| 2023-10-17 10:08:35,205 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,205 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Train: 1214 sentences | |
| 2023-10-17 10:08:35,206 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Training Params: | |
| 2023-10-17 10:08:35,206 - learning_rate: "3e-05" | |
| 2023-10-17 10:08:35,206 - mini_batch_size: "8" | |
| 2023-10-17 10:08:35,206 - max_epochs: "10" | |
| 2023-10-17 10:08:35,206 - shuffle: "True" | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Plugins: | |
| 2023-10-17 10:08:35,206 - TensorboardLogger | |
| 2023-10-17 10:08:35,206 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 10:08:35,206 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Computation: | |
| 2023-10-17 10:08:35,206 - compute on device: cuda:0 | |
| 2023-10-17 10:08:35,206 - embedding storage: none | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,206 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 10:08:35,206 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:35,207 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 10:08:36,100 epoch 1 - iter 15/152 - loss 4.10750195 - time (sec): 0.89 - samples/sec: 3184.94 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 10:08:37,026 epoch 1 - iter 30/152 - loss 3.53724000 - time (sec): 1.82 - samples/sec: 3304.35 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 10:08:37,938 epoch 1 - iter 45/152 - loss 2.91789025 - time (sec): 2.73 - samples/sec: 3296.86 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 10:08:38,822 epoch 1 - iter 60/152 - loss 2.34191391 - time (sec): 3.61 - samples/sec: 3351.44 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 10:08:39,717 epoch 1 - iter 75/152 - loss 2.00063566 - time (sec): 4.51 - samples/sec: 3334.17 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 10:08:40,643 epoch 1 - iter 90/152 - loss 1.74138583 - time (sec): 5.44 - samples/sec: 3345.38 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 10:08:41,583 epoch 1 - iter 105/152 - loss 1.53393664 - time (sec): 6.38 - samples/sec: 3390.84 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 10:08:42,462 epoch 1 - iter 120/152 - loss 1.37866691 - time (sec): 7.25 - samples/sec: 3406.46 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 10:08:43,357 epoch 1 - iter 135/152 - loss 1.25915941 - time (sec): 8.15 - samples/sec: 3420.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 10:08:44,194 epoch 1 - iter 150/152 - loss 1.16541827 - time (sec): 8.99 - samples/sec: 3415.14 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 10:08:44,299 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:44,299 EPOCH 1 done: loss 1.1559 - lr: 0.000029 | |
| 2023-10-17 10:08:45,263 DEV : loss 0.2118874043226242 - f1-score (micro avg) 0.5664 | |
| 2023-10-17 10:08:45,269 saving best model | |
| 2023-10-17 10:08:45,601 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:46,474 epoch 2 - iter 15/152 - loss 0.21136664 - time (sec): 0.87 - samples/sec: 3778.78 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 10:08:47,331 epoch 2 - iter 30/152 - loss 0.22810148 - time (sec): 1.73 - samples/sec: 3633.01 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 10:08:48,181 epoch 2 - iter 45/152 - loss 0.20138984 - time (sec): 2.58 - samples/sec: 3615.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 10:08:49,037 epoch 2 - iter 60/152 - loss 0.19384241 - time (sec): 3.43 - samples/sec: 3626.27 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 10:08:49,928 epoch 2 - iter 75/152 - loss 0.19522356 - time (sec): 4.33 - samples/sec: 3596.25 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 10:08:50,798 epoch 2 - iter 90/152 - loss 0.18813009 - time (sec): 5.20 - samples/sec: 3626.50 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 10:08:51,611 epoch 2 - iter 105/152 - loss 0.17989387 - time (sec): 6.01 - samples/sec: 3581.10 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 10:08:52,495 epoch 2 - iter 120/152 - loss 0.17379162 - time (sec): 6.89 - samples/sec: 3608.68 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 10:08:53,363 epoch 2 - iter 135/152 - loss 0.16792243 - time (sec): 7.76 - samples/sec: 3610.67 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 10:08:54,195 epoch 2 - iter 150/152 - loss 0.16569687 - time (sec): 8.59 - samples/sec: 3569.66 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 10:08:54,290 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:54,290 EPOCH 2 done: loss 0.1644 - lr: 0.000027 | |
| 2023-10-17 10:08:55,296 DEV : loss 0.1441490799188614 - f1-score (micro avg) 0.7808 | |
| 2023-10-17 10:08:55,305 saving best model | |
| 2023-10-17 10:08:55,718 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:08:56,559 epoch 3 - iter 15/152 - loss 0.11363491 - time (sec): 0.84 - samples/sec: 3654.38 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 10:08:57,419 epoch 3 - iter 30/152 - loss 0.09867705 - time (sec): 1.70 - samples/sec: 3596.71 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 10:08:58,345 epoch 3 - iter 45/152 - loss 0.10048734 - time (sec): 2.63 - samples/sec: 3539.79 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 10:08:59,222 epoch 3 - iter 60/152 - loss 0.09765651 - time (sec): 3.50 - samples/sec: 3508.06 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 10:09:00,057 epoch 3 - iter 75/152 - loss 0.09380057 - time (sec): 4.34 - samples/sec: 3484.60 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 10:09:00,847 epoch 3 - iter 90/152 - loss 0.08771727 - time (sec): 5.13 - samples/sec: 3498.40 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 10:09:01,691 epoch 3 - iter 105/152 - loss 0.08939831 - time (sec): 5.97 - samples/sec: 3510.65 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 10:09:02,528 epoch 3 - iter 120/152 - loss 0.09153469 - time (sec): 6.81 - samples/sec: 3572.52 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 10:09:03,446 epoch 3 - iter 135/152 - loss 0.09044341 - time (sec): 7.73 - samples/sec: 3565.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 10:09:04,339 epoch 3 - iter 150/152 - loss 0.09480897 - time (sec): 8.62 - samples/sec: 3546.05 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 10:09:04,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:04,445 EPOCH 3 done: loss 0.0940 - lr: 0.000023 | |
| 2023-10-17 10:09:05,449 DEV : loss 0.1371607482433319 - f1-score (micro avg) 0.8163 | |
| 2023-10-17 10:09:05,457 saving best model | |
| 2023-10-17 10:09:05,939 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:06,872 epoch 4 - iter 15/152 - loss 0.04855091 - time (sec): 0.93 - samples/sec: 3811.93 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 10:09:07,802 epoch 4 - iter 30/152 - loss 0.06349149 - time (sec): 1.86 - samples/sec: 3529.04 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 10:09:08,697 epoch 4 - iter 45/152 - loss 0.06169091 - time (sec): 2.75 - samples/sec: 3466.17 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 10:09:09,596 epoch 4 - iter 60/152 - loss 0.06366120 - time (sec): 3.65 - samples/sec: 3398.54 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 10:09:10,540 epoch 4 - iter 75/152 - loss 0.05983976 - time (sec): 4.60 - samples/sec: 3379.38 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 10:09:11,472 epoch 4 - iter 90/152 - loss 0.06182421 - time (sec): 5.53 - samples/sec: 3385.95 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 10:09:12,431 epoch 4 - iter 105/152 - loss 0.06079492 - time (sec): 6.49 - samples/sec: 3356.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 10:09:13,321 epoch 4 - iter 120/152 - loss 0.06066886 - time (sec): 7.38 - samples/sec: 3361.92 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 10:09:14,156 epoch 4 - iter 135/152 - loss 0.05904551 - time (sec): 8.21 - samples/sec: 3381.59 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 10:09:15,044 epoch 4 - iter 150/152 - loss 0.06154720 - time (sec): 9.10 - samples/sec: 3357.83 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 10:09:15,155 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:15,156 EPOCH 4 done: loss 0.0632 - lr: 0.000020 | |
| 2023-10-17 10:09:16,137 DEV : loss 0.15462778508663177 - f1-score (micro avg) 0.8209 | |
| 2023-10-17 10:09:16,145 saving best model | |
| 2023-10-17 10:09:16,638 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:17,543 epoch 5 - iter 15/152 - loss 0.03337936 - time (sec): 0.90 - samples/sec: 3519.41 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 10:09:18,476 epoch 5 - iter 30/152 - loss 0.04245417 - time (sec): 1.84 - samples/sec: 3321.68 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 10:09:19,387 epoch 5 - iter 45/152 - loss 0.04675805 - time (sec): 2.75 - samples/sec: 3443.64 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 10:09:20,282 epoch 5 - iter 60/152 - loss 0.04485444 - time (sec): 3.64 - samples/sec: 3446.89 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 10:09:21,200 epoch 5 - iter 75/152 - loss 0.04575380 - time (sec): 4.56 - samples/sec: 3436.97 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 10:09:22,101 epoch 5 - iter 90/152 - loss 0.04924817 - time (sec): 5.46 - samples/sec: 3455.09 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 10:09:22,980 epoch 5 - iter 105/152 - loss 0.04947662 - time (sec): 6.34 - samples/sec: 3423.79 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 10:09:23,921 epoch 5 - iter 120/152 - loss 0.05333332 - time (sec): 7.28 - samples/sec: 3430.84 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 10:09:24,835 epoch 5 - iter 135/152 - loss 0.05195013 - time (sec): 8.19 - samples/sec: 3396.88 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 10:09:25,724 epoch 5 - iter 150/152 - loss 0.04874226 - time (sec): 9.08 - samples/sec: 3380.87 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 10:09:25,836 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:25,836 EPOCH 5 done: loss 0.0486 - lr: 0.000017 | |
| 2023-10-17 10:09:26,848 DEV : loss 0.15057812631130219 - f1-score (micro avg) 0.8455 | |
| 2023-10-17 10:09:26,859 saving best model | |
| 2023-10-17 10:09:27,350 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:28,272 epoch 6 - iter 15/152 - loss 0.03678506 - time (sec): 0.92 - samples/sec: 3315.97 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 10:09:29,224 epoch 6 - iter 30/152 - loss 0.02933014 - time (sec): 1.87 - samples/sec: 3326.78 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 10:09:30,089 epoch 6 - iter 45/152 - loss 0.03008315 - time (sec): 2.74 - samples/sec: 3287.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 10:09:30,999 epoch 6 - iter 60/152 - loss 0.02950414 - time (sec): 3.65 - samples/sec: 3393.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 10:09:31,909 epoch 6 - iter 75/152 - loss 0.02716298 - time (sec): 4.56 - samples/sec: 3336.70 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 10:09:32,850 epoch 6 - iter 90/152 - loss 0.03298691 - time (sec): 5.50 - samples/sec: 3352.02 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 10:09:33,709 epoch 6 - iter 105/152 - loss 0.03484644 - time (sec): 6.36 - samples/sec: 3320.10 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 10:09:34,633 epoch 6 - iter 120/152 - loss 0.03592514 - time (sec): 7.28 - samples/sec: 3384.52 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 10:09:35,548 epoch 6 - iter 135/152 - loss 0.03742840 - time (sec): 8.20 - samples/sec: 3389.45 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 10:09:36,426 epoch 6 - iter 150/152 - loss 0.03891420 - time (sec): 9.07 - samples/sec: 3390.27 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 10:09:36,523 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:36,523 EPOCH 6 done: loss 0.0386 - lr: 0.000013 | |
| 2023-10-17 10:09:37,526 DEV : loss 0.16086134314537048 - f1-score (micro avg) 0.8327 | |
| 2023-10-17 10:09:37,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:38,399 epoch 7 - iter 15/152 - loss 0.03043145 - time (sec): 0.86 - samples/sec: 3462.35 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 10:09:39,319 epoch 7 - iter 30/152 - loss 0.02326426 - time (sec): 1.78 - samples/sec: 3513.13 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 10:09:40,141 epoch 7 - iter 45/152 - loss 0.03009332 - time (sec): 2.61 - samples/sec: 3428.29 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 10:09:41,029 epoch 7 - iter 60/152 - loss 0.03076153 - time (sec): 3.49 - samples/sec: 3474.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 10:09:41,949 epoch 7 - iter 75/152 - loss 0.03408682 - time (sec): 4.41 - samples/sec: 3464.06 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 10:09:42,799 epoch 7 - iter 90/152 - loss 0.03450276 - time (sec): 5.26 - samples/sec: 3494.47 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 10:09:43,681 epoch 7 - iter 105/152 - loss 0.03062415 - time (sec): 6.15 - samples/sec: 3506.93 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 10:09:44,578 epoch 7 - iter 120/152 - loss 0.03375577 - time (sec): 7.04 - samples/sec: 3504.12 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 10:09:45,397 epoch 7 - iter 135/152 - loss 0.03216010 - time (sec): 7.86 - samples/sec: 3510.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 10:09:46,261 epoch 7 - iter 150/152 - loss 0.03172133 - time (sec): 8.73 - samples/sec: 3515.89 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 10:09:46,359 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:46,360 EPOCH 7 done: loss 0.0314 - lr: 0.000010 | |
| 2023-10-17 10:09:47,320 DEV : loss 0.17176775634288788 - f1-score (micro avg) 0.8602 | |
| 2023-10-17 10:09:47,328 saving best model | |
| 2023-10-17 10:09:47,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:48,628 epoch 8 - iter 15/152 - loss 0.04202288 - time (sec): 0.85 - samples/sec: 3345.70 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 10:09:49,533 epoch 8 - iter 30/152 - loss 0.02857253 - time (sec): 1.76 - samples/sec: 3304.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 10:09:50,412 epoch 8 - iter 45/152 - loss 0.02036949 - time (sec): 2.64 - samples/sec: 3395.95 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 10:09:51,288 epoch 8 - iter 60/152 - loss 0.02012254 - time (sec): 3.51 - samples/sec: 3392.17 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 10:09:52,199 epoch 8 - iter 75/152 - loss 0.01964777 - time (sec): 4.42 - samples/sec: 3419.41 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 10:09:53,125 epoch 8 - iter 90/152 - loss 0.01753895 - time (sec): 5.35 - samples/sec: 3400.23 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 10:09:53,954 epoch 8 - iter 105/152 - loss 0.01703925 - time (sec): 6.18 - samples/sec: 3438.12 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 10:09:54,843 epoch 8 - iter 120/152 - loss 0.01789699 - time (sec): 7.07 - samples/sec: 3470.05 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 10:09:55,653 epoch 8 - iter 135/152 - loss 0.02286253 - time (sec): 7.88 - samples/sec: 3502.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 10:09:56,497 epoch 8 - iter 150/152 - loss 0.02531880 - time (sec): 8.72 - samples/sec: 3507.09 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 10:09:56,598 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:56,598 EPOCH 8 done: loss 0.0250 - lr: 0.000007 | |
| 2023-10-17 10:09:57,585 DEV : loss 0.1786491572856903 - f1-score (micro avg) 0.8439 | |
| 2023-10-17 10:09:57,593 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:09:58,464 epoch 9 - iter 15/152 - loss 0.01563257 - time (sec): 0.87 - samples/sec: 3474.50 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 10:09:59,367 epoch 9 - iter 30/152 - loss 0.01976328 - time (sec): 1.77 - samples/sec: 3492.20 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 10:10:00,258 epoch 9 - iter 45/152 - loss 0.01830740 - time (sec): 2.66 - samples/sec: 3513.86 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 10:10:01,123 epoch 9 - iter 60/152 - loss 0.02107441 - time (sec): 3.53 - samples/sec: 3499.60 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 10:10:01,987 epoch 9 - iter 75/152 - loss 0.02095114 - time (sec): 4.39 - samples/sec: 3452.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 10:10:02,868 epoch 9 - iter 90/152 - loss 0.02240275 - time (sec): 5.27 - samples/sec: 3482.10 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 10:10:03,744 epoch 9 - iter 105/152 - loss 0.02092200 - time (sec): 6.15 - samples/sec: 3497.51 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 10:10:04,565 epoch 9 - iter 120/152 - loss 0.01974602 - time (sec): 6.97 - samples/sec: 3508.70 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 10:10:05,432 epoch 9 - iter 135/152 - loss 0.02156260 - time (sec): 7.84 - samples/sec: 3513.19 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 10:10:06,307 epoch 9 - iter 150/152 - loss 0.02035076 - time (sec): 8.71 - samples/sec: 3514.31 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 10:10:06,416 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:10:06,416 EPOCH 9 done: loss 0.0202 - lr: 0.000004 | |
| 2023-10-17 10:10:07,431 DEV : loss 0.19476434588432312 - f1-score (micro avg) 0.848 | |
| 2023-10-17 10:10:07,441 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:10:08,295 epoch 10 - iter 15/152 - loss 0.02396233 - time (sec): 0.85 - samples/sec: 3777.37 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 10:10:09,139 epoch 10 - iter 30/152 - loss 0.02483156 - time (sec): 1.70 - samples/sec: 3637.26 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 10:10:10,008 epoch 10 - iter 45/152 - loss 0.01961488 - time (sec): 2.57 - samples/sec: 3527.62 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 10:10:10,874 epoch 10 - iter 60/152 - loss 0.01733208 - time (sec): 3.43 - samples/sec: 3614.95 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 10:10:11,739 epoch 10 - iter 75/152 - loss 0.01417339 - time (sec): 4.30 - samples/sec: 3645.19 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 10:10:12,607 epoch 10 - iter 90/152 - loss 0.01438682 - time (sec): 5.16 - samples/sec: 3622.14 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 10:10:13,451 epoch 10 - iter 105/152 - loss 0.01475819 - time (sec): 6.01 - samples/sec: 3590.96 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 10:10:14,296 epoch 10 - iter 120/152 - loss 0.01656911 - time (sec): 6.85 - samples/sec: 3579.97 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 10:10:15,133 epoch 10 - iter 135/152 - loss 0.01681636 - time (sec): 7.69 - samples/sec: 3580.87 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 10:10:16,033 epoch 10 - iter 150/152 - loss 0.01714759 - time (sec): 8.59 - samples/sec: 3557.64 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 10:10:16,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:10:16,157 EPOCH 10 done: loss 0.0173 - lr: 0.000000 | |
| 2023-10-17 10:10:17,098 DEV : loss 0.19630704820156097 - f1-score (micro avg) 0.8439 | |
| 2023-10-17 10:10:17,466 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 10:10:17,468 Loading model from best epoch ... | |
| 2023-10-17 10:10:18,834 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-17 10:10:19,748 | |
| Results: | |
| - F-score (micro) 0.8017 | |
| - F-score (macro) 0.6499 | |
| - Accuracy 0.6737 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7278 0.7616 0.7443 151 | |
| work 0.7547 0.8421 0.7960 95 | |
| pers 0.8824 0.9375 0.9091 96 | |
| loc 1.0000 0.6667 0.8000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7799 0.8247 0.8017 348 | |
| macro avg 0.6730 0.6416 0.6499 348 | |
| weighted avg 0.7739 0.8247 0.7980 348 | |
| 2023-10-17 10:10:19,748 ---------------------------------------------------------------------------------------------------- | |