| 2023-10-17 09:33:30,241 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 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 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 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 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 Train: 1214 sentences | |
| 2023-10-17 09:33:30,242 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 Training Params: | |
| 2023-10-17 09:33:30,242 - learning_rate: "5e-05" | |
| 2023-10-17 09:33:30,242 - mini_batch_size: "4" | |
| 2023-10-17 09:33:30,242 - max_epochs: "10" | |
| 2023-10-17 09:33:30,242 - shuffle: "True" | |
| 2023-10-17 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 Plugins: | |
| 2023-10-17 09:33:30,242 - TensorboardLogger | |
| 2023-10-17 09:33:30,242 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 09:33:30,242 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 09:33:30,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,242 Computation: | |
| 2023-10-17 09:33:30,242 - compute on device: cuda:0 | |
| 2023-10-17 09:33:30,243 - embedding storage: none | |
| 2023-10-17 09:33:30,243 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,243 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-17 09:33:30,243 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,243 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:30,243 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 09:33:31,606 epoch 1 - iter 30/304 - loss 3.25804981 - time (sec): 1.36 - samples/sec: 2208.37 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:33:32,934 epoch 1 - iter 60/304 - loss 2.36313859 - time (sec): 2.69 - samples/sec: 2211.39 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:33:34,214 epoch 1 - iter 90/304 - loss 1.76687822 - time (sec): 3.97 - samples/sec: 2366.03 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:33:35,519 epoch 1 - iter 120/304 - loss 1.42293198 - time (sec): 5.27 - samples/sec: 2405.55 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:33:36,849 epoch 1 - iter 150/304 - loss 1.23485272 - time (sec): 6.61 - samples/sec: 2340.39 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:33:38,135 epoch 1 - iter 180/304 - loss 1.08832958 - time (sec): 7.89 - samples/sec: 2314.73 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:33:39,417 epoch 1 - iter 210/304 - loss 0.97415434 - time (sec): 9.17 - samples/sec: 2334.11 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 09:33:40,697 epoch 1 - iter 240/304 - loss 0.88672066 - time (sec): 10.45 - samples/sec: 2338.93 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 09:33:42,059 epoch 1 - iter 270/304 - loss 0.81370723 - time (sec): 11.82 - samples/sec: 2323.70 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 09:33:43,448 epoch 1 - iter 300/304 - loss 0.75173915 - time (sec): 13.20 - samples/sec: 2321.25 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:33:43,621 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:43,622 EPOCH 1 done: loss 0.7451 - lr: 0.000049 | |
| 2023-10-17 09:33:44,523 DEV : loss 0.161675825715065 - f1-score (micro avg) 0.6765 | |
| 2023-10-17 09:33:44,530 saving best model | |
| 2023-10-17 09:33:44,878 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:46,288 epoch 2 - iter 30/304 - loss 0.17926316 - time (sec): 1.41 - samples/sec: 2136.46 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:33:47,632 epoch 2 - iter 60/304 - loss 0.17959788 - time (sec): 2.75 - samples/sec: 2218.15 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:33:48,959 epoch 2 - iter 90/304 - loss 0.15959564 - time (sec): 4.08 - samples/sec: 2258.44 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 09:33:50,278 epoch 2 - iter 120/304 - loss 0.14577787 - time (sec): 5.40 - samples/sec: 2268.14 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 09:33:51,661 epoch 2 - iter 150/304 - loss 0.14309388 - time (sec): 6.78 - samples/sec: 2273.91 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 09:33:52,936 epoch 2 - iter 180/304 - loss 0.13888269 - time (sec): 8.06 - samples/sec: 2272.89 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 09:33:54,317 epoch 2 - iter 210/304 - loss 0.13552043 - time (sec): 9.44 - samples/sec: 2242.76 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 09:33:55,729 epoch 2 - iter 240/304 - loss 0.13838089 - time (sec): 10.85 - samples/sec: 2259.83 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 09:33:57,023 epoch 2 - iter 270/304 - loss 0.13466550 - time (sec): 12.14 - samples/sec: 2284.52 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 09:33:58,306 epoch 2 - iter 300/304 - loss 0.13660685 - time (sec): 13.43 - samples/sec: 2285.83 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 09:33:58,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:33:58,477 EPOCH 2 done: loss 0.1357 - lr: 0.000045 | |
| 2023-10-17 09:33:59,429 DEV : loss 0.13294953107833862 - f1-score (micro avg) 0.8388 | |
| 2023-10-17 09:33:59,435 saving best model | |
| 2023-10-17 09:33:59,862 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:01,217 epoch 3 - iter 30/304 - loss 0.10186564 - time (sec): 1.35 - samples/sec: 2147.02 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 09:34:02,552 epoch 3 - iter 60/304 - loss 0.08701531 - time (sec): 2.69 - samples/sec: 2186.79 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 09:34:03,883 epoch 3 - iter 90/304 - loss 0.08470113 - time (sec): 4.02 - samples/sec: 2179.19 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 09:34:05,289 epoch 3 - iter 120/304 - loss 0.08058118 - time (sec): 5.42 - samples/sec: 2159.74 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 09:34:06,696 epoch 3 - iter 150/304 - loss 0.07176557 - time (sec): 6.83 - samples/sec: 2216.09 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 09:34:08,075 epoch 3 - iter 180/304 - loss 0.08766980 - time (sec): 8.21 - samples/sec: 2231.73 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 09:34:09,455 epoch 3 - iter 210/304 - loss 0.09295201 - time (sec): 9.59 - samples/sec: 2235.65 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 09:34:10,749 epoch 3 - iter 240/304 - loss 0.09005317 - time (sec): 10.88 - samples/sec: 2248.59 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 09:34:12,027 epoch 3 - iter 270/304 - loss 0.08696873 - time (sec): 12.16 - samples/sec: 2248.96 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 09:34:13,349 epoch 3 - iter 300/304 - loss 0.08573648 - time (sec): 13.48 - samples/sec: 2273.37 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 09:34:13,530 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:13,531 EPOCH 3 done: loss 0.0855 - lr: 0.000039 | |
| 2023-10-17 09:34:14,488 DEV : loss 0.18068550527095795 - f1-score (micro avg) 0.8046 | |
| 2023-10-17 09:34:14,496 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:15,784 epoch 4 - iter 30/304 - loss 0.05019669 - time (sec): 1.29 - samples/sec: 2416.76 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 09:34:17,052 epoch 4 - iter 60/304 - loss 0.05952380 - time (sec): 2.55 - samples/sec: 2400.94 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 09:34:18,320 epoch 4 - iter 90/304 - loss 0.05936065 - time (sec): 3.82 - samples/sec: 2349.79 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 09:34:19,623 epoch 4 - iter 120/304 - loss 0.05864896 - time (sec): 5.13 - samples/sec: 2414.14 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 09:34:20,901 epoch 4 - iter 150/304 - loss 0.06134356 - time (sec): 6.40 - samples/sec: 2389.22 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 09:34:22,237 epoch 4 - iter 180/304 - loss 0.05914494 - time (sec): 7.74 - samples/sec: 2352.70 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 09:34:23,569 epoch 4 - iter 210/304 - loss 0.06076366 - time (sec): 9.07 - samples/sec: 2360.11 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 09:34:24,883 epoch 4 - iter 240/304 - loss 0.06044483 - time (sec): 10.39 - samples/sec: 2365.35 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 09:34:26,193 epoch 4 - iter 270/304 - loss 0.06275507 - time (sec): 11.70 - samples/sec: 2364.46 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 09:34:27,536 epoch 4 - iter 300/304 - loss 0.06152975 - time (sec): 13.04 - samples/sec: 2355.11 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 09:34:27,723 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:27,723 EPOCH 4 done: loss 0.0620 - lr: 0.000033 | |
| 2023-10-17 09:34:28,672 DEV : loss 0.175832137465477 - f1-score (micro avg) 0.8293 | |
| 2023-10-17 09:34:28,678 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:30,056 epoch 5 - iter 30/304 - loss 0.06038916 - time (sec): 1.38 - samples/sec: 2451.93 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 09:34:31,498 epoch 5 - iter 60/304 - loss 0.05371355 - time (sec): 2.82 - samples/sec: 2251.01 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 09:34:32,830 epoch 5 - iter 90/304 - loss 0.05116334 - time (sec): 4.15 - samples/sec: 2332.16 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 09:34:34,173 epoch 5 - iter 120/304 - loss 0.04426179 - time (sec): 5.49 - samples/sec: 2313.46 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 09:34:35,527 epoch 5 - iter 150/304 - loss 0.04033000 - time (sec): 6.85 - samples/sec: 2304.34 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 09:34:36,853 epoch 5 - iter 180/304 - loss 0.04201480 - time (sec): 8.17 - samples/sec: 2285.13 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:34:38,187 epoch 5 - iter 210/304 - loss 0.04071244 - time (sec): 9.51 - samples/sec: 2280.43 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:34:39,501 epoch 5 - iter 240/304 - loss 0.04523655 - time (sec): 10.82 - samples/sec: 2257.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:34:40,785 epoch 5 - iter 270/304 - loss 0.04313341 - time (sec): 12.11 - samples/sec: 2277.61 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:34:42,094 epoch 5 - iter 300/304 - loss 0.04659600 - time (sec): 13.42 - samples/sec: 2288.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:34:42,256 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:42,256 EPOCH 5 done: loss 0.0462 - lr: 0.000028 | |
| 2023-10-17 09:34:43,227 DEV : loss 0.19779552519321442 - f1-score (micro avg) 0.8475 | |
| 2023-10-17 09:34:43,234 saving best model | |
| 2023-10-17 09:34:43,689 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:45,101 epoch 6 - iter 30/304 - loss 0.05143267 - time (sec): 1.40 - samples/sec: 2210.38 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:34:46,425 epoch 6 - iter 60/304 - loss 0.03537847 - time (sec): 2.73 - samples/sec: 2170.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:34:47,769 epoch 6 - iter 90/304 - loss 0.03156355 - time (sec): 4.07 - samples/sec: 2186.19 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:34:49,120 epoch 6 - iter 120/304 - loss 0.02614683 - time (sec): 5.42 - samples/sec: 2201.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:34:50,493 epoch 6 - iter 150/304 - loss 0.02570856 - time (sec): 6.79 - samples/sec: 2227.33 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:34:51,827 epoch 6 - iter 180/304 - loss 0.02466593 - time (sec): 8.13 - samples/sec: 2229.40 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:34:53,204 epoch 6 - iter 210/304 - loss 0.02965446 - time (sec): 9.51 - samples/sec: 2241.84 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:34:54,541 epoch 6 - iter 240/304 - loss 0.02712866 - time (sec): 10.84 - samples/sec: 2238.86 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:34:55,890 epoch 6 - iter 270/304 - loss 0.02982859 - time (sec): 12.19 - samples/sec: 2246.57 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:34:57,245 epoch 6 - iter 300/304 - loss 0.03308022 - time (sec): 13.55 - samples/sec: 2263.29 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:34:57,420 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:34:57,421 EPOCH 6 done: loss 0.0330 - lr: 0.000022 | |
| 2023-10-17 09:34:58,543 DEV : loss 0.18329085409641266 - f1-score (micro avg) 0.8568 | |
| 2023-10-17 09:34:58,550 saving best model | |
| 2023-10-17 09:34:59,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:00,421 epoch 7 - iter 30/304 - loss 0.00903014 - time (sec): 1.36 - samples/sec: 2058.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:35:01,810 epoch 7 - iter 60/304 - loss 0.01054061 - time (sec): 2.75 - samples/sec: 2120.91 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:35:03,185 epoch 7 - iter 90/304 - loss 0.01510108 - time (sec): 4.13 - samples/sec: 2161.56 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:35:04,616 epoch 7 - iter 120/304 - loss 0.01565376 - time (sec): 5.56 - samples/sec: 2131.48 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:35:06,050 epoch 7 - iter 150/304 - loss 0.01317230 - time (sec): 6.99 - samples/sec: 2143.38 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:35:07,407 epoch 7 - iter 180/304 - loss 0.01320453 - time (sec): 8.35 - samples/sec: 2156.66 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:35:08,703 epoch 7 - iter 210/304 - loss 0.01596236 - time (sec): 9.64 - samples/sec: 2182.73 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:35:10,013 epoch 7 - iter 240/304 - loss 0.01593314 - time (sec): 10.95 - samples/sec: 2230.29 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:35:11,362 epoch 7 - iter 270/304 - loss 0.01798677 - time (sec): 12.30 - samples/sec: 2254.56 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:35:12,771 epoch 7 - iter 300/304 - loss 0.02095176 - time (sec): 13.71 - samples/sec: 2234.42 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:35:12,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:12,970 EPOCH 7 done: loss 0.0211 - lr: 0.000017 | |
| 2023-10-17 09:35:13,928 DEV : loss 0.2318311482667923 - f1-score (micro avg) 0.8571 | |
| 2023-10-17 09:35:13,935 saving best model | |
| 2023-10-17 09:35:14,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:15,821 epoch 8 - iter 30/304 - loss 0.00640611 - time (sec): 1.43 - samples/sec: 2346.78 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:35:17,274 epoch 8 - iter 60/304 - loss 0.00420715 - time (sec): 2.89 - samples/sec: 2210.37 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:35:18,674 epoch 8 - iter 90/304 - loss 0.01207152 - time (sec): 4.29 - samples/sec: 2215.29 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:35:20,025 epoch 8 - iter 120/304 - loss 0.01364647 - time (sec): 5.64 - samples/sec: 2159.32 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:35:21,393 epoch 8 - iter 150/304 - loss 0.01137201 - time (sec): 7.01 - samples/sec: 2216.12 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:35:22,749 epoch 8 - iter 180/304 - loss 0.01119804 - time (sec): 8.36 - samples/sec: 2203.40 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:35:24,097 epoch 8 - iter 210/304 - loss 0.01460673 - time (sec): 9.71 - samples/sec: 2203.24 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:35:25,448 epoch 8 - iter 240/304 - loss 0.01538458 - time (sec): 11.06 - samples/sec: 2216.67 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:35:26,821 epoch 8 - iter 270/304 - loss 0.01486285 - time (sec): 12.43 - samples/sec: 2220.99 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:35:28,153 epoch 8 - iter 300/304 - loss 0.01592791 - time (sec): 13.77 - samples/sec: 2224.23 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:35:28,323 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:28,324 EPOCH 8 done: loss 0.0157 - lr: 0.000011 | |
| 2023-10-17 09:35:29,276 DEV : loss 0.21787002682685852 - f1-score (micro avg) 0.8561 | |
| 2023-10-17 09:35:29,283 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:30,696 epoch 9 - iter 30/304 - loss 0.01042886 - time (sec): 1.41 - samples/sec: 2178.98 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:35:32,023 epoch 9 - iter 60/304 - loss 0.00538462 - time (sec): 2.74 - samples/sec: 2184.25 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:35:33,344 epoch 9 - iter 90/304 - loss 0.01550286 - time (sec): 4.06 - samples/sec: 2257.11 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:35:34,676 epoch 9 - iter 120/304 - loss 0.01188775 - time (sec): 5.39 - samples/sec: 2234.21 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:35:36,048 epoch 9 - iter 150/304 - loss 0.01119042 - time (sec): 6.76 - samples/sec: 2252.88 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:35:37,409 epoch 9 - iter 180/304 - loss 0.01085870 - time (sec): 8.12 - samples/sec: 2259.30 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:35:38,748 epoch 9 - iter 210/304 - loss 0.00941338 - time (sec): 9.46 - samples/sec: 2252.93 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:35:40,069 epoch 9 - iter 240/304 - loss 0.00912920 - time (sec): 10.78 - samples/sec: 2249.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:35:41,405 epoch 9 - iter 270/304 - loss 0.01006905 - time (sec): 12.12 - samples/sec: 2263.51 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:35:42,742 epoch 9 - iter 300/304 - loss 0.01164740 - time (sec): 13.46 - samples/sec: 2277.54 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:35:42,913 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:42,914 EPOCH 9 done: loss 0.0115 - lr: 0.000006 | |
| 2023-10-17 09:35:43,887 DEV : loss 0.22361968457698822 - f1-score (micro avg) 0.8551 | |
| 2023-10-17 09:35:43,895 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:45,259 epoch 10 - iter 30/304 - loss 0.00155770 - time (sec): 1.36 - samples/sec: 2158.68 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:35:46,575 epoch 10 - iter 60/304 - loss 0.00990788 - time (sec): 2.68 - samples/sec: 2231.22 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:35:47,906 epoch 10 - iter 90/304 - loss 0.00933886 - time (sec): 4.01 - samples/sec: 2311.59 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:35:49,363 epoch 10 - iter 120/304 - loss 0.01043367 - time (sec): 5.47 - samples/sec: 2231.01 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:35:50,741 epoch 10 - iter 150/304 - loss 0.00896913 - time (sec): 6.84 - samples/sec: 2212.05 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:35:52,078 epoch 10 - iter 180/304 - loss 0.00836120 - time (sec): 8.18 - samples/sec: 2217.08 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:35:53,436 epoch 10 - iter 210/304 - loss 0.00726658 - time (sec): 9.54 - samples/sec: 2238.68 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:35:54,774 epoch 10 - iter 240/304 - loss 0.00677716 - time (sec): 10.88 - samples/sec: 2236.89 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:35:56,181 epoch 10 - iter 270/304 - loss 0.00720824 - time (sec): 12.28 - samples/sec: 2230.52 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:35:57,552 epoch 10 - iter 300/304 - loss 0.00782340 - time (sec): 13.66 - samples/sec: 2241.83 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:35:57,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:57,727 EPOCH 10 done: loss 0.0079 - lr: 0.000000 | |
| 2023-10-17 09:35:58,665 DEV : loss 0.2244568020105362 - f1-score (micro avg) 0.8565 | |
| 2023-10-17 09:35:59,046 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:35:59,047 Loading model from best epoch ... | |
| 2023-10-17 09:36:00,460 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 09:36:01,338 | |
| Results: | |
| - F-score (micro) 0.8268 | |
| - F-score (macro) 0.605 | |
| - Accuracy 0.7133 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7610 0.8013 0.7806 151 | |
| pers 0.8750 0.9479 0.9100 96 | |
| work 0.7981 0.8737 0.8342 95 | |
| loc 1.0000 0.3333 0.5000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8043 0.8506 0.8268 348 | |
| macro avg 0.6868 0.5913 0.6050 348 | |
| weighted avg 0.7981 0.8506 0.8218 348 | |
| 2023-10-17 09:36:01,338 ---------------------------------------------------------------------------------------------------- | |