| 2023-10-17 23:09:42,760 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences | |
| - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 Train: 5901 sentences | |
| 2023-10-17 23:09:42,761 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 Training Params: | |
| 2023-10-17 23:09:42,761 - learning_rate: "3e-05" | |
| 2023-10-17 23:09:42,761 - mini_batch_size: "8" | |
| 2023-10-17 23:09:42,761 - max_epochs: "10" | |
| 2023-10-17 23:09:42,761 - shuffle: "True" | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 Plugins: | |
| 2023-10-17 23:09:42,761 - TensorboardLogger | |
| 2023-10-17 23:09:42,761 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 23:09:42,761 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 23:09:42,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,761 Computation: | |
| 2023-10-17 23:09:42,761 - compute on device: cuda:0 | |
| 2023-10-17 23:09:42,762 - embedding storage: none | |
| 2023-10-17 23:09:42,762 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,762 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 23:09:42,762 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,762 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:42,762 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 23:09:48,039 epoch 1 - iter 73/738 - loss 3.19073122 - time (sec): 5.28 - samples/sec: 3191.87 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:09:53,271 epoch 1 - iter 146/738 - loss 2.15194656 - time (sec): 10.51 - samples/sec: 3233.82 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:09:58,812 epoch 1 - iter 219/738 - loss 1.58213457 - time (sec): 16.05 - samples/sec: 3238.82 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:10:04,082 epoch 1 - iter 292/738 - loss 1.29002871 - time (sec): 21.32 - samples/sec: 3228.78 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:10:09,235 epoch 1 - iter 365/738 - loss 1.10948564 - time (sec): 26.47 - samples/sec: 3217.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:10:13,873 epoch 1 - iter 438/738 - loss 0.98852831 - time (sec): 31.11 - samples/sec: 3214.60 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:10:18,506 epoch 1 - iter 511/738 - loss 0.89161312 - time (sec): 35.74 - samples/sec: 3224.99 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:10:23,989 epoch 1 - iter 584/738 - loss 0.80257303 - time (sec): 41.23 - samples/sec: 3249.04 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:10:28,747 epoch 1 - iter 657/738 - loss 0.74356117 - time (sec): 45.98 - samples/sec: 3234.03 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:10:33,574 epoch 1 - iter 730/738 - loss 0.68669956 - time (sec): 50.81 - samples/sec: 3244.15 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:10:34,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:10:34,058 EPOCH 1 done: loss 0.6819 - lr: 0.000030 | |
| 2023-10-17 23:10:40,005 DEV : loss 0.1276639848947525 - f1-score (micro avg) 0.7373 | |
| 2023-10-17 23:10:40,039 saving best model | |
| 2023-10-17 23:10:40,487 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:10:45,940 epoch 2 - iter 73/738 - loss 0.14984187 - time (sec): 5.45 - samples/sec: 3104.96 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:10:51,172 epoch 2 - iter 146/738 - loss 0.13233162 - time (sec): 10.68 - samples/sec: 3089.34 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:10:55,945 epoch 2 - iter 219/738 - loss 0.12669524 - time (sec): 15.46 - samples/sec: 3192.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:11:00,853 epoch 2 - iter 292/738 - loss 0.12635740 - time (sec): 20.36 - samples/sec: 3201.48 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:11:05,967 epoch 2 - iter 365/738 - loss 0.12718419 - time (sec): 25.48 - samples/sec: 3154.73 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:11:10,919 epoch 2 - iter 438/738 - loss 0.12366621 - time (sec): 30.43 - samples/sec: 3195.23 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:11:15,809 epoch 2 - iter 511/738 - loss 0.12210520 - time (sec): 35.32 - samples/sec: 3223.55 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:11:21,889 epoch 2 - iter 584/738 - loss 0.11882532 - time (sec): 41.40 - samples/sec: 3223.82 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:11:26,949 epoch 2 - iter 657/738 - loss 0.11894765 - time (sec): 46.46 - samples/sec: 3221.37 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:11:31,595 epoch 2 - iter 730/738 - loss 0.11967070 - time (sec): 51.11 - samples/sec: 3226.47 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:11:32,023 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:11:32,023 EPOCH 2 done: loss 0.1194 - lr: 0.000027 | |
| 2023-10-17 23:11:43,766 DEV : loss 0.09906981885433197 - f1-score (micro avg) 0.8284 | |
| 2023-10-17 23:11:43,814 saving best model | |
| 2023-10-17 23:11:44,354 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:11:49,669 epoch 3 - iter 73/738 - loss 0.06177229 - time (sec): 5.31 - samples/sec: 3036.84 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:11:54,599 epoch 3 - iter 146/738 - loss 0.06208086 - time (sec): 10.24 - samples/sec: 3115.58 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:11:59,668 epoch 3 - iter 219/738 - loss 0.06901740 - time (sec): 15.31 - samples/sec: 3123.15 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:12:04,924 epoch 3 - iter 292/738 - loss 0.07155310 - time (sec): 20.57 - samples/sec: 3126.20 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:12:10,335 epoch 3 - iter 365/738 - loss 0.07449535 - time (sec): 25.98 - samples/sec: 3154.16 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:12:15,067 epoch 3 - iter 438/738 - loss 0.07444339 - time (sec): 30.71 - samples/sec: 3174.87 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:12:20,629 epoch 3 - iter 511/738 - loss 0.07543798 - time (sec): 36.27 - samples/sec: 3196.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:12:25,578 epoch 3 - iter 584/738 - loss 0.07404811 - time (sec): 41.22 - samples/sec: 3192.01 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:12:30,450 epoch 3 - iter 657/738 - loss 0.07268849 - time (sec): 46.09 - samples/sec: 3206.97 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:12:35,719 epoch 3 - iter 730/738 - loss 0.07290388 - time (sec): 51.36 - samples/sec: 3211.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:12:36,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:12:36,158 EPOCH 3 done: loss 0.0740 - lr: 0.000023 | |
| 2023-10-17 23:12:47,879 DEV : loss 0.10388551652431488 - f1-score (micro avg) 0.8357 | |
| 2023-10-17 23:12:47,918 saving best model | |
| 2023-10-17 23:12:48,437 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:12:53,475 epoch 4 - iter 73/738 - loss 0.03830018 - time (sec): 5.04 - samples/sec: 3392.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:12:58,170 epoch 4 - iter 146/738 - loss 0.04844825 - time (sec): 9.73 - samples/sec: 3325.83 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:13:03,973 epoch 4 - iter 219/738 - loss 0.05141719 - time (sec): 15.53 - samples/sec: 3268.78 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:13:09,017 epoch 4 - iter 292/738 - loss 0.05536399 - time (sec): 20.58 - samples/sec: 3302.66 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:13:13,618 epoch 4 - iter 365/738 - loss 0.05397456 - time (sec): 25.18 - samples/sec: 3307.06 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:13:18,267 epoch 4 - iter 438/738 - loss 0.05338880 - time (sec): 29.83 - samples/sec: 3282.20 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:13:23,460 epoch 4 - iter 511/738 - loss 0.05233451 - time (sec): 35.02 - samples/sec: 3277.87 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:13:28,930 epoch 4 - iter 584/738 - loss 0.05264342 - time (sec): 40.49 - samples/sec: 3252.63 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:13:33,763 epoch 4 - iter 657/738 - loss 0.05249207 - time (sec): 45.32 - samples/sec: 3248.08 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:13:38,970 epoch 4 - iter 730/738 - loss 0.05189176 - time (sec): 50.53 - samples/sec: 3249.70 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:13:39,666 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:13:39,667 EPOCH 4 done: loss 0.0518 - lr: 0.000020 | |
| 2023-10-17 23:13:51,275 DEV : loss 0.12748253345489502 - f1-score (micro avg) 0.8524 | |
| 2023-10-17 23:13:51,312 saving best model | |
| 2023-10-17 23:13:51,854 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:13:56,810 epoch 5 - iter 73/738 - loss 0.03736179 - time (sec): 4.95 - samples/sec: 3201.82 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:14:01,605 epoch 5 - iter 146/738 - loss 0.03929666 - time (sec): 9.75 - samples/sec: 3245.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:14:06,236 epoch 5 - iter 219/738 - loss 0.03541404 - time (sec): 14.38 - samples/sec: 3334.61 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:14:11,236 epoch 5 - iter 292/738 - loss 0.03601041 - time (sec): 19.38 - samples/sec: 3341.30 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:14:15,907 epoch 5 - iter 365/738 - loss 0.03509454 - time (sec): 24.05 - samples/sec: 3338.83 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:14:21,821 epoch 5 - iter 438/738 - loss 0.03662298 - time (sec): 29.97 - samples/sec: 3348.28 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:14:27,303 epoch 5 - iter 511/738 - loss 0.03680615 - time (sec): 35.45 - samples/sec: 3328.56 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:14:32,171 epoch 5 - iter 584/738 - loss 0.03686372 - time (sec): 40.31 - samples/sec: 3298.46 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:14:36,629 epoch 5 - iter 657/738 - loss 0.03620067 - time (sec): 44.77 - samples/sec: 3285.23 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:14:41,982 epoch 5 - iter 730/738 - loss 0.03656225 - time (sec): 50.13 - samples/sec: 3286.04 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:14:42,562 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:14:42,563 EPOCH 5 done: loss 0.0369 - lr: 0.000017 | |
| 2023-10-17 23:14:54,151 DEV : loss 0.15179269015789032 - f1-score (micro avg) 0.8499 | |
| 2023-10-17 23:14:54,184 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:14:59,556 epoch 6 - iter 73/738 - loss 0.02916893 - time (sec): 5.37 - samples/sec: 3378.62 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:15:04,598 epoch 6 - iter 146/738 - loss 0.02243981 - time (sec): 10.41 - samples/sec: 3287.02 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:15:09,232 epoch 6 - iter 219/738 - loss 0.02328755 - time (sec): 15.05 - samples/sec: 3321.79 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:15:15,781 epoch 6 - iter 292/738 - loss 0.02427567 - time (sec): 21.59 - samples/sec: 3235.07 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:15:20,572 epoch 6 - iter 365/738 - loss 0.02457259 - time (sec): 26.39 - samples/sec: 3231.48 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:15:25,509 epoch 6 - iter 438/738 - loss 0.02583212 - time (sec): 31.32 - samples/sec: 3216.36 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:15:30,690 epoch 6 - iter 511/738 - loss 0.02625489 - time (sec): 36.50 - samples/sec: 3224.66 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:15:35,595 epoch 6 - iter 584/738 - loss 0.02561750 - time (sec): 41.41 - samples/sec: 3214.56 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:15:40,205 epoch 6 - iter 657/738 - loss 0.02564556 - time (sec): 46.02 - samples/sec: 3230.41 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:15:45,030 epoch 6 - iter 730/738 - loss 0.02550200 - time (sec): 50.84 - samples/sec: 3239.57 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:15:45,530 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:15:45,530 EPOCH 6 done: loss 0.0253 - lr: 0.000013 | |
| 2023-10-17 23:15:57,118 DEV : loss 0.17110277712345123 - f1-score (micro avg) 0.8594 | |
| 2023-10-17 23:15:57,152 saving best model | |
| 2023-10-17 23:15:57,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:16:02,253 epoch 7 - iter 73/738 - loss 0.02540609 - time (sec): 4.52 - samples/sec: 3392.61 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:16:07,182 epoch 7 - iter 146/738 - loss 0.02062297 - time (sec): 9.45 - samples/sec: 3343.81 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:16:11,938 epoch 7 - iter 219/738 - loss 0.02088188 - time (sec): 14.21 - samples/sec: 3308.10 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:16:16,710 epoch 7 - iter 292/738 - loss 0.02062599 - time (sec): 18.98 - samples/sec: 3286.23 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:16:22,336 epoch 7 - iter 365/738 - loss 0.01888039 - time (sec): 24.60 - samples/sec: 3287.90 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:16:26,959 epoch 7 - iter 438/738 - loss 0.01920684 - time (sec): 29.23 - samples/sec: 3282.43 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:16:32,361 epoch 7 - iter 511/738 - loss 0.02131205 - time (sec): 34.63 - samples/sec: 3247.63 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:16:37,805 epoch 7 - iter 584/738 - loss 0.02072057 - time (sec): 40.07 - samples/sec: 3244.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:16:42,983 epoch 7 - iter 657/738 - loss 0.02077910 - time (sec): 45.25 - samples/sec: 3245.39 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:16:48,295 epoch 7 - iter 730/738 - loss 0.02022206 - time (sec): 50.56 - samples/sec: 3253.26 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:16:48,888 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:16:48,889 EPOCH 7 done: loss 0.0202 - lr: 0.000010 | |
| 2023-10-17 23:17:00,601 DEV : loss 0.17666654288768768 - f1-score (micro avg) 0.8551 | |
| 2023-10-17 23:17:00,635 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:17:05,647 epoch 8 - iter 73/738 - loss 0.01531019 - time (sec): 5.01 - samples/sec: 3234.30 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:17:10,312 epoch 8 - iter 146/738 - loss 0.01455679 - time (sec): 9.68 - samples/sec: 3163.59 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:17:15,983 epoch 8 - iter 219/738 - loss 0.01387033 - time (sec): 15.35 - samples/sec: 3175.09 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:17:20,948 epoch 8 - iter 292/738 - loss 0.01356124 - time (sec): 20.31 - samples/sec: 3135.26 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:17:26,656 epoch 8 - iter 365/738 - loss 0.01664918 - time (sec): 26.02 - samples/sec: 3151.06 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:17:31,979 epoch 8 - iter 438/738 - loss 0.01621963 - time (sec): 31.34 - samples/sec: 3137.15 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:17:36,582 epoch 8 - iter 511/738 - loss 0.01654134 - time (sec): 35.95 - samples/sec: 3158.08 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:17:41,113 epoch 8 - iter 584/738 - loss 0.01556838 - time (sec): 40.48 - samples/sec: 3184.98 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:17:45,561 epoch 8 - iter 657/738 - loss 0.01548565 - time (sec): 44.93 - samples/sec: 3205.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:17:51,126 epoch 8 - iter 730/738 - loss 0.01493462 - time (sec): 50.49 - samples/sec: 3219.65 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:17:52,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:17:52,130 EPOCH 8 done: loss 0.0151 - lr: 0.000007 | |
| 2023-10-17 23:18:03,991 DEV : loss 0.17948344349861145 - f1-score (micro avg) 0.8615 | |
| 2023-10-17 23:18:04,027 saving best model | |
| 2023-10-17 23:18:04,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:18:09,493 epoch 9 - iter 73/738 - loss 0.00850263 - time (sec): 4.93 - samples/sec: 3262.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:18:14,417 epoch 9 - iter 146/738 - loss 0.01512494 - time (sec): 9.86 - samples/sec: 3241.41 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:18:19,807 epoch 9 - iter 219/738 - loss 0.01323011 - time (sec): 15.25 - samples/sec: 3261.67 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:18:24,677 epoch 9 - iter 292/738 - loss 0.01076360 - time (sec): 20.12 - samples/sec: 3256.57 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:18:29,821 epoch 9 - iter 365/738 - loss 0.01053439 - time (sec): 25.26 - samples/sec: 3287.97 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:18:34,680 epoch 9 - iter 438/738 - loss 0.01257739 - time (sec): 30.12 - samples/sec: 3276.62 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:18:39,356 epoch 9 - iter 511/738 - loss 0.01192892 - time (sec): 34.80 - samples/sec: 3271.42 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:18:44,914 epoch 9 - iter 584/738 - loss 0.01131486 - time (sec): 40.35 - samples/sec: 3252.99 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:18:49,881 epoch 9 - iter 657/738 - loss 0.01101467 - time (sec): 45.32 - samples/sec: 3255.87 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:18:55,034 epoch 9 - iter 730/738 - loss 0.01067850 - time (sec): 50.47 - samples/sec: 3252.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:18:55,753 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:18:55,753 EPOCH 9 done: loss 0.0107 - lr: 0.000003 | |
| 2023-10-17 23:19:07,442 DEV : loss 0.18703721463680267 - f1-score (micro avg) 0.8547 | |
| 2023-10-17 23:19:07,477 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:19:13,177 epoch 10 - iter 73/738 - loss 0.00499895 - time (sec): 5.70 - samples/sec: 3084.23 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:19:18,035 epoch 10 - iter 146/738 - loss 0.00950824 - time (sec): 10.56 - samples/sec: 3242.33 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:19:23,134 epoch 10 - iter 219/738 - loss 0.00884607 - time (sec): 15.66 - samples/sec: 3211.21 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:19:28,840 epoch 10 - iter 292/738 - loss 0.00992232 - time (sec): 21.36 - samples/sec: 3204.50 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:19:33,908 epoch 10 - iter 365/738 - loss 0.00903071 - time (sec): 26.43 - samples/sec: 3193.68 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:19:38,750 epoch 10 - iter 438/738 - loss 0.00856681 - time (sec): 31.27 - samples/sec: 3227.00 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:19:43,220 epoch 10 - iter 511/738 - loss 0.00799097 - time (sec): 35.74 - samples/sec: 3247.84 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:19:48,193 epoch 10 - iter 584/738 - loss 0.00745098 - time (sec): 40.71 - samples/sec: 3242.78 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:19:53,198 epoch 10 - iter 657/738 - loss 0.00772499 - time (sec): 45.72 - samples/sec: 3246.86 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 23:19:58,146 epoch 10 - iter 730/738 - loss 0.00809159 - time (sec): 50.67 - samples/sec: 3246.74 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 23:19:58,702 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:19:58,703 EPOCH 10 done: loss 0.0081 - lr: 0.000000 | |
| 2023-10-17 23:20:10,391 DEV : loss 0.19134128093719482 - f1-score (micro avg) 0.8576 | |
| 2023-10-17 23:20:10,835 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:10,836 Loading model from best epoch ... | |
| 2023-10-17 23:20:12,318 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod | |
| 2023-10-17 23:20:19,334 | |
| Results: | |
| - F-score (micro) 0.8144 | |
| - F-score (macro) 0.7223 | |
| - Accuracy 0.7034 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8638 0.8869 0.8752 858 | |
| pers 0.7860 0.8138 0.7996 537 | |
| org 0.6250 0.5682 0.5952 132 | |
| prod 0.7419 0.7541 0.7480 61 | |
| time 0.5469 0.6481 0.5932 54 | |
| micro avg 0.8045 0.8246 0.8144 1642 | |
| macro avg 0.7127 0.7342 0.7223 1642 | |
| weighted avg 0.8042 0.8246 0.8140 1642 | |
| 2023-10-17 23:20:19,335 ---------------------------------------------------------------------------------------------------- | |