049 - momentum: 0.000000 2023-10-19 23:54:52,603 epoch 2 - iter 58/292 - loss 0.63439941 - time (sec): 0.87 - samples/sec: 9252.63 - lr: 0.000049 - momentum: 0.000000 2023-10-19 23:54:53,049 epoch 2 - iter 87/292 - loss 0.63149781 - time (sec): 1.32 - samples/sec: 9293.51 - lr: 0.000048 - momentum: 0.000000 2023-10-19 23:54:53,493 epoch 2 - iter 116/292 - loss 0.62294731 - time (sec): 1.76 - samples/sec: 9411.80 - lr: 0.000048 - momentum: 0.000000 2023-10-19 23:54:53,982 epoch 2 - iter 145/292 - loss 0.67190983 - time (sec): 2.25 - samples/sec: 9782.63 - lr: 0.000047 - momentum: 0.000000 2023-10-19 23:54:54,587 epoch 2 - iter 174/292 - loss 0.65041157 - time (sec): 2.85 - samples/sec: 9342.32 - lr: 0.000047 - momentum: 0.000000 2023-10-19 23:54:55,159 epoch 2 - iter 203/292 - loss 0.62124438 - time (sec): 3.43 - samples/sec: 9211.13 - lr: 0.000046 - momentum: 0.000000 2023-10-19 23:54:55,714 epoch 2 - iter 232/292 - loss 0.61325278 - time (sec): 3.98 - samples/sec: 8902.60 - lr: 0.000046 - momentum: 0.000000 2023-10-19 23:54:56,273 epoch 2 - iter 261/292 - loss 0.60750010 - time (sec): 4.54 - samples/sec: 8763.90 - lr: 0.000045 - momentum: 0.000000 2023-10-19 23:54:56,780 epoch 2 - iter 290/292 - loss 0.59371287 - time (sec): 5.05 - samples/sec: 8713.85 - lr: 0.000045 - momentum: 0.000000 2023-10-19 23:54:56,811 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:56,811 EPOCH 2 done: loss 0.5942 - lr: 0.000045 2023-10-19 23:54:57,612 DEV : loss 0.34521862864494324 - f1-score (micro avg) 0.0 2023-10-19 23:54:57,616 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:54:58,150 epoch 3 - iter 29/292 - loss 0.43874260 - time (sec): 0.53 - samples/sec: 8885.33 - lr: 0.000044 - momentum: 0.000000 2023-10-19 23:54:58,660 epoch 3 - iter 58/292 - loss 0.45959734 - time (sec): 1.04 - samples/sec: 8864.19 - lr: 0.000043 - momentum: 0.000000 2023-10-19 23:54:59,178 epoch 3 - iter 87/292 - loss 0.46972901 - time (sec): 1.56 - samples/sec: 8336.04 - lr: 0.000043 - momentum: 0.000000 2023-10-19 23:54:59,714 epoch 3 - iter 116/292 - loss 0.45936071 - time (sec): 2.10 - samples/sec: 8357.63 - lr: 0.000042 - momentum: 0.000000 2023-10-19 23:55:00,257 epoch 3 - iter 145/292 - loss 0.48567862 - time (sec): 2.64 - samples/sec: 8187.12 - lr: 0.000042 - momentum: 0.000000 2023-10-19 23:55:00,798 epoch 3 - iter 174/292 - loss 0.47727066 - time (sec): 3.18 - samples/sec: 8207.62 - lr: 0.000041 - momentum: 0.000000 2023-10-19 23:55:01,351 epoch 3 - iter 203/292 - loss 0.48496424 - time (sec): 3.73 - samples/sec: 8427.15 - lr: 0.000041 - momentum: 0.000000 2023-10-19 23:55:01,873 epoch 3 - iter 232/292 - loss 0.48084606 - time (sec): 4.26 - samples/sec: 8398.02 - lr: 0.000040 - momentum: 0.000000 2023-10-19 23:55:02,397 epoch 3 - iter 261/292 - loss 0.47958169 - time (sec): 4.78 - samples/sec: 8305.75 - lr: 0.000040 - momentum: 0.000000 2023-10-19 23:55:02,917 epoch 3 - iter 290/292 - loss 0.47094732 - time (sec): 5.30 - samples/sec: 8310.97 - lr: 0.000039 - momentum: 0.000000 2023-10-19 23:55:02,952 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:02,953 EPOCH 3 done: loss 0.4685 - lr: 0.000039 2023-10-19 23:55:03,596 DEV : loss 0.31381186842918396 - f1-score (micro avg) 0.1303 2023-10-19 23:55:03,600 saving best model 2023-10-19 23:55:03,629 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:04,156 epoch 4 - iter 29/292 - loss 0.43177072 - time (sec): 0.53 - samples/sec: 8615.07 - lr: 0.000038 - momentum: 0.000000 2023-10-19 23:55:04,683 epoch 4 - iter 58/292 - loss 0.41853015 - time (sec): 1.05 - samples/sec: 8960.14 - lr: 0.000038 - momentum: 0.000000 2023-10-19 23:55:05,216 epoch 4 - iter 87/292 - loss 0.39904768 - time (sec): 1.59 - samples/sec: 8975.40 - lr: 0.000037 - momentum: 0.000000 2023-10-19 23:55:05,693 epoch 4 - iter 116/292 - loss 0.39486048 - time (sec): 2.06 - samples/sec: 8683.45 - lr: 0.000037 - momentum: 0.000000 2023-10-19 23:55:06,182 epoch 4 - iter 145/292 - loss 0.38926525 - time (sec): 2.55 - samples/sec: 8552.06 - lr: 0.000036 - momentum: 0.000000 2023-10-19 23:55:06,693 epoch 4 - iter 174/292 - loss 0.38841178 - time (sec): 3.06 - samples/sec: 8439.81 - lr: 0.000036 - momentum: 0.000000 2023-10-19 23:55:07,187 epoch 4 - iter 203/292 - loss 0.38717609 - time (sec): 3.56 - samples/sec: 8323.23 - lr: 0.000035 - momentum: 0.000000 2023-10-19 23:55:07,715 epoch 4 - iter 232/292 - loss 0.39343263 - time (sec): 4.09 - samples/sec: 8440.52 - lr: 0.000035 - momentum: 0.000000 2023-10-19 23:55:08,255 epoch 4 - iter 261/292 - loss 0.41230712 - time (sec): 4.63 - samples/sec: 8572.69 - lr: 0.000034 - momentum: 0.000000 2023-10-19 23:55:08,816 epoch 4 - iter 290/292 - loss 0.41910163 - time (sec): 5.19 - samples/sec: 8487.60 - lr: 0.000033 - momentum: 0.000000 2023-10-19 23:55:08,856 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:08,856 EPOCH 4 done: loss 0.4154 - lr: 0.000033 2023-10-19 23:55:09,491 DEV : loss 0.3016578257083893 - f1-score (micro avg) 0.2328 2023-10-19 23:55:09,495 saving best model 2023-10-19 23:55:09,530 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:10,074 epoch 5 - iter 29/292 - loss 0.43229368 - time (sec): 0.54 - samples/sec: 8265.43 - lr: 0.000033 - momentum: 0.000000 2023-10-19 23:55:10,601 epoch 5 - iter 58/292 - loss 0.37539253 - time (sec): 1.07 - samples/sec: 8654.01 - lr: 0.000032 - momentum: 0.000000 2023-10-19 23:55:11,118 epoch 5 - iter 87/292 - loss 0.40406274 - time (sec): 1.59 - samples/sec: 8605.36 - lr: 0.000032 - momentum: 0.000000 2023-10-19 23:55:11,636 epoch 5 - iter 116/292 - loss 0.40222319 - time (sec): 2.11 - samples/sec: 8412.63 - lr: 0.000031 - momentum: 0.000000 2023-10-19 23:55:12,149 epoch 5 - iter 145/292 - loss 0.39690686 - time (sec): 2.62 - samples/sec: 8624.99 - lr: 0.000031 - momentum: 0.000000 2023-10-19 23:55:12,669 epoch 5 - iter 174/292 - loss 0.39595604 - time (sec): 3.14 - samples/sec: 8461.59 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:55:13,173 epoch 5 - iter 203/292 - loss 0.39014674 - time (sec): 3.64 - samples/sec: 8592.12 - lr: 0.000030 - momentum: 0.000000 2023-10-19 23:55:13,667 epoch 5 - iter 232/292 - loss 0.39145583 - time (sec): 4.14 - samples/sec: 8507.40 - lr: 0.000029 - momentum: 0.000000 2023-10-19 23:55:14,174 epoch 5 - iter 261/292 - loss 0.38172039 - time (sec): 4.64 - samples/sec: 8575.01 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:55:14,665 epoch 5 - iter 290/292 - loss 0.37542897 - time (sec): 5.13 - samples/sec: 8597.45 - lr: 0.000028 - momentum: 0.000000 2023-10-19 23:55:14,700 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:14,700 EPOCH 5 done: loss 0.3775 - lr: 0.000028 2023-10-19 23:55:15,336 DEV : loss 0.2973732054233551 - f1-score (micro avg) 0.2654 2023-10-19 23:55:15,340 saving best model 2023-10-19 23:55:15,372 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:15,873 epoch 6 - iter 29/292 - loss 0.37312102 - time (sec): 0.50 - samples/sec: 9364.57 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:55:16,391 epoch 6 - iter 58/292 - loss 0.36942596 - time (sec): 1.02 - samples/sec: 8762.88 - lr: 0.000027 - momentum: 0.000000 2023-10-19 23:55:16,914 epoch 6 - iter 87/292 - loss 0.34805366 - time (sec): 1.54 - samples/sec: 8399.49 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:55:17,447 epoch 6 - iter 116/292 - loss 0.37301859 - time (sec): 2.07 - samples/sec: 8795.53 - lr: 0.000026 - momentum: 0.000000 2023-10-19 23:55:17,968 epoch 6 - iter 145/292 - loss 0.38869681 - time (sec): 2.60 - samples/sec: 8817.51 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:55:18,485 epoch 6 - iter 174/292 - loss 0.36418246 - time (sec): 3.11 - samples/sec: 8987.93 - lr: 0.000025 - momentum: 0.000000 2023-10-19 23:55:19,005 epoch 6 - iter 203/292 - loss 0.36949889 - time (sec): 3.63 - samples/sec: 8807.31 - lr: 0.000024 - momentum: 0.000000 2023-10-19 23:55:19,515 epoch 6 - iter 232/292 - loss 0.36160845 - time (sec): 4.14 - samples/sec: 8753.61 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:55:20,009 epoch 6 - iter 261/292 - loss 0.36352966 - time (sec): 4.64 - samples/sec: 8640.60 - lr: 0.000023 - momentum: 0.000000 2023-10-19 23:55:20,507 epoch 6 - iter 290/292 - loss 0.35857782 - time (sec): 5.13 - samples/sec: 8588.66 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:55:20,538 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:20,538 EPOCH 6 done: loss 0.3575 - lr: 0.000022 2023-10-19 23:55:21,183 DEV : loss 0.29466673731803894 - f1-score (micro avg) 0.2937 2023-10-19 23:55:21,187 saving best model 2023-10-19 23:55:21,221 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:21,729 epoch 7 - iter 29/292 - loss 0.38819137 - time (sec): 0.51 - samples/sec: 8190.47 - lr: 0.000022 - momentum: 0.000000 2023-10-19 23:55:22,263 epoch 7 - iter 58/292 - loss 0.34242214 - time (sec): 1.04 - samples/sec: 8732.14 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:55:22,798 epoch 7 - iter 87/292 - loss 0.35717419 - time (sec): 1.58 - samples/sec: 8812.53 - lr: 0.000021 - momentum: 0.000000 2023-10-19 23:55:23,307 epoch 7 - iter 116/292 - loss 0.37602817 - time (sec): 2.09 - samples/sec: 8721.64 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:55:23,820 epoch 7 - iter 145/292 - loss 0.36879662 - time (sec): 2.60 - samples/sec: 8665.03 - lr: 0.000020 - momentum: 0.000000 2023-10-19 23:55:24,342 epoch 7 - iter 174/292 - loss 0.36046721 - time (sec): 3.12 - samples/sec: 8544.70 - lr: 0.000019 - momentum: 0.000000 2023-10-19 23:55:24,835 epoch 7 - iter 203/292 - loss 0.35584894 - time (sec): 3.61 - samples/sec: 8468.06 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:55:25,332 epoch 7 - iter 232/292 - loss 0.35765109 - time (sec): 4.11 - samples/sec: 8520.60 - lr: 0.000018 - momentum: 0.000000 2023-10-19 23:55:25,837 epoch 7 - iter 261/292 - loss 0.34589803 - time (sec): 4.62 - samples/sec: 8620.32 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:55:26,370 epoch 7 - iter 290/292 - loss 0.33965089 - time (sec): 5.15 - samples/sec: 8590.24 - lr: 0.000017 - momentum: 0.000000 2023-10-19 23:55:26,397 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:26,397 EPOCH 7 done: loss 0.3397 - lr: 0.000017 2023-10-19 23:55:27,049 DEV : loss 0.29104095697402954 - f1-score (micro avg) 0.3193 2023-10-19 23:55:27,052 saving best model 2023-10-19 23:55:27,085 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:27,615 epoch 8 - iter 29/292 - loss 0.29154439 - time (sec): 0.53 - samples/sec: 8832.63 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:55:28,142 epoch 8 - iter 58/292 - loss 0.34250586 - time (sec): 1.06 - samples/sec: 9218.94 - lr: 0.000016 - momentum: 0.000000 2023-10-19 23:55:28,629 epoch 8 - iter 87/292 - loss 0.32930383 - time (sec): 1.54 - samples/sec: 8830.03 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:55:29,160 epoch 8 - iter 116/292 - loss 0.32840663 - time (sec): 2.07 - samples/sec: 8764.31 - lr: 0.000015 - momentum: 0.000000 2023-10-19 23:55:29,636 epoch 8 - iter 145/292 - loss 0.32284264 - time (sec): 2.55 - samples/sec: 8542.07 - lr: 0.000014 - momentum: 0.000000 2023-10-19 23:55:30,078 epoch 8 - iter 174/292 - loss 0.32209124 - time (sec): 2.99 - samples/sec: 8424.20 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:55:30,578 epoch 8 - iter 203/292 - loss 0.33155736 - time (sec): 3.49 - samples/sec: 8675.07 - lr: 0.000013 - momentum: 0.000000 2023-10-19 23:55:31,241 epoch 8 - iter 232/292 - loss 0.32136242 - time (sec): 4.16 - samples/sec: 8525.82 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:55:31,714 epoch 8 - iter 261/292 - loss 0.32137603 - time (sec): 4.63 - samples/sec: 8544.97 - lr: 0.000012 - momentum: 0.000000 2023-10-19 23:55:32,222 epoch 8 - iter 290/292 - loss 0.32337631 - time (sec): 5.14 - samples/sec: 8605.69 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:55:32,257 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:32,257 EPOCH 8 done: loss 0.3226 - lr: 0.000011 2023-10-19 23:55:32,918 DEV : loss 0.29328519105911255 - f1-score (micro avg) 0.3129 2023-10-19 23:55:32,923 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:33,419 epoch 9 - iter 29/292 - loss 0.29822543 - time (sec): 0.50 - samples/sec: 8134.79 - lr: 0.000011 - momentum: 0.000000 2023-10-19 23:55:33,914 epoch 9 - iter 58/292 - loss 0.34739399 - time (sec): 0.99 - samples/sec: 8415.03 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:55:34,382 epoch 9 - iter 87/292 - loss 0.34634734 - time (sec): 1.46 - samples/sec: 8010.70 - lr: 0.000010 - momentum: 0.000000 2023-10-19 23:55:34,892 epoch 9 - iter 116/292 - loss 0.34386116 - time (sec): 1.97 - samples/sec: 8071.38 - lr: 0.000009 - momentum: 0.000000 2023-10-19 23:55:35,411 epoch 9 - iter 145/292 - loss 0.34301480 - time (sec): 2.49 - samples/sec: 8269.81 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:55:35,926 epoch 9 - iter 174/292 - loss 0.33151984 - time (sec): 3.00 - samples/sec: 8533.95 - lr: 0.000008 - momentum: 0.000000 2023-10-19 23:55:36,436 epoch 9 - iter 203/292 - loss 0.33282371 - time (sec): 3.51 - samples/sec: 8455.15 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:55:36,974 epoch 9 - iter 232/292 - loss 0.33502228 - time (sec): 4.05 - samples/sec: 8611.47 - lr: 0.000007 - momentum: 0.000000 2023-10-19 23:55:37,492 epoch 9 - iter 261/292 - loss 0.32271061 - time (sec): 4.57 - samples/sec: 8680.15 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:55:38,050 epoch 9 - iter 290/292 - loss 0.31960374 - time (sec): 5.13 - samples/sec: 8640.65 - lr: 0.000006 - momentum: 0.000000 2023-10-19 23:55:38,079 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:38,079 EPOCH 9 done: loss 0.3192 - lr: 0.000006 2023-10-19 23:55:38,728 DEV : loss 0.2915344834327698 - f1-score (micro avg) 0.3067 2023-10-19 23:55:38,731 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:39,234 epoch 10 - iter 29/292 - loss 0.25691072 - time (sec): 0.50 - samples/sec: 9550.60 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:55:39,752 epoch 10 - iter 58/292 - loss 0.32264057 - time (sec): 1.02 - samples/sec: 9710.22 - lr: 0.000005 - momentum: 0.000000 2023-10-19 23:55:40,262 epoch 10 - iter 87/292 - loss 0.29381973 - time (sec): 1.53 - samples/sec: 9342.81 - lr: 0.000004 - momentum: 0.000000 2023-10-19 23:55:40,745 epoch 10 - iter 116/292 - loss 0.29276188 - time (sec): 2.01 - samples/sec: 9055.61 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:55:41,215 epoch 10 - iter 145/292 - loss 0.30739420 - time (sec): 2.48 - samples/sec: 8724.85 - lr: 0.000003 - momentum: 0.000000 2023-10-19 23:55:41,719 epoch 10 - iter 174/292 - loss 0.30017946 - time (sec): 2.99 - samples/sec: 8931.07 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:55:42,236 epoch 10 - iter 203/292 - loss 0.29891419 - time (sec): 3.50 - samples/sec: 8834.20 - lr: 0.000002 - momentum: 0.000000 2023-10-19 23:55:42,768 epoch 10 - iter 232/292 - loss 0.30792335 - time (sec): 4.04 - samples/sec: 8901.96 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:55:43,258 epoch 10 - iter 261/292 - loss 0.31694630 - time (sec): 4.53 - samples/sec: 8787.52 - lr: 0.000001 - momentum: 0.000000 2023-10-19 23:55:43,793 epoch 10 - iter 290/292 - loss 0.31667346 - time (sec): 5.06 - samples/sec: 8740.26 - lr: 0.000000 - momentum: 0.000000 2023-10-19 23:55:43,823 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:43,823 EPOCH 10 done: loss 0.3158 - lr: 0.000000 2023-10-19 23:55:44,474 DEV : loss 0.2926194965839386 - f1-score (micro avg) 0.307 2023-10-19 23:55:44,506 ---------------------------------------------------------------------------------------------------- 2023-10-19 23:55:44,507 Loading model from best epoch ... 2023-10-19 23:55:44,580 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 23:55:45,486 Results: - F-score (micro) 0.3714 - F-score (macro) 0.196 - Accuracy 0.237 By class: precision recall f1-score support PER 0.3965 0.3908 0.3936 348 LOC 0.3316 0.4751 0.3906 261 ORG 0.0000 0.0000 0.0000 52 HumanProd 0.0000 0.0000 0.0000 22 micro avg 0.3626 0.3807 0.3714 683 macro avg 0.1820 0.2165 0.1960 683 weighted avg 0.3287 0.3807 0.3498 683 2023-10-19 23:55:45,486 ----------------------------------------------------------------------------------------------------