2023-10-17 17:51:15,725 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,726 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 17:51:15,726 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 MultiCorpus: 1166 train + 165 dev + 415 test sentences - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Train: 1166 sentences 2023-10-17 17:51:15,727 (train_with_dev=False, train_with_test=False) 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Training Params: 2023-10-17 17:51:15,727 - learning_rate: "5e-05" 2023-10-17 17:51:15,727 - mini_batch_size: "8" 2023-10-17 17:51:15,727 - max_epochs: "10" 2023-10-17 17:51:15,727 - shuffle: "True" 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Plugins: 2023-10-17 17:51:15,727 - TensorboardLogger 2023-10-17 17:51:15,727 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 17:51:15,727 - metric: "('micro avg', 'f1-score')" 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Computation: 2023-10-17 17:51:15,727 - compute on device: cuda:0 2023-10-17 17:51:15,727 - embedding storage: none 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:15,728 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 17:51:17,221 epoch 1 - iter 14/146 - loss 3.64932727 - time (sec): 1.49 - samples/sec: 2867.39 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:51:18,616 epoch 1 - iter 28/146 - loss 3.24147358 - time (sec): 2.89 - samples/sec: 3050.04 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:51:20,366 epoch 1 - iter 42/146 - loss 2.52637762 - time (sec): 4.64 - samples/sec: 2820.99 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:51:21,662 epoch 1 - iter 56/146 - loss 2.07805214 - time (sec): 5.93 - samples/sec: 2843.80 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:51:22,860 epoch 1 - iter 70/146 - loss 1.82936614 - time (sec): 7.13 - samples/sec: 2864.60 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:51:24,170 epoch 1 - iter 84/146 - loss 1.60733726 - time (sec): 8.44 - samples/sec: 2875.49 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:51:25,653 epoch 1 - iter 98/146 - loss 1.41652938 - time (sec): 9.92 - samples/sec: 2901.33 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:51:26,915 epoch 1 - iter 112/146 - loss 1.29603818 - time (sec): 11.19 - samples/sec: 2910.85 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:51:28,301 epoch 1 - iter 126/146 - loss 1.18560723 - time (sec): 12.57 - samples/sec: 2914.11 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:51:30,183 epoch 1 - iter 140/146 - loss 1.07325034 - time (sec): 14.45 - samples/sec: 2922.08 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:51:31,007 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:31,008 EPOCH 1 done: loss 1.0409 - lr: 0.000048 2023-10-17 17:51:31,833 DEV : loss 0.19442486763000488 - f1-score (micro avg) 0.4893 2023-10-17 17:51:31,838 saving best model 2023-10-17 17:51:32,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:33,822 epoch 2 - iter 14/146 - loss 0.28292930 - time (sec): 1.65 - samples/sec: 2889.28 - lr: 0.000050 - momentum: 0.000000 2023-10-17 17:51:35,067 epoch 2 - iter 28/146 - loss 0.25593623 - time (sec): 2.90 - samples/sec: 2924.31 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:51:36,271 epoch 2 - iter 42/146 - loss 0.24056504 - time (sec): 4.10 - samples/sec: 2973.51 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:51:37,400 epoch 2 - iter 56/146 - loss 0.24098347 - time (sec): 5.23 - samples/sec: 3023.55 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:51:39,011 epoch 2 - iter 70/146 - loss 0.23990925 - time (sec): 6.84 - samples/sec: 3004.42 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:51:40,625 epoch 2 - iter 84/146 - loss 0.22035000 - time (sec): 8.46 - samples/sec: 2931.59 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:51:42,021 epoch 2 - iter 98/146 - loss 0.20717226 - time (sec): 9.85 - samples/sec: 2902.48 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:51:43,290 epoch 2 - iter 112/146 - loss 0.20187917 - time (sec): 11.12 - samples/sec: 2913.22 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:51:44,685 epoch 2 - iter 126/146 - loss 0.19646511 - time (sec): 12.52 - samples/sec: 2935.37 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:51:46,635 epoch 2 - iter 140/146 - loss 0.18970816 - time (sec): 14.46 - samples/sec: 2944.06 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:51:47,195 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:47,195 EPOCH 2 done: loss 0.1871 - lr: 0.000045 2023-10-17 17:51:48,684 DEV : loss 0.12840227782726288 - f1-score (micro avg) 0.6597 2023-10-17 17:51:48,690 saving best model 2023-10-17 17:51:49,150 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:50,352 epoch 3 - iter 14/146 - loss 0.12172571 - time (sec): 1.20 - samples/sec: 2897.39 - lr: 0.000044 - momentum: 0.000000 2023-10-17 17:51:52,174 epoch 3 - iter 28/146 - loss 0.09513845 - time (sec): 3.02 - samples/sec: 2796.32 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:51:53,613 epoch 3 - iter 42/146 - loss 0.09306659 - time (sec): 4.46 - samples/sec: 2847.48 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:51:55,371 epoch 3 - iter 56/146 - loss 0.08892443 - time (sec): 6.22 - samples/sec: 2801.67 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:51:56,653 epoch 3 - iter 70/146 - loss 0.09802952 - time (sec): 7.50 - samples/sec: 2817.17 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:51:58,035 epoch 3 - iter 84/146 - loss 0.09938552 - time (sec): 8.88 - samples/sec: 2849.02 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:51:59,244 epoch 3 - iter 98/146 - loss 0.09932542 - time (sec): 10.09 - samples/sec: 2830.08 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:52:00,940 epoch 3 - iter 112/146 - loss 0.09988457 - time (sec): 11.79 - samples/sec: 2851.55 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:52:02,529 epoch 3 - iter 126/146 - loss 0.09937404 - time (sec): 13.38 - samples/sec: 2840.97 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:52:04,197 epoch 3 - iter 140/146 - loss 0.10083464 - time (sec): 15.04 - samples/sec: 2855.29 - lr: 0.000039 - momentum: 0.000000 2023-10-17 17:52:04,661 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:04,661 EPOCH 3 done: loss 0.0986 - lr: 0.000039 2023-10-17 17:52:05,924 DEV : loss 0.11469055712223053 - f1-score (micro avg) 0.7558 2023-10-17 17:52:05,929 saving best model 2023-10-17 17:52:06,381 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:07,886 epoch 4 - iter 14/146 - loss 0.08001683 - time (sec): 1.50 - samples/sec: 3162.98 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:52:09,311 epoch 4 - iter 28/146 - loss 0.08313806 - time (sec): 2.92 - samples/sec: 3113.44 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:52:10,918 epoch 4 - iter 42/146 - loss 0.08932962 - time (sec): 4.53 - samples/sec: 2955.43 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:52:12,208 epoch 4 - iter 56/146 - loss 0.08311168 - time (sec): 5.82 - samples/sec: 2896.03 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:52:13,719 epoch 4 - iter 70/146 - loss 0.07749470 - time (sec): 7.33 - samples/sec: 2885.81 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:52:15,338 epoch 4 - iter 84/146 - loss 0.07439762 - time (sec): 8.95 - samples/sec: 2898.06 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:52:16,556 epoch 4 - iter 98/146 - loss 0.07128648 - time (sec): 10.17 - samples/sec: 2885.30 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:52:17,985 epoch 4 - iter 112/146 - loss 0.07040154 - time (sec): 11.60 - samples/sec: 2874.41 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:52:19,504 epoch 4 - iter 126/146 - loss 0.06725890 - time (sec): 13.12 - samples/sec: 2895.24 - lr: 0.000034 - momentum: 0.000000 2023-10-17 17:52:21,050 epoch 4 - iter 140/146 - loss 0.06467563 - time (sec): 14.66 - samples/sec: 2904.48 - lr: 0.000034 - momentum: 0.000000 2023-10-17 17:52:21,683 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:21,684 EPOCH 4 done: loss 0.0643 - lr: 0.000034 2023-10-17 17:52:22,973 DEV : loss 0.12082179635763168 - f1-score (micro avg) 0.7424 2023-10-17 17:52:22,978 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:24,381 epoch 5 - iter 14/146 - loss 0.06422344 - time (sec): 1.40 - samples/sec: 2739.89 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:52:25,958 epoch 5 - iter 28/146 - loss 0.05442231 - time (sec): 2.98 - samples/sec: 2842.57 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:52:27,408 epoch 5 - iter 42/146 - loss 0.04507790 - time (sec): 4.43 - samples/sec: 2940.79 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:52:29,131 epoch 5 - iter 56/146 - loss 0.05002005 - time (sec): 6.15 - samples/sec: 2884.12 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:52:30,452 epoch 5 - iter 70/146 - loss 0.04635323 - time (sec): 7.47 - samples/sec: 2896.08 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:52:31,711 epoch 5 - iter 84/146 - loss 0.04594857 - time (sec): 8.73 - samples/sec: 2876.47 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:52:33,300 epoch 5 - iter 98/146 - loss 0.04185253 - time (sec): 10.32 - samples/sec: 2899.36 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:52:34,569 epoch 5 - iter 112/146 - loss 0.04051975 - time (sec): 11.59 - samples/sec: 2904.58 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:52:36,442 epoch 5 - iter 126/146 - loss 0.04226250 - time (sec): 13.46 - samples/sec: 2874.79 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:52:37,925 epoch 5 - iter 140/146 - loss 0.04401633 - time (sec): 14.95 - samples/sec: 2857.55 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:52:38,457 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:38,458 EPOCH 5 done: loss 0.0431 - lr: 0.000028 2023-10-17 17:52:39,713 DEV : loss 0.12378506362438202 - f1-score (micro avg) 0.7638 2023-10-17 17:52:39,718 saving best model 2023-10-17 17:52:40,156 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:41,483 epoch 6 - iter 14/146 - loss 0.02821174 - time (sec): 1.32 - samples/sec: 2970.80 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:52:43,424 epoch 6 - iter 28/146 - loss 0.02719467 - time (sec): 3.27 - samples/sec: 2716.97 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:52:44,685 epoch 6 - iter 42/146 - loss 0.02593663 - time (sec): 4.53 - samples/sec: 2689.02 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:52:46,264 epoch 6 - iter 56/146 - loss 0.02530266 - time (sec): 6.11 - samples/sec: 2759.35 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:52:48,033 epoch 6 - iter 70/146 - loss 0.02607955 - time (sec): 7.87 - samples/sec: 2739.94 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:52:49,466 epoch 6 - iter 84/146 - loss 0.02856308 - time (sec): 9.31 - samples/sec: 2799.68 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:52:50,941 epoch 6 - iter 98/146 - loss 0.03007988 - time (sec): 10.78 - samples/sec: 2810.94 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:52:52,315 epoch 6 - iter 112/146 - loss 0.02972773 - time (sec): 12.16 - samples/sec: 2807.81 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:52:53,786 epoch 6 - iter 126/146 - loss 0.02975220 - time (sec): 13.63 - samples/sec: 2816.61 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:52:55,150 epoch 6 - iter 140/146 - loss 0.03021626 - time (sec): 14.99 - samples/sec: 2858.97 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:52:55,649 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:55,649 EPOCH 6 done: loss 0.0306 - lr: 0.000023 2023-10-17 17:52:56,904 DEV : loss 0.1446683704853058 - f1-score (micro avg) 0.7591 2023-10-17 17:52:56,909 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:58,252 epoch 7 - iter 14/146 - loss 0.01067881 - time (sec): 1.34 - samples/sec: 2768.15 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:52:59,748 epoch 7 - iter 28/146 - loss 0.01553625 - time (sec): 2.84 - samples/sec: 2972.30 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:53:01,210 epoch 7 - iter 42/146 - loss 0.02338274 - time (sec): 4.30 - samples/sec: 3013.27 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:53:02,788 epoch 7 - iter 56/146 - loss 0.02276518 - time (sec): 5.88 - samples/sec: 2958.23 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:53:04,135 epoch 7 - iter 70/146 - loss 0.02040107 - time (sec): 7.22 - samples/sec: 2979.45 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:53:05,707 epoch 7 - iter 84/146 - loss 0.01887587 - time (sec): 8.80 - samples/sec: 2899.23 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:53:07,090 epoch 7 - iter 98/146 - loss 0.02062489 - time (sec): 10.18 - samples/sec: 2927.81 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:53:08,404 epoch 7 - iter 112/146 - loss 0.02270664 - time (sec): 11.49 - samples/sec: 2967.68 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:53:10,026 epoch 7 - iter 126/146 - loss 0.02108995 - time (sec): 13.12 - samples/sec: 2940.26 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:53:11,723 epoch 7 - iter 140/146 - loss 0.02146590 - time (sec): 14.81 - samples/sec: 2904.13 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:53:12,214 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:12,214 EPOCH 7 done: loss 0.0221 - lr: 0.000017 2023-10-17 17:53:13,493 DEV : loss 0.13926248252391815 - f1-score (micro avg) 0.7588 2023-10-17 17:53:13,498 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:14,805 epoch 8 - iter 14/146 - loss 0.04199538 - time (sec): 1.31 - samples/sec: 2869.25 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:53:16,360 epoch 8 - iter 28/146 - loss 0.03623353 - time (sec): 2.86 - samples/sec: 2858.33 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:53:17,765 epoch 8 - iter 42/146 - loss 0.02909497 - time (sec): 4.27 - samples/sec: 2789.70 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:53:19,130 epoch 8 - iter 56/146 - loss 0.02582501 - time (sec): 5.63 - samples/sec: 2822.08 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:53:20,472 epoch 8 - iter 70/146 - loss 0.02248507 - time (sec): 6.97 - samples/sec: 2905.70 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:53:21,992 epoch 8 - iter 84/146 - loss 0.02039668 - time (sec): 8.49 - samples/sec: 2948.75 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:53:23,243 epoch 8 - iter 98/146 - loss 0.02065091 - time (sec): 9.74 - samples/sec: 2953.56 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:53:24,793 epoch 8 - iter 112/146 - loss 0.01976567 - time (sec): 11.29 - samples/sec: 2967.93 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:53:26,152 epoch 8 - iter 126/146 - loss 0.01878112 - time (sec): 12.65 - samples/sec: 2964.08 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:53:27,832 epoch 8 - iter 140/146 - loss 0.01820202 - time (sec): 14.33 - samples/sec: 2977.10 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:53:28,544 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:28,544 EPOCH 8 done: loss 0.0180 - lr: 0.000012 2023-10-17 17:53:29,816 DEV : loss 0.1338219791650772 - f1-score (micro avg) 0.8125 2023-10-17 17:53:29,821 saving best model 2023-10-17 17:53:30,265 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:31,690 epoch 9 - iter 14/146 - loss 0.00900173 - time (sec): 1.42 - samples/sec: 3146.38 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:53:33,172 epoch 9 - iter 28/146 - loss 0.01353775 - time (sec): 2.91 - samples/sec: 2969.76 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:53:34,800 epoch 9 - iter 42/146 - loss 0.01411638 - time (sec): 4.53 - samples/sec: 2925.56 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:53:36,570 epoch 9 - iter 56/146 - loss 0.01717406 - time (sec): 6.30 - samples/sec: 2832.55 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:53:38,322 epoch 9 - iter 70/146 - loss 0.01651724 - time (sec): 8.06 - samples/sec: 2779.14 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:53:39,653 epoch 9 - iter 84/146 - loss 0.01447022 - time (sec): 9.39 - samples/sec: 2809.42 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:53:41,289 epoch 9 - iter 98/146 - loss 0.01305284 - time (sec): 11.02 - samples/sec: 2793.58 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:53:42,484 epoch 9 - iter 112/146 - loss 0.01276152 - time (sec): 12.22 - samples/sec: 2817.73 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:53:43,877 epoch 9 - iter 126/146 - loss 0.01240197 - time (sec): 13.61 - samples/sec: 2825.26 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:53:45,221 epoch 9 - iter 140/146 - loss 0.01247661 - time (sec): 14.95 - samples/sec: 2864.35 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:53:45,888 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:45,888 EPOCH 9 done: loss 0.0125 - lr: 0.000006 2023-10-17 17:53:47,153 DEV : loss 0.1447986215353012 - f1-score (micro avg) 0.7973 2023-10-17 17:53:47,157 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:48,470 epoch 10 - iter 14/146 - loss 0.01128755 - time (sec): 1.31 - samples/sec: 3088.10 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:53:49,879 epoch 10 - iter 28/146 - loss 0.01029360 - time (sec): 2.72 - samples/sec: 2992.37 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:53:51,519 epoch 10 - iter 42/146 - loss 0.01240356 - time (sec): 4.36 - samples/sec: 2861.25 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:53:52,894 epoch 10 - iter 56/146 - loss 0.01088444 - time (sec): 5.74 - samples/sec: 2944.20 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:53:54,438 epoch 10 - iter 70/146 - loss 0.01024052 - time (sec): 7.28 - samples/sec: 2969.04 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:53:56,006 epoch 10 - iter 84/146 - loss 0.00903528 - time (sec): 8.85 - samples/sec: 2930.05 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:53:57,751 epoch 10 - iter 98/146 - loss 0.01043615 - time (sec): 10.59 - samples/sec: 2857.32 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:53:59,290 epoch 10 - iter 112/146 - loss 0.01019047 - time (sec): 12.13 - samples/sec: 2865.50 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:54:00,771 epoch 10 - iter 126/146 - loss 0.00966469 - time (sec): 13.61 - samples/sec: 2864.12 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:54:02,058 epoch 10 - iter 140/146 - loss 0.01137448 - time (sec): 14.90 - samples/sec: 2865.91 - lr: 0.000000 - momentum: 0.000000 2023-10-17 17:54:02,617 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:54:02,617 EPOCH 10 done: loss 0.0111 - lr: 0.000000 2023-10-17 17:54:03,903 DEV : loss 0.14230762422084808 - f1-score (micro avg) 0.8044 2023-10-17 17:54:04,247 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:54:04,249 Loading model from best epoch ... 2023-10-17 17:54:05,633 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-17 17:54:08,070 Results: - F-score (micro) 0.7704 - F-score (macro) 0.7203 - Accuracy 0.6484 By class: precision recall f1-score support PER 0.8179 0.8649 0.8408 348 LOC 0.6503 0.8123 0.7223 261 ORG 0.5745 0.5192 0.5455 52 HumanProd 0.7727 0.7727 0.7727 22 micro avg 0.7300 0.8155 0.7704 683 macro avg 0.7039 0.7423 0.7203 683 weighted avg 0.7339 0.8155 0.7708 683 2023-10-17 17:54:08,070 ----------------------------------------------------------------------------------------------------