| 2023-10-17 18:57:52,091 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,093 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 18:57:52,093 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,093 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-17 18:57:52,093 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,093 Train: 3575 sentences | |
| 2023-10-17 18:57:52,094 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:57:52,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,094 Training Params: | |
| 2023-10-17 18:57:52,094 - learning_rate: "5e-05" | |
| 2023-10-17 18:57:52,094 - mini_batch_size: "4" | |
| 2023-10-17 18:57:52,094 - max_epochs: "10" | |
| 2023-10-17 18:57:52,094 - shuffle: "True" | |
| 2023-10-17 18:57:52,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,094 Plugins: | |
| 2023-10-17 18:57:52,094 - TensorboardLogger | |
| 2023-10-17 18:57:52,094 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:57:52,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,094 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:57:52,094 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:57:52,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,095 Computation: | |
| 2023-10-17 18:57:52,095 - compute on device: cuda:0 | |
| 2023-10-17 18:57:52,095 - embedding storage: none | |
| 2023-10-17 18:57:52,095 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,095 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:57:52,095 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,095 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:57:52,095 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:57:58,931 epoch 1 - iter 89/894 - loss 3.00225299 - time (sec): 6.83 - samples/sec: 1202.01 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:58:05,870 epoch 1 - iter 178/894 - loss 1.79069375 - time (sec): 13.77 - samples/sec: 1206.03 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:58:13,106 epoch 1 - iter 267/894 - loss 1.31705555 - time (sec): 21.01 - samples/sec: 1210.50 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:58:19,938 epoch 1 - iter 356/894 - loss 1.07438081 - time (sec): 27.84 - samples/sec: 1201.72 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:58:26,897 epoch 1 - iter 445/894 - loss 0.91287612 - time (sec): 34.80 - samples/sec: 1213.00 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:58:33,882 epoch 1 - iter 534/894 - loss 0.82028036 - time (sec): 41.79 - samples/sec: 1201.28 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:58:41,226 epoch 1 - iter 623/894 - loss 0.73685559 - time (sec): 49.13 - samples/sec: 1193.86 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:58:48,391 epoch 1 - iter 712/894 - loss 0.66554276 - time (sec): 56.29 - samples/sec: 1203.17 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:58:55,466 epoch 1 - iter 801/894 - loss 0.60697439 - time (sec): 63.37 - samples/sec: 1212.86 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:59:03,146 epoch 1 - iter 890/894 - loss 0.56625986 - time (sec): 71.05 - samples/sec: 1213.13 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 18:59:03,472 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:59:03,472 EPOCH 1 done: loss 0.5641 - lr: 0.000050 | |
| 2023-10-17 18:59:10,298 DEV : loss 0.1641440987586975 - f1-score (micro avg) 0.6191 | |
| 2023-10-17 18:59:10,363 saving best model | |
| 2023-10-17 18:59:10,899 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:59:18,143 epoch 2 - iter 89/894 - loss 0.15794860 - time (sec): 7.24 - samples/sec: 1382.36 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:59:25,658 epoch 2 - iter 178/894 - loss 0.17315256 - time (sec): 14.76 - samples/sec: 1259.52 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:59:32,636 epoch 2 - iter 267/894 - loss 0.16955826 - time (sec): 21.73 - samples/sec: 1218.46 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:59:39,880 epoch 2 - iter 356/894 - loss 0.16310974 - time (sec): 28.98 - samples/sec: 1213.18 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:59:47,181 epoch 2 - iter 445/894 - loss 0.15719978 - time (sec): 36.28 - samples/sec: 1193.70 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:59:54,203 epoch 2 - iter 534/894 - loss 0.15641959 - time (sec): 43.30 - samples/sec: 1216.41 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 19:00:01,701 epoch 2 - iter 623/894 - loss 0.15556446 - time (sec): 50.80 - samples/sec: 1197.75 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:00:08,829 epoch 2 - iter 712/894 - loss 0.15363448 - time (sec): 57.93 - samples/sec: 1199.92 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:00:16,271 epoch 2 - iter 801/894 - loss 0.15304683 - time (sec): 65.37 - samples/sec: 1187.87 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 19:00:23,793 epoch 2 - iter 890/894 - loss 0.15066106 - time (sec): 72.89 - samples/sec: 1180.58 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:00:24,111 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:24,111 EPOCH 2 done: loss 0.1504 - lr: 0.000044 | |
| 2023-10-17 19:00:35,210 DEV : loss 0.18480995297431946 - f1-score (micro avg) 0.6824 | |
| 2023-10-17 19:00:35,280 saving best model | |
| 2023-10-17 19:00:36,773 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:44,207 epoch 3 - iter 89/894 - loss 0.10262602 - time (sec): 7.43 - samples/sec: 1156.20 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:00:51,543 epoch 3 - iter 178/894 - loss 0.10632283 - time (sec): 14.77 - samples/sec: 1129.54 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:00:59,146 epoch 3 - iter 267/894 - loss 0.10131406 - time (sec): 22.37 - samples/sec: 1159.43 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:01:06,517 epoch 3 - iter 356/894 - loss 0.10708151 - time (sec): 29.74 - samples/sec: 1154.81 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:01:13,599 epoch 3 - iter 445/894 - loss 0.10588775 - time (sec): 36.82 - samples/sec: 1169.24 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:01:20,881 epoch 3 - iter 534/894 - loss 0.10796682 - time (sec): 44.10 - samples/sec: 1193.24 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:01:27,787 epoch 3 - iter 623/894 - loss 0.10768458 - time (sec): 51.01 - samples/sec: 1189.83 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:01:34,808 epoch 3 - iter 712/894 - loss 0.10710551 - time (sec): 58.03 - samples/sec: 1190.19 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:01:41,848 epoch 3 - iter 801/894 - loss 0.10295354 - time (sec): 65.07 - samples/sec: 1188.45 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 19:01:49,373 epoch 3 - iter 890/894 - loss 0.10328161 - time (sec): 72.60 - samples/sec: 1186.01 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 19:01:49,715 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:01:49,715 EPOCH 3 done: loss 0.1031 - lr: 0.000039 | |
| 2023-10-17 19:02:00,859 DEV : loss 0.1962013840675354 - f1-score (micro avg) 0.7387 | |
| 2023-10-17 19:02:00,916 saving best model | |
| 2023-10-17 19:02:02,326 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:02:09,542 epoch 4 - iter 89/894 - loss 0.04452472 - time (sec): 7.21 - samples/sec: 1048.57 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:02:16,679 epoch 4 - iter 178/894 - loss 0.05905823 - time (sec): 14.35 - samples/sec: 1153.82 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:02:23,887 epoch 4 - iter 267/894 - loss 0.06476324 - time (sec): 21.56 - samples/sec: 1202.03 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:02:30,893 epoch 4 - iter 356/894 - loss 0.07137867 - time (sec): 28.56 - samples/sec: 1221.77 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:02:38,140 epoch 4 - iter 445/894 - loss 0.07551925 - time (sec): 35.81 - samples/sec: 1207.72 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:02:45,733 epoch 4 - iter 534/894 - loss 0.07291703 - time (sec): 43.40 - samples/sec: 1197.24 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:02:53,181 epoch 4 - iter 623/894 - loss 0.07411859 - time (sec): 50.85 - samples/sec: 1195.67 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 19:03:00,307 epoch 4 - iter 712/894 - loss 0.07308605 - time (sec): 57.98 - samples/sec: 1194.32 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:03:07,370 epoch 4 - iter 801/894 - loss 0.07206437 - time (sec): 65.04 - samples/sec: 1201.71 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:03:14,207 epoch 4 - iter 890/894 - loss 0.07099225 - time (sec): 71.88 - samples/sec: 1199.37 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:03:14,508 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:14,508 EPOCH 4 done: loss 0.0707 - lr: 0.000033 | |
| 2023-10-17 19:03:25,597 DEV : loss 0.20233656466007233 - f1-score (micro avg) 0.7493 | |
| 2023-10-17 19:03:25,659 saving best model | |
| 2023-10-17 19:03:27,156 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:34,492 epoch 5 - iter 89/894 - loss 0.03267879 - time (sec): 7.33 - samples/sec: 1167.64 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:03:41,819 epoch 5 - iter 178/894 - loss 0.04292784 - time (sec): 14.66 - samples/sec: 1177.46 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:03:49,250 epoch 5 - iter 267/894 - loss 0.03836055 - time (sec): 22.09 - samples/sec: 1210.20 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:03:56,478 epoch 5 - iter 356/894 - loss 0.03997784 - time (sec): 29.32 - samples/sec: 1197.60 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:04:03,597 epoch 5 - iter 445/894 - loss 0.04386553 - time (sec): 36.44 - samples/sec: 1178.16 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:04:10,959 epoch 5 - iter 534/894 - loss 0.04250446 - time (sec): 43.80 - samples/sec: 1178.17 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 19:04:18,388 epoch 5 - iter 623/894 - loss 0.04348624 - time (sec): 51.23 - samples/sec: 1177.13 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:04:25,406 epoch 5 - iter 712/894 - loss 0.04515069 - time (sec): 58.25 - samples/sec: 1172.83 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:04:33,093 epoch 5 - iter 801/894 - loss 0.04710607 - time (sec): 65.93 - samples/sec: 1159.01 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:04:40,554 epoch 5 - iter 890/894 - loss 0.04592844 - time (sec): 73.40 - samples/sec: 1174.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:04:40,881 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:04:40,881 EPOCH 5 done: loss 0.0457 - lr: 0.000028 | |
| 2023-10-17 19:04:52,692 DEV : loss 0.2360163778066635 - f1-score (micro avg) 0.7779 | |
| 2023-10-17 19:04:52,750 saving best model | |
| 2023-10-17 19:04:54,180 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:05:01,845 epoch 6 - iter 89/894 - loss 0.01149976 - time (sec): 7.66 - samples/sec: 1263.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:05:09,303 epoch 6 - iter 178/894 - loss 0.02451550 - time (sec): 15.12 - samples/sec: 1179.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:05:16,170 epoch 6 - iter 267/894 - loss 0.02732072 - time (sec): 21.99 - samples/sec: 1179.96 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:05:23,068 epoch 6 - iter 356/894 - loss 0.02567363 - time (sec): 28.88 - samples/sec: 1186.14 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:05:30,144 epoch 6 - iter 445/894 - loss 0.02565507 - time (sec): 35.96 - samples/sec: 1181.82 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 19:05:37,584 epoch 6 - iter 534/894 - loss 0.02724422 - time (sec): 43.40 - samples/sec: 1183.74 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:05:44,541 epoch 6 - iter 623/894 - loss 0.02748912 - time (sec): 50.36 - samples/sec: 1189.75 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:05:51,801 epoch 6 - iter 712/894 - loss 0.02961830 - time (sec): 57.62 - samples/sec: 1205.02 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:05:59,381 epoch 6 - iter 801/894 - loss 0.03061449 - time (sec): 65.20 - samples/sec: 1200.70 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:06:06,705 epoch 6 - iter 890/894 - loss 0.03059783 - time (sec): 72.52 - samples/sec: 1187.95 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:06:07,039 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:06:07,041 EPOCH 6 done: loss 0.0306 - lr: 0.000022 | |
| 2023-10-17 19:06:18,622 DEV : loss 0.26993367075920105 - f1-score (micro avg) 0.7554 | |
| 2023-10-17 19:06:18,677 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:06:26,150 epoch 7 - iter 89/894 - loss 0.01061319 - time (sec): 7.47 - samples/sec: 1180.43 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:06:33,151 epoch 7 - iter 178/894 - loss 0.01720578 - time (sec): 14.47 - samples/sec: 1185.25 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:06:40,480 epoch 7 - iter 267/894 - loss 0.01736450 - time (sec): 21.80 - samples/sec: 1167.73 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:06:47,520 epoch 7 - iter 356/894 - loss 0.01641373 - time (sec): 28.84 - samples/sec: 1182.45 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:06:54,381 epoch 7 - iter 445/894 - loss 0.01756040 - time (sec): 35.70 - samples/sec: 1190.16 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:07:01,235 epoch 7 - iter 534/894 - loss 0.01848064 - time (sec): 42.56 - samples/sec: 1192.17 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:07:08,148 epoch 7 - iter 623/894 - loss 0.01888162 - time (sec): 49.47 - samples/sec: 1201.31 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:07:15,100 epoch 7 - iter 712/894 - loss 0.01793327 - time (sec): 56.42 - samples/sec: 1200.36 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:07:22,436 epoch 7 - iter 801/894 - loss 0.01765536 - time (sec): 63.76 - samples/sec: 1220.72 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:07:29,336 epoch 7 - iter 890/894 - loss 0.01794690 - time (sec): 70.66 - samples/sec: 1218.98 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:07:29,666 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:07:29,667 EPOCH 7 done: loss 0.0179 - lr: 0.000017 | |
| 2023-10-17 19:07:41,350 DEV : loss 0.2559952437877655 - f1-score (micro avg) 0.7682 | |
| 2023-10-17 19:07:41,415 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:07:48,666 epoch 8 - iter 89/894 - loss 0.00418217 - time (sec): 7.25 - samples/sec: 1098.61 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:07:55,712 epoch 8 - iter 178/894 - loss 0.00926357 - time (sec): 14.29 - samples/sec: 1168.98 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:08:02,788 epoch 8 - iter 267/894 - loss 0.01003390 - time (sec): 21.37 - samples/sec: 1267.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:08:09,602 epoch 8 - iter 356/894 - loss 0.01001150 - time (sec): 28.18 - samples/sec: 1243.38 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:08:16,385 epoch 8 - iter 445/894 - loss 0.01084819 - time (sec): 34.97 - samples/sec: 1239.62 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:08:23,255 epoch 8 - iter 534/894 - loss 0.01123504 - time (sec): 41.84 - samples/sec: 1242.38 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:08:31,006 epoch 8 - iter 623/894 - loss 0.01130336 - time (sec): 49.59 - samples/sec: 1226.23 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:08:38,228 epoch 8 - iter 712/894 - loss 0.01157568 - time (sec): 56.81 - samples/sec: 1219.93 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:08:45,047 epoch 8 - iter 801/894 - loss 0.01127330 - time (sec): 63.63 - samples/sec: 1210.31 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:08:52,150 epoch 8 - iter 890/894 - loss 0.01057093 - time (sec): 70.73 - samples/sec: 1219.24 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:08:52,453 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:08:52,453 EPOCH 8 done: loss 0.0105 - lr: 0.000011 | |
| 2023-10-17 19:09:03,092 DEV : loss 0.27024897933006287 - f1-score (micro avg) 0.7726 | |
| 2023-10-17 19:09:03,152 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:09:10,821 epoch 9 - iter 89/894 - loss 0.00360434 - time (sec): 7.67 - samples/sec: 1040.93 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:09:18,205 epoch 9 - iter 178/894 - loss 0.00565799 - time (sec): 15.05 - samples/sec: 1090.50 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:09:25,863 epoch 9 - iter 267/894 - loss 0.00507366 - time (sec): 22.71 - samples/sec: 1097.93 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:09:33,952 epoch 9 - iter 356/894 - loss 0.00531567 - time (sec): 30.80 - samples/sec: 1121.02 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:09:41,522 epoch 9 - iter 445/894 - loss 0.00513708 - time (sec): 38.37 - samples/sec: 1101.26 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:48,777 epoch 9 - iter 534/894 - loss 0.00571170 - time (sec): 45.62 - samples/sec: 1104.59 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:56,160 epoch 9 - iter 623/894 - loss 0.00624185 - time (sec): 53.01 - samples/sec: 1111.21 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:10:03,766 epoch 9 - iter 712/894 - loss 0.00585911 - time (sec): 60.61 - samples/sec: 1125.45 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:10:11,350 epoch 9 - iter 801/894 - loss 0.00569284 - time (sec): 68.20 - samples/sec: 1138.08 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:10:18,597 epoch 9 - iter 890/894 - loss 0.00557183 - time (sec): 75.44 - samples/sec: 1142.99 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:10:18,924 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:18,924 EPOCH 9 done: loss 0.0056 - lr: 0.000006 | |
| 2023-10-17 19:10:30,263 DEV : loss 0.2831907570362091 - f1-score (micro avg) 0.7883 | |
| 2023-10-17 19:10:30,335 saving best model | |
| 2023-10-17 19:10:31,798 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:39,599 epoch 10 - iter 89/894 - loss 0.00821683 - time (sec): 7.80 - samples/sec: 1176.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:10:46,872 epoch 10 - iter 178/894 - loss 0.00610798 - time (sec): 15.07 - samples/sec: 1267.45 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:10:54,031 epoch 10 - iter 267/894 - loss 0.00562470 - time (sec): 22.23 - samples/sec: 1240.04 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:11:01,068 epoch 10 - iter 356/894 - loss 0.00514968 - time (sec): 29.27 - samples/sec: 1240.12 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:11:07,994 epoch 10 - iter 445/894 - loss 0.00468347 - time (sec): 36.19 - samples/sec: 1229.33 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:11:15,362 epoch 10 - iter 534/894 - loss 0.00476647 - time (sec): 43.56 - samples/sec: 1215.10 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:11:22,828 epoch 10 - iter 623/894 - loss 0.00468070 - time (sec): 51.03 - samples/sec: 1196.79 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:11:30,064 epoch 10 - iter 712/894 - loss 0.00443002 - time (sec): 58.26 - samples/sec: 1186.03 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:11:37,851 epoch 10 - iter 801/894 - loss 0.00419002 - time (sec): 66.05 - samples/sec: 1172.63 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:11:44,539 epoch 10 - iter 890/894 - loss 0.00386993 - time (sec): 72.74 - samples/sec: 1182.57 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 19:11:44,847 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:11:44,847 EPOCH 10 done: loss 0.0038 - lr: 0.000000 | |
| 2023-10-17 19:11:56,138 DEV : loss 0.2942058742046356 - f1-score (micro avg) 0.7877 | |
| 2023-10-17 19:11:56,763 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:11:56,765 Loading model from best epoch ... | |
| 2023-10-17 19:11:59,022 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-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-17 19:12:04,771 | |
| Results: | |
| - F-score (micro) 0.76 | |
| - F-score (macro) 0.6777 | |
| - Accuracy 0.6269 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8608 0.8406 0.8506 596 | |
| pers 0.7180 0.7417 0.7297 333 | |
| org 0.5577 0.4394 0.4915 132 | |
| prod 0.6875 0.5000 0.5789 66 | |
| time 0.7037 0.7755 0.7379 49 | |
| micro avg 0.7747 0.7457 0.7600 1176 | |
| macro avg 0.7055 0.6594 0.6777 1176 | |
| weighted avg 0.7701 0.7457 0.7561 1176 | |
| 2023-10-17 19:12:04,771 ---------------------------------------------------------------------------------------------------- | |