| 2023-10-16 20:11:42,385 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,386 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=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 MultiCorpus: 1085 train + 148 dev + 364 test sentences | |
| - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Train: 1085 sentences | |
| 2023-10-16 20:11:42,387 (train_with_dev=False, train_with_test=False) | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Training Params: | |
| 2023-10-16 20:11:42,387 - learning_rate: "5e-05" | |
| 2023-10-16 20:11:42,387 - mini_batch_size: "4" | |
| 2023-10-16 20:11:42,387 - max_epochs: "10" | |
| 2023-10-16 20:11:42,387 - shuffle: "True" | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Plugins: | |
| 2023-10-16 20:11:42,387 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-16 20:11:42,387 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Computation: | |
| 2023-10-16 20:11:42,387 - compute on device: cuda:0 | |
| 2023-10-16 20:11:42,387 - embedding storage: none | |
| 2023-10-16 20:11:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,387 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-16 20:11:42,388 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:42,388 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:43,924 epoch 1 - iter 27/272 - loss 2.95922567 - time (sec): 1.54 - samples/sec: 3298.78 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-16 20:11:45,701 epoch 1 - iter 54/272 - loss 2.32051200 - time (sec): 3.31 - samples/sec: 3299.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-16 20:11:47,348 epoch 1 - iter 81/272 - loss 1.73864625 - time (sec): 4.96 - samples/sec: 3285.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-16 20:11:48,971 epoch 1 - iter 108/272 - loss 1.38585266 - time (sec): 6.58 - samples/sec: 3350.45 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-16 20:11:50,588 epoch 1 - iter 135/272 - loss 1.17450241 - time (sec): 8.20 - samples/sec: 3370.04 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-16 20:11:52,042 epoch 1 - iter 162/272 - loss 1.06209535 - time (sec): 9.65 - samples/sec: 3333.26 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-16 20:11:53,643 epoch 1 - iter 189/272 - loss 0.95412205 - time (sec): 11.25 - samples/sec: 3293.65 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-16 20:11:55,144 epoch 1 - iter 216/272 - loss 0.87249746 - time (sec): 12.75 - samples/sec: 3282.64 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 20:11:56,784 epoch 1 - iter 243/272 - loss 0.79404191 - time (sec): 14.39 - samples/sec: 3282.89 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-16 20:11:58,211 epoch 1 - iter 270/272 - loss 0.74711671 - time (sec): 15.82 - samples/sec: 3271.21 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 20:11:58,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:11:58,297 EPOCH 1 done: loss 0.7444 - lr: 0.000049 | |
| 2023-10-16 20:11:59,192 DEV : loss 0.13936997950077057 - f1-score (micro avg) 0.7209 | |
| 2023-10-16 20:11:59,200 saving best model | |
| 2023-10-16 20:11:59,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:01,066 epoch 2 - iter 27/272 - loss 0.16359337 - time (sec): 1.49 - samples/sec: 3175.52 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 20:12:02,642 epoch 2 - iter 54/272 - loss 0.13838335 - time (sec): 3.07 - samples/sec: 3239.45 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 20:12:04,264 epoch 2 - iter 81/272 - loss 0.12859783 - time (sec): 4.69 - samples/sec: 3280.03 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-16 20:12:05,734 epoch 2 - iter 108/272 - loss 0.13307366 - time (sec): 6.16 - samples/sec: 3296.41 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-16 20:12:07,240 epoch 2 - iter 135/272 - loss 0.14563773 - time (sec): 7.67 - samples/sec: 3232.49 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-16 20:12:08,846 epoch 2 - iter 162/272 - loss 0.14873637 - time (sec): 9.27 - samples/sec: 3204.70 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-16 20:12:10,597 epoch 2 - iter 189/272 - loss 0.14467753 - time (sec): 11.02 - samples/sec: 3196.66 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-16 20:12:12,254 epoch 2 - iter 216/272 - loss 0.14245295 - time (sec): 12.68 - samples/sec: 3238.99 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-16 20:12:13,895 epoch 2 - iter 243/272 - loss 0.13866363 - time (sec): 14.32 - samples/sec: 3251.61 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-16 20:12:15,469 epoch 2 - iter 270/272 - loss 0.13692941 - time (sec): 15.90 - samples/sec: 3264.82 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-16 20:12:15,550 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:15,550 EPOCH 2 done: loss 0.1367 - lr: 0.000045 | |
| 2023-10-16 20:12:17,247 DEV : loss 0.1134832352399826 - f1-score (micro avg) 0.7569 | |
| 2023-10-16 20:12:17,252 saving best model | |
| 2023-10-16 20:12:17,749 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:19,424 epoch 3 - iter 27/272 - loss 0.10085692 - time (sec): 1.67 - samples/sec: 3479.84 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-16 20:12:21,055 epoch 3 - iter 54/272 - loss 0.09648160 - time (sec): 3.30 - samples/sec: 3521.68 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-16 20:12:22,603 epoch 3 - iter 81/272 - loss 0.08501000 - time (sec): 4.85 - samples/sec: 3374.61 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-16 20:12:24,277 epoch 3 - iter 108/272 - loss 0.09393010 - time (sec): 6.53 - samples/sec: 3289.17 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-16 20:12:25,730 epoch 3 - iter 135/272 - loss 0.09122040 - time (sec): 7.98 - samples/sec: 3250.99 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-16 20:12:27,230 epoch 3 - iter 162/272 - loss 0.08865571 - time (sec): 9.48 - samples/sec: 3247.59 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-16 20:12:28,936 epoch 3 - iter 189/272 - loss 0.08680863 - time (sec): 11.19 - samples/sec: 3292.09 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-16 20:12:30,418 epoch 3 - iter 216/272 - loss 0.08315365 - time (sec): 12.67 - samples/sec: 3273.29 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 20:12:31,934 epoch 3 - iter 243/272 - loss 0.08167352 - time (sec): 14.18 - samples/sec: 3281.90 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 20:12:33,576 epoch 3 - iter 270/272 - loss 0.08177957 - time (sec): 15.83 - samples/sec: 3270.36 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-16 20:12:33,663 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:33,663 EPOCH 3 done: loss 0.0815 - lr: 0.000039 | |
| 2023-10-16 20:12:35,145 DEV : loss 0.12934227287769318 - f1-score (micro avg) 0.7786 | |
| 2023-10-16 20:12:35,150 saving best model | |
| 2023-10-16 20:12:35,614 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:37,307 epoch 4 - iter 27/272 - loss 0.06994923 - time (sec): 1.69 - samples/sec: 3074.91 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-16 20:12:38,883 epoch 4 - iter 54/272 - loss 0.05718223 - time (sec): 3.27 - samples/sec: 3239.55 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-16 20:12:40,442 epoch 4 - iter 81/272 - loss 0.05004048 - time (sec): 4.83 - samples/sec: 3312.38 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-16 20:12:42,095 epoch 4 - iter 108/272 - loss 0.05133187 - time (sec): 6.48 - samples/sec: 3323.67 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-16 20:12:43,593 epoch 4 - iter 135/272 - loss 0.05180209 - time (sec): 7.98 - samples/sec: 3261.06 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-16 20:12:45,363 epoch 4 - iter 162/272 - loss 0.05254018 - time (sec): 9.75 - samples/sec: 3283.13 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-16 20:12:46,964 epoch 4 - iter 189/272 - loss 0.05384827 - time (sec): 11.35 - samples/sec: 3256.76 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-16 20:12:48,626 epoch 4 - iter 216/272 - loss 0.05136057 - time (sec): 13.01 - samples/sec: 3235.03 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-16 20:12:50,220 epoch 4 - iter 243/272 - loss 0.04939585 - time (sec): 14.60 - samples/sec: 3250.81 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-16 20:12:51,632 epoch 4 - iter 270/272 - loss 0.04895622 - time (sec): 16.02 - samples/sec: 3237.43 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-16 20:12:51,724 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:51,724 EPOCH 4 done: loss 0.0490 - lr: 0.000033 | |
| 2023-10-16 20:12:53,185 DEV : loss 0.13081075251102448 - f1-score (micro avg) 0.8286 | |
| 2023-10-16 20:12:53,192 saving best model | |
| 2023-10-16 20:12:53,667 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:12:55,298 epoch 5 - iter 27/272 - loss 0.05425176 - time (sec): 1.63 - samples/sec: 3037.57 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-16 20:12:56,770 epoch 5 - iter 54/272 - loss 0.05287029 - time (sec): 3.10 - samples/sec: 3045.97 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-16 20:12:58,299 epoch 5 - iter 81/272 - loss 0.04416411 - time (sec): 4.63 - samples/sec: 3241.53 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-16 20:13:00,025 epoch 5 - iter 108/272 - loss 0.04256412 - time (sec): 6.35 - samples/sec: 3175.71 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-16 20:13:01,566 epoch 5 - iter 135/272 - loss 0.03979846 - time (sec): 7.89 - samples/sec: 3164.58 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-16 20:13:03,123 epoch 5 - iter 162/272 - loss 0.03933371 - time (sec): 9.45 - samples/sec: 3186.42 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-16 20:13:04,803 epoch 5 - iter 189/272 - loss 0.03588228 - time (sec): 11.13 - samples/sec: 3207.14 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-16 20:13:06,412 epoch 5 - iter 216/272 - loss 0.03528880 - time (sec): 12.74 - samples/sec: 3224.43 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-16 20:13:07,991 epoch 5 - iter 243/272 - loss 0.03455066 - time (sec): 14.32 - samples/sec: 3225.97 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-16 20:13:09,530 epoch 5 - iter 270/272 - loss 0.03343776 - time (sec): 15.86 - samples/sec: 3240.11 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-16 20:13:09,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:09,727 EPOCH 5 done: loss 0.0331 - lr: 0.000028 | |
| 2023-10-16 20:13:11,202 DEV : loss 0.1527273952960968 - f1-score (micro avg) 0.7935 | |
| 2023-10-16 20:13:11,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:12,713 epoch 6 - iter 27/272 - loss 0.01883225 - time (sec): 1.51 - samples/sec: 3001.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-16 20:13:14,269 epoch 6 - iter 54/272 - loss 0.02182728 - time (sec): 3.06 - samples/sec: 3091.68 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-16 20:13:15,971 epoch 6 - iter 81/272 - loss 0.02015877 - time (sec): 4.76 - samples/sec: 3205.41 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-16 20:13:17,821 epoch 6 - iter 108/272 - loss 0.02272207 - time (sec): 6.61 - samples/sec: 3260.86 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-16 20:13:19,409 epoch 6 - iter 135/272 - loss 0.02407593 - time (sec): 8.20 - samples/sec: 3271.97 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-16 20:13:21,087 epoch 6 - iter 162/272 - loss 0.02539970 - time (sec): 9.88 - samples/sec: 3142.44 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-16 20:13:22,652 epoch 6 - iter 189/272 - loss 0.02622946 - time (sec): 11.44 - samples/sec: 3134.59 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-16 20:13:24,262 epoch 6 - iter 216/272 - loss 0.02509676 - time (sec): 13.05 - samples/sec: 3177.71 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-16 20:13:25,864 epoch 6 - iter 243/272 - loss 0.02277234 - time (sec): 14.66 - samples/sec: 3224.19 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-16 20:13:27,277 epoch 6 - iter 270/272 - loss 0.02396847 - time (sec): 16.07 - samples/sec: 3224.61 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-16 20:13:27,369 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:27,369 EPOCH 6 done: loss 0.0242 - lr: 0.000022 | |
| 2023-10-16 20:13:28,839 DEV : loss 0.15852421522140503 - f1-score (micro avg) 0.8133 | |
| 2023-10-16 20:13:28,844 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:30,407 epoch 7 - iter 27/272 - loss 0.01518661 - time (sec): 1.56 - samples/sec: 3243.62 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-16 20:13:32,194 epoch 7 - iter 54/272 - loss 0.01064029 - time (sec): 3.35 - samples/sec: 3364.96 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-16 20:13:33,880 epoch 7 - iter 81/272 - loss 0.01487741 - time (sec): 5.04 - samples/sec: 3289.63 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-16 20:13:35,587 epoch 7 - iter 108/272 - loss 0.02170189 - time (sec): 6.74 - samples/sec: 3303.03 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-16 20:13:37,127 epoch 7 - iter 135/272 - loss 0.02038448 - time (sec): 8.28 - samples/sec: 3261.03 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-16 20:13:38,794 epoch 7 - iter 162/272 - loss 0.01901781 - time (sec): 9.95 - samples/sec: 3299.77 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-16 20:13:40,322 epoch 7 - iter 189/272 - loss 0.01954576 - time (sec): 11.48 - samples/sec: 3287.24 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-16 20:13:41,770 epoch 7 - iter 216/272 - loss 0.01865636 - time (sec): 12.93 - samples/sec: 3273.03 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-16 20:13:43,348 epoch 7 - iter 243/272 - loss 0.01877717 - time (sec): 14.50 - samples/sec: 3253.76 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-16 20:13:44,842 epoch 7 - iter 270/272 - loss 0.01826347 - time (sec): 16.00 - samples/sec: 3234.50 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-16 20:13:44,935 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:44,936 EPOCH 7 done: loss 0.0182 - lr: 0.000017 | |
| 2023-10-16 20:13:46,403 DEV : loss 0.1606188863515854 - f1-score (micro avg) 0.8022 | |
| 2023-10-16 20:13:46,409 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:13:47,916 epoch 8 - iter 27/272 - loss 0.01279749 - time (sec): 1.51 - samples/sec: 2910.79 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-16 20:13:49,411 epoch 8 - iter 54/272 - loss 0.01405124 - time (sec): 3.00 - samples/sec: 3058.02 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-16 20:13:50,897 epoch 8 - iter 81/272 - loss 0.01180266 - time (sec): 4.49 - samples/sec: 3078.08 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-16 20:13:52,510 epoch 8 - iter 108/272 - loss 0.01124551 - time (sec): 6.10 - samples/sec: 3145.57 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-16 20:13:54,170 epoch 8 - iter 135/272 - loss 0.01015956 - time (sec): 7.76 - samples/sec: 3180.26 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-16 20:13:55,748 epoch 8 - iter 162/272 - loss 0.00918604 - time (sec): 9.34 - samples/sec: 3204.25 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-16 20:13:57,409 epoch 8 - iter 189/272 - loss 0.00923296 - time (sec): 11.00 - samples/sec: 3250.85 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-16 20:13:59,023 epoch 8 - iter 216/272 - loss 0.01026326 - time (sec): 12.61 - samples/sec: 3222.45 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-16 20:14:00,747 epoch 8 - iter 243/272 - loss 0.01130313 - time (sec): 14.34 - samples/sec: 3254.11 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-16 20:14:02,335 epoch 8 - iter 270/272 - loss 0.01201146 - time (sec): 15.92 - samples/sec: 3246.25 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-16 20:14:02,434 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:02,434 EPOCH 8 done: loss 0.0119 - lr: 0.000011 | |
| 2023-10-16 20:14:03,922 DEV : loss 0.1735740751028061 - f1-score (micro avg) 0.8111 | |
| 2023-10-16 20:14:03,928 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:05,664 epoch 9 - iter 27/272 - loss 0.01240591 - time (sec): 1.73 - samples/sec: 3381.09 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-16 20:14:07,209 epoch 9 - iter 54/272 - loss 0.00910613 - time (sec): 3.28 - samples/sec: 3363.52 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-16 20:14:08,673 epoch 9 - iter 81/272 - loss 0.01017944 - time (sec): 4.74 - samples/sec: 3238.20 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-16 20:14:10,290 epoch 9 - iter 108/272 - loss 0.00815891 - time (sec): 6.36 - samples/sec: 3269.78 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-16 20:14:11,895 epoch 9 - iter 135/272 - loss 0.00791519 - time (sec): 7.97 - samples/sec: 3293.98 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-16 20:14:13,471 epoch 9 - iter 162/272 - loss 0.00875581 - time (sec): 9.54 - samples/sec: 3304.22 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-16 20:14:15,146 epoch 9 - iter 189/272 - loss 0.00801884 - time (sec): 11.22 - samples/sec: 3260.87 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-16 20:14:16,833 epoch 9 - iter 216/272 - loss 0.00860070 - time (sec): 12.90 - samples/sec: 3289.81 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-16 20:14:18,379 epoch 9 - iter 243/272 - loss 0.00817350 - time (sec): 14.45 - samples/sec: 3288.83 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-16 20:14:19,871 epoch 9 - iter 270/272 - loss 0.00901566 - time (sec): 15.94 - samples/sec: 3254.91 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-16 20:14:19,958 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:19,958 EPOCH 9 done: loss 0.0091 - lr: 0.000006 | |
| 2023-10-16 20:14:21,469 DEV : loss 0.16326886415481567 - f1-score (micro avg) 0.8095 | |
| 2023-10-16 20:14:21,475 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:23,346 epoch 10 - iter 27/272 - loss 0.00105081 - time (sec): 1.87 - samples/sec: 2931.62 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-16 20:14:24,727 epoch 10 - iter 54/272 - loss 0.00079658 - time (sec): 3.25 - samples/sec: 2951.64 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-16 20:14:26,210 epoch 10 - iter 81/272 - loss 0.00416132 - time (sec): 4.73 - samples/sec: 2993.52 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-16 20:14:27,787 epoch 10 - iter 108/272 - loss 0.00376567 - time (sec): 6.31 - samples/sec: 3094.50 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-16 20:14:29,309 epoch 10 - iter 135/272 - loss 0.00421615 - time (sec): 7.83 - samples/sec: 3150.25 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-16 20:14:30,754 epoch 10 - iter 162/272 - loss 0.00373493 - time (sec): 9.28 - samples/sec: 3136.20 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-16 20:14:32,440 epoch 10 - iter 189/272 - loss 0.00621518 - time (sec): 10.96 - samples/sec: 3185.75 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-16 20:14:34,013 epoch 10 - iter 216/272 - loss 0.00638498 - time (sec): 12.54 - samples/sec: 3209.92 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-16 20:14:35,653 epoch 10 - iter 243/272 - loss 0.00582988 - time (sec): 14.18 - samples/sec: 3226.26 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-16 20:14:37,311 epoch 10 - iter 270/272 - loss 0.00598226 - time (sec): 15.84 - samples/sec: 3263.04 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-16 20:14:37,397 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:37,397 EPOCH 10 done: loss 0.0059 - lr: 0.000000 | |
| 2023-10-16 20:14:38,897 DEV : loss 0.17024299502372742 - f1-score (micro avg) 0.792 | |
| 2023-10-16 20:14:39,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 20:14:39,274 Loading model from best epoch ... | |
| 2023-10-16 20:14:40,853 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-16 20:14:42,964 | |
| Results: | |
| - F-score (micro) 0.7734 | |
| - F-score (macro) 0.7221 | |
| - Accuracy 0.647 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8306 0.8173 0.8239 312 | |
| PER 0.7296 0.8173 0.7710 208 | |
| ORG 0.4815 0.4727 0.4771 55 | |
| HumanProd 0.7407 0.9091 0.8163 22 | |
| micro avg 0.7585 0.7889 0.7734 597 | |
| macro avg 0.6956 0.7541 0.7221 597 | |
| weighted avg 0.7600 0.7889 0.7732 597 | |
| 2023-10-16 20:14:42,964 ---------------------------------------------------------------------------------------------------- | |