2023-10-25 21:31:24,935 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,936 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 21:31:24,936 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,936 MultiCorpus: 1085 train + 148 dev + 364 test sentences - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator 2023-10-25 21:31:24,936 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Train: 1085 sentences 2023-10-25 21:31:24,937 (train_with_dev=False, train_with_test=False) 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Training Params: 2023-10-25 21:31:24,937 - learning_rate: "3e-05" 2023-10-25 21:31:24,937 - mini_batch_size: "8" 2023-10-25 21:31:24,937 - max_epochs: "10" 2023-10-25 21:31:24,937 - shuffle: "True" 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Plugins: 2023-10-25 21:31:24,937 - TensorboardLogger 2023-10-25 21:31:24,937 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:31:24,937 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Computation: 2023-10-25 21:31:24,937 - compute on device: cuda:0 2023-10-25 21:31:24,937 - embedding storage: none 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:24,937 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:31:25,855 epoch 1 - iter 13/136 - loss 2.67862976 - time (sec): 0.92 - samples/sec: 5455.64 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:31:26,870 epoch 1 - iter 26/136 - loss 2.31862643 - time (sec): 1.93 - samples/sec: 5241.39 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:31:27,857 epoch 1 - iter 39/136 - loss 1.79659135 - time (sec): 2.92 - samples/sec: 5245.24 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:31:28,918 epoch 1 - iter 52/136 - loss 1.46309717 - time (sec): 3.98 - samples/sec: 5273.26 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:31:29,964 epoch 1 - iter 65/136 - loss 1.28129944 - time (sec): 5.03 - samples/sec: 5140.43 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:31:31,013 epoch 1 - iter 78/136 - loss 1.14224358 - time (sec): 6.07 - samples/sec: 5077.33 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:31:32,039 epoch 1 - iter 91/136 - loss 1.02123046 - time (sec): 7.10 - samples/sec: 5116.90 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:31:33,016 epoch 1 - iter 104/136 - loss 0.93704629 - time (sec): 8.08 - samples/sec: 5082.36 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:31:34,048 epoch 1 - iter 117/136 - loss 0.86134920 - time (sec): 9.11 - samples/sec: 5049.79 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:31:34,972 epoch 1 - iter 130/136 - loss 0.81315635 - time (sec): 10.03 - samples/sec: 4978.28 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:31:35,395 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:35,395 EPOCH 1 done: loss 0.7886 - lr: 0.000028 2023-10-25 21:31:36,496 DEV : loss 0.15381869673728943 - f1-score (micro avg) 0.6475 2023-10-25 21:31:36,503 saving best model 2023-10-25 21:31:37,020 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:38,009 epoch 2 - iter 13/136 - loss 0.14729279 - time (sec): 0.99 - samples/sec: 5174.73 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:31:38,993 epoch 2 - iter 26/136 - loss 0.17121608 - time (sec): 1.97 - samples/sec: 5363.99 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:31:40,025 epoch 2 - iter 39/136 - loss 0.16370443 - time (sec): 3.00 - samples/sec: 4965.75 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:31:41,014 epoch 2 - iter 52/136 - loss 0.15904671 - time (sec): 3.99 - samples/sec: 4935.00 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:31:41,969 epoch 2 - iter 65/136 - loss 0.15169814 - time (sec): 4.95 - samples/sec: 4959.65 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:31:42,925 epoch 2 - iter 78/136 - loss 0.15515706 - time (sec): 5.90 - samples/sec: 5047.51 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:31:43,922 epoch 2 - iter 91/136 - loss 0.15141408 - time (sec): 6.90 - samples/sec: 5069.46 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:31:44,959 epoch 2 - iter 104/136 - loss 0.15001351 - time (sec): 7.94 - samples/sec: 4974.03 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:31:45,937 epoch 2 - iter 117/136 - loss 0.14937968 - time (sec): 8.92 - samples/sec: 5053.65 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:31:46,900 epoch 2 - iter 130/136 - loss 0.14671523 - time (sec): 9.88 - samples/sec: 5019.57 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:31:47,358 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:47,359 EPOCH 2 done: loss 0.1457 - lr: 0.000027 2023-10-25 21:31:48,659 DEV : loss 0.10822859406471252 - f1-score (micro avg) 0.7601 2023-10-25 21:31:48,666 saving best model 2023-10-25 21:31:49,411 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:50,343 epoch 3 - iter 13/136 - loss 0.09159492 - time (sec): 0.93 - samples/sec: 4581.24 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:31:51,270 epoch 3 - iter 26/136 - loss 0.09188390 - time (sec): 1.86 - samples/sec: 4829.89 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:31:52,317 epoch 3 - iter 39/136 - loss 0.07817653 - time (sec): 2.90 - samples/sec: 4913.41 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:31:53,237 epoch 3 - iter 52/136 - loss 0.07930223 - time (sec): 3.82 - samples/sec: 4985.05 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:31:54,301 epoch 3 - iter 65/136 - loss 0.07711853 - time (sec): 4.89 - samples/sec: 4930.78 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:31:55,353 epoch 3 - iter 78/136 - loss 0.07404006 - time (sec): 5.94 - samples/sec: 5104.97 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:31:56,460 epoch 3 - iter 91/136 - loss 0.07528584 - time (sec): 7.05 - samples/sec: 5062.43 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:31:57,382 epoch 3 - iter 104/136 - loss 0.07545838 - time (sec): 7.97 - samples/sec: 5024.83 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:31:58,355 epoch 3 - iter 117/136 - loss 0.07590779 - time (sec): 8.94 - samples/sec: 4957.33 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:31:59,312 epoch 3 - iter 130/136 - loss 0.07606308 - time (sec): 9.90 - samples/sec: 4978.39 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:31:59,829 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:59,830 EPOCH 3 done: loss 0.0758 - lr: 0.000024 2023-10-25 21:32:01,578 DEV : loss 0.10140043497085571 - f1-score (micro avg) 0.7633 2023-10-25 21:32:01,585 saving best model 2023-10-25 21:32:02,308 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:03,306 epoch 4 - iter 13/136 - loss 0.04720147 - time (sec): 1.00 - samples/sec: 5398.05 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:32:04,364 epoch 4 - iter 26/136 - loss 0.04723812 - time (sec): 2.05 - samples/sec: 5475.58 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:32:05,451 epoch 4 - iter 39/136 - loss 0.04375497 - time (sec): 3.14 - samples/sec: 5265.04 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:32:06,345 epoch 4 - iter 52/136 - loss 0.04366552 - time (sec): 4.04 - samples/sec: 5215.14 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:32:07,242 epoch 4 - iter 65/136 - loss 0.04276438 - time (sec): 4.93 - samples/sec: 5140.59 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:32:08,243 epoch 4 - iter 78/136 - loss 0.04392016 - time (sec): 5.93 - samples/sec: 5061.38 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:32:09,338 epoch 4 - iter 91/136 - loss 0.04355417 - time (sec): 7.03 - samples/sec: 5010.34 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:32:10,401 epoch 4 - iter 104/136 - loss 0.04553449 - time (sec): 8.09 - samples/sec: 5030.91 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:32:11,297 epoch 4 - iter 117/136 - loss 0.04613281 - time (sec): 8.99 - samples/sec: 5012.27 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:32:12,347 epoch 4 - iter 130/136 - loss 0.04531020 - time (sec): 10.04 - samples/sec: 4970.93 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:32:12,767 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:12,767 EPOCH 4 done: loss 0.0456 - lr: 0.000020 2023-10-25 21:32:14,146 DEV : loss 0.10330618172883987 - f1-score (micro avg) 0.8 2023-10-25 21:32:14,152 saving best model 2023-10-25 21:32:14,883 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:15,913 epoch 5 - iter 13/136 - loss 0.02499789 - time (sec): 1.03 - samples/sec: 4912.36 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:32:16,874 epoch 5 - iter 26/136 - loss 0.01992048 - time (sec): 1.99 - samples/sec: 4736.67 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:32:17,823 epoch 5 - iter 39/136 - loss 0.02764478 - time (sec): 2.94 - samples/sec: 4782.33 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:32:18,798 epoch 5 - iter 52/136 - loss 0.02728486 - time (sec): 3.91 - samples/sec: 4825.41 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:32:19,695 epoch 5 - iter 65/136 - loss 0.03034797 - time (sec): 4.81 - samples/sec: 4828.95 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:32:20,826 epoch 5 - iter 78/136 - loss 0.03063707 - time (sec): 5.94 - samples/sec: 4901.53 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:32:22,099 epoch 5 - iter 91/136 - loss 0.03029661 - time (sec): 7.21 - samples/sec: 4867.24 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:32:23,087 epoch 5 - iter 104/136 - loss 0.03057002 - time (sec): 8.20 - samples/sec: 4899.67 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:32:23,977 epoch 5 - iter 117/136 - loss 0.03238794 - time (sec): 9.09 - samples/sec: 4905.19 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:32:24,939 epoch 5 - iter 130/136 - loss 0.03113197 - time (sec): 10.05 - samples/sec: 4943.76 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:32:25,365 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:25,366 EPOCH 5 done: loss 0.0304 - lr: 0.000017 2023-10-25 21:32:27,025 DEV : loss 0.1195770800113678 - f1-score (micro avg) 0.8037 2023-10-25 21:32:27,032 saving best model 2023-10-25 21:32:27,749 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:28,803 epoch 6 - iter 13/136 - loss 0.01756530 - time (sec): 1.05 - samples/sec: 5366.79 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:32:29,850 epoch 6 - iter 26/136 - loss 0.02348632 - time (sec): 2.10 - samples/sec: 5058.44 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:32:30,796 epoch 6 - iter 39/136 - loss 0.02052357 - time (sec): 3.05 - samples/sec: 5110.69 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:32:31,849 epoch 6 - iter 52/136 - loss 0.02138897 - time (sec): 4.10 - samples/sec: 4940.68 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:32:32,811 epoch 6 - iter 65/136 - loss 0.02488717 - time (sec): 5.06 - samples/sec: 4853.29 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:32:33,815 epoch 6 - iter 78/136 - loss 0.02260196 - time (sec): 6.06 - samples/sec: 4945.45 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:32:34,799 epoch 6 - iter 91/136 - loss 0.02378811 - time (sec): 7.05 - samples/sec: 4971.81 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:32:35,887 epoch 6 - iter 104/136 - loss 0.02407465 - time (sec): 8.14 - samples/sec: 5025.23 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:32:36,916 epoch 6 - iter 117/136 - loss 0.02377918 - time (sec): 9.17 - samples/sec: 4953.62 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:32:37,826 epoch 6 - iter 130/136 - loss 0.02268322 - time (sec): 10.08 - samples/sec: 5001.50 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:32:38,197 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:38,197 EPOCH 6 done: loss 0.0222 - lr: 0.000014 2023-10-25 21:32:39,383 DEV : loss 0.1351010650396347 - f1-score (micro avg) 0.7927 2023-10-25 21:32:39,390 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:40,439 epoch 7 - iter 13/136 - loss 0.01667780 - time (sec): 1.05 - samples/sec: 4199.34 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:32:41,346 epoch 7 - iter 26/136 - loss 0.01388388 - time (sec): 1.95 - samples/sec: 4535.34 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:32:42,346 epoch 7 - iter 39/136 - loss 0.01450612 - time (sec): 2.95 - samples/sec: 4460.74 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:32:43,416 epoch 7 - iter 52/136 - loss 0.01658526 - time (sec): 4.03 - samples/sec: 4680.42 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:32:44,330 epoch 7 - iter 65/136 - loss 0.01539127 - time (sec): 4.94 - samples/sec: 4724.57 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:32:45,264 epoch 7 - iter 78/136 - loss 0.01885348 - time (sec): 5.87 - samples/sec: 4879.61 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:32:46,287 epoch 7 - iter 91/136 - loss 0.01876729 - time (sec): 6.90 - samples/sec: 4938.69 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:32:47,232 epoch 7 - iter 104/136 - loss 0.01819473 - time (sec): 7.84 - samples/sec: 4961.39 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:32:48,233 epoch 7 - iter 117/136 - loss 0.01693316 - time (sec): 8.84 - samples/sec: 5000.54 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:32:49,163 epoch 7 - iter 130/136 - loss 0.01647128 - time (sec): 9.77 - samples/sec: 5032.42 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:32:49,680 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:49,681 EPOCH 7 done: loss 0.0166 - lr: 0.000010 2023-10-25 21:32:50,858 DEV : loss 0.1340150088071823 - f1-score (micro avg) 0.8 2023-10-25 21:32:50,865 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:32:52,199 epoch 8 - iter 13/136 - loss 0.00560534 - time (sec): 1.33 - samples/sec: 3356.32 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:32:53,265 epoch 8 - iter 26/136 - loss 0.00976307 - time (sec): 2.40 - samples/sec: 4207.42 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:32:54,304 epoch 8 - iter 39/136 - loss 0.01070634 - time (sec): 3.44 - samples/sec: 4583.64 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:32:55,296 epoch 8 - iter 52/136 - loss 0.01208915 - time (sec): 4.43 - samples/sec: 4643.84 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:32:56,323 epoch 8 - iter 65/136 - loss 0.01109595 - time (sec): 5.46 - samples/sec: 4568.73 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:32:57,330 epoch 8 - iter 78/136 - loss 0.01173631 - time (sec): 6.46 - samples/sec: 4733.52 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:32:58,296 epoch 8 - iter 91/136 - loss 0.01105965 - time (sec): 7.43 - samples/sec: 4775.36 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:32:59,316 epoch 8 - iter 104/136 - loss 0.01148285 - time (sec): 8.45 - samples/sec: 4777.31 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:33:00,234 epoch 8 - iter 117/136 - loss 0.01174659 - time (sec): 9.37 - samples/sec: 4800.88 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:33:01,265 epoch 8 - iter 130/136 - loss 0.01071709 - time (sec): 10.40 - samples/sec: 4801.33 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:33:01,692 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:01,693 EPOCH 8 done: loss 0.0121 - lr: 0.000007 2023-10-25 21:33:02,845 DEV : loss 0.16605901718139648 - f1-score (micro avg) 0.8051 2023-10-25 21:33:02,852 saving best model 2023-10-25 21:33:03,579 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:04,564 epoch 9 - iter 13/136 - loss 0.00519371 - time (sec): 0.98 - samples/sec: 4935.82 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:33:05,403 epoch 9 - iter 26/136 - loss 0.00741030 - time (sec): 1.81 - samples/sec: 4742.54 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:33:06,394 epoch 9 - iter 39/136 - loss 0.00860202 - time (sec): 2.81 - samples/sec: 4879.48 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:33:07,354 epoch 9 - iter 52/136 - loss 0.00994720 - time (sec): 3.76 - samples/sec: 4840.00 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:33:08,435 epoch 9 - iter 65/136 - loss 0.00914803 - time (sec): 4.85 - samples/sec: 4892.40 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:33:09,545 epoch 9 - iter 78/136 - loss 0.00869169 - time (sec): 5.96 - samples/sec: 4949.71 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:33:10,573 epoch 9 - iter 91/136 - loss 0.00816170 - time (sec): 6.98 - samples/sec: 5004.09 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:33:11,706 epoch 9 - iter 104/136 - loss 0.00799395 - time (sec): 8.12 - samples/sec: 5036.45 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:33:12,646 epoch 9 - iter 117/136 - loss 0.00901235 - time (sec): 9.06 - samples/sec: 5069.49 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:33:13,534 epoch 9 - iter 130/136 - loss 0.00901908 - time (sec): 9.95 - samples/sec: 5056.08 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:33:13,901 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:13,901 EPOCH 9 done: loss 0.0090 - lr: 0.000004 2023-10-25 21:33:15,092 DEV : loss 0.17188507318496704 - f1-score (micro avg) 0.8124 2023-10-25 21:33:15,098 saving best model 2023-10-25 21:33:15,802 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:16,783 epoch 10 - iter 13/136 - loss 0.00872606 - time (sec): 0.97 - samples/sec: 4629.98 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:33:17,714 epoch 10 - iter 26/136 - loss 0.01279988 - time (sec): 1.91 - samples/sec: 4849.49 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:33:19,030 epoch 10 - iter 39/136 - loss 0.00977020 - time (sec): 3.22 - samples/sec: 4685.56 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:33:19,887 epoch 10 - iter 52/136 - loss 0.00929420 - time (sec): 4.08 - samples/sec: 4725.22 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:33:20,819 epoch 10 - iter 65/136 - loss 0.00906255 - time (sec): 5.01 - samples/sec: 4785.44 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:33:21,900 epoch 10 - iter 78/136 - loss 0.00778176 - time (sec): 6.09 - samples/sec: 4778.21 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:33:22,977 epoch 10 - iter 91/136 - loss 0.00714978 - time (sec): 7.17 - samples/sec: 4762.80 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:33:23,940 epoch 10 - iter 104/136 - loss 0.00657170 - time (sec): 8.13 - samples/sec: 4838.79 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:33:24,878 epoch 10 - iter 117/136 - loss 0.00701785 - time (sec): 9.07 - samples/sec: 4910.58 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:33:25,928 epoch 10 - iter 130/136 - loss 0.00745080 - time (sec): 10.12 - samples/sec: 4919.23 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:33:26,456 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:26,457 EPOCH 10 done: loss 0.0077 - lr: 0.000000 2023-10-25 21:33:27,624 DEV : loss 0.16700904071331024 - f1-score (micro avg) 0.8145 2023-10-25 21:33:27,630 saving best model 2023-10-25 21:33:28,840 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:33:28,841 Loading model from best epoch ... 2023-10-25 21:33:30,739 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG 2023-10-25 21:33:32,729 Results: - F-score (micro) 0.7818 - F-score (macro) 0.7411 - Accuracy 0.657 By class: precision recall f1-score support LOC 0.7959 0.8622 0.8277 312 PER 0.6894 0.8750 0.7712 208 ORG 0.5400 0.4909 0.5143 55 HumanProd 0.8000 0.9091 0.8511 22 micro avg 0.7356 0.8342 0.7818 597 macro avg 0.7063 0.7843 0.7411 597 weighted avg 0.7353 0.8342 0.7800 597 2023-10-25 21:33:32,729 ----------------------------------------------------------------------------------------------------