2023-10-17 18:18:51,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 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 18:18:51,728 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 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 18:18:51,728 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 Train: 1166 sentences 2023-10-17 18:18:51,728 (train_with_dev=False, train_with_test=False) 2023-10-17 18:18:51,728 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 Training Params: 2023-10-17 18:18:51,728 - learning_rate: "5e-05" 2023-10-17 18:18:51,728 - mini_batch_size: "8" 2023-10-17 18:18:51,728 - max_epochs: "10" 2023-10-17 18:18:51,728 - shuffle: "True" 2023-10-17 18:18:51,728 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 Plugins: 2023-10-17 18:18:51,728 - TensorboardLogger 2023-10-17 18:18:51,728 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 18:18:51,728 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,728 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 18:18:51,728 - metric: "('micro avg', 'f1-score')" 2023-10-17 18:18:51,729 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,729 Computation: 2023-10-17 18:18:51,729 - compute on device: cuda:0 2023-10-17 18:18:51,729 - embedding storage: none 2023-10-17 18:18:51,729 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,729 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-17 18:18:51,729 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,729 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:18:51,729 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 18:18:53,207 epoch 1 - iter 14/146 - loss 3.57138140 - time (sec): 1.48 - samples/sec: 3117.02 - lr: 0.000004 - momentum: 0.000000 2023-10-17 18:18:54,839 epoch 1 - iter 28/146 - loss 3.25629001 - time (sec): 3.11 - samples/sec: 2929.60 - lr: 0.000009 - momentum: 0.000000 2023-10-17 18:18:56,377 epoch 1 - iter 42/146 - loss 2.62329353 - time (sec): 4.65 - samples/sec: 2849.91 - lr: 0.000014 - momentum: 0.000000 2023-10-17 18:18:58,017 epoch 1 - iter 56/146 - loss 2.16516736 - time (sec): 6.29 - samples/sec: 2897.17 - lr: 0.000019 - momentum: 0.000000 2023-10-17 18:18:59,544 epoch 1 - iter 70/146 - loss 1.79573783 - time (sec): 7.81 - samples/sec: 2954.85 - lr: 0.000024 - momentum: 0.000000 2023-10-17 18:19:00,998 epoch 1 - iter 84/146 - loss 1.58428127 - time (sec): 9.27 - samples/sec: 2941.43 - lr: 0.000028 - momentum: 0.000000 2023-10-17 18:19:02,279 epoch 1 - iter 98/146 - loss 1.44725030 - time (sec): 10.55 - samples/sec: 2972.42 - lr: 0.000033 - momentum: 0.000000 2023-10-17 18:19:03,479 epoch 1 - iter 112/146 - loss 1.32663289 - time (sec): 11.75 - samples/sec: 2990.30 - lr: 0.000038 - momentum: 0.000000 2023-10-17 18:19:04,639 epoch 1 - iter 126/146 - loss 1.23401294 - time (sec): 12.91 - samples/sec: 2988.08 - lr: 0.000043 - momentum: 0.000000 2023-10-17 18:19:06,192 epoch 1 - iter 140/146 - loss 1.13546776 - time (sec): 14.46 - samples/sec: 2968.79 - lr: 0.000048 - momentum: 0.000000 2023-10-17 18:19:06,709 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:06,709 EPOCH 1 done: loss 1.1051 - lr: 0.000048 2023-10-17 18:19:07,780 DEV : loss 0.18029391765594482 - f1-score (micro avg) 0.4518 2023-10-17 18:19:07,786 saving best model 2023-10-17 18:19:08,120 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:09,578 epoch 2 - iter 14/146 - loss 0.20642889 - time (sec): 1.46 - samples/sec: 3236.63 - lr: 0.000050 - momentum: 0.000000 2023-10-17 18:19:10,987 epoch 2 - iter 28/146 - loss 0.19816193 - time (sec): 2.87 - samples/sec: 3059.66 - lr: 0.000049 - momentum: 0.000000 2023-10-17 18:19:12,153 epoch 2 - iter 42/146 - loss 0.21577244 - time (sec): 4.03 - samples/sec: 3137.94 - lr: 0.000048 - momentum: 0.000000 2023-10-17 18:19:13,699 epoch 2 - iter 56/146 - loss 0.21590787 - time (sec): 5.58 - samples/sec: 3016.92 - lr: 0.000048 - momentum: 0.000000 2023-10-17 18:19:15,252 epoch 2 - iter 70/146 - loss 0.20769861 - time (sec): 7.13 - samples/sec: 2997.00 - lr: 0.000047 - momentum: 0.000000 2023-10-17 18:19:16,922 epoch 2 - iter 84/146 - loss 0.19984801 - time (sec): 8.80 - samples/sec: 2995.60 - lr: 0.000047 - momentum: 0.000000 2023-10-17 18:19:18,566 epoch 2 - iter 98/146 - loss 0.19155294 - time (sec): 10.44 - samples/sec: 3007.57 - lr: 0.000046 - momentum: 0.000000 2023-10-17 18:19:19,863 epoch 2 - iter 112/146 - loss 0.19859158 - time (sec): 11.74 - samples/sec: 3030.45 - lr: 0.000046 - momentum: 0.000000 2023-10-17 18:19:21,351 epoch 2 - iter 126/146 - loss 0.19709102 - time (sec): 13.23 - samples/sec: 2962.73 - lr: 0.000045 - momentum: 0.000000 2023-10-17 18:19:22,731 epoch 2 - iter 140/146 - loss 0.19273806 - time (sec): 14.61 - samples/sec: 2964.24 - lr: 0.000045 - momentum: 0.000000 2023-10-17 18:19:23,139 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:23,139 EPOCH 2 done: loss 0.1917 - lr: 0.000045 2023-10-17 18:19:24,422 DEV : loss 0.1203632652759552 - f1-score (micro avg) 0.6582 2023-10-17 18:19:24,428 saving best model 2023-10-17 18:19:24,853 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:26,517 epoch 3 - iter 14/146 - loss 0.09267755 - time (sec): 1.66 - samples/sec: 2600.35 - lr: 0.000044 - momentum: 0.000000 2023-10-17 18:19:27,981 epoch 3 - iter 28/146 - loss 0.10326544 - time (sec): 3.13 - samples/sec: 2865.97 - lr: 0.000043 - momentum: 0.000000 2023-10-17 18:19:29,298 epoch 3 - iter 42/146 - loss 0.09818320 - time (sec): 4.44 - samples/sec: 2782.45 - lr: 0.000043 - momentum: 0.000000 2023-10-17 18:19:30,952 epoch 3 - iter 56/146 - loss 0.09912457 - time (sec): 6.10 - samples/sec: 2856.56 - lr: 0.000042 - momentum: 0.000000 2023-10-17 18:19:32,383 epoch 3 - iter 70/146 - loss 0.09709361 - time (sec): 7.53 - samples/sec: 2916.81 - lr: 0.000042 - momentum: 0.000000 2023-10-17 18:19:33,511 epoch 3 - iter 84/146 - loss 0.09349095 - time (sec): 8.66 - samples/sec: 2928.46 - lr: 0.000041 - momentum: 0.000000 2023-10-17 18:19:34,943 epoch 3 - iter 98/146 - loss 0.09138427 - time (sec): 10.09 - samples/sec: 2961.60 - lr: 0.000041 - momentum: 0.000000 2023-10-17 18:19:36,615 epoch 3 - iter 112/146 - loss 0.10036149 - time (sec): 11.76 - samples/sec: 2903.60 - lr: 0.000040 - momentum: 0.000000 2023-10-17 18:19:38,076 epoch 3 - iter 126/146 - loss 0.09911074 - time (sec): 13.22 - samples/sec: 2908.58 - lr: 0.000040 - momentum: 0.000000 2023-10-17 18:19:39,489 epoch 3 - iter 140/146 - loss 0.10141433 - time (sec): 14.63 - samples/sec: 2910.08 - lr: 0.000039 - momentum: 0.000000 2023-10-17 18:19:40,109 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:40,109 EPOCH 3 done: loss 0.1021 - lr: 0.000039 2023-10-17 18:19:41,334 DEV : loss 0.11388804763555527 - f1-score (micro avg) 0.6987 2023-10-17 18:19:41,339 saving best model 2023-10-17 18:19:41,750 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:43,144 epoch 4 - iter 14/146 - loss 0.06414953 - time (sec): 1.39 - samples/sec: 3119.81 - lr: 0.000038 - momentum: 0.000000 2023-10-17 18:19:44,622 epoch 4 - iter 28/146 - loss 0.05727491 - time (sec): 2.87 - samples/sec: 3113.91 - lr: 0.000038 - momentum: 0.000000 2023-10-17 18:19:45,777 epoch 4 - iter 42/146 - loss 0.05337460 - time (sec): 4.02 - samples/sec: 3175.45 - lr: 0.000037 - momentum: 0.000000 2023-10-17 18:19:47,224 epoch 4 - iter 56/146 - loss 0.05571035 - time (sec): 5.47 - samples/sec: 3116.51 - lr: 0.000037 - momentum: 0.000000 2023-10-17 18:19:48,677 epoch 4 - iter 70/146 - loss 0.05504218 - time (sec): 6.92 - samples/sec: 3039.65 - lr: 0.000036 - momentum: 0.000000 2023-10-17 18:19:49,994 epoch 4 - iter 84/146 - loss 0.05492070 - time (sec): 8.24 - samples/sec: 3050.17 - lr: 0.000036 - momentum: 0.000000 2023-10-17 18:19:51,688 epoch 4 - iter 98/146 - loss 0.06015328 - time (sec): 9.94 - samples/sec: 3020.01 - lr: 0.000035 - momentum: 0.000000 2023-10-17 18:19:53,192 epoch 4 - iter 112/146 - loss 0.06333164 - time (sec): 11.44 - samples/sec: 3024.92 - lr: 0.000035 - momentum: 0.000000 2023-10-17 18:19:54,596 epoch 4 - iter 126/146 - loss 0.06145486 - time (sec): 12.84 - samples/sec: 2992.93 - lr: 0.000034 - momentum: 0.000000 2023-10-17 18:19:56,082 epoch 4 - iter 140/146 - loss 0.06061764 - time (sec): 14.33 - samples/sec: 2988.54 - lr: 0.000034 - momentum: 0.000000 2023-10-17 18:19:56,587 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:56,587 EPOCH 4 done: loss 0.0598 - lr: 0.000034 2023-10-17 18:19:57,821 DEV : loss 0.1203216090798378 - f1-score (micro avg) 0.7059 2023-10-17 18:19:57,827 saving best model 2023-10-17 18:19:58,254 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:19:59,666 epoch 5 - iter 14/146 - loss 0.06225692 - time (sec): 1.41 - samples/sec: 2691.92 - lr: 0.000033 - momentum: 0.000000 2023-10-17 18:20:01,084 epoch 5 - iter 28/146 - loss 0.04994899 - time (sec): 2.83 - samples/sec: 2840.72 - lr: 0.000032 - momentum: 0.000000 2023-10-17 18:20:02,658 epoch 5 - iter 42/146 - loss 0.04348932 - time (sec): 4.40 - samples/sec: 2902.82 - lr: 0.000032 - momentum: 0.000000 2023-10-17 18:20:03,902 epoch 5 - iter 56/146 - loss 0.03584489 - time (sec): 5.65 - samples/sec: 2918.20 - lr: 0.000031 - momentum: 0.000000 2023-10-17 18:20:05,298 epoch 5 - iter 70/146 - loss 0.04017369 - time (sec): 7.04 - samples/sec: 2968.42 - lr: 0.000031 - momentum: 0.000000 2023-10-17 18:20:06,800 epoch 5 - iter 84/146 - loss 0.04557808 - time (sec): 8.54 - samples/sec: 2966.33 - lr: 0.000030 - momentum: 0.000000 2023-10-17 18:20:08,284 epoch 5 - iter 98/146 - loss 0.04297787 - time (sec): 10.03 - samples/sec: 2971.64 - lr: 0.000030 - momentum: 0.000000 2023-10-17 18:20:09,323 epoch 5 - iter 112/146 - loss 0.04523185 - time (sec): 11.07 - samples/sec: 2988.29 - lr: 0.000029 - momentum: 0.000000 2023-10-17 18:20:10,752 epoch 5 - iter 126/146 - loss 0.04441842 - time (sec): 12.50 - samples/sec: 3007.23 - lr: 0.000029 - momentum: 0.000000 2023-10-17 18:20:12,525 epoch 5 - iter 140/146 - loss 0.04365021 - time (sec): 14.27 - samples/sec: 2987.44 - lr: 0.000028 - momentum: 0.000000 2023-10-17 18:20:13,147 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:13,148 EPOCH 5 done: loss 0.0434 - lr: 0.000028 2023-10-17 18:20:14,430 DEV : loss 0.13626918196678162 - f1-score (micro avg) 0.7626 2023-10-17 18:20:14,435 saving best model 2023-10-17 18:20:14,859 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:16,178 epoch 6 - iter 14/146 - loss 0.02567778 - time (sec): 1.32 - samples/sec: 2909.87 - lr: 0.000027 - momentum: 0.000000 2023-10-17 18:20:17,659 epoch 6 - iter 28/146 - loss 0.02978228 - time (sec): 2.80 - samples/sec: 2840.82 - lr: 0.000027 - momentum: 0.000000 2023-10-17 18:20:19,453 epoch 6 - iter 42/146 - loss 0.02585818 - time (sec): 4.59 - samples/sec: 2744.48 - lr: 0.000026 - momentum: 0.000000 2023-10-17 18:20:21,013 epoch 6 - iter 56/146 - loss 0.02827968 - time (sec): 6.15 - samples/sec: 2777.90 - lr: 0.000026 - momentum: 0.000000 2023-10-17 18:20:22,447 epoch 6 - iter 70/146 - loss 0.03036843 - time (sec): 7.59 - samples/sec: 2776.72 - lr: 0.000025 - momentum: 0.000000 2023-10-17 18:20:23,931 epoch 6 - iter 84/146 - loss 0.02907844 - time (sec): 9.07 - samples/sec: 2764.46 - lr: 0.000025 - momentum: 0.000000 2023-10-17 18:20:25,337 epoch 6 - iter 98/146 - loss 0.02934355 - time (sec): 10.48 - samples/sec: 2805.93 - lr: 0.000024 - momentum: 0.000000 2023-10-17 18:20:26,986 epoch 6 - iter 112/146 - loss 0.03072343 - time (sec): 12.13 - samples/sec: 2840.23 - lr: 0.000024 - momentum: 0.000000 2023-10-17 18:20:28,501 epoch 6 - iter 126/146 - loss 0.02984132 - time (sec): 13.64 - samples/sec: 2851.61 - lr: 0.000023 - momentum: 0.000000 2023-10-17 18:20:29,795 epoch 6 - iter 140/146 - loss 0.02945338 - time (sec): 14.93 - samples/sec: 2865.59 - lr: 0.000023 - momentum: 0.000000 2023-10-17 18:20:30,379 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:30,379 EPOCH 6 done: loss 0.0291 - lr: 0.000023 2023-10-17 18:20:31,674 DEV : loss 0.12430983781814575 - f1-score (micro avg) 0.7601 2023-10-17 18:20:31,685 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:33,162 epoch 7 - iter 14/146 - loss 0.01936975 - time (sec): 1.48 - samples/sec: 2723.21 - lr: 0.000022 - momentum: 0.000000 2023-10-17 18:20:34,672 epoch 7 - iter 28/146 - loss 0.02306047 - time (sec): 2.99 - samples/sec: 2848.46 - lr: 0.000021 - momentum: 0.000000 2023-10-17 18:20:36,124 epoch 7 - iter 42/146 - loss 0.02391709 - time (sec): 4.44 - samples/sec: 2826.28 - lr: 0.000021 - momentum: 0.000000 2023-10-17 18:20:37,323 epoch 7 - iter 56/146 - loss 0.02142364 - time (sec): 5.64 - samples/sec: 2838.38 - lr: 0.000020 - momentum: 0.000000 2023-10-17 18:20:38,950 epoch 7 - iter 70/146 - loss 0.02362173 - time (sec): 7.26 - samples/sec: 2818.86 - lr: 0.000020 - momentum: 0.000000 2023-10-17 18:20:40,530 epoch 7 - iter 84/146 - loss 0.02178736 - time (sec): 8.84 - samples/sec: 2859.09 - lr: 0.000019 - momentum: 0.000000 2023-10-17 18:20:41,874 epoch 7 - iter 98/146 - loss 0.02161645 - time (sec): 10.19 - samples/sec: 2885.03 - lr: 0.000019 - momentum: 0.000000 2023-10-17 18:20:43,483 epoch 7 - iter 112/146 - loss 0.01989179 - time (sec): 11.80 - samples/sec: 2911.61 - lr: 0.000018 - momentum: 0.000000 2023-10-17 18:20:44,838 epoch 7 - iter 126/146 - loss 0.02011158 - time (sec): 13.15 - samples/sec: 2934.47 - lr: 0.000018 - momentum: 0.000000 2023-10-17 18:20:46,397 epoch 7 - iter 140/146 - loss 0.02190589 - time (sec): 14.71 - samples/sec: 2915.69 - lr: 0.000017 - momentum: 0.000000 2023-10-17 18:20:46,912 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:46,912 EPOCH 7 done: loss 0.0220 - lr: 0.000017 2023-10-17 18:20:48,161 DEV : loss 0.13426262140274048 - f1-score (micro avg) 0.7555 2023-10-17 18:20:48,166 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:20:49,790 epoch 8 - iter 14/146 - loss 0.00931042 - time (sec): 1.62 - samples/sec: 2783.08 - lr: 0.000016 - momentum: 0.000000 2023-10-17 18:20:51,345 epoch 8 - iter 28/146 - loss 0.01739007 - time (sec): 3.18 - samples/sec: 2910.73 - lr: 0.000016 - momentum: 0.000000 2023-10-17 18:20:52,902 epoch 8 - iter 42/146 - loss 0.01451596 - time (sec): 4.74 - samples/sec: 2893.79 - lr: 0.000015 - momentum: 0.000000 2023-10-17 18:20:54,489 epoch 8 - iter 56/146 - loss 0.01415561 - time (sec): 6.32 - samples/sec: 2901.64 - lr: 0.000015 - momentum: 0.000000 2023-10-17 18:20:55,872 epoch 8 - iter 70/146 - loss 0.01323646 - time (sec): 7.71 - samples/sec: 2911.93 - lr: 0.000014 - momentum: 0.000000 2023-10-17 18:20:57,064 epoch 8 - iter 84/146 - loss 0.01398395 - time (sec): 8.90 - samples/sec: 2942.06 - lr: 0.000014 - momentum: 0.000000 2023-10-17 18:20:58,563 epoch 8 - iter 98/146 - loss 0.01498906 - time (sec): 10.40 - samples/sec: 2970.57 - lr: 0.000013 - momentum: 0.000000 2023-10-17 18:20:59,831 epoch 8 - iter 112/146 - loss 0.01619772 - time (sec): 11.66 - samples/sec: 2984.01 - lr: 0.000013 - momentum: 0.000000 2023-10-17 18:21:00,910 epoch 8 - iter 126/146 - loss 0.01546532 - time (sec): 12.74 - samples/sec: 2986.70 - lr: 0.000012 - momentum: 0.000000 2023-10-17 18:21:02,605 epoch 8 - iter 140/146 - loss 0.01469667 - time (sec): 14.44 - samples/sec: 2953.15 - lr: 0.000012 - momentum: 0.000000 2023-10-17 18:21:03,120 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:03,120 EPOCH 8 done: loss 0.0145 - lr: 0.000012 2023-10-17 18:21:04,469 DEV : loss 0.1528475284576416 - f1-score (micro avg) 0.7964 2023-10-17 18:21:04,477 saving best model 2023-10-17 18:21:04,986 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:06,462 epoch 9 - iter 14/146 - loss 0.00654971 - time (sec): 1.47 - samples/sec: 2731.72 - lr: 0.000011 - momentum: 0.000000 2023-10-17 18:21:07,829 epoch 9 - iter 28/146 - loss 0.01042476 - time (sec): 2.84 - samples/sec: 3029.21 - lr: 0.000010 - momentum: 0.000000 2023-10-17 18:21:09,456 epoch 9 - iter 42/146 - loss 0.00979821 - time (sec): 4.47 - samples/sec: 2995.46 - lr: 0.000010 - momentum: 0.000000 2023-10-17 18:21:10,877 epoch 9 - iter 56/146 - loss 0.00776655 - time (sec): 5.89 - samples/sec: 2991.33 - lr: 0.000009 - momentum: 0.000000 2023-10-17 18:21:12,371 epoch 9 - iter 70/146 - loss 0.00765477 - time (sec): 7.38 - samples/sec: 2972.77 - lr: 0.000009 - momentum: 0.000000 2023-10-17 18:21:13,842 epoch 9 - iter 84/146 - loss 0.00853630 - time (sec): 8.85 - samples/sec: 2881.96 - lr: 0.000008 - momentum: 0.000000 2023-10-17 18:21:15,287 epoch 9 - iter 98/146 - loss 0.00833710 - time (sec): 10.30 - samples/sec: 2869.04 - lr: 0.000008 - momentum: 0.000000 2023-10-17 18:21:16,932 epoch 9 - iter 112/146 - loss 0.00889373 - time (sec): 11.94 - samples/sec: 2855.52 - lr: 0.000007 - momentum: 0.000000 2023-10-17 18:21:18,337 epoch 9 - iter 126/146 - loss 0.00916008 - time (sec): 13.35 - samples/sec: 2866.00 - lr: 0.000007 - momentum: 0.000000 2023-10-17 18:21:20,144 epoch 9 - iter 140/146 - loss 0.01040999 - time (sec): 15.16 - samples/sec: 2840.72 - lr: 0.000006 - momentum: 0.000000 2023-10-17 18:21:20,785 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:20,785 EPOCH 9 done: loss 0.0102 - lr: 0.000006 2023-10-17 18:21:22,122 DEV : loss 0.15759235620498657 - f1-score (micro avg) 0.7729 2023-10-17 18:21:22,129 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:23,627 epoch 10 - iter 14/146 - loss 0.00461926 - time (sec): 1.50 - samples/sec: 2600.98 - lr: 0.000005 - momentum: 0.000000 2023-10-17 18:21:24,914 epoch 10 - iter 28/146 - loss 0.00522148 - time (sec): 2.78 - samples/sec: 2808.60 - lr: 0.000005 - momentum: 0.000000 2023-10-17 18:21:26,424 epoch 10 - iter 42/146 - loss 0.00457207 - time (sec): 4.29 - samples/sec: 2837.86 - lr: 0.000004 - momentum: 0.000000 2023-10-17 18:21:27,827 epoch 10 - iter 56/146 - loss 0.00463493 - time (sec): 5.70 - samples/sec: 2888.41 - lr: 0.000004 - momentum: 0.000000 2023-10-17 18:21:29,449 epoch 10 - iter 70/146 - loss 0.00433431 - time (sec): 7.32 - samples/sec: 2974.36 - lr: 0.000003 - momentum: 0.000000 2023-10-17 18:21:30,782 epoch 10 - iter 84/146 - loss 0.00576813 - time (sec): 8.65 - samples/sec: 2969.54 - lr: 0.000003 - momentum: 0.000000 2023-10-17 18:21:32,528 epoch 10 - iter 98/146 - loss 0.00654355 - time (sec): 10.40 - samples/sec: 2903.48 - lr: 0.000002 - momentum: 0.000000 2023-10-17 18:21:33,908 epoch 10 - iter 112/146 - loss 0.00753927 - time (sec): 11.78 - samples/sec: 2913.78 - lr: 0.000002 - momentum: 0.000000 2023-10-17 18:21:35,323 epoch 10 - iter 126/146 - loss 0.00754727 - time (sec): 13.19 - samples/sec: 2877.14 - lr: 0.000001 - momentum: 0.000000 2023-10-17 18:21:36,771 epoch 10 - iter 140/146 - loss 0.00764366 - time (sec): 14.64 - samples/sec: 2919.96 - lr: 0.000000 - momentum: 0.000000 2023-10-17 18:21:37,361 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:37,362 EPOCH 10 done: loss 0.0075 - lr: 0.000000 2023-10-17 18:21:38,630 DEV : loss 0.16067492961883545 - f1-score (micro avg) 0.7768 2023-10-17 18:21:38,964 ---------------------------------------------------------------------------------------------------- 2023-10-17 18:21:38,965 Loading model from best epoch ... 2023-10-17 18:21:40,331 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 18:21:42,849 Results: - F-score (micro) 0.7645 - F-score (macro) 0.669 - Accuracy 0.6352 By class: precision recall f1-score support PER 0.8232 0.8563 0.8394 348 LOC 0.6585 0.8276 0.7334 261 ORG 0.5116 0.4231 0.4632 52 HumanProd 0.5714 0.7273 0.6400 22 micro avg 0.7254 0.8082 0.7645 683 macro avg 0.6412 0.7086 0.6690 683 weighted avg 0.7284 0.8082 0.7639 683 2023-10-17 18:21:42,849 ----------------------------------------------------------------------------------------------------