| 2023-10-17 17:20:40,694 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,696 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 17:20:40,696 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,696 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 17:20:40,697 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,697 Train: 3575 sentences | |
| 2023-10-17 17:20:40,697 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 17:20:40,697 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,697 Training Params: | |
| 2023-10-17 17:20:40,697 - learning_rate: "5e-05" | |
| 2023-10-17 17:20:40,697 - mini_batch_size: "4" | |
| 2023-10-17 17:20:40,697 - max_epochs: "10" | |
| 2023-10-17 17:20:40,697 - shuffle: "True" | |
| 2023-10-17 17:20:40,697 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,697 Plugins: | |
| 2023-10-17 17:20:40,697 - TensorboardLogger | |
| 2023-10-17 17:20:40,697 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 17:20:40,697 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,697 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 17:20:40,698 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 17:20:40,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,698 Computation: | |
| 2023-10-17 17:20:40,698 - compute on device: cuda:0 | |
| 2023-10-17 17:20:40,698 - embedding storage: none | |
| 2023-10-17 17:20:40,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,698 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 17:20:40,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:20:40,698 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 17:20:47,605 epoch 1 - iter 89/894 - loss 3.03990857 - time (sec): 6.91 - samples/sec: 1132.15 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 17:20:54,757 epoch 1 - iter 178/894 - loss 1.78520040 - time (sec): 14.06 - samples/sec: 1212.12 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 17:21:01,831 epoch 1 - iter 267/894 - loss 1.32800676 - time (sec): 21.13 - samples/sec: 1221.44 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:21:08,879 epoch 1 - iter 356/894 - loss 1.08814028 - time (sec): 28.18 - samples/sec: 1205.04 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 17:21:15,816 epoch 1 - iter 445/894 - loss 0.93203560 - time (sec): 35.12 - samples/sec: 1211.74 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 17:21:23,001 epoch 1 - iter 534/894 - loss 0.79925903 - time (sec): 42.30 - samples/sec: 1240.41 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 17:21:30,033 epoch 1 - iter 623/894 - loss 0.72337780 - time (sec): 49.33 - samples/sec: 1236.78 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 17:21:36,976 epoch 1 - iter 712/894 - loss 0.66747105 - time (sec): 56.28 - samples/sec: 1228.23 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 17:21:44,256 epoch 1 - iter 801/894 - loss 0.61270239 - time (sec): 63.56 - samples/sec: 1231.53 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 17:21:51,315 epoch 1 - iter 890/894 - loss 0.57797410 - time (sec): 70.62 - samples/sec: 1218.76 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 17:21:51,635 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:21:51,636 EPOCH 1 done: loss 0.5755 - lr: 0.000050 | |
| 2023-10-17 17:21:57,988 DEV : loss 0.19460029900074005 - f1-score (micro avg) 0.6137 | |
| 2023-10-17 17:21:58,044 saving best model | |
| 2023-10-17 17:21:58,580 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:22:05,697 epoch 2 - iter 89/894 - loss 0.16003986 - time (sec): 7.12 - samples/sec: 1204.20 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 17:22:12,777 epoch 2 - iter 178/894 - loss 0.15424274 - time (sec): 14.20 - samples/sec: 1203.33 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 17:22:19,836 epoch 2 - iter 267/894 - loss 0.14896442 - time (sec): 21.25 - samples/sec: 1174.60 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 17:22:26,808 epoch 2 - iter 356/894 - loss 0.15842510 - time (sec): 28.23 - samples/sec: 1144.80 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 17:22:34,036 epoch 2 - iter 445/894 - loss 0.15722699 - time (sec): 35.45 - samples/sec: 1179.79 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 17:22:41,249 epoch 2 - iter 534/894 - loss 0.16060261 - time (sec): 42.67 - samples/sec: 1202.85 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 17:22:48,061 epoch 2 - iter 623/894 - loss 0.16329369 - time (sec): 49.48 - samples/sec: 1207.00 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 17:22:54,996 epoch 2 - iter 712/894 - loss 0.16030192 - time (sec): 56.41 - samples/sec: 1218.15 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 17:23:01,984 epoch 2 - iter 801/894 - loss 0.15853588 - time (sec): 63.40 - samples/sec: 1232.82 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 17:23:08,791 epoch 2 - iter 890/894 - loss 0.15689717 - time (sec): 70.21 - samples/sec: 1227.17 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 17:23:09,089 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:23:09,089 EPOCH 2 done: loss 0.1579 - lr: 0.000044 | |
| 2023-10-17 17:23:20,463 DEV : loss 0.13591983914375305 - f1-score (micro avg) 0.7137 | |
| 2023-10-17 17:23:20,518 saving best model | |
| 2023-10-17 17:23:21,901 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:23:28,588 epoch 3 - iter 89/894 - loss 0.10586379 - time (sec): 6.68 - samples/sec: 1291.96 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 17:23:34,965 epoch 3 - iter 178/894 - loss 0.09310855 - time (sec): 13.06 - samples/sec: 1355.00 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 17:23:41,263 epoch 3 - iter 267/894 - loss 0.08343594 - time (sec): 19.36 - samples/sec: 1365.90 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 17:23:47,523 epoch 3 - iter 356/894 - loss 0.09356011 - time (sec): 25.62 - samples/sec: 1338.16 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 17:23:53,919 epoch 3 - iter 445/894 - loss 0.09659849 - time (sec): 32.01 - samples/sec: 1347.39 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 17:24:01,292 epoch 3 - iter 534/894 - loss 0.09801984 - time (sec): 39.39 - samples/sec: 1326.81 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 17:24:08,278 epoch 3 - iter 623/894 - loss 0.09757948 - time (sec): 46.37 - samples/sec: 1308.60 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 17:24:15,229 epoch 3 - iter 712/894 - loss 0.09967059 - time (sec): 53.32 - samples/sec: 1299.91 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 17:24:22,205 epoch 3 - iter 801/894 - loss 0.09645513 - time (sec): 60.30 - samples/sec: 1297.95 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 17:24:29,257 epoch 3 - iter 890/894 - loss 0.09586911 - time (sec): 67.35 - samples/sec: 1279.48 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 17:24:29,568 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:24:29,569 EPOCH 3 done: loss 0.0958 - lr: 0.000039 | |
| 2023-10-17 17:24:41,377 DEV : loss 0.2212122529745102 - f1-score (micro avg) 0.7327 | |
| 2023-10-17 17:24:41,434 saving best model | |
| 2023-10-17 17:24:42,026 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:24:49,211 epoch 4 - iter 89/894 - loss 0.06634274 - time (sec): 7.18 - samples/sec: 1268.33 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 17:24:56,183 epoch 4 - iter 178/894 - loss 0.06540443 - time (sec): 14.15 - samples/sec: 1234.94 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 17:25:03,579 epoch 4 - iter 267/894 - loss 0.05971285 - time (sec): 21.55 - samples/sec: 1213.46 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 17:25:10,710 epoch 4 - iter 356/894 - loss 0.06243303 - time (sec): 28.68 - samples/sec: 1201.41 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 17:25:17,864 epoch 4 - iter 445/894 - loss 0.06441040 - time (sec): 35.84 - samples/sec: 1202.25 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 17:25:25,005 epoch 4 - iter 534/894 - loss 0.06566270 - time (sec): 42.98 - samples/sec: 1204.48 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 17:25:32,357 epoch 4 - iter 623/894 - loss 0.06750837 - time (sec): 50.33 - samples/sec: 1192.38 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 17:25:39,440 epoch 4 - iter 712/894 - loss 0.06895087 - time (sec): 57.41 - samples/sec: 1187.88 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 17:25:46,721 epoch 4 - iter 801/894 - loss 0.06819038 - time (sec): 64.69 - samples/sec: 1204.92 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 17:25:53,566 epoch 4 - iter 890/894 - loss 0.06982787 - time (sec): 71.54 - samples/sec: 1204.85 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 17:25:53,873 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:25:53,874 EPOCH 4 done: loss 0.0696 - lr: 0.000033 | |
| 2023-10-17 17:26:05,574 DEV : loss 0.19206839799880981 - f1-score (micro avg) 0.7691 | |
| 2023-10-17 17:26:05,632 saving best model | |
| 2023-10-17 17:26:07,033 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:26:14,126 epoch 5 - iter 89/894 - loss 0.02919367 - time (sec): 7.09 - samples/sec: 1173.67 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 17:26:21,132 epoch 5 - iter 178/894 - loss 0.03698239 - time (sec): 14.10 - samples/sec: 1227.83 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 17:26:28,344 epoch 5 - iter 267/894 - loss 0.03943436 - time (sec): 21.31 - samples/sec: 1265.01 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 17:26:35,428 epoch 5 - iter 356/894 - loss 0.03761578 - time (sec): 28.39 - samples/sec: 1224.66 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 17:26:42,329 epoch 5 - iter 445/894 - loss 0.03479110 - time (sec): 35.29 - samples/sec: 1246.89 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 17:26:49,445 epoch 5 - iter 534/894 - loss 0.03644592 - time (sec): 42.41 - samples/sec: 1241.59 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 17:26:56,505 epoch 5 - iter 623/894 - loss 0.03666781 - time (sec): 49.47 - samples/sec: 1231.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 17:27:03,948 epoch 5 - iter 712/894 - loss 0.03950081 - time (sec): 56.91 - samples/sec: 1211.83 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 17:27:11,156 epoch 5 - iter 801/894 - loss 0.04385206 - time (sec): 64.12 - samples/sec: 1215.42 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 17:27:18,349 epoch 5 - iter 890/894 - loss 0.04340555 - time (sec): 71.31 - samples/sec: 1208.53 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 17:27:18,668 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:27:18,668 EPOCH 5 done: loss 0.0433 - lr: 0.000028 | |
| 2023-10-17 17:27:29,730 DEV : loss 0.20923025906085968 - f1-score (micro avg) 0.7762 | |
| 2023-10-17 17:27:29,802 saving best model | |
| 2023-10-17 17:27:31,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:27:38,444 epoch 6 - iter 89/894 - loss 0.02754922 - time (sec): 7.15 - samples/sec: 1239.20 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:27:44,996 epoch 6 - iter 178/894 - loss 0.02795744 - time (sec): 13.70 - samples/sec: 1349.10 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 17:27:51,425 epoch 6 - iter 267/894 - loss 0.02495614 - time (sec): 20.13 - samples/sec: 1340.51 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 17:27:57,843 epoch 6 - iter 356/894 - loss 0.02469061 - time (sec): 26.55 - samples/sec: 1305.08 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 17:28:04,897 epoch 6 - iter 445/894 - loss 0.02518819 - time (sec): 33.60 - samples/sec: 1243.31 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 17:28:12,457 epoch 6 - iter 534/894 - loss 0.02419714 - time (sec): 41.16 - samples/sec: 1222.06 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:28:20,359 epoch 6 - iter 623/894 - loss 0.02647867 - time (sec): 49.07 - samples/sec: 1217.81 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 17:28:27,726 epoch 6 - iter 712/894 - loss 0.02578653 - time (sec): 56.43 - samples/sec: 1212.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 17:28:35,280 epoch 6 - iter 801/894 - loss 0.02692607 - time (sec): 63.99 - samples/sec: 1221.29 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 17:28:42,735 epoch 6 - iter 890/894 - loss 0.02725347 - time (sec): 71.44 - samples/sec: 1208.54 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 17:28:43,065 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:28:43,066 EPOCH 6 done: loss 0.0277 - lr: 0.000022 | |
| 2023-10-17 17:28:54,470 DEV : loss 0.26610851287841797 - f1-score (micro avg) 0.7585 | |
| 2023-10-17 17:28:54,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:29:02,164 epoch 7 - iter 89/894 - loss 0.01770895 - time (sec): 7.61 - samples/sec: 1218.30 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 17:29:09,554 epoch 7 - iter 178/894 - loss 0.01895195 - time (sec): 15.00 - samples/sec: 1160.73 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:29:16,836 epoch 7 - iter 267/894 - loss 0.01605232 - time (sec): 22.28 - samples/sec: 1176.64 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 17:29:23,965 epoch 7 - iter 356/894 - loss 0.01681043 - time (sec): 29.41 - samples/sec: 1160.67 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 17:29:30,951 epoch 7 - iter 445/894 - loss 0.01686728 - time (sec): 36.39 - samples/sec: 1160.61 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 17:29:38,090 epoch 7 - iter 534/894 - loss 0.01757958 - time (sec): 43.53 - samples/sec: 1172.66 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 17:29:45,052 epoch 7 - iter 623/894 - loss 0.01842906 - time (sec): 50.50 - samples/sec: 1175.54 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:29:52,094 epoch 7 - iter 712/894 - loss 0.01735328 - time (sec): 57.54 - samples/sec: 1182.60 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 17:29:59,028 epoch 7 - iter 801/894 - loss 0.01820784 - time (sec): 64.47 - samples/sec: 1187.92 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 17:30:06,149 epoch 7 - iter 890/894 - loss 0.01848393 - time (sec): 71.59 - samples/sec: 1203.67 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 17:30:06,468 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:30:06,468 EPOCH 7 done: loss 0.0185 - lr: 0.000017 | |
| 2023-10-17 17:30:17,968 DEV : loss 0.2510668933391571 - f1-score (micro avg) 0.7811 | |
| 2023-10-17 17:30:18,033 saving best model | |
| 2023-10-17 17:30:19,580 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:30:26,769 epoch 8 - iter 89/894 - loss 0.00642061 - time (sec): 7.18 - samples/sec: 1213.37 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 17:30:34,337 epoch 8 - iter 178/894 - loss 0.01382205 - time (sec): 14.75 - samples/sec: 1157.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 17:30:41,390 epoch 8 - iter 267/894 - loss 0.01323906 - time (sec): 21.81 - samples/sec: 1188.96 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 17:30:48,572 epoch 8 - iter 356/894 - loss 0.01361992 - time (sec): 28.99 - samples/sec: 1176.14 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 17:30:55,637 epoch 8 - iter 445/894 - loss 0.01168000 - time (sec): 36.05 - samples/sec: 1174.66 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 17:31:02,718 epoch 8 - iter 534/894 - loss 0.01271779 - time (sec): 43.13 - samples/sec: 1194.19 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 17:31:09,825 epoch 8 - iter 623/894 - loss 0.01196624 - time (sec): 50.24 - samples/sec: 1194.57 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 17:31:16,936 epoch 8 - iter 712/894 - loss 0.01341929 - time (sec): 57.35 - samples/sec: 1194.44 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:31:24,309 epoch 8 - iter 801/894 - loss 0.01292337 - time (sec): 64.72 - samples/sec: 1208.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 17:31:31,384 epoch 8 - iter 890/894 - loss 0.01284735 - time (sec): 71.80 - samples/sec: 1201.09 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 17:31:31,693 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:31:31,693 EPOCH 8 done: loss 0.0128 - lr: 0.000011 | |
| 2023-10-17 17:31:43,205 DEV : loss 0.2856707274913788 - f1-score (micro avg) 0.7775 | |
| 2023-10-17 17:31:43,272 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:31:50,628 epoch 9 - iter 89/894 - loss 0.00785870 - time (sec): 7.35 - samples/sec: 1221.70 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 17:31:57,992 epoch 9 - iter 178/894 - loss 0.00424210 - time (sec): 14.72 - samples/sec: 1303.06 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 17:32:05,110 epoch 9 - iter 267/894 - loss 0.00429337 - time (sec): 21.84 - samples/sec: 1258.65 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 17:32:12,161 epoch 9 - iter 356/894 - loss 0.00467458 - time (sec): 28.89 - samples/sec: 1234.06 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 17:32:19,435 epoch 9 - iter 445/894 - loss 0.00520006 - time (sec): 36.16 - samples/sec: 1237.67 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 17:32:26,684 epoch 9 - iter 534/894 - loss 0.00494801 - time (sec): 43.41 - samples/sec: 1235.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 17:32:33,721 epoch 9 - iter 623/894 - loss 0.00570335 - time (sec): 50.45 - samples/sec: 1228.77 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 17:32:40,703 epoch 9 - iter 712/894 - loss 0.00668224 - time (sec): 57.43 - samples/sec: 1219.17 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 17:32:47,813 epoch 9 - iter 801/894 - loss 0.00640754 - time (sec): 64.54 - samples/sec: 1211.90 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 17:32:54,862 epoch 9 - iter 890/894 - loss 0.00668945 - time (sec): 71.59 - samples/sec: 1203.41 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 17:32:55,172 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:32:55,173 EPOCH 9 done: loss 0.0067 - lr: 0.000006 | |
| 2023-10-17 17:33:06,235 DEV : loss 0.2777999937534332 - f1-score (micro avg) 0.7784 | |
| 2023-10-17 17:33:06,291 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:33:13,306 epoch 10 - iter 89/894 - loss 0.00657773 - time (sec): 7.01 - samples/sec: 1229.27 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 17:33:20,345 epoch 10 - iter 178/894 - loss 0.00391865 - time (sec): 14.05 - samples/sec: 1205.70 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 17:33:27,294 epoch 10 - iter 267/894 - loss 0.00273605 - time (sec): 21.00 - samples/sec: 1190.76 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 17:33:34,693 epoch 10 - iter 356/894 - loss 0.00243882 - time (sec): 28.40 - samples/sec: 1187.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 17:33:42,145 epoch 10 - iter 445/894 - loss 0.00353196 - time (sec): 35.85 - samples/sec: 1188.92 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 17:33:49,493 epoch 10 - iter 534/894 - loss 0.00395560 - time (sec): 43.20 - samples/sec: 1204.94 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 17:33:56,461 epoch 10 - iter 623/894 - loss 0.00434004 - time (sec): 50.17 - samples/sec: 1200.65 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 17:34:03,804 epoch 10 - iter 712/894 - loss 0.00458182 - time (sec): 57.51 - samples/sec: 1202.46 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 17:34:11,918 epoch 10 - iter 801/894 - loss 0.00468585 - time (sec): 65.62 - samples/sec: 1179.89 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 17:34:19,228 epoch 10 - iter 890/894 - loss 0.00452729 - time (sec): 72.94 - samples/sec: 1181.35 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 17:34:19,542 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:19,543 EPOCH 10 done: loss 0.0046 - lr: 0.000000 | |
| 2023-10-17 17:34:30,411 DEV : loss 0.2798316776752472 - f1-score (micro avg) 0.7858 | |
| 2023-10-17 17:34:30,474 saving best model | |
| 2023-10-17 17:34:32,485 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 17:34:32,487 Loading model from best epoch ... | |
| 2023-10-17 17:34:34,890 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 17:34:41,204 | |
| Results: | |
| - F-score (micro) 0.7491 | |
| - F-score (macro) 0.6739 | |
| - Accuracy 0.6123 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8522 0.8221 0.8369 596 | |
| pers 0.7022 0.7508 0.7257 333 | |
| org 0.5077 0.5000 0.5038 132 | |
| prod 0.6383 0.4545 0.5310 66 | |
| time 0.7500 0.7959 0.7723 49 | |
| micro avg 0.7543 0.7440 0.7491 1176 | |
| macro avg 0.6901 0.6647 0.6739 1176 | |
| weighted avg 0.7548 0.7440 0.7482 1176 | |
| 2023-10-17 17:34:41,204 ---------------------------------------------------------------------------------------------------- | |