2023-10-17 20:22:26,600 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,601 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): ElectraModel( (embeddings): ElectraEmbeddings( (word_embeddings): Embedding(32001, 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): ElectraEncoder( (layer): ModuleList( (0-11): 12 x ElectraLayer( (attention): ElectraAttention( (self): ElectraSelfAttention( (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): ElectraSelfOutput( (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): ElectraIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): ElectraOutput( (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) ) ) ) ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 20:22:26,601 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,601 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 2023-10-17 20:22:26,601 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,601 Train: 1085 sentences 2023-10-17 20:22:26,601 (train_with_dev=False, train_with_test=False) 2023-10-17 20:22:26,601 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,601 Training Params: 2023-10-17 20:22:26,601 - learning_rate: "5e-05" 2023-10-17 20:22:26,601 - mini_batch_size: "4" 2023-10-17 20:22:26,601 - max_epochs: "10" 2023-10-17 20:22:26,601 - shuffle: "True" 2023-10-17 20:22:26,601 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,601 Plugins: 2023-10-17 20:22:26,602 - TensorboardLogger 2023-10-17 20:22:26,602 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 20:22:26,602 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,602 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 20:22:26,602 - metric: "('micro avg', 'f1-score')" 2023-10-17 20:22:26,602 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,602 Computation: 2023-10-17 20:22:26,602 - compute on device: cuda:0 2023-10-17 20:22:26,602 - embedding storage: none 2023-10-17 20:22:26,602 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,602 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-17 20:22:26,602 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,602 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:26,602 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 20:22:28,205 epoch 1 - iter 27/272 - loss 3.40623895 - time (sec): 1.60 - samples/sec: 3386.92 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:22:29,850 epoch 1 - iter 54/272 - loss 2.64778140 - time (sec): 3.25 - samples/sec: 3205.45 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:22:31,678 epoch 1 - iter 81/272 - loss 1.89470970 - time (sec): 5.07 - samples/sec: 3228.54 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:22:33,184 epoch 1 - iter 108/272 - loss 1.55945154 - time (sec): 6.58 - samples/sec: 3243.02 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:22:34,720 epoch 1 - iter 135/272 - loss 1.32041644 - time (sec): 8.12 - samples/sec: 3280.25 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:22:36,310 epoch 1 - iter 162/272 - loss 1.17756978 - time (sec): 9.71 - samples/sec: 3206.49 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:22:37,849 epoch 1 - iter 189/272 - loss 1.04336124 - time (sec): 11.25 - samples/sec: 3227.97 - lr: 0.000035 - momentum: 0.000000 2023-10-17 20:22:39,527 epoch 1 - iter 216/272 - loss 0.92669269 - time (sec): 12.92 - samples/sec: 3249.42 - lr: 0.000040 - momentum: 0.000000 2023-10-17 20:22:41,040 epoch 1 - iter 243/272 - loss 0.86162728 - time (sec): 14.44 - samples/sec: 3223.74 - lr: 0.000044 - momentum: 0.000000 2023-10-17 20:22:42,626 epoch 1 - iter 270/272 - loss 0.79081358 - time (sec): 16.02 - samples/sec: 3238.48 - lr: 0.000049 - momentum: 0.000000 2023-10-17 20:22:42,723 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:42,723 EPOCH 1 done: loss 0.7899 - lr: 0.000049 2023-10-17 20:22:43,970 DEV : loss 0.16378863155841827 - f1-score (micro avg) 0.6164 2023-10-17 20:22:43,974 saving best model 2023-10-17 20:22:44,399 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:22:45,968 epoch 2 - iter 27/272 - loss 0.25767374 - time (sec): 1.57 - samples/sec: 3194.61 - lr: 0.000049 - momentum: 0.000000 2023-10-17 20:22:47,585 epoch 2 - iter 54/272 - loss 0.18763097 - time (sec): 3.18 - samples/sec: 3270.50 - lr: 0.000049 - momentum: 0.000000 2023-10-17 20:22:49,123 epoch 2 - iter 81/272 - loss 0.17973790 - time (sec): 4.72 - samples/sec: 3435.04 - lr: 0.000048 - momentum: 0.000000 2023-10-17 20:22:50,626 epoch 2 - iter 108/272 - loss 0.16187387 - time (sec): 6.22 - samples/sec: 3516.89 - lr: 0.000048 - momentum: 0.000000 2023-10-17 20:22:52,065 epoch 2 - iter 135/272 - loss 0.16105113 - time (sec): 7.66 - samples/sec: 3368.57 - lr: 0.000047 - momentum: 0.000000 2023-10-17 20:22:53,717 epoch 2 - iter 162/272 - loss 0.15784438 - time (sec): 9.32 - samples/sec: 3373.16 - lr: 0.000047 - momentum: 0.000000 2023-10-17 20:22:55,227 epoch 2 - iter 189/272 - loss 0.15170985 - time (sec): 10.83 - samples/sec: 3379.62 - lr: 0.000046 - momentum: 0.000000 2023-10-17 20:22:56,786 epoch 2 - iter 216/272 - loss 0.14931401 - time (sec): 12.39 - samples/sec: 3346.42 - lr: 0.000046 - momentum: 0.000000 2023-10-17 20:22:58,384 epoch 2 - iter 243/272 - loss 0.14546742 - time (sec): 13.98 - samples/sec: 3377.89 - lr: 0.000045 - momentum: 0.000000 2023-10-17 20:22:59,861 epoch 2 - iter 270/272 - loss 0.14667348 - time (sec): 15.46 - samples/sec: 3338.96 - lr: 0.000045 - momentum: 0.000000 2023-10-17 20:23:00,006 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:00,006 EPOCH 2 done: loss 0.1460 - lr: 0.000045 2023-10-17 20:23:01,511 DEV : loss 0.13631020486354828 - f1-score (micro avg) 0.7405 2023-10-17 20:23:01,515 saving best model 2023-10-17 20:23:02,008 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:03,542 epoch 3 - iter 27/272 - loss 0.12873334 - time (sec): 1.53 - samples/sec: 3222.01 - lr: 0.000044 - momentum: 0.000000 2023-10-17 20:23:05,152 epoch 3 - iter 54/272 - loss 0.09958223 - time (sec): 3.14 - samples/sec: 3055.89 - lr: 0.000043 - momentum: 0.000000 2023-10-17 20:23:06,773 epoch 3 - iter 81/272 - loss 0.08615905 - time (sec): 4.76 - samples/sec: 3113.14 - lr: 0.000043 - momentum: 0.000000 2023-10-17 20:23:08,467 epoch 3 - iter 108/272 - loss 0.09050520 - time (sec): 6.46 - samples/sec: 3123.51 - lr: 0.000042 - momentum: 0.000000 2023-10-17 20:23:10,010 epoch 3 - iter 135/272 - loss 0.10892810 - time (sec): 8.00 - samples/sec: 3119.86 - lr: 0.000042 - momentum: 0.000000 2023-10-17 20:23:11,605 epoch 3 - iter 162/272 - loss 0.10570646 - time (sec): 9.59 - samples/sec: 3156.75 - lr: 0.000041 - momentum: 0.000000 2023-10-17 20:23:13,179 epoch 3 - iter 189/272 - loss 0.09847848 - time (sec): 11.17 - samples/sec: 3149.61 - lr: 0.000041 - momentum: 0.000000 2023-10-17 20:23:14,859 epoch 3 - iter 216/272 - loss 0.09658563 - time (sec): 12.85 - samples/sec: 3226.18 - lr: 0.000040 - momentum: 0.000000 2023-10-17 20:23:16,369 epoch 3 - iter 243/272 - loss 0.09713728 - time (sec): 14.36 - samples/sec: 3209.44 - lr: 0.000040 - momentum: 0.000000 2023-10-17 20:23:18,084 epoch 3 - iter 270/272 - loss 0.09473854 - time (sec): 16.07 - samples/sec: 3218.02 - lr: 0.000039 - momentum: 0.000000 2023-10-17 20:23:18,185 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:18,185 EPOCH 3 done: loss 0.0946 - lr: 0.000039 2023-10-17 20:23:19,896 DEV : loss 0.12857291102409363 - f1-score (micro avg) 0.7695 2023-10-17 20:23:19,901 saving best model 2023-10-17 20:23:20,369 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:22,050 epoch 4 - iter 27/272 - loss 0.04863011 - time (sec): 1.68 - samples/sec: 3532.90 - lr: 0.000038 - momentum: 0.000000 2023-10-17 20:23:23,565 epoch 4 - iter 54/272 - loss 0.04952118 - time (sec): 3.19 - samples/sec: 3365.08 - lr: 0.000038 - momentum: 0.000000 2023-10-17 20:23:25,299 epoch 4 - iter 81/272 - loss 0.04821615 - time (sec): 4.93 - samples/sec: 3464.45 - lr: 0.000037 - momentum: 0.000000 2023-10-17 20:23:26,994 epoch 4 - iter 108/272 - loss 0.04656621 - time (sec): 6.62 - samples/sec: 3432.94 - lr: 0.000037 - momentum: 0.000000 2023-10-17 20:23:28,582 epoch 4 - iter 135/272 - loss 0.04950359 - time (sec): 8.21 - samples/sec: 3362.25 - lr: 0.000036 - momentum: 0.000000 2023-10-17 20:23:30,082 epoch 4 - iter 162/272 - loss 0.05105052 - time (sec): 9.71 - samples/sec: 3296.71 - lr: 0.000036 - momentum: 0.000000 2023-10-17 20:23:31,689 epoch 4 - iter 189/272 - loss 0.05366686 - time (sec): 11.32 - samples/sec: 3237.27 - lr: 0.000035 - momentum: 0.000000 2023-10-17 20:23:33,411 epoch 4 - iter 216/272 - loss 0.05164999 - time (sec): 13.04 - samples/sec: 3240.84 - lr: 0.000034 - momentum: 0.000000 2023-10-17 20:23:34,963 epoch 4 - iter 243/272 - loss 0.05133109 - time (sec): 14.59 - samples/sec: 3225.19 - lr: 0.000034 - momentum: 0.000000 2023-10-17 20:23:36,481 epoch 4 - iter 270/272 - loss 0.05924423 - time (sec): 16.11 - samples/sec: 3216.17 - lr: 0.000033 - momentum: 0.000000 2023-10-17 20:23:36,568 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:36,568 EPOCH 4 done: loss 0.0591 - lr: 0.000033 2023-10-17 20:23:38,107 DEV : loss 0.14095589518547058 - f1-score (micro avg) 0.8248 2023-10-17 20:23:38,115 saving best model 2023-10-17 20:23:38,647 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:40,181 epoch 5 - iter 27/272 - loss 0.04161918 - time (sec): 1.53 - samples/sec: 3371.72 - lr: 0.000033 - momentum: 0.000000 2023-10-17 20:23:41,797 epoch 5 - iter 54/272 - loss 0.03906740 - time (sec): 3.15 - samples/sec: 3286.92 - lr: 0.000032 - momentum: 0.000000 2023-10-17 20:23:43,295 epoch 5 - iter 81/272 - loss 0.03980555 - time (sec): 4.65 - samples/sec: 3305.42 - lr: 0.000032 - momentum: 0.000000 2023-10-17 20:23:44,934 epoch 5 - iter 108/272 - loss 0.04222380 - time (sec): 6.29 - samples/sec: 3294.55 - lr: 0.000031 - momentum: 0.000000 2023-10-17 20:23:46,547 epoch 5 - iter 135/272 - loss 0.04134787 - time (sec): 7.90 - samples/sec: 3329.13 - lr: 0.000031 - momentum: 0.000000 2023-10-17 20:23:48,180 epoch 5 - iter 162/272 - loss 0.03847928 - time (sec): 9.53 - samples/sec: 3319.66 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:23:49,690 epoch 5 - iter 189/272 - loss 0.04003670 - time (sec): 11.04 - samples/sec: 3326.51 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:23:51,339 epoch 5 - iter 216/272 - loss 0.03896642 - time (sec): 12.69 - samples/sec: 3324.71 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:23:52,752 epoch 5 - iter 243/272 - loss 0.03875774 - time (sec): 14.10 - samples/sec: 3286.69 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:23:54,441 epoch 5 - iter 270/272 - loss 0.03752829 - time (sec): 15.79 - samples/sec: 3275.49 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:23:54,552 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:54,552 EPOCH 5 done: loss 0.0375 - lr: 0.000028 2023-10-17 20:23:56,053 DEV : loss 0.14450490474700928 - f1-score (micro avg) 0.8303 2023-10-17 20:23:56,057 saving best model 2023-10-17 20:23:56,529 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:23:58,265 epoch 6 - iter 27/272 - loss 0.02331958 - time (sec): 1.73 - samples/sec: 3400.01 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:23:59,798 epoch 6 - iter 54/272 - loss 0.02778531 - time (sec): 3.27 - samples/sec: 3378.82 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:24:01,382 epoch 6 - iter 81/272 - loss 0.02856352 - time (sec): 4.85 - samples/sec: 3399.05 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:24:02,988 epoch 6 - iter 108/272 - loss 0.02887330 - time (sec): 6.46 - samples/sec: 3419.07 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:24:04,498 epoch 6 - iter 135/272 - loss 0.02445293 - time (sec): 7.97 - samples/sec: 3406.75 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:24:06,001 epoch 6 - iter 162/272 - loss 0.02445139 - time (sec): 9.47 - samples/sec: 3355.78 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:24:07,542 epoch 6 - iter 189/272 - loss 0.02422895 - time (sec): 11.01 - samples/sec: 3360.71 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:24:09,131 epoch 6 - iter 216/272 - loss 0.02456752 - time (sec): 12.60 - samples/sec: 3357.57 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:24:10,700 epoch 6 - iter 243/272 - loss 0.02951527 - time (sec): 14.17 - samples/sec: 3303.46 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:24:12,292 epoch 6 - iter 270/272 - loss 0.02803499 - time (sec): 15.76 - samples/sec: 3294.17 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:24:12,377 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:12,378 EPOCH 6 done: loss 0.0280 - lr: 0.000022 2023-10-17 20:24:13,893 DEV : loss 0.164916530251503 - f1-score (micro avg) 0.8349 2023-10-17 20:24:13,898 saving best model 2023-10-17 20:24:14,377 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:16,001 epoch 7 - iter 27/272 - loss 0.02600591 - time (sec): 1.62 - samples/sec: 3156.24 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:24:17,553 epoch 7 - iter 54/272 - loss 0.02176704 - time (sec): 3.17 - samples/sec: 3042.50 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:24:19,116 epoch 7 - iter 81/272 - loss 0.02312263 - time (sec): 4.74 - samples/sec: 3180.06 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:24:20,639 epoch 7 - iter 108/272 - loss 0.02098405 - time (sec): 6.26 - samples/sec: 3186.77 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:24:22,295 epoch 7 - iter 135/272 - loss 0.02136903 - time (sec): 7.92 - samples/sec: 3168.51 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:24:23,839 epoch 7 - iter 162/272 - loss 0.01922451 - time (sec): 9.46 - samples/sec: 3247.84 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:24:25,360 epoch 7 - iter 189/272 - loss 0.01820994 - time (sec): 10.98 - samples/sec: 3232.36 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:24:27,097 epoch 7 - iter 216/272 - loss 0.01760377 - time (sec): 12.72 - samples/sec: 3252.49 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:24:28,705 epoch 7 - iter 243/272 - loss 0.01983655 - time (sec): 14.32 - samples/sec: 3285.53 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:24:30,192 epoch 7 - iter 270/272 - loss 0.02082722 - time (sec): 15.81 - samples/sec: 3267.16 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:24:30,289 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:30,289 EPOCH 7 done: loss 0.0214 - lr: 0.000017 2023-10-17 20:24:31,970 DEV : loss 0.1378893107175827 - f1-score (micro avg) 0.8466 2023-10-17 20:24:31,974 saving best model 2023-10-17 20:24:32,437 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:34,194 epoch 8 - iter 27/272 - loss 0.02138210 - time (sec): 1.76 - samples/sec: 3402.72 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:24:35,940 epoch 8 - iter 54/272 - loss 0.01603143 - time (sec): 3.50 - samples/sec: 3511.78 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:24:37,649 epoch 8 - iter 81/272 - loss 0.01321229 - time (sec): 5.21 - samples/sec: 3438.41 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:24:39,220 epoch 8 - iter 108/272 - loss 0.01354273 - time (sec): 6.78 - samples/sec: 3379.13 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:24:40,760 epoch 8 - iter 135/272 - loss 0.01494549 - time (sec): 8.32 - samples/sec: 3317.33 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:24:42,340 epoch 8 - iter 162/272 - loss 0.01356546 - time (sec): 9.90 - samples/sec: 3302.23 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:24:44,005 epoch 8 - iter 189/272 - loss 0.01223719 - time (sec): 11.57 - samples/sec: 3292.22 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:24:45,450 epoch 8 - iter 216/272 - loss 0.01234719 - time (sec): 13.01 - samples/sec: 3226.97 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:24:47,009 epoch 8 - iter 243/272 - loss 0.01158905 - time (sec): 14.57 - samples/sec: 3223.70 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:24:48,502 epoch 8 - iter 270/272 - loss 0.01164301 - time (sec): 16.06 - samples/sec: 3227.93 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:24:48,584 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:48,584 EPOCH 8 done: loss 0.0116 - lr: 0.000011 2023-10-17 20:24:50,133 DEV : loss 0.17313425242900848 - f1-score (micro avg) 0.8411 2023-10-17 20:24:50,139 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:24:51,767 epoch 9 - iter 27/272 - loss 0.01050858 - time (sec): 1.63 - samples/sec: 3239.68 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:24:53,284 epoch 9 - iter 54/272 - loss 0.00816307 - time (sec): 3.14 - samples/sec: 3430.50 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:24:55,016 epoch 9 - iter 81/272 - loss 0.00563877 - time (sec): 4.88 - samples/sec: 3331.55 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:24:56,573 epoch 9 - iter 108/272 - loss 0.00751326 - time (sec): 6.43 - samples/sec: 3319.73 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:24:58,184 epoch 9 - iter 135/272 - loss 0.00746821 - time (sec): 8.04 - samples/sec: 3333.63 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:24:59,745 epoch 9 - iter 162/272 - loss 0.00835793 - time (sec): 9.60 - samples/sec: 3302.04 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:25:01,328 epoch 9 - iter 189/272 - loss 0.00843661 - time (sec): 11.19 - samples/sec: 3278.39 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:25:03,008 epoch 9 - iter 216/272 - loss 0.00844583 - time (sec): 12.87 - samples/sec: 3268.37 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:25:04,632 epoch 9 - iter 243/272 - loss 0.00798675 - time (sec): 14.49 - samples/sec: 3245.09 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:25:06,262 epoch 9 - iter 270/272 - loss 0.00914489 - time (sec): 16.12 - samples/sec: 3208.36 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:25:06,364 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:25:06,364 EPOCH 9 done: loss 0.0091 - lr: 0.000006 2023-10-17 20:25:07,842 DEV : loss 0.16325917840003967 - f1-score (micro avg) 0.8454 2023-10-17 20:25:07,848 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:25:09,333 epoch 10 - iter 27/272 - loss 0.01177117 - time (sec): 1.48 - samples/sec: 3150.74 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:25:10,839 epoch 10 - iter 54/272 - loss 0.00588272 - time (sec): 2.99 - samples/sec: 3203.39 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:25:12,334 epoch 10 - iter 81/272 - loss 0.00422933 - time (sec): 4.49 - samples/sec: 3248.98 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:25:13,912 epoch 10 - iter 108/272 - loss 0.00469858 - time (sec): 6.06 - samples/sec: 3231.54 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:25:15,425 epoch 10 - iter 135/272 - loss 0.00590915 - time (sec): 7.58 - samples/sec: 3187.05 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:25:16,981 epoch 10 - iter 162/272 - loss 0.00571912 - time (sec): 9.13 - samples/sec: 3238.99 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:25:18,598 epoch 10 - iter 189/272 - loss 0.00575909 - time (sec): 10.75 - samples/sec: 3253.20 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:25:20,320 epoch 10 - iter 216/272 - loss 0.00592286 - time (sec): 12.47 - samples/sec: 3244.35 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:25:22,153 epoch 10 - iter 243/272 - loss 0.00637850 - time (sec): 14.30 - samples/sec: 3226.88 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:25:23,793 epoch 10 - iter 270/272 - loss 0.00590127 - time (sec): 15.94 - samples/sec: 3246.86 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:25:23,884 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:25:23,885 EPOCH 10 done: loss 0.0059 - lr: 0.000000 2023-10-17 20:25:25,440 DEV : loss 0.16820533573627472 - f1-score (micro avg) 0.8296 2023-10-17 20:25:25,843 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:25:25,844 Loading model from best epoch ... 2023-10-17 20:25:27,361 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 2023-10-17 20:25:29,711 Results: - F-score (micro) 0.7984 - F-score (macro) 0.7542 - Accuracy 0.6809 By class: precision recall f1-score support LOC 0.8439 0.8141 0.8287 312 PER 0.7541 0.8846 0.8142 208 ORG 0.5500 0.6000 0.5739 55 HumanProd 0.6667 1.0000 0.8000 22 micro avg 0.7727 0.8258 0.7984 597 macro avg 0.7037 0.8247 0.7542 597 weighted avg 0.7790 0.8258 0.7991 597 2023-10-17 20:25:29,711 ----------------------------------------------------------------------------------------------------