| 2023-10-18 18:27:41,081 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,081 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-18 18:27:41,081 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,081 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 | |
| 2023-10-18 18:27:41,081 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,081 Train: 3575 sentences | |
| 2023-10-18 18:27:41,081 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Training Params: | |
| 2023-10-18 18:27:41,082 - learning_rate: "5e-05" | |
| 2023-10-18 18:27:41,082 - mini_batch_size: "4" | |
| 2023-10-18 18:27:41,082 - max_epochs: "10" | |
| 2023-10-18 18:27:41,082 - shuffle: "True" | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Plugins: | |
| 2023-10-18 18:27:41,082 - TensorboardLogger | |
| 2023-10-18 18:27:41,082 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 18:27:41,082 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Computation: | |
| 2023-10-18 18:27:41,082 - compute on device: cuda:0 | |
| 2023-10-18 18:27:41,082 - embedding storage: none | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:41,082 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 18:27:42,484 epoch 1 - iter 89/894 - loss 3.41107969 - time (sec): 1.40 - samples/sec: 6802.89 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 18:27:43,913 epoch 1 - iter 178/894 - loss 3.19741479 - time (sec): 2.83 - samples/sec: 6532.72 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 18:27:45,319 epoch 1 - iter 267/894 - loss 2.75348000 - time (sec): 4.24 - samples/sec: 6457.95 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:27:46,746 epoch 1 - iter 356/894 - loss 2.35673844 - time (sec): 5.66 - samples/sec: 6272.25 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 18:27:48,216 epoch 1 - iter 445/894 - loss 2.02890086 - time (sec): 7.13 - samples/sec: 6222.55 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 18:27:49,617 epoch 1 - iter 534/894 - loss 1.80326419 - time (sec): 8.53 - samples/sec: 6177.43 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 18:27:50,993 epoch 1 - iter 623/894 - loss 1.64019919 - time (sec): 9.91 - samples/sec: 6186.33 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 18:27:52,383 epoch 1 - iter 712/894 - loss 1.51273727 - time (sec): 11.30 - samples/sec: 6159.43 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 18:27:53,785 epoch 1 - iter 801/894 - loss 1.41315171 - time (sec): 12.70 - samples/sec: 6135.25 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 18:27:55,152 epoch 1 - iter 890/894 - loss 1.33192532 - time (sec): 14.07 - samples/sec: 6118.99 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-18 18:27:55,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:55,214 EPOCH 1 done: loss 1.3270 - lr: 0.000050 | |
| 2023-10-18 18:27:57,145 DEV : loss 0.40020185708999634 - f1-score (micro avg) 0.0 | |
| 2023-10-18 18:27:57,170 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:27:58,590 epoch 2 - iter 89/894 - loss 0.49527024 - time (sec): 1.42 - samples/sec: 6831.62 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 18:28:00,298 epoch 2 - iter 178/894 - loss 0.48637380 - time (sec): 3.13 - samples/sec: 5980.55 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 18:28:01,706 epoch 2 - iter 267/894 - loss 0.46255258 - time (sec): 4.54 - samples/sec: 5969.96 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 18:28:02,986 epoch 2 - iter 356/894 - loss 0.44116644 - time (sec): 5.82 - samples/sec: 6121.42 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 18:28:04,229 epoch 2 - iter 445/894 - loss 0.43615971 - time (sec): 7.06 - samples/sec: 6164.56 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 18:28:05,541 epoch 2 - iter 534/894 - loss 0.43240093 - time (sec): 8.37 - samples/sec: 6180.42 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 18:28:06,934 epoch 2 - iter 623/894 - loss 0.43284058 - time (sec): 9.76 - samples/sec: 6234.01 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 18:28:08,295 epoch 2 - iter 712/894 - loss 0.43590184 - time (sec): 11.12 - samples/sec: 6248.52 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 18:28:09,693 epoch 2 - iter 801/894 - loss 0.43638346 - time (sec): 12.52 - samples/sec: 6210.86 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 18:28:11,075 epoch 2 - iter 890/894 - loss 0.43549143 - time (sec): 13.90 - samples/sec: 6204.71 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 18:28:11,132 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:11,132 EPOCH 2 done: loss 0.4358 - lr: 0.000044 | |
| 2023-10-18 18:28:16,010 DEV : loss 0.3361940383911133 - f1-score (micro avg) 0.2145 | |
| 2023-10-18 18:28:16,036 saving best model | |
| 2023-10-18 18:28:16,068 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:17,467 epoch 3 - iter 89/894 - loss 0.40109413 - time (sec): 1.40 - samples/sec: 6297.77 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 18:28:18,833 epoch 3 - iter 178/894 - loss 0.40822413 - time (sec): 2.76 - samples/sec: 6191.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 18:28:20,178 epoch 3 - iter 267/894 - loss 0.39533388 - time (sec): 4.11 - samples/sec: 6294.03 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 18:28:21,538 epoch 3 - iter 356/894 - loss 0.38348937 - time (sec): 5.47 - samples/sec: 6222.82 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 18:28:22,957 epoch 3 - iter 445/894 - loss 0.38947787 - time (sec): 6.89 - samples/sec: 6236.91 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 18:28:24,314 epoch 3 - iter 534/894 - loss 0.38207063 - time (sec): 8.25 - samples/sec: 6208.34 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 18:28:25,753 epoch 3 - iter 623/894 - loss 0.37655257 - time (sec): 9.68 - samples/sec: 6286.71 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 18:28:27,147 epoch 3 - iter 712/894 - loss 0.37547493 - time (sec): 11.08 - samples/sec: 6228.02 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 18:28:28,544 epoch 3 - iter 801/894 - loss 0.37667688 - time (sec): 12.48 - samples/sec: 6244.41 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 18:28:29,912 epoch 3 - iter 890/894 - loss 0.37253884 - time (sec): 13.84 - samples/sec: 6232.41 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 18:28:29,973 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:29,973 EPOCH 3 done: loss 0.3725 - lr: 0.000039 | |
| 2023-10-18 18:28:35,228 DEV : loss 0.3129556179046631 - f1-score (micro avg) 0.3398 | |
| 2023-10-18 18:28:35,254 saving best model | |
| 2023-10-18 18:28:35,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:36,535 epoch 4 - iter 89/894 - loss 0.31905254 - time (sec): 1.25 - samples/sec: 7257.23 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 18:28:37,917 epoch 4 - iter 178/894 - loss 0.31151319 - time (sec): 2.63 - samples/sec: 6761.27 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 18:28:39,330 epoch 4 - iter 267/894 - loss 0.31487409 - time (sec): 4.04 - samples/sec: 6779.46 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 18:28:40,725 epoch 4 - iter 356/894 - loss 0.32858231 - time (sec): 5.44 - samples/sec: 6680.54 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 18:28:42,103 epoch 4 - iter 445/894 - loss 0.32782339 - time (sec): 6.82 - samples/sec: 6476.42 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 18:28:43,488 epoch 4 - iter 534/894 - loss 0.33208690 - time (sec): 8.20 - samples/sec: 6503.13 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 18:28:44,842 epoch 4 - iter 623/894 - loss 0.33442800 - time (sec): 9.55 - samples/sec: 6431.29 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 18:28:46,190 epoch 4 - iter 712/894 - loss 0.33661458 - time (sec): 10.90 - samples/sec: 6393.71 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 18:28:47,572 epoch 4 - iter 801/894 - loss 0.33599717 - time (sec): 12.28 - samples/sec: 6338.63 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 18:28:48,953 epoch 4 - iter 890/894 - loss 0.33575512 - time (sec): 13.66 - samples/sec: 6306.29 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-18 18:28:49,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:49,015 EPOCH 4 done: loss 0.3357 - lr: 0.000033 | |
| 2023-10-18 18:28:54,302 DEV : loss 0.3030177354812622 - f1-score (micro avg) 0.3312 | |
| 2023-10-18 18:28:54,327 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:28:55,699 epoch 5 - iter 89/894 - loss 0.35702426 - time (sec): 1.37 - samples/sec: 5665.85 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-18 18:28:57,091 epoch 5 - iter 178/894 - loss 0.32420012 - time (sec): 2.76 - samples/sec: 5731.95 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 18:28:58,456 epoch 5 - iter 267/894 - loss 0.32031718 - time (sec): 4.13 - samples/sec: 5872.56 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 18:28:59,881 epoch 5 - iter 356/894 - loss 0.30064946 - time (sec): 5.55 - samples/sec: 6092.07 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 18:29:01,282 epoch 5 - iter 445/894 - loss 0.29561401 - time (sec): 6.95 - samples/sec: 6226.51 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 18:29:02,671 epoch 5 - iter 534/894 - loss 0.29665882 - time (sec): 8.34 - samples/sec: 6312.81 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 18:29:03,937 epoch 5 - iter 623/894 - loss 0.29657716 - time (sec): 9.61 - samples/sec: 6344.01 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 18:29:05,320 epoch 5 - iter 712/894 - loss 0.30045153 - time (sec): 10.99 - samples/sec: 6292.58 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 18:29:06,719 epoch 5 - iter 801/894 - loss 0.30113299 - time (sec): 12.39 - samples/sec: 6267.79 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 18:29:08,105 epoch 5 - iter 890/894 - loss 0.30518006 - time (sec): 13.78 - samples/sec: 6262.12 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 18:29:08,167 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:08,167 EPOCH 5 done: loss 0.3047 - lr: 0.000028 | |
| 2023-10-18 18:29:13,478 DEV : loss 0.30577316880226135 - f1-score (micro avg) 0.3593 | |
| 2023-10-18 18:29:13,504 saving best model | |
| 2023-10-18 18:29:13,542 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:14,955 epoch 6 - iter 89/894 - loss 0.26832203 - time (sec): 1.41 - samples/sec: 6075.82 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:29:16,377 epoch 6 - iter 178/894 - loss 0.28611994 - time (sec): 2.83 - samples/sec: 6127.23 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:29:17,827 epoch 6 - iter 267/894 - loss 0.28634822 - time (sec): 4.28 - samples/sec: 6356.47 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 18:29:19,184 epoch 6 - iter 356/894 - loss 0.28936804 - time (sec): 5.64 - samples/sec: 6304.55 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 18:29:20,590 epoch 6 - iter 445/894 - loss 0.29315417 - time (sec): 7.05 - samples/sec: 6235.92 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 18:29:21,923 epoch 6 - iter 534/894 - loss 0.28966787 - time (sec): 8.38 - samples/sec: 6153.24 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:29:23,326 epoch 6 - iter 623/894 - loss 0.28961136 - time (sec): 9.78 - samples/sec: 6163.56 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:29:24,707 epoch 6 - iter 712/894 - loss 0.28874325 - time (sec): 11.16 - samples/sec: 6158.15 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 18:29:26,073 epoch 6 - iter 801/894 - loss 0.29000085 - time (sec): 12.53 - samples/sec: 6181.58 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 18:29:27,468 epoch 6 - iter 890/894 - loss 0.28502336 - time (sec): 13.93 - samples/sec: 6190.45 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 18:29:27,527 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:27,528 EPOCH 6 done: loss 0.2842 - lr: 0.000022 | |
| 2023-10-18 18:29:32,498 DEV : loss 0.3079672157764435 - f1-score (micro avg) 0.3617 | |
| 2023-10-18 18:29:32,523 saving best model | |
| 2023-10-18 18:29:32,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:33,944 epoch 7 - iter 89/894 - loss 0.29011633 - time (sec): 1.39 - samples/sec: 6127.79 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 18:29:35,340 epoch 7 - iter 178/894 - loss 0.26920405 - time (sec): 2.78 - samples/sec: 6027.29 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:29:36,651 epoch 7 - iter 267/894 - loss 0.26706714 - time (sec): 4.10 - samples/sec: 6065.90 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:29:37,901 epoch 7 - iter 356/894 - loss 0.26434876 - time (sec): 5.34 - samples/sec: 6391.15 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 18:29:39,252 epoch 7 - iter 445/894 - loss 0.26500313 - time (sec): 6.70 - samples/sec: 6422.62 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 18:29:40,624 epoch 7 - iter 534/894 - loss 0.26000296 - time (sec): 8.07 - samples/sec: 6428.25 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 18:29:42,006 epoch 7 - iter 623/894 - loss 0.26918289 - time (sec): 9.45 - samples/sec: 6401.06 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:29:43,758 epoch 7 - iter 712/894 - loss 0.26880946 - time (sec): 11.20 - samples/sec: 6224.17 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:29:45,150 epoch 7 - iter 801/894 - loss 0.26969539 - time (sec): 12.59 - samples/sec: 6194.44 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 18:29:46,539 epoch 7 - iter 890/894 - loss 0.26911572 - time (sec): 13.98 - samples/sec: 6159.93 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 18:29:46,605 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:46,605 EPOCH 7 done: loss 0.2683 - lr: 0.000017 | |
| 2023-10-18 18:29:51,592 DEV : loss 0.30530446767807007 - f1-score (micro avg) 0.3729 | |
| 2023-10-18 18:29:51,618 saving best model | |
| 2023-10-18 18:29:51,658 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:29:53,038 epoch 8 - iter 89/894 - loss 0.27926806 - time (sec): 1.38 - samples/sec: 6199.09 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 18:29:54,406 epoch 8 - iter 178/894 - loss 0.26615970 - time (sec): 2.75 - samples/sec: 6182.68 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 18:29:55,792 epoch 8 - iter 267/894 - loss 0.27250183 - time (sec): 4.13 - samples/sec: 6266.44 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:29:57,067 epoch 8 - iter 356/894 - loss 0.27294376 - time (sec): 5.41 - samples/sec: 6418.59 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 18:29:58,310 epoch 8 - iter 445/894 - loss 0.26958943 - time (sec): 6.65 - samples/sec: 6509.10 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 18:29:59,586 epoch 8 - iter 534/894 - loss 0.26501812 - time (sec): 7.93 - samples/sec: 6698.31 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 18:30:00,903 epoch 8 - iter 623/894 - loss 0.26337124 - time (sec): 9.24 - samples/sec: 6602.18 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 18:30:02,303 epoch 8 - iter 712/894 - loss 0.26398454 - time (sec): 10.64 - samples/sec: 6548.88 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:30:03,695 epoch 8 - iter 801/894 - loss 0.25847704 - time (sec): 12.04 - samples/sec: 6556.75 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:30:05,051 epoch 8 - iter 890/894 - loss 0.26097250 - time (sec): 13.39 - samples/sec: 6438.89 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 18:30:05,107 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:05,107 EPOCH 8 done: loss 0.2606 - lr: 0.000011 | |
| 2023-10-18 18:30:10,376 DEV : loss 0.3058369755744934 - f1-score (micro avg) 0.3789 | |
| 2023-10-18 18:30:10,402 saving best model | |
| 2023-10-18 18:30:10,438 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:11,818 epoch 9 - iter 89/894 - loss 0.22849598 - time (sec): 1.38 - samples/sec: 5809.18 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 18:30:13,259 epoch 9 - iter 178/894 - loss 0.25523926 - time (sec): 2.82 - samples/sec: 6331.01 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 18:30:14,625 epoch 9 - iter 267/894 - loss 0.27346974 - time (sec): 4.19 - samples/sec: 6288.83 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:30:16,020 epoch 9 - iter 356/894 - loss 0.26469584 - time (sec): 5.58 - samples/sec: 6259.18 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:30:17,401 epoch 9 - iter 445/894 - loss 0.26281820 - time (sec): 6.96 - samples/sec: 6183.94 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 18:30:18,773 epoch 9 - iter 534/894 - loss 0.25909388 - time (sec): 8.33 - samples/sec: 6321.42 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 18:30:20,014 epoch 9 - iter 623/894 - loss 0.25428350 - time (sec): 9.58 - samples/sec: 6435.17 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 18:30:21,348 epoch 9 - iter 712/894 - loss 0.25478754 - time (sec): 10.91 - samples/sec: 6395.98 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 18:30:22,731 epoch 9 - iter 801/894 - loss 0.25297570 - time (sec): 12.29 - samples/sec: 6370.94 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:30:24,086 epoch 9 - iter 890/894 - loss 0.25061435 - time (sec): 13.65 - samples/sec: 6326.55 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:30:24,142 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:24,142 EPOCH 9 done: loss 0.2509 - lr: 0.000006 | |
| 2023-10-18 18:30:29,469 DEV : loss 0.310301274061203 - f1-score (micro avg) 0.3822 | |
| 2023-10-18 18:30:29,497 saving best model | |
| 2023-10-18 18:30:29,537 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:30,976 epoch 10 - iter 89/894 - loss 0.20663355 - time (sec): 1.44 - samples/sec: 6219.17 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 18:30:32,338 epoch 10 - iter 178/894 - loss 0.21406280 - time (sec): 2.80 - samples/sec: 6257.50 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 18:30:33,664 epoch 10 - iter 267/894 - loss 0.20949232 - time (sec): 4.13 - samples/sec: 6102.03 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 18:30:35,048 epoch 10 - iter 356/894 - loss 0.22041080 - time (sec): 5.51 - samples/sec: 6045.24 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:30:36,427 epoch 10 - iter 445/894 - loss 0.22589832 - time (sec): 6.89 - samples/sec: 6029.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:30:37,802 epoch 10 - iter 534/894 - loss 0.23045096 - time (sec): 8.26 - samples/sec: 6010.35 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 18:30:39,178 epoch 10 - iter 623/894 - loss 0.23335194 - time (sec): 9.64 - samples/sec: 6024.46 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 18:30:40,601 epoch 10 - iter 712/894 - loss 0.23654913 - time (sec): 11.06 - samples/sec: 6101.95 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 18:30:42,027 epoch 10 - iter 801/894 - loss 0.23561267 - time (sec): 12.49 - samples/sec: 6217.60 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 18:30:43,401 epoch 10 - iter 890/894 - loss 0.24226094 - time (sec): 13.86 - samples/sec: 6220.52 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 18:30:43,458 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:43,458 EPOCH 10 done: loss 0.2425 - lr: 0.000000 | |
| 2023-10-18 18:30:48,847 DEV : loss 0.3040592074394226 - f1-score (micro avg) 0.3858 | |
| 2023-10-18 18:30:48,871 saving best model | |
| 2023-10-18 18:30:48,931 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:30:48,931 Loading model from best epoch ... | |
| 2023-10-18 18:30:49,004 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 | |
| 2023-10-18 18:30:50,932 | |
| Results: | |
| - F-score (micro) 0.3766 | |
| - F-score (macro) 0.1915 | |
| - Accuracy 0.2454 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.5280 0.5688 0.5477 596 | |
| pers 0.1922 0.2943 0.2325 333 | |
| org 0.0000 0.0000 0.0000 132 | |
| time 0.2333 0.1429 0.1772 49 | |
| prod 0.0000 0.0000 0.0000 66 | |
| micro avg 0.3756 0.3776 0.3766 1176 | |
| macro avg 0.1907 0.2012 0.1915 1176 | |
| weighted avg 0.3317 0.3776 0.3508 1176 | |
| 2023-10-18 18:30:50,932 ---------------------------------------------------------------------------------------------------- | |