| 2023-10-13 09:01:06,799 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,800 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (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): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (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): BertSelfOutput( | |
| (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): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-13 09:01:06,800 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,800 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-13 09:01:06,800 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,800 Train: 1214 sentences | |
| 2023-10-13 09:01:06,800 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 Training Params: | |
| 2023-10-13 09:01:06,801 - learning_rate: "3e-05" | |
| 2023-10-13 09:01:06,801 - mini_batch_size: "4" | |
| 2023-10-13 09:01:06,801 - max_epochs: "10" | |
| 2023-10-13 09:01:06,801 - shuffle: "True" | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 Plugins: | |
| 2023-10-13 09:01:06,801 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 09:01:06,801 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 Computation: | |
| 2023-10-13 09:01:06,801 - compute on device: cuda:0 | |
| 2023-10-13 09:01:06,801 - embedding storage: none | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:06,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:09,388 epoch 1 - iter 30/304 - loss 3.40050317 - time (sec): 2.59 - samples/sec: 1251.05 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:01:10,711 epoch 1 - iter 60/304 - loss 2.96319610 - time (sec): 3.91 - samples/sec: 1632.20 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:01:12,024 epoch 1 - iter 90/304 - loss 2.22978533 - time (sec): 5.22 - samples/sec: 1862.60 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:01:13,349 epoch 1 - iter 120/304 - loss 1.85975330 - time (sec): 6.55 - samples/sec: 1964.06 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:01:14,660 epoch 1 - iter 150/304 - loss 1.61169959 - time (sec): 7.86 - samples/sec: 2023.66 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:01:15,984 epoch 1 - iter 180/304 - loss 1.44135127 - time (sec): 9.18 - samples/sec: 2031.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:01:17,331 epoch 1 - iter 210/304 - loss 1.27621715 - time (sec): 10.53 - samples/sec: 2080.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:01:18,640 epoch 1 - iter 240/304 - loss 1.16340234 - time (sec): 11.84 - samples/sec: 2093.13 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:01:19,960 epoch 1 - iter 270/304 - loss 1.07642680 - time (sec): 13.16 - samples/sec: 2095.69 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:01:21,268 epoch 1 - iter 300/304 - loss 0.99624251 - time (sec): 14.47 - samples/sec: 2117.14 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:01:21,446 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:21,446 EPOCH 1 done: loss 0.9872 - lr: 0.000030 | |
| 2023-10-13 09:01:22,377 DEV : loss 0.23720592260360718 - f1-score (micro avg) 0.5167 | |
| 2023-10-13 09:01:22,385 saving best model | |
| 2023-10-13 09:01:22,860 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:24,176 epoch 2 - iter 30/304 - loss 0.22148770 - time (sec): 1.31 - samples/sec: 2349.65 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:01:25,466 epoch 2 - iter 60/304 - loss 0.22348749 - time (sec): 2.61 - samples/sec: 2298.63 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:01:26,798 epoch 2 - iter 90/304 - loss 0.18914858 - time (sec): 3.94 - samples/sec: 2342.72 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:01:28,112 epoch 2 - iter 120/304 - loss 0.18052355 - time (sec): 5.25 - samples/sec: 2299.33 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:01:29,443 epoch 2 - iter 150/304 - loss 0.16611600 - time (sec): 6.58 - samples/sec: 2338.04 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:01:30,751 epoch 2 - iter 180/304 - loss 0.16059345 - time (sec): 7.89 - samples/sec: 2345.81 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:01:32,049 epoch 2 - iter 210/304 - loss 0.16048340 - time (sec): 9.19 - samples/sec: 2373.92 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:01:33,373 epoch 2 - iter 240/304 - loss 0.16403089 - time (sec): 10.51 - samples/sec: 2351.52 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:01:34,693 epoch 2 - iter 270/304 - loss 0.16086139 - time (sec): 11.83 - samples/sec: 2326.24 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:01:36,172 epoch 2 - iter 300/304 - loss 0.15317695 - time (sec): 13.31 - samples/sec: 2309.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:01:36,342 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:36,342 EPOCH 2 done: loss 0.1529 - lr: 0.000027 | |
| 2023-10-13 09:01:37,237 DEV : loss 0.15026724338531494 - f1-score (micro avg) 0.7944 | |
| 2023-10-13 09:01:37,243 saving best model | |
| 2023-10-13 09:01:37,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:39,162 epoch 3 - iter 30/304 - loss 0.05069063 - time (sec): 1.34 - samples/sec: 2247.73 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:01:40,491 epoch 3 - iter 60/304 - loss 0.07144414 - time (sec): 2.67 - samples/sec: 2275.43 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:01:41,843 epoch 3 - iter 90/304 - loss 0.08697225 - time (sec): 4.02 - samples/sec: 2244.13 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:01:43,163 epoch 3 - iter 120/304 - loss 0.08548438 - time (sec): 5.34 - samples/sec: 2263.70 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:01:44,459 epoch 3 - iter 150/304 - loss 0.09596620 - time (sec): 6.64 - samples/sec: 2257.80 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:01:45,799 epoch 3 - iter 180/304 - loss 0.09258520 - time (sec): 7.98 - samples/sec: 2263.59 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:01:47,150 epoch 3 - iter 210/304 - loss 0.09448288 - time (sec): 9.33 - samples/sec: 2308.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:01:48,486 epoch 3 - iter 240/304 - loss 0.09343742 - time (sec): 10.66 - samples/sec: 2311.57 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:01:49,829 epoch 3 - iter 270/304 - loss 0.08885765 - time (sec): 12.01 - samples/sec: 2291.17 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:01:51,136 epoch 3 - iter 300/304 - loss 0.08661682 - time (sec): 13.31 - samples/sec: 2304.60 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:01:51,311 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:51,311 EPOCH 3 done: loss 0.0888 - lr: 0.000023 | |
| 2023-10-13 09:01:52,211 DEV : loss 0.15172874927520752 - f1-score (micro avg) 0.8237 | |
| 2023-10-13 09:01:52,217 saving best model | |
| 2023-10-13 09:01:52,889 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:01:54,170 epoch 4 - iter 30/304 - loss 0.02760543 - time (sec): 1.28 - samples/sec: 2355.48 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:01:55,450 epoch 4 - iter 60/304 - loss 0.07114577 - time (sec): 2.56 - samples/sec: 2394.31 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:01:56,721 epoch 4 - iter 90/304 - loss 0.06279818 - time (sec): 3.83 - samples/sec: 2403.52 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:01:57,979 epoch 4 - iter 120/304 - loss 0.06289064 - time (sec): 5.09 - samples/sec: 2393.63 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:01:59,329 epoch 4 - iter 150/304 - loss 0.06413469 - time (sec): 6.44 - samples/sec: 2343.87 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:02:00,651 epoch 4 - iter 180/304 - loss 0.06212759 - time (sec): 7.76 - samples/sec: 2348.66 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:02:01,975 epoch 4 - iter 210/304 - loss 0.06043917 - time (sec): 9.08 - samples/sec: 2338.99 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:02:03,288 epoch 4 - iter 240/304 - loss 0.05862333 - time (sec): 10.40 - samples/sec: 2316.68 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:02:04,621 epoch 4 - iter 270/304 - loss 0.05843536 - time (sec): 11.73 - samples/sec: 2342.41 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:02:05,974 epoch 4 - iter 300/304 - loss 0.06313090 - time (sec): 13.08 - samples/sec: 2339.82 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:02:06,147 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:06,147 EPOCH 4 done: loss 0.0634 - lr: 0.000020 | |
| 2023-10-13 09:02:07,070 DEV : loss 0.17067818343639374 - f1-score (micro avg) 0.8197 | |
| 2023-10-13 09:02:07,076 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:08,401 epoch 5 - iter 30/304 - loss 0.05422141 - time (sec): 1.32 - samples/sec: 2519.92 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:02:09,802 epoch 5 - iter 60/304 - loss 0.04545324 - time (sec): 2.72 - samples/sec: 2265.69 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:02:11,131 epoch 5 - iter 90/304 - loss 0.04471901 - time (sec): 4.05 - samples/sec: 2336.17 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:02:12,410 epoch 5 - iter 120/304 - loss 0.04286872 - time (sec): 5.33 - samples/sec: 2356.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:02:13,676 epoch 5 - iter 150/304 - loss 0.04197271 - time (sec): 6.60 - samples/sec: 2353.98 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:02:15,016 epoch 5 - iter 180/304 - loss 0.04147644 - time (sec): 7.94 - samples/sec: 2351.34 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:02:16,355 epoch 5 - iter 210/304 - loss 0.04183084 - time (sec): 9.28 - samples/sec: 2329.96 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:02:17,684 epoch 5 - iter 240/304 - loss 0.03928846 - time (sec): 10.61 - samples/sec: 2355.03 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:02:18,989 epoch 5 - iter 270/304 - loss 0.04104058 - time (sec): 11.91 - samples/sec: 2338.67 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:02:20,290 epoch 5 - iter 300/304 - loss 0.04669995 - time (sec): 13.21 - samples/sec: 2323.64 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:02:20,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:20,460 EPOCH 5 done: loss 0.0470 - lr: 0.000017 | |
| 2023-10-13 09:02:21,393 DEV : loss 0.17316469550132751 - f1-score (micro avg) 0.8376 | |
| 2023-10-13 09:02:21,399 saving best model | |
| 2023-10-13 09:02:22,002 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:23,358 epoch 6 - iter 30/304 - loss 0.03247053 - time (sec): 1.35 - samples/sec: 2463.58 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:02:24,648 epoch 6 - iter 60/304 - loss 0.03171894 - time (sec): 2.64 - samples/sec: 2300.97 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:02:25,956 epoch 6 - iter 90/304 - loss 0.03519381 - time (sec): 3.95 - samples/sec: 2324.05 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:02:27,295 epoch 6 - iter 120/304 - loss 0.03113449 - time (sec): 5.29 - samples/sec: 2396.79 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:02:28,623 epoch 6 - iter 150/304 - loss 0.03491689 - time (sec): 6.62 - samples/sec: 2351.08 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:02:29,939 epoch 6 - iter 180/304 - loss 0.03395763 - time (sec): 7.94 - samples/sec: 2336.92 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:02:31,233 epoch 6 - iter 210/304 - loss 0.03204121 - time (sec): 9.23 - samples/sec: 2298.61 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:02:32,580 epoch 6 - iter 240/304 - loss 0.03089909 - time (sec): 10.58 - samples/sec: 2304.24 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:02:33,971 epoch 6 - iter 270/304 - loss 0.03622043 - time (sec): 11.97 - samples/sec: 2304.75 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:02:35,281 epoch 6 - iter 300/304 - loss 0.03510874 - time (sec): 13.28 - samples/sec: 2304.49 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:02:35,450 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:35,450 EPOCH 6 done: loss 0.0352 - lr: 0.000013 | |
| 2023-10-13 09:02:36,363 DEV : loss 0.18857930600643158 - f1-score (micro avg) 0.8324 | |
| 2023-10-13 09:02:36,368 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:37,657 epoch 7 - iter 30/304 - loss 0.03699191 - time (sec): 1.29 - samples/sec: 2183.21 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:02:38,984 epoch 7 - iter 60/304 - loss 0.03397541 - time (sec): 2.61 - samples/sec: 2246.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:02:40,293 epoch 7 - iter 90/304 - loss 0.03917064 - time (sec): 3.92 - samples/sec: 2265.81 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:02:41,639 epoch 7 - iter 120/304 - loss 0.03462082 - time (sec): 5.27 - samples/sec: 2349.37 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:02:42,974 epoch 7 - iter 150/304 - loss 0.03164356 - time (sec): 6.60 - samples/sec: 2298.37 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:02:44,375 epoch 7 - iter 180/304 - loss 0.02856759 - time (sec): 8.01 - samples/sec: 2295.30 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:02:45,728 epoch 7 - iter 210/304 - loss 0.02535493 - time (sec): 9.36 - samples/sec: 2258.28 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:02:47,048 epoch 7 - iter 240/304 - loss 0.02954486 - time (sec): 10.68 - samples/sec: 2259.26 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:02:48,359 epoch 7 - iter 270/304 - loss 0.02999567 - time (sec): 11.99 - samples/sec: 2276.71 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:02:49,705 epoch 7 - iter 300/304 - loss 0.02936003 - time (sec): 13.34 - samples/sec: 2292.34 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:02:49,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:49,893 EPOCH 7 done: loss 0.0290 - lr: 0.000010 | |
| 2023-10-13 09:02:50,967 DEV : loss 0.21805648505687714 - f1-score (micro avg) 0.8234 | |
| 2023-10-13 09:02:50,973 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:02:52,268 epoch 8 - iter 30/304 - loss 0.01719997 - time (sec): 1.29 - samples/sec: 2250.33 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:02:53,582 epoch 8 - iter 60/304 - loss 0.01190032 - time (sec): 2.61 - samples/sec: 2243.24 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:02:54,896 epoch 8 - iter 90/304 - loss 0.01599804 - time (sec): 3.92 - samples/sec: 2286.79 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:02:56,185 epoch 8 - iter 120/304 - loss 0.01795423 - time (sec): 5.21 - samples/sec: 2323.66 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:02:57,480 epoch 8 - iter 150/304 - loss 0.01844222 - time (sec): 6.51 - samples/sec: 2352.00 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:02:58,752 epoch 8 - iter 180/304 - loss 0.01586027 - time (sec): 7.78 - samples/sec: 2323.80 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:03:00,024 epoch 8 - iter 210/304 - loss 0.01718384 - time (sec): 9.05 - samples/sec: 2342.58 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:03:01,311 epoch 8 - iter 240/304 - loss 0.01548976 - time (sec): 10.34 - samples/sec: 2357.21 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:03:02,669 epoch 8 - iter 270/304 - loss 0.01963074 - time (sec): 11.69 - samples/sec: 2366.98 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:03:03,975 epoch 8 - iter 300/304 - loss 0.02125844 - time (sec): 13.00 - samples/sec: 2358.11 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:03:04,145 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:04,145 EPOCH 8 done: loss 0.0210 - lr: 0.000007 | |
| 2023-10-13 09:03:05,089 DEV : loss 0.20849579572677612 - f1-score (micro avg) 0.8287 | |
| 2023-10-13 09:03:05,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:06,448 epoch 9 - iter 30/304 - loss 0.02793687 - time (sec): 1.35 - samples/sec: 2381.56 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:03:07,844 epoch 9 - iter 60/304 - loss 0.01535474 - time (sec): 2.75 - samples/sec: 2267.84 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:03:09,176 epoch 9 - iter 90/304 - loss 0.01314652 - time (sec): 4.08 - samples/sec: 2240.24 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:03:10,504 epoch 9 - iter 120/304 - loss 0.01852826 - time (sec): 5.41 - samples/sec: 2295.89 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:03:11,872 epoch 9 - iter 150/304 - loss 0.01964515 - time (sec): 6.78 - samples/sec: 2303.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:03:13,206 epoch 9 - iter 180/304 - loss 0.01872359 - time (sec): 8.11 - samples/sec: 2289.97 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:03:14,518 epoch 9 - iter 210/304 - loss 0.01878046 - time (sec): 9.42 - samples/sec: 2281.06 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:03:15,880 epoch 9 - iter 240/304 - loss 0.01671311 - time (sec): 10.78 - samples/sec: 2299.79 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:03:17,237 epoch 9 - iter 270/304 - loss 0.01607859 - time (sec): 12.14 - samples/sec: 2284.21 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:03:18,552 epoch 9 - iter 300/304 - loss 0.01568710 - time (sec): 13.46 - samples/sec: 2284.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:03:18,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:18,728 EPOCH 9 done: loss 0.0156 - lr: 0.000003 | |
| 2023-10-13 09:03:19,646 DEV : loss 0.20852698385715485 - f1-score (micro avg) 0.8327 | |
| 2023-10-13 09:03:19,652 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:20,968 epoch 10 - iter 30/304 - loss 0.01516768 - time (sec): 1.32 - samples/sec: 2379.19 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:03:22,283 epoch 10 - iter 60/304 - loss 0.00807043 - time (sec): 2.63 - samples/sec: 2350.40 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:03:23,607 epoch 10 - iter 90/304 - loss 0.00923733 - time (sec): 3.95 - samples/sec: 2311.19 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:03:24,941 epoch 10 - iter 120/304 - loss 0.00860137 - time (sec): 5.29 - samples/sec: 2278.31 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:03:26,279 epoch 10 - iter 150/304 - loss 0.00946498 - time (sec): 6.63 - samples/sec: 2262.10 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:03:27,662 epoch 10 - iter 180/304 - loss 0.01013030 - time (sec): 8.01 - samples/sec: 2269.90 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:03:29,050 epoch 10 - iter 210/304 - loss 0.01109952 - time (sec): 9.40 - samples/sec: 2273.78 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:03:30,424 epoch 10 - iter 240/304 - loss 0.01112300 - time (sec): 10.77 - samples/sec: 2271.00 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:03:31,805 epoch 10 - iter 270/304 - loss 0.01275687 - time (sec): 12.15 - samples/sec: 2262.27 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 09:03:33,210 epoch 10 - iter 300/304 - loss 0.01208816 - time (sec): 13.56 - samples/sec: 2255.26 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 09:03:33,403 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:33,403 EPOCH 10 done: loss 0.0121 - lr: 0.000000 | |
| 2023-10-13 09:03:34,323 DEV : loss 0.21789805591106415 - f1-score (micro avg) 0.826 | |
| 2023-10-13 09:03:34,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:03:34,893 Loading model from best epoch ... | |
| 2023-10-13 09:03:37,263 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-13 09:03:38,134 | |
| Results: | |
| - F-score (micro) 0.787 | |
| - F-score (macro) 0.4777 | |
| - Accuracy 0.6576 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7662 0.7815 0.7738 151 | |
| pers 0.7417 0.9271 0.8241 96 | |
| work 0.7217 0.8737 0.7905 95 | |
| loc 0.0000 0.0000 0.0000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7455 0.8333 0.7870 348 | |
| macro avg 0.4459 0.5164 0.4777 348 | |
| weighted avg 0.7341 0.8333 0.7789 348 | |
| 2023-10-13 09:03:38,135 ---------------------------------------------------------------------------------------------------- | |