2023-10-25 21:12:45,451 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,452 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 21:12:45,452 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 MultiCorpus: 1166 train + 165 dev + 415 test sentences - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Train: 1166 sentences 2023-10-25 21:12:45,453 (train_with_dev=False, train_with_test=False) 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Training Params: 2023-10-25 21:12:45,453 - learning_rate: "5e-05" 2023-10-25 21:12:45,453 - mini_batch_size: "4" 2023-10-25 21:12:45,453 - max_epochs: "10" 2023-10-25 21:12:45,453 - shuffle: "True" 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Plugins: 2023-10-25 21:12:45,453 - TensorboardLogger 2023-10-25 21:12:45,453 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:12:45,453 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Computation: 2023-10-25 21:12:45,453 - compute on device: cuda:0 2023-10-25 21:12:45,453 - embedding storage: none 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:45,453 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:12:46,773 epoch 1 - iter 29/292 - loss 2.60630160 - time (sec): 1.32 - samples/sec: 2620.93 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:12:48,030 epoch 1 - iter 58/292 - loss 1.73093403 - time (sec): 2.58 - samples/sec: 2898.55 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:12:49,336 epoch 1 - iter 87/292 - loss 1.29007377 - time (sec): 3.88 - samples/sec: 3112.26 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:12:50,589 epoch 1 - iter 116/292 - loss 1.08928573 - time (sec): 5.13 - samples/sec: 3136.32 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:12:51,860 epoch 1 - iter 145/292 - loss 0.93038328 - time (sec): 6.41 - samples/sec: 3201.92 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:12:53,193 epoch 1 - iter 174/292 - loss 0.83340092 - time (sec): 7.74 - samples/sec: 3228.79 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:12:54,501 epoch 1 - iter 203/292 - loss 0.74787824 - time (sec): 9.05 - samples/sec: 3289.33 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:12:55,918 epoch 1 - iter 232/292 - loss 0.68293476 - time (sec): 10.46 - samples/sec: 3333.71 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:12:57,231 epoch 1 - iter 261/292 - loss 0.61828383 - time (sec): 11.78 - samples/sec: 3395.00 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:12:58,524 epoch 1 - iter 290/292 - loss 0.57952199 - time (sec): 13.07 - samples/sec: 3387.23 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:12:58,602 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:12:58,602 EPOCH 1 done: loss 0.5801 - lr: 0.000049 2023-10-25 21:12:59,117 DEV : loss 0.1393888294696808 - f1-score (micro avg) 0.6157 2023-10-25 21:12:59,121 saving best model 2023-10-25 21:12:59,633 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:00,938 epoch 2 - iter 29/292 - loss 0.16641729 - time (sec): 1.30 - samples/sec: 3551.69 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:13:02,295 epoch 2 - iter 58/292 - loss 0.14870205 - time (sec): 2.66 - samples/sec: 3657.47 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:13:03,566 epoch 2 - iter 87/292 - loss 0.15224226 - time (sec): 3.93 - samples/sec: 3558.93 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:13:04,863 epoch 2 - iter 116/292 - loss 0.15195587 - time (sec): 5.23 - samples/sec: 3491.95 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:13:06,114 epoch 2 - iter 145/292 - loss 0.15173369 - time (sec): 6.48 - samples/sec: 3425.51 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:13:07,298 epoch 2 - iter 174/292 - loss 0.16302891 - time (sec): 7.66 - samples/sec: 3398.01 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:13:08,492 epoch 2 - iter 203/292 - loss 0.16090612 - time (sec): 8.86 - samples/sec: 3414.98 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:13:09,795 epoch 2 - iter 232/292 - loss 0.15301547 - time (sec): 10.16 - samples/sec: 3440.05 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:13:11,060 epoch 2 - iter 261/292 - loss 0.15185628 - time (sec): 11.43 - samples/sec: 3468.19 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:13:12,335 epoch 2 - iter 290/292 - loss 0.15180422 - time (sec): 12.70 - samples/sec: 3473.70 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:13:12,422 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:12,423 EPOCH 2 done: loss 0.1516 - lr: 0.000045 2023-10-25 21:13:13,340 DEV : loss 0.1067458763718605 - f1-score (micro avg) 0.7253 2023-10-25 21:13:13,344 saving best model 2023-10-25 21:13:14,183 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:15,560 epoch 3 - iter 29/292 - loss 0.07559153 - time (sec): 1.37 - samples/sec: 3251.25 - lr: 0.000044 - momentum: 0.000000 2023-10-25 21:13:16,805 epoch 3 - iter 58/292 - loss 0.07386580 - time (sec): 2.62 - samples/sec: 2941.45 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:13:18,136 epoch 3 - iter 87/292 - loss 0.07463057 - time (sec): 3.95 - samples/sec: 3118.77 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:13:19,407 epoch 3 - iter 116/292 - loss 0.07309791 - time (sec): 5.22 - samples/sec: 3058.69 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:13:20,812 epoch 3 - iter 145/292 - loss 0.07859240 - time (sec): 6.62 - samples/sec: 3310.07 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:13:22,125 epoch 3 - iter 174/292 - loss 0.08064284 - time (sec): 7.94 - samples/sec: 3359.83 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:13:23,411 epoch 3 - iter 203/292 - loss 0.08000187 - time (sec): 9.22 - samples/sec: 3387.08 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:13:24,634 epoch 3 - iter 232/292 - loss 0.07888199 - time (sec): 10.45 - samples/sec: 3370.63 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:13:25,866 epoch 3 - iter 261/292 - loss 0.07895832 - time (sec): 11.68 - samples/sec: 3351.73 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:13:27,159 epoch 3 - iter 290/292 - loss 0.08051650 - time (sec): 12.97 - samples/sec: 3374.19 - lr: 0.000039 - momentum: 0.000000 2023-10-25 21:13:27,266 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:27,266 EPOCH 3 done: loss 0.0807 - lr: 0.000039 2023-10-25 21:13:28,186 DEV : loss 0.10645782947540283 - f1-score (micro avg) 0.7273 2023-10-25 21:13:28,190 saving best model 2023-10-25 21:13:28,853 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:30,194 epoch 4 - iter 29/292 - loss 0.05879957 - time (sec): 1.34 - samples/sec: 3783.44 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:13:31,451 epoch 4 - iter 58/292 - loss 0.05787533 - time (sec): 2.60 - samples/sec: 3488.46 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:13:32,757 epoch 4 - iter 87/292 - loss 0.05964165 - time (sec): 3.90 - samples/sec: 3404.79 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:13:34,060 epoch 4 - iter 116/292 - loss 0.05624702 - time (sec): 5.21 - samples/sec: 3327.34 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:13:35,289 epoch 4 - iter 145/292 - loss 0.05478522 - time (sec): 6.43 - samples/sec: 3263.01 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:13:36,625 epoch 4 - iter 174/292 - loss 0.05936602 - time (sec): 7.77 - samples/sec: 3299.85 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:13:37,824 epoch 4 - iter 203/292 - loss 0.05877258 - time (sec): 8.97 - samples/sec: 3309.89 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:13:39,052 epoch 4 - iter 232/292 - loss 0.05534208 - time (sec): 10.20 - samples/sec: 3293.06 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:13:40,403 epoch 4 - iter 261/292 - loss 0.05738089 - time (sec): 11.55 - samples/sec: 3384.13 - lr: 0.000034 - momentum: 0.000000 2023-10-25 21:13:41,720 epoch 4 - iter 290/292 - loss 0.05628166 - time (sec): 12.86 - samples/sec: 3443.39 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:13:41,808 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:41,808 EPOCH 4 done: loss 0.0561 - lr: 0.000033 2023-10-25 21:13:42,726 DEV : loss 0.13811993598937988 - f1-score (micro avg) 0.7425 2023-10-25 21:13:42,730 saving best model 2023-10-25 21:13:43,402 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:44,735 epoch 5 - iter 29/292 - loss 0.02917983 - time (sec): 1.33 - samples/sec: 3600.95 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:13:45,986 epoch 5 - iter 58/292 - loss 0.03003225 - time (sec): 2.58 - samples/sec: 3317.20 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:13:47,328 epoch 5 - iter 87/292 - loss 0.03965107 - time (sec): 3.92 - samples/sec: 3485.40 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:13:48,619 epoch 5 - iter 116/292 - loss 0.04015937 - time (sec): 5.21 - samples/sec: 3403.14 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:13:49,919 epoch 5 - iter 145/292 - loss 0.03738301 - time (sec): 6.51 - samples/sec: 3370.76 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:13:51,199 epoch 5 - iter 174/292 - loss 0.03512502 - time (sec): 7.79 - samples/sec: 3305.98 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:13:52,517 epoch 5 - iter 203/292 - loss 0.03795555 - time (sec): 9.11 - samples/sec: 3285.02 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:13:53,848 epoch 5 - iter 232/292 - loss 0.04076074 - time (sec): 10.44 - samples/sec: 3339.81 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:13:55,256 epoch 5 - iter 261/292 - loss 0.03934850 - time (sec): 11.85 - samples/sec: 3380.71 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:13:56,543 epoch 5 - iter 290/292 - loss 0.04048060 - time (sec): 13.14 - samples/sec: 3374.10 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:13:56,617 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:56,617 EPOCH 5 done: loss 0.0404 - lr: 0.000028 2023-10-25 21:13:57,540 DEV : loss 0.12971803545951843 - f1-score (micro avg) 0.7451 2023-10-25 21:13:57,544 saving best model 2023-10-25 21:13:58,224 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:13:59,472 epoch 6 - iter 29/292 - loss 0.02180752 - time (sec): 1.24 - samples/sec: 3433.49 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:14:00,795 epoch 6 - iter 58/292 - loss 0.02936813 - time (sec): 2.57 - samples/sec: 3411.13 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:14:02,143 epoch 6 - iter 87/292 - loss 0.02555129 - time (sec): 3.91 - samples/sec: 3498.75 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:14:03,427 epoch 6 - iter 116/292 - loss 0.02657167 - time (sec): 5.20 - samples/sec: 3501.91 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:14:04,721 epoch 6 - iter 145/292 - loss 0.02565577 - time (sec): 6.49 - samples/sec: 3419.27 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:14:06,062 epoch 6 - iter 174/292 - loss 0.02343463 - time (sec): 7.83 - samples/sec: 3344.78 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:14:07,348 epoch 6 - iter 203/292 - loss 0.02416227 - time (sec): 9.12 - samples/sec: 3368.83 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:14:08,679 epoch 6 - iter 232/292 - loss 0.02927410 - time (sec): 10.45 - samples/sec: 3384.05 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:14:09,995 epoch 6 - iter 261/292 - loss 0.03021667 - time (sec): 11.77 - samples/sec: 3401.67 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:14:11,280 epoch 6 - iter 290/292 - loss 0.03036653 - time (sec): 13.05 - samples/sec: 3389.93 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:14:11,367 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:11,367 EPOCH 6 done: loss 0.0307 - lr: 0.000022 2023-10-25 21:14:12,290 DEV : loss 0.15307584404945374 - f1-score (micro avg) 0.7665 2023-10-25 21:14:12,294 saving best model 2023-10-25 21:14:12,958 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:14,228 epoch 7 - iter 29/292 - loss 0.02367547 - time (sec): 1.27 - samples/sec: 3400.04 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:14:15,919 epoch 7 - iter 58/292 - loss 0.02823955 - time (sec): 2.96 - samples/sec: 3480.61 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:14:17,150 epoch 7 - iter 87/292 - loss 0.02673198 - time (sec): 4.19 - samples/sec: 3329.46 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:14:18,398 epoch 7 - iter 116/292 - loss 0.02646895 - time (sec): 5.44 - samples/sec: 3258.84 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:14:19,722 epoch 7 - iter 145/292 - loss 0.02552160 - time (sec): 6.76 - samples/sec: 3321.63 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:14:21,003 epoch 7 - iter 174/292 - loss 0.02323132 - time (sec): 8.04 - samples/sec: 3367.73 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:14:22,256 epoch 7 - iter 203/292 - loss 0.02225006 - time (sec): 9.29 - samples/sec: 3393.37 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:14:23,470 epoch 7 - iter 232/292 - loss 0.02294774 - time (sec): 10.51 - samples/sec: 3343.71 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:14:24,767 epoch 7 - iter 261/292 - loss 0.02407455 - time (sec): 11.80 - samples/sec: 3361.55 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:14:26,083 epoch 7 - iter 290/292 - loss 0.02328112 - time (sec): 13.12 - samples/sec: 3374.12 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:14:26,163 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:26,163 EPOCH 7 done: loss 0.0232 - lr: 0.000017 2023-10-25 21:14:27,082 DEV : loss 0.1477293223142624 - f1-score (micro avg) 0.787 2023-10-25 21:14:27,087 saving best model 2023-10-25 21:14:27,754 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:29,068 epoch 8 - iter 29/292 - loss 0.04019118 - time (sec): 1.31 - samples/sec: 3033.76 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:14:30,486 epoch 8 - iter 58/292 - loss 0.02562495 - time (sec): 2.73 - samples/sec: 3338.48 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:14:31,835 epoch 8 - iter 87/292 - loss 0.02135462 - time (sec): 4.08 - samples/sec: 3416.50 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:14:33,120 epoch 8 - iter 116/292 - loss 0.02053731 - time (sec): 5.36 - samples/sec: 3408.96 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:14:34,425 epoch 8 - iter 145/292 - loss 0.02012399 - time (sec): 6.67 - samples/sec: 3372.65 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:14:35,694 epoch 8 - iter 174/292 - loss 0.01842217 - time (sec): 7.94 - samples/sec: 3388.27 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:14:36,985 epoch 8 - iter 203/292 - loss 0.01663993 - time (sec): 9.23 - samples/sec: 3331.69 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:14:38,289 epoch 8 - iter 232/292 - loss 0.01669885 - time (sec): 10.53 - samples/sec: 3367.99 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:14:39,605 epoch 8 - iter 261/292 - loss 0.01668062 - time (sec): 11.85 - samples/sec: 3368.50 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:14:40,885 epoch 8 - iter 290/292 - loss 0.01628557 - time (sec): 13.13 - samples/sec: 3376.27 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:14:40,973 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:40,973 EPOCH 8 done: loss 0.0162 - lr: 0.000011 2023-10-25 21:14:41,893 DEV : loss 0.1719065010547638 - f1-score (micro avg) 0.7582 2023-10-25 21:14:41,897 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:43,194 epoch 9 - iter 29/292 - loss 0.00358527 - time (sec): 1.30 - samples/sec: 3663.02 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:14:44,499 epoch 9 - iter 58/292 - loss 0.00492909 - time (sec): 2.60 - samples/sec: 3524.73 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:14:45,755 epoch 9 - iter 87/292 - loss 0.00373125 - time (sec): 3.86 - samples/sec: 3372.51 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:14:47,134 epoch 9 - iter 116/292 - loss 0.00767643 - time (sec): 5.24 - samples/sec: 3419.71 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:14:48,469 epoch 9 - iter 145/292 - loss 0.01032308 - time (sec): 6.57 - samples/sec: 3470.78 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:14:49,777 epoch 9 - iter 174/292 - loss 0.01017440 - time (sec): 7.88 - samples/sec: 3476.45 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:14:51,085 epoch 9 - iter 203/292 - loss 0.00944404 - time (sec): 9.19 - samples/sec: 3441.81 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:14:52,353 epoch 9 - iter 232/292 - loss 0.01116023 - time (sec): 10.45 - samples/sec: 3406.07 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:14:53,666 epoch 9 - iter 261/292 - loss 0.01067018 - time (sec): 11.77 - samples/sec: 3371.12 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:14:54,957 epoch 9 - iter 290/292 - loss 0.00991839 - time (sec): 13.06 - samples/sec: 3384.07 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:14:55,046 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:55,047 EPOCH 9 done: loss 0.0099 - lr: 0.000006 2023-10-25 21:14:55,967 DEV : loss 0.17519107460975647 - f1-score (micro avg) 0.7682 2023-10-25 21:14:55,971 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:14:57,251 epoch 10 - iter 29/292 - loss 0.00493698 - time (sec): 1.28 - samples/sec: 3374.74 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:14:58,512 epoch 10 - iter 58/292 - loss 0.00797778 - time (sec): 2.54 - samples/sec: 3427.40 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:14:59,849 epoch 10 - iter 87/292 - loss 0.01121526 - time (sec): 3.88 - samples/sec: 3401.36 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:15:01,143 epoch 10 - iter 116/292 - loss 0.00908355 - time (sec): 5.17 - samples/sec: 3370.72 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:15:02,436 epoch 10 - iter 145/292 - loss 0.00825735 - time (sec): 6.46 - samples/sec: 3348.68 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:15:03,716 epoch 10 - iter 174/292 - loss 0.00808191 - time (sec): 7.74 - samples/sec: 3310.53 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:15:05,138 epoch 10 - iter 203/292 - loss 0.00845788 - time (sec): 9.17 - samples/sec: 3386.32 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:15:06,420 epoch 10 - iter 232/292 - loss 0.00783064 - time (sec): 10.45 - samples/sec: 3375.44 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:15:07,819 epoch 10 - iter 261/292 - loss 0.00786645 - time (sec): 11.85 - samples/sec: 3371.73 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:15:09,104 epoch 10 - iter 290/292 - loss 0.00733907 - time (sec): 13.13 - samples/sec: 3362.91 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:15:09,186 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:15:09,187 EPOCH 10 done: loss 0.0073 - lr: 0.000000 2023-10-25 21:15:10,107 DEV : loss 0.177558034658432 - f1-score (micro avg) 0.7613 2023-10-25 21:15:10,525 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:15:10,527 Loading model from best epoch ... 2023-10-25 21:15:12,151 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-25 21:15:13,880 Results: - F-score (micro) 0.7417 - F-score (macro) 0.6377 - Accuracy 0.6109 By class: precision recall f1-score support PER 0.7983 0.8190 0.8085 348 LOC 0.6450 0.8352 0.7279 261 ORG 0.4390 0.3462 0.3871 52 HumanProd 0.5517 0.7273 0.6275 22 micro avg 0.7020 0.7862 0.7417 683 macro avg 0.6085 0.6819 0.6377 683 weighted avg 0.7044 0.7862 0.7398 683 2023-10-25 21:15:13,880 ----------------------------------------------------------------------------------------------------