| 2023-10-16 19:45:08,871 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 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 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 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 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 Train: 1085 sentences | |
| 2023-10-16 19:45:08,872 (train_with_dev=False, train_with_test=False) | |
| 2023-10-16 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 Training Params: | |
| 2023-10-16 19:45:08,872 - learning_rate: "5e-05" | |
| 2023-10-16 19:45:08,872 - mini_batch_size: "4" | |
| 2023-10-16 19:45:08,872 - max_epochs: "10" | |
| 2023-10-16 19:45:08,872 - shuffle: "True" | |
| 2023-10-16 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 Plugins: | |
| 2023-10-16 19:45:08,872 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-16 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-16 19:45:08,872 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-16 19:45:08,872 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,872 Computation: | |
| 2023-10-16 19:45:08,872 - compute on device: cuda:0 | |
| 2023-10-16 19:45:08,872 - embedding storage: none | |
| 2023-10-16 19:45:08,873 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,873 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-16 19:45:08,873 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:08,873 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:10,678 epoch 1 - iter 27/272 - loss 2.96086262 - time (sec): 1.80 - samples/sec: 3480.03 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-16 19:45:12,125 epoch 1 - iter 54/272 - loss 2.36130554 - time (sec): 3.25 - samples/sec: 3370.99 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-16 19:45:13,608 epoch 1 - iter 81/272 - loss 1.79808365 - time (sec): 4.73 - samples/sec: 3399.34 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-16 19:45:15,120 epoch 1 - iter 108/272 - loss 1.50600816 - time (sec): 6.25 - samples/sec: 3338.13 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-16 19:45:16,814 epoch 1 - iter 135/272 - loss 1.26819459 - time (sec): 7.94 - samples/sec: 3326.24 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-16 19:45:18,426 epoch 1 - iter 162/272 - loss 1.12275943 - time (sec): 9.55 - samples/sec: 3308.46 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-16 19:45:20,100 epoch 1 - iter 189/272 - loss 0.99283442 - time (sec): 11.23 - samples/sec: 3339.66 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-16 19:45:21,612 epoch 1 - iter 216/272 - loss 0.91857983 - time (sec): 12.74 - samples/sec: 3290.94 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 19:45:23,087 epoch 1 - iter 243/272 - loss 0.85492511 - time (sec): 14.21 - samples/sec: 3292.10 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-16 19:45:24,709 epoch 1 - iter 270/272 - loss 0.79776594 - time (sec): 15.84 - samples/sec: 3260.44 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 19:45:24,835 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:24,835 EPOCH 1 done: loss 0.7948 - lr: 0.000049 | |
| 2023-10-16 19:45:25,760 DEV : loss 0.15580207109451294 - f1-score (micro avg) 0.663 | |
| 2023-10-16 19:45:25,769 saving best model | |
| 2023-10-16 19:45:26,201 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:27,812 epoch 2 - iter 27/272 - loss 0.14714516 - time (sec): 1.61 - samples/sec: 3341.25 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 19:45:29,482 epoch 2 - iter 54/272 - loss 0.15012254 - time (sec): 3.28 - samples/sec: 3322.33 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-16 19:45:31,464 epoch 2 - iter 81/272 - loss 0.15178807 - time (sec): 5.26 - samples/sec: 3282.77 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-16 19:45:33,059 epoch 2 - iter 108/272 - loss 0.16371495 - time (sec): 6.86 - samples/sec: 3245.66 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-16 19:45:34,472 epoch 2 - iter 135/272 - loss 0.16423471 - time (sec): 8.27 - samples/sec: 3245.58 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-16 19:45:35,972 epoch 2 - iter 162/272 - loss 0.15787672 - time (sec): 9.77 - samples/sec: 3277.95 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-16 19:45:37,380 epoch 2 - iter 189/272 - loss 0.15891193 - time (sec): 11.18 - samples/sec: 3247.36 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-16 19:45:38,984 epoch 2 - iter 216/272 - loss 0.14944095 - time (sec): 12.78 - samples/sec: 3302.38 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-16 19:45:40,408 epoch 2 - iter 243/272 - loss 0.15144390 - time (sec): 14.21 - samples/sec: 3280.60 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-16 19:45:41,987 epoch 2 - iter 270/272 - loss 0.15335946 - time (sec): 15.78 - samples/sec: 3268.76 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-16 19:45:42,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:42,124 EPOCH 2 done: loss 0.1529 - lr: 0.000045 | |
| 2023-10-16 19:45:43,604 DEV : loss 0.10786943882703781 - f1-score (micro avg) 0.7299 | |
| 2023-10-16 19:45:43,610 saving best model | |
| 2023-10-16 19:45:44,174 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:45:45,775 epoch 3 - iter 27/272 - loss 0.11497974 - time (sec): 1.60 - samples/sec: 3353.49 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-16 19:45:47,367 epoch 3 - iter 54/272 - loss 0.11897320 - time (sec): 3.19 - samples/sec: 3381.17 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-16 19:45:48,752 epoch 3 - iter 81/272 - loss 0.10305969 - time (sec): 4.58 - samples/sec: 3299.87 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-16 19:45:50,470 epoch 3 - iter 108/272 - loss 0.09887392 - time (sec): 6.29 - samples/sec: 3243.54 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-16 19:45:52,108 epoch 3 - iter 135/272 - loss 0.10322268 - time (sec): 7.93 - samples/sec: 3222.86 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-16 19:45:53,627 epoch 3 - iter 162/272 - loss 0.10022417 - time (sec): 9.45 - samples/sec: 3239.27 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-16 19:45:55,059 epoch 3 - iter 189/272 - loss 0.10007514 - time (sec): 10.88 - samples/sec: 3210.32 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-16 19:45:56,642 epoch 3 - iter 216/272 - loss 0.09311613 - time (sec): 12.47 - samples/sec: 3270.13 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 19:45:58,193 epoch 3 - iter 243/272 - loss 0.08965973 - time (sec): 14.02 - samples/sec: 3281.12 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-16 19:45:59,910 epoch 3 - iter 270/272 - loss 0.08566273 - time (sec): 15.73 - samples/sec: 3286.40 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-16 19:46:00,002 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:00,002 EPOCH 3 done: loss 0.0852 - lr: 0.000039 | |
| 2023-10-16 19:46:01,437 DEV : loss 0.12968279421329498 - f1-score (micro avg) 0.7607 | |
| 2023-10-16 19:46:01,441 saving best model | |
| 2023-10-16 19:46:01,910 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:03,507 epoch 4 - iter 27/272 - loss 0.06325830 - time (sec): 1.59 - samples/sec: 3087.79 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-16 19:46:04,958 epoch 4 - iter 54/272 - loss 0.05768070 - time (sec): 3.04 - samples/sec: 3048.52 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-16 19:46:06,497 epoch 4 - iter 81/272 - loss 0.06187859 - time (sec): 4.58 - samples/sec: 3239.23 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-16 19:46:08,091 epoch 4 - iter 108/272 - loss 0.05467391 - time (sec): 6.17 - samples/sec: 3244.93 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-16 19:46:09,593 epoch 4 - iter 135/272 - loss 0.05895317 - time (sec): 7.68 - samples/sec: 3263.99 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-16 19:46:11,140 epoch 4 - iter 162/272 - loss 0.05428778 - time (sec): 9.22 - samples/sec: 3279.22 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-16 19:46:12,830 epoch 4 - iter 189/272 - loss 0.05499807 - time (sec): 10.91 - samples/sec: 3261.29 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-16 19:46:14,528 epoch 4 - iter 216/272 - loss 0.05405387 - time (sec): 12.61 - samples/sec: 3255.85 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-16 19:46:16,104 epoch 4 - iter 243/272 - loss 0.05087587 - time (sec): 14.19 - samples/sec: 3254.79 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-16 19:46:17,735 epoch 4 - iter 270/272 - loss 0.05246963 - time (sec): 15.82 - samples/sec: 3280.27 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-16 19:46:17,816 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:17,816 EPOCH 4 done: loss 0.0531 - lr: 0.000033 | |
| 2023-10-16 19:46:19,246 DEV : loss 0.1382606476545334 - f1-score (micro avg) 0.7804 | |
| 2023-10-16 19:46:19,251 saving best model | |
| 2023-10-16 19:46:19,747 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:21,212 epoch 5 - iter 27/272 - loss 0.02778358 - time (sec): 1.46 - samples/sec: 3105.59 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-16 19:46:22,688 epoch 5 - iter 54/272 - loss 0.02467950 - time (sec): 2.94 - samples/sec: 3262.26 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-16 19:46:24,296 epoch 5 - iter 81/272 - loss 0.03050316 - time (sec): 4.55 - samples/sec: 3337.02 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-16 19:46:25,861 epoch 5 - iter 108/272 - loss 0.02863410 - time (sec): 6.11 - samples/sec: 3368.48 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-16 19:46:27,445 epoch 5 - iter 135/272 - loss 0.02590019 - time (sec): 7.69 - samples/sec: 3328.21 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-16 19:46:28,998 epoch 5 - iter 162/272 - loss 0.02918530 - time (sec): 9.25 - samples/sec: 3350.04 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-16 19:46:30,642 epoch 5 - iter 189/272 - loss 0.03505049 - time (sec): 10.89 - samples/sec: 3332.87 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-16 19:46:32,147 epoch 5 - iter 216/272 - loss 0.03695742 - time (sec): 12.40 - samples/sec: 3348.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-16 19:46:33,693 epoch 5 - iter 243/272 - loss 0.03836264 - time (sec): 13.94 - samples/sec: 3324.84 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-16 19:46:35,304 epoch 5 - iter 270/272 - loss 0.04024680 - time (sec): 15.55 - samples/sec: 3318.24 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-16 19:46:35,410 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:35,411 EPOCH 5 done: loss 0.0404 - lr: 0.000028 | |
| 2023-10-16 19:46:37,035 DEV : loss 0.13831038773059845 - f1-score (micro avg) 0.8281 | |
| 2023-10-16 19:46:37,039 saving best model | |
| 2023-10-16 19:46:37,537 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:39,141 epoch 6 - iter 27/272 - loss 0.02201561 - time (sec): 1.60 - samples/sec: 3173.74 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-16 19:46:40,759 epoch 6 - iter 54/272 - loss 0.02366348 - time (sec): 3.22 - samples/sec: 3202.67 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-16 19:46:42,240 epoch 6 - iter 81/272 - loss 0.02393184 - time (sec): 4.70 - samples/sec: 3243.73 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-16 19:46:43,674 epoch 6 - iter 108/272 - loss 0.02461930 - time (sec): 6.13 - samples/sec: 3228.93 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-16 19:46:45,268 epoch 6 - iter 135/272 - loss 0.03024604 - time (sec): 7.73 - samples/sec: 3287.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-16 19:46:46,899 epoch 6 - iter 162/272 - loss 0.03209193 - time (sec): 9.36 - samples/sec: 3323.90 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-16 19:46:48,464 epoch 6 - iter 189/272 - loss 0.02936378 - time (sec): 10.92 - samples/sec: 3333.47 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-16 19:46:50,208 epoch 6 - iter 216/272 - loss 0.02718790 - time (sec): 12.67 - samples/sec: 3331.93 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-16 19:46:51,727 epoch 6 - iter 243/272 - loss 0.02497498 - time (sec): 14.19 - samples/sec: 3327.98 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-16 19:46:53,259 epoch 6 - iter 270/272 - loss 0.02583978 - time (sec): 15.72 - samples/sec: 3301.49 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-16 19:46:53,349 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:53,349 EPOCH 6 done: loss 0.0259 - lr: 0.000022 | |
| 2023-10-16 19:46:54,778 DEV : loss 0.16786816716194153 - f1-score (micro avg) 0.829 | |
| 2023-10-16 19:46:54,782 saving best model | |
| 2023-10-16 19:46:55,269 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:46:56,998 epoch 7 - iter 27/272 - loss 0.01192496 - time (sec): 1.72 - samples/sec: 3108.05 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-16 19:46:58,498 epoch 7 - iter 54/272 - loss 0.01313309 - time (sec): 3.22 - samples/sec: 3116.45 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-16 19:47:00,113 epoch 7 - iter 81/272 - loss 0.01828642 - time (sec): 4.84 - samples/sec: 3302.04 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-16 19:47:01,549 epoch 7 - iter 108/272 - loss 0.01997851 - time (sec): 6.27 - samples/sec: 3220.44 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-16 19:47:03,099 epoch 7 - iter 135/272 - loss 0.01792751 - time (sec): 7.82 - samples/sec: 3184.97 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-16 19:47:04,732 epoch 7 - iter 162/272 - loss 0.01681276 - time (sec): 9.46 - samples/sec: 3254.06 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-16 19:47:06,392 epoch 7 - iter 189/272 - loss 0.01581105 - time (sec): 11.12 - samples/sec: 3294.33 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-16 19:47:08,055 epoch 7 - iter 216/272 - loss 0.01718819 - time (sec): 12.78 - samples/sec: 3281.35 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-16 19:47:09,600 epoch 7 - iter 243/272 - loss 0.01668342 - time (sec): 14.33 - samples/sec: 3274.57 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-16 19:47:11,136 epoch 7 - iter 270/272 - loss 0.01703726 - time (sec): 15.86 - samples/sec: 3270.62 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-16 19:47:11,225 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:11,225 EPOCH 7 done: loss 0.0171 - lr: 0.000017 | |
| 2023-10-16 19:47:12,660 DEV : loss 0.1661759316921234 - f1-score (micro avg) 0.816 | |
| 2023-10-16 19:47:12,665 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:14,262 epoch 8 - iter 27/272 - loss 0.00878954 - time (sec): 1.60 - samples/sec: 3343.98 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-16 19:47:15,837 epoch 8 - iter 54/272 - loss 0.01349225 - time (sec): 3.17 - samples/sec: 3311.94 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-16 19:47:17,393 epoch 8 - iter 81/272 - loss 0.01362705 - time (sec): 4.73 - samples/sec: 3256.86 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-16 19:47:18,911 epoch 8 - iter 108/272 - loss 0.01720786 - time (sec): 6.25 - samples/sec: 3296.03 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-16 19:47:20,416 epoch 8 - iter 135/272 - loss 0.01657915 - time (sec): 7.75 - samples/sec: 3270.86 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-16 19:47:22,232 epoch 8 - iter 162/272 - loss 0.01707526 - time (sec): 9.57 - samples/sec: 3318.88 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-16 19:47:23,687 epoch 8 - iter 189/272 - loss 0.01518853 - time (sec): 11.02 - samples/sec: 3300.73 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-16 19:47:25,183 epoch 8 - iter 216/272 - loss 0.01442840 - time (sec): 12.52 - samples/sec: 3319.84 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-16 19:47:26,605 epoch 8 - iter 243/272 - loss 0.01387485 - time (sec): 13.94 - samples/sec: 3297.79 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-16 19:47:28,370 epoch 8 - iter 270/272 - loss 0.01535666 - time (sec): 15.70 - samples/sec: 3302.33 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-16 19:47:28,453 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:28,454 EPOCH 8 done: loss 0.0153 - lr: 0.000011 | |
| 2023-10-16 19:47:29,907 DEV : loss 0.16990669071674347 - f1-score (micro avg) 0.8168 | |
| 2023-10-16 19:47:29,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:31,702 epoch 9 - iter 27/272 - loss 0.00924822 - time (sec): 1.79 - samples/sec: 3811.79 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-16 19:47:33,246 epoch 9 - iter 54/272 - loss 0.00584536 - time (sec): 3.33 - samples/sec: 3549.08 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-16 19:47:34,939 epoch 9 - iter 81/272 - loss 0.00695411 - time (sec): 5.03 - samples/sec: 3275.93 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-16 19:47:36,477 epoch 9 - iter 108/272 - loss 0.00913707 - time (sec): 6.56 - samples/sec: 3308.04 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-16 19:47:38,135 epoch 9 - iter 135/272 - loss 0.00808347 - time (sec): 8.22 - samples/sec: 3302.30 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-16 19:47:39,677 epoch 9 - iter 162/272 - loss 0.00873095 - time (sec): 9.76 - samples/sec: 3269.77 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-16 19:47:41,210 epoch 9 - iter 189/272 - loss 0.00838996 - time (sec): 11.30 - samples/sec: 3294.32 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-16 19:47:42,757 epoch 9 - iter 216/272 - loss 0.00860744 - time (sec): 12.84 - samples/sec: 3270.87 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-16 19:47:44,332 epoch 9 - iter 243/272 - loss 0.00878071 - time (sec): 14.42 - samples/sec: 3269.45 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-16 19:47:45,829 epoch 9 - iter 270/272 - loss 0.00852981 - time (sec): 15.92 - samples/sec: 3256.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-16 19:47:45,921 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:45,921 EPOCH 9 done: loss 0.0085 - lr: 0.000006 | |
| 2023-10-16 19:47:47,348 DEV : loss 0.1631445735692978 - f1-score (micro avg) 0.8278 | |
| 2023-10-16 19:47:47,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:47:48,866 epoch 10 - iter 27/272 - loss 0.00818875 - time (sec): 1.51 - samples/sec: 3617.91 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-16 19:47:50,236 epoch 10 - iter 54/272 - loss 0.00537678 - time (sec): 2.88 - samples/sec: 3331.19 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-16 19:47:51,839 epoch 10 - iter 81/272 - loss 0.00434446 - time (sec): 4.49 - samples/sec: 3324.57 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-16 19:47:53,372 epoch 10 - iter 108/272 - loss 0.00584214 - time (sec): 6.02 - samples/sec: 3338.86 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-16 19:47:54,917 epoch 10 - iter 135/272 - loss 0.00657058 - time (sec): 7.56 - samples/sec: 3321.54 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-16 19:47:56,668 epoch 10 - iter 162/272 - loss 0.00641731 - time (sec): 9.31 - samples/sec: 3306.33 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-16 19:47:58,254 epoch 10 - iter 189/272 - loss 0.00705789 - time (sec): 10.90 - samples/sec: 3309.06 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-16 19:47:59,767 epoch 10 - iter 216/272 - loss 0.00738649 - time (sec): 12.41 - samples/sec: 3293.63 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-16 19:48:01,330 epoch 10 - iter 243/272 - loss 0.00671284 - time (sec): 13.98 - samples/sec: 3278.61 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-16 19:48:02,982 epoch 10 - iter 270/272 - loss 0.00632955 - time (sec): 15.63 - samples/sec: 3315.19 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-16 19:48:03,063 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:48:03,063 EPOCH 10 done: loss 0.0063 - lr: 0.000000 | |
| 2023-10-16 19:48:04,504 DEV : loss 0.1695002317428589 - f1-score (micro avg) 0.8275 | |
| 2023-10-16 19:48:04,845 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-16 19:48:04,846 Loading model from best epoch ... | |
| 2023-10-16 19:48:06,389 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 19:48:08,347 | |
| Results: | |
| - F-score (micro) 0.7847 | |
| - F-score (macro) 0.746 | |
| - Accuracy 0.6601 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.7865 0.8974 0.8383 312 | |
| PER 0.6822 0.8462 0.7554 208 | |
| ORG 0.5814 0.4545 0.5102 55 | |
| HumanProd 0.7857 1.0000 0.8800 22 | |
| micro avg 0.7343 0.8425 0.7847 597 | |
| macro avg 0.7089 0.7995 0.7460 597 | |
| weighted avg 0.7312 0.8425 0.7807 597 | |
| 2023-10-16 19:48:08,347 ---------------------------------------------------------------------------------------------------- | |