2023-10-17 19:51:52,385 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 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=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 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 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 Train: 1085 sentences 2023-10-17 19:51:52,386 (train_with_dev=False, train_with_test=False) 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 Training Params: 2023-10-17 19:51:52,386 - learning_rate: "3e-05" 2023-10-17 19:51:52,386 - mini_batch_size: "4" 2023-10-17 19:51:52,386 - max_epochs: "10" 2023-10-17 19:51:52,386 - shuffle: "True" 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 Plugins: 2023-10-17 19:51:52,386 - TensorboardLogger 2023-10-17 19:51:52,386 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 19:51:52,386 - metric: "('micro avg', 'f1-score')" 2023-10-17 19:51:52,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,386 Computation: 2023-10-17 19:51:52,386 - compute on device: cuda:0 2023-10-17 19:51:52,386 - embedding storage: none 2023-10-17 19:51:52,387 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,387 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-17 19:51:52,387 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,387 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:51:52,387 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 19:51:53,991 epoch 1 - iter 27/272 - loss 3.68614455 - time (sec): 1.60 - samples/sec: 3013.94 - lr: 0.000003 - momentum: 0.000000 2023-10-17 19:51:55,492 epoch 1 - iter 54/272 - loss 3.27911665 - time (sec): 3.10 - samples/sec: 2936.58 - lr: 0.000006 - momentum: 0.000000 2023-10-17 19:51:57,102 epoch 1 - iter 81/272 - loss 2.42782165 - time (sec): 4.71 - samples/sec: 3172.39 - lr: 0.000009 - momentum: 0.000000 2023-10-17 19:51:58,619 epoch 1 - iter 108/272 - loss 1.93547446 - time (sec): 6.23 - samples/sec: 3222.39 - lr: 0.000012 - momentum: 0.000000 2023-10-17 19:52:00,174 epoch 1 - iter 135/272 - loss 1.66887966 - time (sec): 7.79 - samples/sec: 3167.82 - lr: 0.000015 - momentum: 0.000000 2023-10-17 19:52:01,759 epoch 1 - iter 162/272 - loss 1.43150079 - time (sec): 9.37 - samples/sec: 3235.06 - lr: 0.000018 - momentum: 0.000000 2023-10-17 19:52:03,295 epoch 1 - iter 189/272 - loss 1.27708928 - time (sec): 10.91 - samples/sec: 3248.58 - lr: 0.000021 - momentum: 0.000000 2023-10-17 19:52:05,064 epoch 1 - iter 216/272 - loss 1.11895645 - time (sec): 12.68 - samples/sec: 3302.85 - lr: 0.000024 - momentum: 0.000000 2023-10-17 19:52:06,572 epoch 1 - iter 243/272 - loss 1.03839737 - time (sec): 14.18 - samples/sec: 3295.24 - lr: 0.000027 - momentum: 0.000000 2023-10-17 19:52:08,173 epoch 1 - iter 270/272 - loss 0.95699653 - time (sec): 15.78 - samples/sec: 3280.80 - lr: 0.000030 - momentum: 0.000000 2023-10-17 19:52:08,284 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:08,285 EPOCH 1 done: loss 0.9543 - lr: 0.000030 2023-10-17 19:52:09,325 DEV : loss 0.17717474699020386 - f1-score (micro avg) 0.5914 2023-10-17 19:52:09,329 saving best model 2023-10-17 19:52:09,689 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:11,253 epoch 2 - iter 27/272 - loss 0.16203503 - time (sec): 1.56 - samples/sec: 3304.40 - lr: 0.000030 - momentum: 0.000000 2023-10-17 19:52:12,809 epoch 2 - iter 54/272 - loss 0.17472666 - time (sec): 3.12 - samples/sec: 3375.93 - lr: 0.000029 - momentum: 0.000000 2023-10-17 19:52:14,492 epoch 2 - iter 81/272 - loss 0.18110744 - time (sec): 4.80 - samples/sec: 3347.54 - lr: 0.000029 - momentum: 0.000000 2023-10-17 19:52:16,126 epoch 2 - iter 108/272 - loss 0.17792809 - time (sec): 6.44 - samples/sec: 3312.91 - lr: 0.000029 - momentum: 0.000000 2023-10-17 19:52:17,559 epoch 2 - iter 135/272 - loss 0.17288065 - time (sec): 7.87 - samples/sec: 3279.42 - lr: 0.000028 - momentum: 0.000000 2023-10-17 19:52:19,203 epoch 2 - iter 162/272 - loss 0.18156776 - time (sec): 9.51 - samples/sec: 3278.49 - lr: 0.000028 - momentum: 0.000000 2023-10-17 19:52:20,692 epoch 2 - iter 189/272 - loss 0.17360395 - time (sec): 11.00 - samples/sec: 3239.67 - lr: 0.000028 - momentum: 0.000000 2023-10-17 19:52:22,312 epoch 2 - iter 216/272 - loss 0.16404397 - time (sec): 12.62 - samples/sec: 3275.19 - lr: 0.000027 - momentum: 0.000000 2023-10-17 19:52:23,951 epoch 2 - iter 243/272 - loss 0.15732808 - time (sec): 14.26 - samples/sec: 3265.49 - lr: 0.000027 - momentum: 0.000000 2023-10-17 19:52:25,422 epoch 2 - iter 270/272 - loss 0.15548570 - time (sec): 15.73 - samples/sec: 3287.26 - lr: 0.000027 - momentum: 0.000000 2023-10-17 19:52:25,512 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:25,513 EPOCH 2 done: loss 0.1553 - lr: 0.000027 2023-10-17 19:52:26,935 DEV : loss 0.1165740042924881 - f1-score (micro avg) 0.7687 2023-10-17 19:52:26,939 saving best model 2023-10-17 19:52:27,426 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:29,141 epoch 3 - iter 27/272 - loss 0.07582860 - time (sec): 1.71 - samples/sec: 3187.78 - lr: 0.000026 - momentum: 0.000000 2023-10-17 19:52:30,790 epoch 3 - iter 54/272 - loss 0.08158520 - time (sec): 3.36 - samples/sec: 3334.75 - lr: 0.000026 - momentum: 0.000000 2023-10-17 19:52:32,345 epoch 3 - iter 81/272 - loss 0.08034283 - time (sec): 4.92 - samples/sec: 3356.99 - lr: 0.000026 - momentum: 0.000000 2023-10-17 19:52:33,932 epoch 3 - iter 108/272 - loss 0.08966396 - time (sec): 6.50 - samples/sec: 3372.91 - lr: 0.000025 - momentum: 0.000000 2023-10-17 19:52:35,546 epoch 3 - iter 135/272 - loss 0.08284123 - time (sec): 8.12 - samples/sec: 3357.93 - lr: 0.000025 - momentum: 0.000000 2023-10-17 19:52:37,046 epoch 3 - iter 162/272 - loss 0.08763320 - time (sec): 9.62 - samples/sec: 3337.11 - lr: 0.000025 - momentum: 0.000000 2023-10-17 19:52:38,616 epoch 3 - iter 189/272 - loss 0.08674857 - time (sec): 11.19 - samples/sec: 3323.91 - lr: 0.000024 - momentum: 0.000000 2023-10-17 19:52:40,057 epoch 3 - iter 216/272 - loss 0.08622983 - time (sec): 12.63 - samples/sec: 3291.27 - lr: 0.000024 - momentum: 0.000000 2023-10-17 19:52:41,676 epoch 3 - iter 243/272 - loss 0.08383335 - time (sec): 14.25 - samples/sec: 3304.56 - lr: 0.000024 - momentum: 0.000000 2023-10-17 19:52:43,140 epoch 3 - iter 270/272 - loss 0.08380410 - time (sec): 15.71 - samples/sec: 3298.30 - lr: 0.000023 - momentum: 0.000000 2023-10-17 19:52:43,229 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:43,229 EPOCH 3 done: loss 0.0836 - lr: 0.000023 2023-10-17 19:52:44,666 DEV : loss 0.11597966402769089 - f1-score (micro avg) 0.7549 2023-10-17 19:52:44,671 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:52:46,238 epoch 4 - iter 27/272 - loss 0.03817143 - time (sec): 1.57 - samples/sec: 3114.22 - lr: 0.000023 - momentum: 0.000000 2023-10-17 19:52:47,801 epoch 4 - iter 54/272 - loss 0.03346733 - time (sec): 3.13 - samples/sec: 3175.76 - lr: 0.000023 - momentum: 0.000000 2023-10-17 19:52:49,482 epoch 4 - iter 81/272 - loss 0.04517407 - time (sec): 4.81 - samples/sec: 3294.02 - lr: 0.000022 - momentum: 0.000000 2023-10-17 19:52:50,892 epoch 4 - iter 108/272 - loss 0.04319358 - time (sec): 6.22 - samples/sec: 3243.83 - lr: 0.000022 - momentum: 0.000000 2023-10-17 19:52:52,431 epoch 4 - iter 135/272 - loss 0.04534533 - time (sec): 7.76 - samples/sec: 3249.82 - lr: 0.000022 - momentum: 0.000000 2023-10-17 19:52:54,112 epoch 4 - iter 162/272 - loss 0.04889301 - time (sec): 9.44 - samples/sec: 3285.66 - lr: 0.000021 - momentum: 0.000000 2023-10-17 19:52:55,709 epoch 4 - iter 189/272 - loss 0.05064160 - time (sec): 11.04 - samples/sec: 3265.73 - lr: 0.000021 - momentum: 0.000000 2023-10-17 19:52:57,341 epoch 4 - iter 216/272 - loss 0.05215477 - time (sec): 12.67 - samples/sec: 3256.61 - lr: 0.000021 - momentum: 0.000000 2023-10-17 19:52:58,816 epoch 4 - iter 243/272 - loss 0.05121743 - time (sec): 14.14 - samples/sec: 3280.18 - lr: 0.000020 - momentum: 0.000000 2023-10-17 19:53:00,346 epoch 4 - iter 270/272 - loss 0.05390532 - time (sec): 15.67 - samples/sec: 3301.63 - lr: 0.000020 - momentum: 0.000000 2023-10-17 19:53:00,433 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:00,434 EPOCH 4 done: loss 0.0540 - lr: 0.000020 2023-10-17 19:53:01,866 DEV : loss 0.1187073215842247 - f1-score (micro avg) 0.7993 2023-10-17 19:53:01,870 saving best model 2023-10-17 19:53:02,345 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:03,909 epoch 5 - iter 27/272 - loss 0.04055481 - time (sec): 1.56 - samples/sec: 3484.10 - lr: 0.000020 - momentum: 0.000000 2023-10-17 19:53:05,449 epoch 5 - iter 54/272 - loss 0.04184600 - time (sec): 3.10 - samples/sec: 3498.71 - lr: 0.000019 - momentum: 0.000000 2023-10-17 19:53:06,981 epoch 5 - iter 81/272 - loss 0.03728394 - time (sec): 4.63 - samples/sec: 3467.31 - lr: 0.000019 - momentum: 0.000000 2023-10-17 19:53:08,584 epoch 5 - iter 108/272 - loss 0.03770208 - time (sec): 6.23 - samples/sec: 3376.47 - lr: 0.000019 - momentum: 0.000000 2023-10-17 19:53:10,292 epoch 5 - iter 135/272 - loss 0.03610795 - time (sec): 7.94 - samples/sec: 3291.87 - lr: 0.000018 - momentum: 0.000000 2023-10-17 19:53:11,877 epoch 5 - iter 162/272 - loss 0.03311822 - time (sec): 9.53 - samples/sec: 3282.79 - lr: 0.000018 - momentum: 0.000000 2023-10-17 19:53:13,423 epoch 5 - iter 189/272 - loss 0.03480952 - time (sec): 11.07 - samples/sec: 3272.28 - lr: 0.000018 - momentum: 0.000000 2023-10-17 19:53:15,042 epoch 5 - iter 216/272 - loss 0.03330190 - time (sec): 12.69 - samples/sec: 3281.77 - lr: 0.000017 - momentum: 0.000000 2023-10-17 19:53:16,639 epoch 5 - iter 243/272 - loss 0.03351532 - time (sec): 14.29 - samples/sec: 3239.63 - lr: 0.000017 - momentum: 0.000000 2023-10-17 19:53:18,245 epoch 5 - iter 270/272 - loss 0.03210995 - time (sec): 15.89 - samples/sec: 3262.48 - lr: 0.000017 - momentum: 0.000000 2023-10-17 19:53:18,326 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:18,326 EPOCH 5 done: loss 0.0321 - lr: 0.000017 2023-10-17 19:53:19,962 DEV : loss 0.1374482363462448 - f1-score (micro avg) 0.8007 2023-10-17 19:53:19,967 saving best model 2023-10-17 19:53:20,434 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:21,874 epoch 6 - iter 27/272 - loss 0.01735343 - time (sec): 1.44 - samples/sec: 3253.81 - lr: 0.000016 - momentum: 0.000000 2023-10-17 19:53:23,513 epoch 6 - iter 54/272 - loss 0.03248622 - time (sec): 3.08 - samples/sec: 3203.61 - lr: 0.000016 - momentum: 0.000000 2023-10-17 19:53:25,105 epoch 6 - iter 81/272 - loss 0.02783744 - time (sec): 4.67 - samples/sec: 3253.09 - lr: 0.000016 - momentum: 0.000000 2023-10-17 19:53:26,637 epoch 6 - iter 108/272 - loss 0.02635058 - time (sec): 6.20 - samples/sec: 3270.39 - lr: 0.000015 - momentum: 0.000000 2023-10-17 19:53:28,205 epoch 6 - iter 135/272 - loss 0.02425374 - time (sec): 7.77 - samples/sec: 3335.38 - lr: 0.000015 - momentum: 0.000000 2023-10-17 19:53:29,847 epoch 6 - iter 162/272 - loss 0.02336843 - time (sec): 9.41 - samples/sec: 3393.10 - lr: 0.000015 - momentum: 0.000000 2023-10-17 19:53:31,441 epoch 6 - iter 189/272 - loss 0.02378891 - time (sec): 11.00 - samples/sec: 3362.54 - lr: 0.000014 - momentum: 0.000000 2023-10-17 19:53:32,990 epoch 6 - iter 216/272 - loss 0.02378025 - time (sec): 12.55 - samples/sec: 3323.37 - lr: 0.000014 - momentum: 0.000000 2023-10-17 19:53:34,525 epoch 6 - iter 243/272 - loss 0.02280147 - time (sec): 14.09 - samples/sec: 3307.37 - lr: 0.000014 - momentum: 0.000000 2023-10-17 19:53:36,095 epoch 6 - iter 270/272 - loss 0.02523429 - time (sec): 15.66 - samples/sec: 3308.99 - lr: 0.000013 - momentum: 0.000000 2023-10-17 19:53:36,194 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:36,194 EPOCH 6 done: loss 0.0252 - lr: 0.000013 2023-10-17 19:53:37,620 DEV : loss 0.15510904788970947 - f1-score (micro avg) 0.8015 2023-10-17 19:53:37,625 saving best model 2023-10-17 19:53:38,100 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:39,945 epoch 7 - iter 27/272 - loss 0.02080006 - time (sec): 1.84 - samples/sec: 3386.14 - lr: 0.000013 - momentum: 0.000000 2023-10-17 19:53:41,440 epoch 7 - iter 54/272 - loss 0.02050320 - time (sec): 3.34 - samples/sec: 3404.08 - lr: 0.000013 - momentum: 0.000000 2023-10-17 19:53:42,852 epoch 7 - iter 81/272 - loss 0.01895013 - time (sec): 4.75 - samples/sec: 3325.27 - lr: 0.000012 - momentum: 0.000000 2023-10-17 19:53:44,336 epoch 7 - iter 108/272 - loss 0.01855506 - time (sec): 6.23 - samples/sec: 3236.28 - lr: 0.000012 - momentum: 0.000000 2023-10-17 19:53:45,911 epoch 7 - iter 135/272 - loss 0.01638277 - time (sec): 7.81 - samples/sec: 3220.02 - lr: 0.000012 - momentum: 0.000000 2023-10-17 19:53:47,494 epoch 7 - iter 162/272 - loss 0.01646283 - time (sec): 9.39 - samples/sec: 3229.98 - lr: 0.000011 - momentum: 0.000000 2023-10-17 19:53:49,033 epoch 7 - iter 189/272 - loss 0.01493295 - time (sec): 10.93 - samples/sec: 3265.83 - lr: 0.000011 - momentum: 0.000000 2023-10-17 19:53:50,573 epoch 7 - iter 216/272 - loss 0.01531514 - time (sec): 12.47 - samples/sec: 3293.68 - lr: 0.000011 - momentum: 0.000000 2023-10-17 19:53:52,264 epoch 7 - iter 243/272 - loss 0.01629045 - time (sec): 14.16 - samples/sec: 3275.62 - lr: 0.000010 - momentum: 0.000000 2023-10-17 19:53:53,909 epoch 7 - iter 270/272 - loss 0.01759728 - time (sec): 15.81 - samples/sec: 3268.76 - lr: 0.000010 - momentum: 0.000000 2023-10-17 19:53:54,017 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:54,017 EPOCH 7 done: loss 0.0175 - lr: 0.000010 2023-10-17 19:53:55,472 DEV : loss 0.1710209846496582 - f1-score (micro avg) 0.8118 2023-10-17 19:53:55,477 saving best model 2023-10-17 19:53:55,954 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:53:57,507 epoch 8 - iter 27/272 - loss 0.01604160 - time (sec): 1.55 - samples/sec: 3207.60 - lr: 0.000010 - momentum: 0.000000 2023-10-17 19:53:59,234 epoch 8 - iter 54/272 - loss 0.01064724 - time (sec): 3.28 - samples/sec: 3353.42 - lr: 0.000009 - momentum: 0.000000 2023-10-17 19:54:00,786 epoch 8 - iter 81/272 - loss 0.00922370 - time (sec): 4.83 - samples/sec: 3384.65 - lr: 0.000009 - momentum: 0.000000 2023-10-17 19:54:02,279 epoch 8 - iter 108/272 - loss 0.01069396 - time (sec): 6.32 - samples/sec: 3298.73 - lr: 0.000009 - momentum: 0.000000 2023-10-17 19:54:03,890 epoch 8 - iter 135/272 - loss 0.01198809 - time (sec): 7.93 - samples/sec: 3323.78 - lr: 0.000008 - momentum: 0.000000 2023-10-17 19:54:05,494 epoch 8 - iter 162/272 - loss 0.01143605 - time (sec): 9.54 - samples/sec: 3313.47 - lr: 0.000008 - momentum: 0.000000 2023-10-17 19:54:07,237 epoch 8 - iter 189/272 - loss 0.01236243 - time (sec): 11.28 - samples/sec: 3354.86 - lr: 0.000008 - momentum: 0.000000 2023-10-17 19:54:08,640 epoch 8 - iter 216/272 - loss 0.01336567 - time (sec): 12.68 - samples/sec: 3310.13 - lr: 0.000007 - momentum: 0.000000 2023-10-17 19:54:10,128 epoch 8 - iter 243/272 - loss 0.01295151 - time (sec): 14.17 - samples/sec: 3263.95 - lr: 0.000007 - momentum: 0.000000 2023-10-17 19:54:11,769 epoch 8 - iter 270/272 - loss 0.01256788 - time (sec): 15.81 - samples/sec: 3273.79 - lr: 0.000007 - momentum: 0.000000 2023-10-17 19:54:11,859 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:11,859 EPOCH 8 done: loss 0.0126 - lr: 0.000007 2023-10-17 19:54:13,299 DEV : loss 0.17594939470291138 - f1-score (micro avg) 0.8118 2023-10-17 19:54:13,305 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:14,823 epoch 9 - iter 27/272 - loss 0.00194437 - time (sec): 1.52 - samples/sec: 3162.49 - lr: 0.000006 - momentum: 0.000000 2023-10-17 19:54:16,484 epoch 9 - iter 54/272 - loss 0.00302095 - time (sec): 3.18 - samples/sec: 3141.62 - lr: 0.000006 - momentum: 0.000000 2023-10-17 19:54:17,957 epoch 9 - iter 81/272 - loss 0.00280715 - time (sec): 4.65 - samples/sec: 3030.41 - lr: 0.000006 - momentum: 0.000000 2023-10-17 19:54:19,699 epoch 9 - iter 108/272 - loss 0.00750767 - time (sec): 6.39 - samples/sec: 3148.64 - lr: 0.000005 - momentum: 0.000000 2023-10-17 19:54:21,168 epoch 9 - iter 135/272 - loss 0.01060348 - time (sec): 7.86 - samples/sec: 3153.49 - lr: 0.000005 - momentum: 0.000000 2023-10-17 19:54:22,717 epoch 9 - iter 162/272 - loss 0.01005783 - time (sec): 9.41 - samples/sec: 3157.07 - lr: 0.000005 - momentum: 0.000000 2023-10-17 19:54:24,425 epoch 9 - iter 189/272 - loss 0.00964176 - time (sec): 11.12 - samples/sec: 3278.39 - lr: 0.000004 - momentum: 0.000000 2023-10-17 19:54:26,194 epoch 9 - iter 216/272 - loss 0.01037476 - time (sec): 12.89 - samples/sec: 3239.70 - lr: 0.000004 - momentum: 0.000000 2023-10-17 19:54:27,722 epoch 9 - iter 243/272 - loss 0.00974212 - time (sec): 14.42 - samples/sec: 3207.43 - lr: 0.000004 - momentum: 0.000000 2023-10-17 19:54:29,301 epoch 9 - iter 270/272 - loss 0.00880051 - time (sec): 15.99 - samples/sec: 3238.36 - lr: 0.000003 - momentum: 0.000000 2023-10-17 19:54:29,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:29,386 EPOCH 9 done: loss 0.0089 - lr: 0.000003 2023-10-17 19:54:30,831 DEV : loss 0.18299776315689087 - f1-score (micro avg) 0.8059 2023-10-17 19:54:30,836 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:32,339 epoch 10 - iter 27/272 - loss 0.00732078 - time (sec): 1.50 - samples/sec: 3372.08 - lr: 0.000003 - momentum: 0.000000 2023-10-17 19:54:33,860 epoch 10 - iter 54/272 - loss 0.00549127 - time (sec): 3.02 - samples/sec: 3236.59 - lr: 0.000003 - momentum: 0.000000 2023-10-17 19:54:35,365 epoch 10 - iter 81/272 - loss 0.00525623 - time (sec): 4.53 - samples/sec: 3208.88 - lr: 0.000002 - momentum: 0.000000 2023-10-17 19:54:36,901 epoch 10 - iter 108/272 - loss 0.00566812 - time (sec): 6.06 - samples/sec: 3298.58 - lr: 0.000002 - momentum: 0.000000 2023-10-17 19:54:38,576 epoch 10 - iter 135/272 - loss 0.00528647 - time (sec): 7.74 - samples/sec: 3324.83 - lr: 0.000002 - momentum: 0.000000 2023-10-17 19:54:40,325 epoch 10 - iter 162/272 - loss 0.00586342 - time (sec): 9.49 - samples/sec: 3329.11 - lr: 0.000001 - momentum: 0.000000 2023-10-17 19:54:41,862 epoch 10 - iter 189/272 - loss 0.00551525 - time (sec): 11.03 - samples/sec: 3281.65 - lr: 0.000001 - momentum: 0.000000 2023-10-17 19:54:43,484 epoch 10 - iter 216/272 - loss 0.00658959 - time (sec): 12.65 - samples/sec: 3263.82 - lr: 0.000001 - momentum: 0.000000 2023-10-17 19:54:45,242 epoch 10 - iter 243/272 - loss 0.00839720 - time (sec): 14.40 - samples/sec: 3257.94 - lr: 0.000000 - momentum: 0.000000 2023-10-17 19:54:46,813 epoch 10 - iter 270/272 - loss 0.00763962 - time (sec): 15.98 - samples/sec: 3242.16 - lr: 0.000000 - momentum: 0.000000 2023-10-17 19:54:46,910 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:46,911 EPOCH 10 done: loss 0.0076 - lr: 0.000000 2023-10-17 19:54:48,333 DEV : loss 0.1869087666273117 - f1-score (micro avg) 0.8067 2023-10-17 19:54:48,709 ---------------------------------------------------------------------------------------------------- 2023-10-17 19:54:48,710 Loading model from best epoch ... 2023-10-17 19:54:50,049 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 2023-10-17 19:54:52,035 Results: - F-score (micro) 0.781 - F-score (macro) 0.7137 - Accuracy 0.6595 By class: precision recall f1-score support LOC 0.7988 0.8526 0.8248 312 PER 0.7143 0.8654 0.7826 208 ORG 0.5778 0.4727 0.5200 55 HumanProd 0.6061 0.9091 0.7273 22 micro avg 0.7421 0.8241 0.7810 597 macro avg 0.6742 0.7749 0.7137 597 weighted avg 0.7419 0.8241 0.7784 597 2023-10-17 19:54:52,036 ----------------------------------------------------------------------------------------------------