| 2023-10-17 09:30:31,178 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,178 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 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 | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 Train: 1214 sentences | |
| 2023-10-17 09:30:31,179 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 Training Params: | |
| 2023-10-17 09:30:31,179 - learning_rate: "3e-05" | |
| 2023-10-17 09:30:31,179 - mini_batch_size: "4" | |
| 2023-10-17 09:30:31,179 - max_epochs: "10" | |
| 2023-10-17 09:30:31,179 - shuffle: "True" | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 Plugins: | |
| 2023-10-17 09:30:31,179 - TensorboardLogger | |
| 2023-10-17 09:30:31,179 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 09:30:31,179 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,179 Computation: | |
| 2023-10-17 09:30:31,179 - compute on device: cuda:0 | |
| 2023-10-17 09:30:31,179 - embedding storage: none | |
| 2023-10-17 09:30:31,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,180 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-17 09:30:31,180 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,180 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:31,180 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 09:30:33,540 epoch 1 - iter 30/304 - loss 3.40341811 - time (sec): 2.36 - samples/sec: 1275.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:30:34,870 epoch 1 - iter 60/304 - loss 2.76268533 - time (sec): 3.69 - samples/sec: 1612.88 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:30:36,273 epoch 1 - iter 90/304 - loss 2.09069265 - time (sec): 5.09 - samples/sec: 1844.82 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:30:37,679 epoch 1 - iter 120/304 - loss 1.68530411 - time (sec): 6.50 - samples/sec: 1952.76 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:30:39,073 epoch 1 - iter 150/304 - loss 1.46288557 - time (sec): 7.89 - samples/sec: 1958.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:30:40,419 epoch 1 - iter 180/304 - loss 1.28563337 - time (sec): 9.24 - samples/sec: 1977.24 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:30:41,811 epoch 1 - iter 210/304 - loss 1.14935430 - time (sec): 10.63 - samples/sec: 2014.34 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:30:43,137 epoch 1 - iter 240/304 - loss 1.04594044 - time (sec): 11.96 - samples/sec: 2044.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:30:44,462 epoch 1 - iter 270/304 - loss 0.95951493 - time (sec): 13.28 - samples/sec: 2067.26 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:30:45,861 epoch 1 - iter 300/304 - loss 0.88553963 - time (sec): 14.68 - samples/sec: 2087.86 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:30:46,032 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:46,032 EPOCH 1 done: loss 0.8781 - lr: 0.000030 | |
| 2023-10-17 09:30:46,938 DEV : loss 0.1928645819425583 - f1-score (micro avg) 0.6572 | |
| 2023-10-17 09:30:46,944 saving best model | |
| 2023-10-17 09:30:47,324 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:30:48,689 epoch 2 - iter 30/304 - loss 0.19033845 - time (sec): 1.36 - samples/sec: 2207.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:30:50,068 epoch 2 - iter 60/304 - loss 0.19049934 - time (sec): 2.74 - samples/sec: 2227.36 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:30:51,445 epoch 2 - iter 90/304 - loss 0.17286170 - time (sec): 4.12 - samples/sec: 2237.14 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:30:52,772 epoch 2 - iter 120/304 - loss 0.16185954 - time (sec): 5.45 - samples/sec: 2248.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:30:54,086 epoch 2 - iter 150/304 - loss 0.15626809 - time (sec): 6.76 - samples/sec: 2281.43 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:30:55,357 epoch 2 - iter 180/304 - loss 0.15121608 - time (sec): 8.03 - samples/sec: 2280.31 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:30:56,667 epoch 2 - iter 210/304 - loss 0.14604985 - time (sec): 9.34 - samples/sec: 2265.86 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:30:58,020 epoch 2 - iter 240/304 - loss 0.14876228 - time (sec): 10.69 - samples/sec: 2292.74 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:30:59,361 epoch 2 - iter 270/304 - loss 0.14221295 - time (sec): 12.03 - samples/sec: 2305.12 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:31:00,721 epoch 2 - iter 300/304 - loss 0.14474972 - time (sec): 13.39 - samples/sec: 2291.33 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:31:00,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:00,892 EPOCH 2 done: loss 0.1438 - lr: 0.000027 | |
| 2023-10-17 09:31:01,837 DEV : loss 0.14745701849460602 - f1-score (micro avg) 0.8038 | |
| 2023-10-17 09:31:01,843 saving best model | |
| 2023-10-17 09:31:02,338 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:03,654 epoch 3 - iter 30/304 - loss 0.09474617 - time (sec): 1.31 - samples/sec: 2209.40 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:31:05,063 epoch 3 - iter 60/304 - loss 0.08922804 - time (sec): 2.72 - samples/sec: 2157.78 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:31:06,505 epoch 3 - iter 90/304 - loss 0.08927453 - time (sec): 4.17 - samples/sec: 2102.13 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:31:07,910 epoch 3 - iter 120/304 - loss 0.08498659 - time (sec): 5.57 - samples/sec: 2103.13 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:31:09,349 epoch 3 - iter 150/304 - loss 0.07743174 - time (sec): 7.01 - samples/sec: 2159.77 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:31:10,691 epoch 3 - iter 180/304 - loss 0.09126252 - time (sec): 8.35 - samples/sec: 2194.22 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:31:12,047 epoch 3 - iter 210/304 - loss 0.09607426 - time (sec): 9.71 - samples/sec: 2208.73 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:31:13,398 epoch 3 - iter 240/304 - loss 0.09411271 - time (sec): 11.06 - samples/sec: 2213.20 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:31:14,728 epoch 3 - iter 270/304 - loss 0.08853084 - time (sec): 12.39 - samples/sec: 2207.82 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:31:16,067 epoch 3 - iter 300/304 - loss 0.08617369 - time (sec): 13.73 - samples/sec: 2232.98 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:31:16,241 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:16,242 EPOCH 3 done: loss 0.0868 - lr: 0.000023 | |
| 2023-10-17 09:31:17,177 DEV : loss 0.150361567735672 - f1-score (micro avg) 0.8233 | |
| 2023-10-17 09:31:17,184 saving best model | |
| 2023-10-17 09:31:17,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:19,216 epoch 4 - iter 30/304 - loss 0.04765358 - time (sec): 1.44 - samples/sec: 2152.91 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:31:20,604 epoch 4 - iter 60/304 - loss 0.06898020 - time (sec): 2.83 - samples/sec: 2164.59 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:31:21,980 epoch 4 - iter 90/304 - loss 0.06988082 - time (sec): 4.21 - samples/sec: 2134.50 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:31:23,320 epoch 4 - iter 120/304 - loss 0.06829514 - time (sec): 5.55 - samples/sec: 2230.06 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:31:24,661 epoch 4 - iter 150/304 - loss 0.06516852 - time (sec): 6.89 - samples/sec: 2220.38 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:31:26,023 epoch 4 - iter 180/304 - loss 0.06321737 - time (sec): 8.25 - samples/sec: 2206.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:31:27,357 epoch 4 - iter 210/304 - loss 0.06440426 - time (sec): 9.59 - samples/sec: 2233.44 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:31:28,782 epoch 4 - iter 240/304 - loss 0.06148461 - time (sec): 11.01 - samples/sec: 2231.14 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:31:30,299 epoch 4 - iter 270/304 - loss 0.06405485 - time (sec): 12.53 - samples/sec: 2207.24 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:31:31,821 epoch 4 - iter 300/304 - loss 0.06259846 - time (sec): 14.05 - samples/sec: 2185.49 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:31:32,021 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:32,022 EPOCH 4 done: loss 0.0626 - lr: 0.000020 | |
| 2023-10-17 09:31:33,007 DEV : loss 0.19989213347434998 - f1-score (micro avg) 0.8248 | |
| 2023-10-17 09:31:33,015 saving best model | |
| 2023-10-17 09:31:33,506 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:34,851 epoch 5 - iter 30/304 - loss 0.07427175 - time (sec): 1.34 - samples/sec: 2515.11 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:31:36,202 epoch 5 - iter 60/304 - loss 0.05862733 - time (sec): 2.69 - samples/sec: 2355.67 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:31:37,538 epoch 5 - iter 90/304 - loss 0.05988285 - time (sec): 4.03 - samples/sec: 2402.34 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:31:38,865 epoch 5 - iter 120/304 - loss 0.04951363 - time (sec): 5.36 - samples/sec: 2372.69 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:31:40,251 epoch 5 - iter 150/304 - loss 0.04470615 - time (sec): 6.74 - samples/sec: 2340.22 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:31:41,572 epoch 5 - iter 180/304 - loss 0.04611420 - time (sec): 8.06 - samples/sec: 2316.33 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:31:42,887 epoch 5 - iter 210/304 - loss 0.04532396 - time (sec): 9.38 - samples/sec: 2311.70 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:31:44,192 epoch 5 - iter 240/304 - loss 0.04875675 - time (sec): 10.68 - samples/sec: 2287.02 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:31:45,542 epoch 5 - iter 270/304 - loss 0.04694412 - time (sec): 12.03 - samples/sec: 2291.36 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:31:46,970 epoch 5 - iter 300/304 - loss 0.05007069 - time (sec): 13.46 - samples/sec: 2280.60 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:31:47,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:47,157 EPOCH 5 done: loss 0.0498 - lr: 0.000017 | |
| 2023-10-17 09:31:48,120 DEV : loss 0.2023184597492218 - f1-score (micro avg) 0.841 | |
| 2023-10-17 09:31:48,127 saving best model | |
| 2023-10-17 09:31:48,632 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:31:50,025 epoch 6 - iter 30/304 - loss 0.04511870 - time (sec): 1.39 - samples/sec: 2230.73 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:31:51,435 epoch 6 - iter 60/304 - loss 0.03883136 - time (sec): 2.80 - samples/sec: 2113.38 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:31:52,772 epoch 6 - iter 90/304 - loss 0.03906137 - time (sec): 4.14 - samples/sec: 2150.93 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:31:54,154 epoch 6 - iter 120/304 - loss 0.03579353 - time (sec): 5.52 - samples/sec: 2162.09 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:31:55,567 epoch 6 - iter 150/304 - loss 0.03494026 - time (sec): 6.93 - samples/sec: 2182.94 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:31:56,932 epoch 6 - iter 180/304 - loss 0.03394086 - time (sec): 8.30 - samples/sec: 2184.06 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:31:58,280 epoch 6 - iter 210/304 - loss 0.03922439 - time (sec): 9.64 - samples/sec: 2209.43 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:31:59,637 epoch 6 - iter 240/304 - loss 0.03719479 - time (sec): 11.00 - samples/sec: 2206.25 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:32:01,032 epoch 6 - iter 270/304 - loss 0.03881903 - time (sec): 12.40 - samples/sec: 2209.13 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:32:02,428 epoch 6 - iter 300/304 - loss 0.03998433 - time (sec): 13.79 - samples/sec: 2222.87 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:32:02,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:02,610 EPOCH 6 done: loss 0.0398 - lr: 0.000013 | |
| 2023-10-17 09:32:03,536 DEV : loss 0.19735880196094513 - f1-score (micro avg) 0.8606 | |
| 2023-10-17 09:32:03,542 saving best model | |
| 2023-10-17 09:32:04,046 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:05,471 epoch 7 - iter 30/304 - loss 0.01823262 - time (sec): 1.42 - samples/sec: 1968.60 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:32:06,844 epoch 7 - iter 60/304 - loss 0.01379847 - time (sec): 2.80 - samples/sec: 2085.82 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:32:08,155 epoch 7 - iter 90/304 - loss 0.01965802 - time (sec): 4.11 - samples/sec: 2171.32 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:32:09,500 epoch 7 - iter 120/304 - loss 0.02037882 - time (sec): 5.45 - samples/sec: 2172.21 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:32:10,830 epoch 7 - iter 150/304 - loss 0.01800502 - time (sec): 6.78 - samples/sec: 2209.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:32:12,189 epoch 7 - iter 180/304 - loss 0.01811769 - time (sec): 8.14 - samples/sec: 2211.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:32:13,541 epoch 7 - iter 210/304 - loss 0.02066402 - time (sec): 9.49 - samples/sec: 2217.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:32:14,893 epoch 7 - iter 240/304 - loss 0.02128125 - time (sec): 10.85 - samples/sec: 2252.69 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:32:16,182 epoch 7 - iter 270/304 - loss 0.02352683 - time (sec): 12.13 - samples/sec: 2285.78 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:32:17,486 epoch 7 - iter 300/304 - loss 0.02762806 - time (sec): 13.44 - samples/sec: 2279.83 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:32:17,667 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:17,668 EPOCH 7 done: loss 0.0278 - lr: 0.000010 | |
| 2023-10-17 09:32:18,600 DEV : loss 0.22195689380168915 - f1-score (micro avg) 0.8413 | |
| 2023-10-17 09:32:18,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:19,989 epoch 8 - iter 30/304 - loss 0.01263015 - time (sec): 1.38 - samples/sec: 2437.36 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:32:21,353 epoch 8 - iter 60/304 - loss 0.01338996 - time (sec): 2.74 - samples/sec: 2325.69 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:32:22,717 epoch 8 - iter 90/304 - loss 0.02176368 - time (sec): 4.11 - samples/sec: 2311.46 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:32:24,063 epoch 8 - iter 120/304 - loss 0.01886905 - time (sec): 5.45 - samples/sec: 2232.01 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:32:25,422 epoch 8 - iter 150/304 - loss 0.01578714 - time (sec): 6.81 - samples/sec: 2278.52 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:32:26,753 epoch 8 - iter 180/304 - loss 0.01908566 - time (sec): 8.14 - samples/sec: 2262.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:32:28,141 epoch 8 - iter 210/304 - loss 0.02325066 - time (sec): 9.53 - samples/sec: 2244.39 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:32:29,540 epoch 8 - iter 240/304 - loss 0.02452136 - time (sec): 10.93 - samples/sec: 2242.79 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:32:30,896 epoch 8 - iter 270/304 - loss 0.02299051 - time (sec): 12.29 - samples/sec: 2247.51 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:32:32,238 epoch 8 - iter 300/304 - loss 0.02348440 - time (sec): 13.63 - samples/sec: 2246.47 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:32:32,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:32,419 EPOCH 8 done: loss 0.0232 - lr: 0.000007 | |
| 2023-10-17 09:32:33,398 DEV : loss 0.2149593085050583 - f1-score (micro avg) 0.8527 | |
| 2023-10-17 09:32:33,406 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:35,020 epoch 9 - iter 30/304 - loss 0.02915313 - time (sec): 1.61 - samples/sec: 1907.76 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:32:36,612 epoch 9 - iter 60/304 - loss 0.01511731 - time (sec): 3.20 - samples/sec: 1866.16 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:32:38,222 epoch 9 - iter 90/304 - loss 0.01855884 - time (sec): 4.81 - samples/sec: 1903.60 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:32:39,672 epoch 9 - iter 120/304 - loss 0.01614332 - time (sec): 6.26 - samples/sec: 1922.74 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:32:41,136 epoch 9 - iter 150/304 - loss 0.01755943 - time (sec): 7.73 - samples/sec: 1971.62 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:32:42,567 epoch 9 - iter 180/304 - loss 0.01749215 - time (sec): 9.16 - samples/sec: 2003.99 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:32:43,882 epoch 9 - iter 210/304 - loss 0.01545958 - time (sec): 10.47 - samples/sec: 2035.36 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:32:45,181 epoch 9 - iter 240/304 - loss 0.01559802 - time (sec): 11.77 - samples/sec: 2060.93 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:32:46,548 epoch 9 - iter 270/304 - loss 0.01720692 - time (sec): 13.14 - samples/sec: 2087.79 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:32:47,898 epoch 9 - iter 300/304 - loss 0.01840772 - time (sec): 14.49 - samples/sec: 2115.19 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:32:48,066 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:48,066 EPOCH 9 done: loss 0.0182 - lr: 0.000003 | |
| 2023-10-17 09:32:49,027 DEV : loss 0.21825647354125977 - f1-score (micro avg) 0.8547 | |
| 2023-10-17 09:32:49,033 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:32:50,363 epoch 10 - iter 30/304 - loss 0.00382941 - time (sec): 1.33 - samples/sec: 2212.97 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:32:51,806 epoch 10 - iter 60/304 - loss 0.01280602 - time (sec): 2.77 - samples/sec: 2156.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:32:53,180 epoch 10 - iter 90/304 - loss 0.01157864 - time (sec): 4.15 - samples/sec: 2235.64 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:32:54,513 epoch 10 - iter 120/304 - loss 0.01749777 - time (sec): 5.48 - samples/sec: 2225.87 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:32:55,851 epoch 10 - iter 150/304 - loss 0.01594405 - time (sec): 6.82 - samples/sec: 2221.32 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:32:57,231 epoch 10 - iter 180/304 - loss 0.01600590 - time (sec): 8.20 - samples/sec: 2213.10 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:32:58,559 epoch 10 - iter 210/304 - loss 0.01401505 - time (sec): 9.52 - samples/sec: 2242.13 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:32:59,884 epoch 10 - iter 240/304 - loss 0.01299417 - time (sec): 10.85 - samples/sec: 2242.61 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:33:01,211 epoch 10 - iter 270/304 - loss 0.01365368 - time (sec): 12.18 - samples/sec: 2250.29 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:33:02,541 epoch 10 - iter 300/304 - loss 0.01386075 - time (sec): 13.51 - samples/sec: 2266.65 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:33:02,721 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:02,721 EPOCH 10 done: loss 0.0143 - lr: 0.000000 | |
| 2023-10-17 09:33:03,723 DEV : loss 0.21264854073524475 - f1-score (micro avg) 0.8517 | |
| 2023-10-17 09:33:04,116 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:04,117 Loading model from best epoch ... | |
| 2023-10-17 09:33:06,307 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 | |
| 2023-10-17 09:33:07,013 | |
| Results: | |
| - F-score (micro) 0.8156 | |
| - F-score (macro) 0.6596 | |
| - Accuracy 0.6952 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7312 0.7748 0.7524 151 | |
| work 0.7685 0.8737 0.8177 95 | |
| pers 0.9184 0.9375 0.9278 96 | |
| loc 1.0000 0.6667 0.8000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7935 0.8391 0.8156 348 | |
| macro avg 0.6836 0.6505 0.6596 348 | |
| weighted avg 0.7891 0.8391 0.8126 348 | |
| 2023-10-17 09:33:07,014 ---------------------------------------------------------------------------------------------------- | |