| 2023-10-18 18:00:28,510 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 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 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 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 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 Train: 3575 sentences | |
| 2023-10-18 18:00:28,511 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 Training Params: | |
| 2023-10-18 18:00:28,511 - learning_rate: "3e-05" | |
| 2023-10-18 18:00:28,511 - mini_batch_size: "4" | |
| 2023-10-18 18:00:28,511 - max_epochs: "10" | |
| 2023-10-18 18:00:28,511 - shuffle: "True" | |
| 2023-10-18 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 Plugins: | |
| 2023-10-18 18:00:28,511 - TensorboardLogger | |
| 2023-10-18 18:00:28,511 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 18:00:28,511 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 18:00:28,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,511 Computation: | |
| 2023-10-18 18:00:28,512 - compute on device: cuda:0 | |
| 2023-10-18 18:00:28,512 - embedding storage: none | |
| 2023-10-18 18:00:28,512 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,512 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-18 18:00:28,512 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,512 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:28,512 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 18:00:29,842 epoch 1 - iter 89/894 - loss 3.47720738 - time (sec): 1.33 - samples/sec: 6076.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:00:31,074 epoch 1 - iter 178/894 - loss 3.26012265 - time (sec): 2.56 - samples/sec: 6404.36 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:00:32,466 epoch 1 - iter 267/894 - loss 2.94964775 - time (sec): 3.95 - samples/sec: 6442.77 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:00:33,867 epoch 1 - iter 356/894 - loss 2.55034837 - time (sec): 5.36 - samples/sec: 6441.75 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:00:35,262 epoch 1 - iter 445/894 - loss 2.22532146 - time (sec): 6.75 - samples/sec: 6366.77 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:00:36,638 epoch 1 - iter 534/894 - loss 1.98044920 - time (sec): 8.13 - samples/sec: 6274.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:00:38,008 epoch 1 - iter 623/894 - loss 1.78776894 - time (sec): 9.50 - samples/sec: 6241.02 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:00:39,396 epoch 1 - iter 712/894 - loss 1.63136830 - time (sec): 10.88 - samples/sec: 6265.61 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:00:40,838 epoch 1 - iter 801/894 - loss 1.50892338 - time (sec): 12.33 - samples/sec: 6302.71 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:00:42,211 epoch 1 - iter 890/894 - loss 1.41796507 - time (sec): 13.70 - samples/sec: 6288.61 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 18:00:42,272 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:42,272 EPOCH 1 done: loss 1.4167 - lr: 0.000030 | |
| 2023-10-18 18:00:44,511 DEV : loss 0.46221593022346497 - f1-score (micro avg) 0.0 | |
| 2023-10-18 18:00:44,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:45,908 epoch 2 - iter 89/894 - loss 0.53965102 - time (sec): 1.37 - samples/sec: 6473.76 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 18:00:47,295 epoch 2 - iter 178/894 - loss 0.53998811 - time (sec): 2.76 - samples/sec: 6299.09 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 18:00:48,666 epoch 2 - iter 267/894 - loss 0.53762330 - time (sec): 4.13 - samples/sec: 6199.42 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 18:00:50,051 epoch 2 - iter 356/894 - loss 0.53608027 - time (sec): 5.52 - samples/sec: 6099.51 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 18:00:51,436 epoch 2 - iter 445/894 - loss 0.53380079 - time (sec): 6.90 - samples/sec: 6092.46 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 18:00:52,845 epoch 2 - iter 534/894 - loss 0.51793174 - time (sec): 8.31 - samples/sec: 6117.45 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 18:00:54,238 epoch 2 - iter 623/894 - loss 0.51806145 - time (sec): 9.70 - samples/sec: 6078.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 18:00:55,547 epoch 2 - iter 712/894 - loss 0.50629182 - time (sec): 11.01 - samples/sec: 6243.33 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:00:56,887 epoch 2 - iter 801/894 - loss 0.50500686 - time (sec): 12.35 - samples/sec: 6297.13 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:00:58,286 epoch 2 - iter 890/894 - loss 0.49779972 - time (sec): 13.75 - samples/sec: 6275.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 18:00:58,341 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:00:58,341 EPOCH 2 done: loss 0.4984 - lr: 0.000027 | |
| 2023-10-18 18:01:03,629 DEV : loss 0.36310797929763794 - f1-score (micro avg) 0.0659 | |
| 2023-10-18 18:01:03,656 saving best model | |
| 2023-10-18 18:01:03,691 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:05,140 epoch 3 - iter 89/894 - loss 0.46261754 - time (sec): 1.45 - samples/sec: 5713.97 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 18:01:06,556 epoch 3 - iter 178/894 - loss 0.48194337 - time (sec): 2.86 - samples/sec: 5973.79 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 18:01:07,954 epoch 3 - iter 267/894 - loss 0.46562612 - time (sec): 4.26 - samples/sec: 6198.53 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 18:01:09,365 epoch 3 - iter 356/894 - loss 0.46102644 - time (sec): 5.67 - samples/sec: 6220.14 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 18:01:10,727 epoch 3 - iter 445/894 - loss 0.45309118 - time (sec): 7.04 - samples/sec: 6213.32 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 18:01:12,120 epoch 3 - iter 534/894 - loss 0.43617221 - time (sec): 8.43 - samples/sec: 6233.77 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 18:01:13,497 epoch 3 - iter 623/894 - loss 0.42980845 - time (sec): 9.81 - samples/sec: 6237.84 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:01:14,859 epoch 3 - iter 712/894 - loss 0.42508549 - time (sec): 11.17 - samples/sec: 6196.81 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:01:16,272 epoch 3 - iter 801/894 - loss 0.42413621 - time (sec): 12.58 - samples/sec: 6195.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 18:01:17,657 epoch 3 - iter 890/894 - loss 0.42143294 - time (sec): 13.97 - samples/sec: 6165.33 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 18:01:17,715 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:17,716 EPOCH 3 done: loss 0.4214 - lr: 0.000023 | |
| 2023-10-18 18:01:23,002 DEV : loss 0.34216511249542236 - f1-score (micro avg) 0.2547 | |
| 2023-10-18 18:01:23,028 saving best model | |
| 2023-10-18 18:01:23,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:24,460 epoch 4 - iter 89/894 - loss 0.38257387 - time (sec): 1.40 - samples/sec: 6145.77 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 18:01:25,846 epoch 4 - iter 178/894 - loss 0.41047799 - time (sec): 2.78 - samples/sec: 6227.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 18:01:27,219 epoch 4 - iter 267/894 - loss 0.40657509 - time (sec): 4.16 - samples/sec: 6293.75 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 18:01:28,618 epoch 4 - iter 356/894 - loss 0.38753137 - time (sec): 5.56 - samples/sec: 6387.97 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 18:01:30,013 epoch 4 - iter 445/894 - loss 0.38928001 - time (sec): 6.95 - samples/sec: 6490.07 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 18:01:31,419 epoch 4 - iter 534/894 - loss 0.39281104 - time (sec): 8.36 - samples/sec: 6339.34 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:01:32,780 epoch 4 - iter 623/894 - loss 0.38261370 - time (sec): 9.72 - samples/sec: 6331.61 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:01:34,156 epoch 4 - iter 712/894 - loss 0.38588466 - time (sec): 11.09 - samples/sec: 6292.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 18:01:35,451 epoch 4 - iter 801/894 - loss 0.38455298 - time (sec): 12.39 - samples/sec: 6253.02 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 18:01:36,706 epoch 4 - iter 890/894 - loss 0.38059774 - time (sec): 13.64 - samples/sec: 6323.32 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 18:01:36,760 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:36,760 EPOCH 4 done: loss 0.3807 - lr: 0.000020 | |
| 2023-10-18 18:01:41,760 DEV : loss 0.33357590436935425 - f1-score (micro avg) 0.2831 | |
| 2023-10-18 18:01:41,786 saving best model | |
| 2023-10-18 18:01:41,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:43,066 epoch 5 - iter 89/894 - loss 0.36835419 - time (sec): 1.24 - samples/sec: 6812.86 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 18:01:44,652 epoch 5 - iter 178/894 - loss 0.36526170 - time (sec): 2.83 - samples/sec: 6471.45 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 18:01:46,113 epoch 5 - iter 267/894 - loss 0.36494379 - time (sec): 4.29 - samples/sec: 6370.54 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 18:01:47,503 epoch 5 - iter 356/894 - loss 0.36282400 - time (sec): 5.68 - samples/sec: 6281.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 18:01:48,808 epoch 5 - iter 445/894 - loss 0.36785318 - time (sec): 6.98 - samples/sec: 6253.29 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:01:50,333 epoch 5 - iter 534/894 - loss 0.36650001 - time (sec): 8.51 - samples/sec: 6099.75 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:01:51,703 epoch 5 - iter 623/894 - loss 0.36490601 - time (sec): 9.88 - samples/sec: 6137.93 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 18:01:53,130 epoch 5 - iter 712/894 - loss 0.36466791 - time (sec): 11.31 - samples/sec: 6171.94 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 18:01:54,542 epoch 5 - iter 801/894 - loss 0.36141892 - time (sec): 12.72 - samples/sec: 6147.71 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 18:01:55,971 epoch 5 - iter 890/894 - loss 0.35848906 - time (sec): 14.15 - samples/sec: 6095.21 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 18:01:56,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:01:56,030 EPOCH 5 done: loss 0.3583 - lr: 0.000017 | |
| 2023-10-18 18:02:01,024 DEV : loss 0.3251766562461853 - f1-score (micro avg) 0.3029 | |
| 2023-10-18 18:02:01,050 saving best model | |
| 2023-10-18 18:02:01,083 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:02,492 epoch 6 - iter 89/894 - loss 0.29911401 - time (sec): 1.41 - samples/sec: 6589.86 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 18:02:03,865 epoch 6 - iter 178/894 - loss 0.33016547 - time (sec): 2.78 - samples/sec: 6372.59 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 18:02:05,251 epoch 6 - iter 267/894 - loss 0.35328330 - time (sec): 4.17 - samples/sec: 6238.38 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 18:02:06,633 epoch 6 - iter 356/894 - loss 0.35220783 - time (sec): 5.55 - samples/sec: 6233.65 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:02:08,026 epoch 6 - iter 445/894 - loss 0.35655484 - time (sec): 6.94 - samples/sec: 6290.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:02:09,414 epoch 6 - iter 534/894 - loss 0.35239010 - time (sec): 8.33 - samples/sec: 6249.98 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 18:02:10,804 epoch 6 - iter 623/894 - loss 0.34528875 - time (sec): 9.72 - samples/sec: 6207.28 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 18:02:12,183 epoch 6 - iter 712/894 - loss 0.34025091 - time (sec): 11.10 - samples/sec: 6210.97 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 18:02:13,577 epoch 6 - iter 801/894 - loss 0.33584252 - time (sec): 12.49 - samples/sec: 6224.43 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 18:02:14,955 epoch 6 - iter 890/894 - loss 0.34022539 - time (sec): 13.87 - samples/sec: 6210.36 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 18:02:15,018 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:15,018 EPOCH 6 done: loss 0.3399 - lr: 0.000013 | |
| 2023-10-18 18:02:20,353 DEV : loss 0.32095086574554443 - f1-score (micro avg) 0.3121 | |
| 2023-10-18 18:02:20,379 saving best model | |
| 2023-10-18 18:02:20,414 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:21,792 epoch 7 - iter 89/894 - loss 0.29036338 - time (sec): 1.38 - samples/sec: 5916.59 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 18:02:23,232 epoch 7 - iter 178/894 - loss 0.32315512 - time (sec): 2.82 - samples/sec: 6279.32 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 18:02:24,652 epoch 7 - iter 267/894 - loss 0.32199177 - time (sec): 4.24 - samples/sec: 6133.97 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:02:26,089 epoch 7 - iter 356/894 - loss 0.31963448 - time (sec): 5.67 - samples/sec: 6344.48 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:02:27,455 epoch 7 - iter 445/894 - loss 0.32435811 - time (sec): 7.04 - samples/sec: 6307.25 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 18:02:28,909 epoch 7 - iter 534/894 - loss 0.32202630 - time (sec): 8.49 - samples/sec: 6337.39 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 18:02:30,284 epoch 7 - iter 623/894 - loss 0.31985686 - time (sec): 9.87 - samples/sec: 6234.95 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 18:02:31,679 epoch 7 - iter 712/894 - loss 0.32618461 - time (sec): 11.26 - samples/sec: 6240.32 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 18:02:33,026 epoch 7 - iter 801/894 - loss 0.32697320 - time (sec): 12.61 - samples/sec: 6189.31 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 18:02:34,430 epoch 7 - iter 890/894 - loss 0.32816588 - time (sec): 14.02 - samples/sec: 6146.80 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 18:02:34,490 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:34,490 EPOCH 7 done: loss 0.3275 - lr: 0.000010 | |
| 2023-10-18 18:02:39,856 DEV : loss 0.3155861496925354 - f1-score (micro avg) 0.3204 | |
| 2023-10-18 18:02:39,883 saving best model | |
| 2023-10-18 18:02:39,923 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:41,289 epoch 8 - iter 89/894 - loss 0.29543599 - time (sec): 1.37 - samples/sec: 5810.43 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 18:02:42,643 epoch 8 - iter 178/894 - loss 0.30056323 - time (sec): 2.72 - samples/sec: 5629.53 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:02:44,023 epoch 8 - iter 267/894 - loss 0.30791330 - time (sec): 4.10 - samples/sec: 5858.01 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:02:45,424 epoch 8 - iter 356/894 - loss 0.32106558 - time (sec): 5.50 - samples/sec: 5892.48 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 18:02:46,790 epoch 8 - iter 445/894 - loss 0.31239277 - time (sec): 6.87 - samples/sec: 5886.26 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 18:02:48,201 epoch 8 - iter 534/894 - loss 0.31223381 - time (sec): 8.28 - samples/sec: 5855.44 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 18:02:49,694 epoch 8 - iter 623/894 - loss 0.30739347 - time (sec): 9.77 - samples/sec: 5953.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 18:02:51,271 epoch 8 - iter 712/894 - loss 0.31585638 - time (sec): 11.35 - samples/sec: 5965.33 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 18:02:52,694 epoch 8 - iter 801/894 - loss 0.31590622 - time (sec): 12.77 - samples/sec: 5942.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 18:02:54,107 epoch 8 - iter 890/894 - loss 0.31458767 - time (sec): 14.18 - samples/sec: 6001.79 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 18:02:54,198 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:02:54,198 EPOCH 8 done: loss 0.3137 - lr: 0.000007 | |
| 2023-10-18 18:02:59,584 DEV : loss 0.3094746768474579 - f1-score (micro avg) 0.3213 | |
| 2023-10-18 18:02:59,611 saving best model | |
| 2023-10-18 18:02:59,650 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:03:01,115 epoch 9 - iter 89/894 - loss 0.33597402 - time (sec): 1.47 - samples/sec: 6725.14 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:03:02,484 epoch 9 - iter 178/894 - loss 0.34653954 - time (sec): 2.83 - samples/sec: 6500.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:03:03,748 epoch 9 - iter 267/894 - loss 0.33458364 - time (sec): 4.10 - samples/sec: 6705.02 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 18:03:04,977 epoch 9 - iter 356/894 - loss 0.33027321 - time (sec): 5.33 - samples/sec: 6569.42 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 18:03:06,220 epoch 9 - iter 445/894 - loss 0.31343385 - time (sec): 6.57 - samples/sec: 6604.81 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 18:03:07,466 epoch 9 - iter 534/894 - loss 0.32342682 - time (sec): 7.82 - samples/sec: 6658.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 18:03:08,806 epoch 9 - iter 623/894 - loss 0.31647783 - time (sec): 9.16 - samples/sec: 6601.37 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 18:03:10,198 epoch 9 - iter 712/894 - loss 0.31201076 - time (sec): 10.55 - samples/sec: 6552.60 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 18:03:11,583 epoch 9 - iter 801/894 - loss 0.30997413 - time (sec): 11.93 - samples/sec: 6503.82 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 18:03:12,987 epoch 9 - iter 890/894 - loss 0.31007472 - time (sec): 13.34 - samples/sec: 6456.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:03:13,055 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:03:13,055 EPOCH 9 done: loss 0.3113 - lr: 0.000003 | |
| 2023-10-18 18:03:18,075 DEV : loss 0.313385546207428 - f1-score (micro avg) 0.3291 | |
| 2023-10-18 18:03:18,103 saving best model | |
| 2023-10-18 18:03:18,134 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:03:19,534 epoch 10 - iter 89/894 - loss 0.33123978 - time (sec): 1.40 - samples/sec: 6376.22 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:03:20,922 epoch 10 - iter 178/894 - loss 0.33004373 - time (sec): 2.79 - samples/sec: 6381.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 18:03:22,281 epoch 10 - iter 267/894 - loss 0.31823562 - time (sec): 4.15 - samples/sec: 6234.71 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 18:03:23,648 epoch 10 - iter 356/894 - loss 0.32311896 - time (sec): 5.51 - samples/sec: 6115.74 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 18:03:25,371 epoch 10 - iter 445/894 - loss 0.32122107 - time (sec): 7.24 - samples/sec: 5912.86 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 18:03:26,701 epoch 10 - iter 534/894 - loss 0.31637427 - time (sec): 8.57 - samples/sec: 5920.11 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 18:03:28,124 epoch 10 - iter 623/894 - loss 0.30980662 - time (sec): 9.99 - samples/sec: 5999.17 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 18:03:29,517 epoch 10 - iter 712/894 - loss 0.30583933 - time (sec): 11.38 - samples/sec: 6044.37 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 18:03:30,833 epoch 10 - iter 801/894 - loss 0.30618552 - time (sec): 12.70 - samples/sec: 6098.80 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 18:03:32,243 epoch 10 - iter 890/894 - loss 0.30716566 - time (sec): 14.11 - samples/sec: 6110.70 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 18:03:32,301 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:03:32,301 EPOCH 10 done: loss 0.3067 - lr: 0.000000 | |
| 2023-10-18 18:03:37,341 DEV : loss 0.3104316294193268 - f1-score (micro avg) 0.3269 | |
| 2023-10-18 18:03:37,398 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 18:03:37,399 Loading model from best epoch ... | |
| 2023-10-18 18:03:37,476 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 18:03:39,816 | |
| Results: | |
| - F-score (micro) 0.3144 | |
| - F-score (macro) 0.1225 | |
| - Accuracy 0.1974 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.4540 0.5050 0.4782 596 | |
| pers 0.1281 0.1411 0.1343 333 | |
| org 0.0000 0.0000 0.0000 132 | |
| prod 0.0000 0.0000 0.0000 66 | |
| time 0.0000 0.0000 0.0000 49 | |
| micro avg 0.3353 0.2959 0.3144 1176 | |
| macro avg 0.1164 0.1292 0.1225 1176 | |
| weighted avg 0.2664 0.2959 0.2804 1176 | |
| 2023-10-18 18:03:39,816 ---------------------------------------------------------------------------------------------------- | |