2023-10-16 10:55:48,313 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,314 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 10:55:48,314 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,314 MultiCorpus: 7142 train + 698 dev + 2570 test sentences - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator 2023-10-16 10:55:48,314 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,314 Train: 7142 sentences 2023-10-16 10:55:48,314 (train_with_dev=False, train_with_test=False) 2023-10-16 10:55:48,314 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 Training Params: 2023-10-16 10:55:48,315 - learning_rate: "5e-05" 2023-10-16 10:55:48,315 - mini_batch_size: "4" 2023-10-16 10:55:48,315 - max_epochs: "10" 2023-10-16 10:55:48,315 - shuffle: "True" 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 Plugins: 2023-10-16 10:55:48,315 - LinearScheduler | warmup_fraction: '0.1' 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 Final evaluation on model from best epoch (best-model.pt) 2023-10-16 10:55:48,315 - metric: "('micro avg', 'f1-score')" 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 Computation: 2023-10-16 10:55:48,315 - compute on device: cuda:0 2023-10-16 10:55:48,315 - embedding storage: none 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 Model training base path: "hmbench-newseye/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:48,315 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:55:57,101 epoch 1 - iter 178/1786 - loss 1.86473963 - time (sec): 8.78 - samples/sec: 2798.20 - lr: 0.000005 - momentum: 0.000000 2023-10-16 10:56:05,989 epoch 1 - iter 356/1786 - loss 1.15143669 - time (sec): 17.67 - samples/sec: 2805.49 - lr: 0.000010 - momentum: 0.000000 2023-10-16 10:56:14,650 epoch 1 - iter 534/1786 - loss 0.89028895 - time (sec): 26.33 - samples/sec: 2786.50 - lr: 0.000015 - momentum: 0.000000 2023-10-16 10:56:23,319 epoch 1 - iter 712/1786 - loss 0.72907805 - time (sec): 35.00 - samples/sec: 2791.74 - lr: 0.000020 - momentum: 0.000000 2023-10-16 10:56:32,196 epoch 1 - iter 890/1786 - loss 0.61722937 - time (sec): 43.88 - samples/sec: 2795.47 - lr: 0.000025 - momentum: 0.000000 2023-10-16 10:56:40,923 epoch 1 - iter 1068/1786 - loss 0.54496368 - time (sec): 52.61 - samples/sec: 2804.43 - lr: 0.000030 - momentum: 0.000000 2023-10-16 10:56:49,517 epoch 1 - iter 1246/1786 - loss 0.49315943 - time (sec): 61.20 - samples/sec: 2810.17 - lr: 0.000035 - momentum: 0.000000 2023-10-16 10:56:58,516 epoch 1 - iter 1424/1786 - loss 0.44831232 - time (sec): 70.20 - samples/sec: 2810.84 - lr: 0.000040 - momentum: 0.000000 2023-10-16 10:57:07,385 epoch 1 - iter 1602/1786 - loss 0.41610604 - time (sec): 79.07 - samples/sec: 2819.82 - lr: 0.000045 - momentum: 0.000000 2023-10-16 10:57:16,356 epoch 1 - iter 1780/1786 - loss 0.38771319 - time (sec): 88.04 - samples/sec: 2818.72 - lr: 0.000050 - momentum: 0.000000 2023-10-16 10:57:16,622 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:57:16,623 EPOCH 1 done: loss 0.3871 - lr: 0.000050 2023-10-16 10:57:19,749 DEV : loss 0.14844156801700592 - f1-score (micro avg) 0.7097 2023-10-16 10:57:19,766 saving best model 2023-10-16 10:57:20,235 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:57:29,212 epoch 2 - iter 178/1786 - loss 0.11605918 - time (sec): 8.98 - samples/sec: 2852.83 - lr: 0.000049 - momentum: 0.000000 2023-10-16 10:57:38,138 epoch 2 - iter 356/1786 - loss 0.12100219 - time (sec): 17.90 - samples/sec: 2815.83 - lr: 0.000049 - momentum: 0.000000 2023-10-16 10:57:46,829 epoch 2 - iter 534/1786 - loss 0.12074401 - time (sec): 26.59 - samples/sec: 2813.99 - lr: 0.000048 - momentum: 0.000000 2023-10-16 10:57:55,616 epoch 2 - iter 712/1786 - loss 0.12193352 - time (sec): 35.38 - samples/sec: 2817.75 - lr: 0.000048 - momentum: 0.000000 2023-10-16 10:58:04,529 epoch 2 - iter 890/1786 - loss 0.12062941 - time (sec): 44.29 - samples/sec: 2848.46 - lr: 0.000047 - momentum: 0.000000 2023-10-16 10:58:13,257 epoch 2 - iter 1068/1786 - loss 0.12155219 - time (sec): 53.02 - samples/sec: 2842.58 - lr: 0.000047 - momentum: 0.000000 2023-10-16 10:58:21,966 epoch 2 - iter 1246/1786 - loss 0.12243129 - time (sec): 61.73 - samples/sec: 2853.56 - lr: 0.000046 - momentum: 0.000000 2023-10-16 10:58:30,614 epoch 2 - iter 1424/1786 - loss 0.12158950 - time (sec): 70.38 - samples/sec: 2851.52 - lr: 0.000046 - momentum: 0.000000 2023-10-16 10:58:39,167 epoch 2 - iter 1602/1786 - loss 0.12123775 - time (sec): 78.93 - samples/sec: 2850.42 - lr: 0.000045 - momentum: 0.000000 2023-10-16 10:58:47,748 epoch 2 - iter 1780/1786 - loss 0.11991333 - time (sec): 87.51 - samples/sec: 2836.16 - lr: 0.000044 - momentum: 0.000000 2023-10-16 10:58:48,021 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:58:48,022 EPOCH 2 done: loss 0.1201 - lr: 0.000044 2023-10-16 10:58:52,252 DEV : loss 0.12567166984081268 - f1-score (micro avg) 0.7381 2023-10-16 10:58:52,278 saving best model 2023-10-16 10:58:52,816 ---------------------------------------------------------------------------------------------------- 2023-10-16 10:59:02,942 epoch 3 - iter 178/1786 - loss 0.07602399 - time (sec): 10.12 - samples/sec: 2507.17 - lr: 0.000044 - momentum: 0.000000 2023-10-16 10:59:12,927 epoch 3 - iter 356/1786 - loss 0.08707339 - time (sec): 20.11 - samples/sec: 2555.56 - lr: 0.000043 - momentum: 0.000000 2023-10-16 10:59:21,653 epoch 3 - iter 534/1786 - loss 0.08690813 - time (sec): 28.83 - samples/sec: 2648.10 - lr: 0.000043 - momentum: 0.000000 2023-10-16 10:59:30,119 epoch 3 - iter 712/1786 - loss 0.08815103 - time (sec): 37.30 - samples/sec: 2670.85 - lr: 0.000042 - momentum: 0.000000 2023-10-16 10:59:38,819 epoch 3 - iter 890/1786 - loss 0.08755368 - time (sec): 46.00 - samples/sec: 2695.07 - lr: 0.000042 - momentum: 0.000000 2023-10-16 10:59:47,465 epoch 3 - iter 1068/1786 - loss 0.08864883 - time (sec): 54.65 - samples/sec: 2710.43 - lr: 0.000041 - momentum: 0.000000 2023-10-16 10:59:56,372 epoch 3 - iter 1246/1786 - loss 0.08622224 - time (sec): 63.55 - samples/sec: 2735.57 - lr: 0.000041 - momentum: 0.000000 2023-10-16 11:00:05,220 epoch 3 - iter 1424/1786 - loss 0.08740866 - time (sec): 72.40 - samples/sec: 2750.50 - lr: 0.000040 - momentum: 0.000000 2023-10-16 11:00:13,804 epoch 3 - iter 1602/1786 - loss 0.08628163 - time (sec): 80.98 - samples/sec: 2760.57 - lr: 0.000039 - momentum: 0.000000 2023-10-16 11:00:22,397 epoch 3 - iter 1780/1786 - loss 0.08517479 - time (sec): 89.58 - samples/sec: 2763.43 - lr: 0.000039 - momentum: 0.000000 2023-10-16 11:00:22,747 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:00:22,747 EPOCH 3 done: loss 0.0851 - lr: 0.000039 2023-10-16 11:00:28,065 DEV : loss 0.14893780648708344 - f1-score (micro avg) 0.763 2023-10-16 11:00:28,095 saving best model 2023-10-16 11:00:28,742 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:00:37,510 epoch 4 - iter 178/1786 - loss 0.05930779 - time (sec): 8.77 - samples/sec: 2921.05 - lr: 0.000038 - momentum: 0.000000 2023-10-16 11:00:46,255 epoch 4 - iter 356/1786 - loss 0.06322745 - time (sec): 17.51 - samples/sec: 2865.97 - lr: 0.000038 - momentum: 0.000000 2023-10-16 11:00:54,769 epoch 4 - iter 534/1786 - loss 0.06363083 - time (sec): 26.03 - samples/sec: 2834.26 - lr: 0.000037 - momentum: 0.000000 2023-10-16 11:01:03,344 epoch 4 - iter 712/1786 - loss 0.06394879 - time (sec): 34.60 - samples/sec: 2818.00 - lr: 0.000037 - momentum: 0.000000 2023-10-16 11:01:12,317 epoch 4 - iter 890/1786 - loss 0.06327639 - time (sec): 43.57 - samples/sec: 2815.14 - lr: 0.000036 - momentum: 0.000000 2023-10-16 11:01:21,136 epoch 4 - iter 1068/1786 - loss 0.06455310 - time (sec): 52.39 - samples/sec: 2814.42 - lr: 0.000036 - momentum: 0.000000 2023-10-16 11:01:29,981 epoch 4 - iter 1246/1786 - loss 0.06478828 - time (sec): 61.24 - samples/sec: 2837.72 - lr: 0.000035 - momentum: 0.000000 2023-10-16 11:01:38,780 epoch 4 - iter 1424/1786 - loss 0.06518193 - time (sec): 70.04 - samples/sec: 2829.75 - lr: 0.000034 - momentum: 0.000000 2023-10-16 11:01:47,514 epoch 4 - iter 1602/1786 - loss 0.06559590 - time (sec): 78.77 - samples/sec: 2834.31 - lr: 0.000034 - momentum: 0.000000 2023-10-16 11:01:56,245 epoch 4 - iter 1780/1786 - loss 0.06474763 - time (sec): 87.50 - samples/sec: 2832.00 - lr: 0.000033 - momentum: 0.000000 2023-10-16 11:01:56,584 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:01:56,584 EPOCH 4 done: loss 0.0647 - lr: 0.000033 2023-10-16 11:02:01,327 DEV : loss 0.17378392815589905 - f1-score (micro avg) 0.7717 2023-10-16 11:02:01,343 saving best model 2023-10-16 11:02:01,929 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:02:10,798 epoch 5 - iter 178/1786 - loss 0.04377203 - time (sec): 8.86 - samples/sec: 2853.88 - lr: 0.000033 - momentum: 0.000000 2023-10-16 11:02:19,500 epoch 5 - iter 356/1786 - loss 0.04754169 - time (sec): 17.56 - samples/sec: 2891.83 - lr: 0.000032 - momentum: 0.000000 2023-10-16 11:02:28,081 epoch 5 - iter 534/1786 - loss 0.04802223 - time (sec): 26.15 - samples/sec: 2810.91 - lr: 0.000032 - momentum: 0.000000 2023-10-16 11:02:36,836 epoch 5 - iter 712/1786 - loss 0.04911834 - time (sec): 34.90 - samples/sec: 2859.03 - lr: 0.000031 - momentum: 0.000000 2023-10-16 11:02:45,355 epoch 5 - iter 890/1786 - loss 0.04948678 - time (sec): 43.42 - samples/sec: 2844.94 - lr: 0.000031 - momentum: 0.000000 2023-10-16 11:02:54,112 epoch 5 - iter 1068/1786 - loss 0.04806990 - time (sec): 52.18 - samples/sec: 2848.29 - lr: 0.000030 - momentum: 0.000000 2023-10-16 11:03:02,929 epoch 5 - iter 1246/1786 - loss 0.04825570 - time (sec): 60.99 - samples/sec: 2841.27 - lr: 0.000029 - momentum: 0.000000 2023-10-16 11:03:11,923 epoch 5 - iter 1424/1786 - loss 0.04891461 - time (sec): 69.99 - samples/sec: 2857.31 - lr: 0.000029 - momentum: 0.000000 2023-10-16 11:03:20,483 epoch 5 - iter 1602/1786 - loss 0.04962470 - time (sec): 78.55 - samples/sec: 2857.09 - lr: 0.000028 - momentum: 0.000000 2023-10-16 11:03:29,083 epoch 5 - iter 1780/1786 - loss 0.04904968 - time (sec): 87.15 - samples/sec: 2845.88 - lr: 0.000028 - momentum: 0.000000 2023-10-16 11:03:29,351 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:03:29,351 EPOCH 5 done: loss 0.0490 - lr: 0.000028 2023-10-16 11:03:33,517 DEV : loss 0.17484842240810394 - f1-score (micro avg) 0.7728 2023-10-16 11:03:33,537 saving best model 2023-10-16 11:03:34,174 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:03:43,090 epoch 6 - iter 178/1786 - loss 0.03564048 - time (sec): 8.91 - samples/sec: 2725.57 - lr: 0.000027 - momentum: 0.000000 2023-10-16 11:03:52,442 epoch 6 - iter 356/1786 - loss 0.03852911 - time (sec): 18.26 - samples/sec: 2720.29 - lr: 0.000027 - momentum: 0.000000 2023-10-16 11:04:01,277 epoch 6 - iter 534/1786 - loss 0.04136964 - time (sec): 27.10 - samples/sec: 2738.01 - lr: 0.000026 - momentum: 0.000000 2023-10-16 11:04:09,800 epoch 6 - iter 712/1786 - loss 0.04024227 - time (sec): 35.62 - samples/sec: 2769.91 - lr: 0.000026 - momentum: 0.000000 2023-10-16 11:04:18,513 epoch 6 - iter 890/1786 - loss 0.04012505 - time (sec): 44.34 - samples/sec: 2778.95 - lr: 0.000025 - momentum: 0.000000 2023-10-16 11:04:27,194 epoch 6 - iter 1068/1786 - loss 0.04289492 - time (sec): 53.02 - samples/sec: 2807.61 - lr: 0.000024 - momentum: 0.000000 2023-10-16 11:04:36,047 epoch 6 - iter 1246/1786 - loss 0.04221536 - time (sec): 61.87 - samples/sec: 2818.13 - lr: 0.000024 - momentum: 0.000000 2023-10-16 11:04:44,578 epoch 6 - iter 1424/1786 - loss 0.04182216 - time (sec): 70.40 - samples/sec: 2812.76 - lr: 0.000023 - momentum: 0.000000 2023-10-16 11:04:53,113 epoch 6 - iter 1602/1786 - loss 0.04171130 - time (sec): 78.94 - samples/sec: 2819.50 - lr: 0.000023 - momentum: 0.000000 2023-10-16 11:05:01,768 epoch 6 - iter 1780/1786 - loss 0.04099380 - time (sec): 87.59 - samples/sec: 2833.27 - lr: 0.000022 - momentum: 0.000000 2023-10-16 11:05:02,038 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:05:02,038 EPOCH 6 done: loss 0.0410 - lr: 0.000022 2023-10-16 11:05:07,359 DEV : loss 0.16918683052062988 - f1-score (micro avg) 0.7777 2023-10-16 11:05:07,384 saving best model 2023-10-16 11:05:08,130 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:05:16,990 epoch 7 - iter 178/1786 - loss 0.02648365 - time (sec): 8.86 - samples/sec: 3052.78 - lr: 0.000022 - momentum: 0.000000 2023-10-16 11:05:25,906 epoch 7 - iter 356/1786 - loss 0.02728552 - time (sec): 17.77 - samples/sec: 2869.74 - lr: 0.000021 - momentum: 0.000000 2023-10-16 11:05:34,815 epoch 7 - iter 534/1786 - loss 0.02817086 - time (sec): 26.68 - samples/sec: 2837.46 - lr: 0.000021 - momentum: 0.000000 2023-10-16 11:05:43,583 epoch 7 - iter 712/1786 - loss 0.02776279 - time (sec): 35.45 - samples/sec: 2851.27 - lr: 0.000020 - momentum: 0.000000 2023-10-16 11:05:52,253 epoch 7 - iter 890/1786 - loss 0.02711624 - time (sec): 44.12 - samples/sec: 2851.82 - lr: 0.000019 - momentum: 0.000000 2023-10-16 11:06:00,861 epoch 7 - iter 1068/1786 - loss 0.02876745 - time (sec): 52.73 - samples/sec: 2839.91 - lr: 0.000019 - momentum: 0.000000 2023-10-16 11:06:09,636 epoch 7 - iter 1246/1786 - loss 0.02936533 - time (sec): 61.50 - samples/sec: 2815.16 - lr: 0.000018 - momentum: 0.000000 2023-10-16 11:06:18,532 epoch 7 - iter 1424/1786 - loss 0.02812044 - time (sec): 70.40 - samples/sec: 2830.18 - lr: 0.000018 - momentum: 0.000000 2023-10-16 11:06:27,146 epoch 7 - iter 1602/1786 - loss 0.02927136 - time (sec): 79.01 - samples/sec: 2823.45 - lr: 0.000017 - momentum: 0.000000 2023-10-16 11:06:35,809 epoch 7 - iter 1780/1786 - loss 0.02918995 - time (sec): 87.68 - samples/sec: 2825.84 - lr: 0.000017 - momentum: 0.000000 2023-10-16 11:06:36,138 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:06:36,139 EPOCH 7 done: loss 0.0292 - lr: 0.000017 2023-10-16 11:06:40,964 DEV : loss 0.186806321144104 - f1-score (micro avg) 0.7809 2023-10-16 11:06:40,981 saving best model 2023-10-16 11:06:41,594 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:06:50,242 epoch 8 - iter 178/1786 - loss 0.02299188 - time (sec): 8.65 - samples/sec: 2815.85 - lr: 0.000016 - momentum: 0.000000 2023-10-16 11:06:58,827 epoch 8 - iter 356/1786 - loss 0.02359001 - time (sec): 17.23 - samples/sec: 2827.78 - lr: 0.000016 - momentum: 0.000000 2023-10-16 11:07:07,629 epoch 8 - iter 534/1786 - loss 0.02254523 - time (sec): 26.03 - samples/sec: 2811.01 - lr: 0.000015 - momentum: 0.000000 2023-10-16 11:07:16,444 epoch 8 - iter 712/1786 - loss 0.02199670 - time (sec): 34.85 - samples/sec: 2838.40 - lr: 0.000014 - momentum: 0.000000 2023-10-16 11:07:25,076 epoch 8 - iter 890/1786 - loss 0.02265221 - time (sec): 43.48 - samples/sec: 2842.73 - lr: 0.000014 - momentum: 0.000000 2023-10-16 11:07:33,588 epoch 8 - iter 1068/1786 - loss 0.02375428 - time (sec): 51.99 - samples/sec: 2838.22 - lr: 0.000013 - momentum: 0.000000 2023-10-16 11:07:42,171 epoch 8 - iter 1246/1786 - loss 0.02271185 - time (sec): 60.57 - samples/sec: 2838.00 - lr: 0.000013 - momentum: 0.000000 2023-10-16 11:07:50,996 epoch 8 - iter 1424/1786 - loss 0.02264176 - time (sec): 69.40 - samples/sec: 2830.78 - lr: 0.000012 - momentum: 0.000000 2023-10-16 11:07:59,917 epoch 8 - iter 1602/1786 - loss 0.02278864 - time (sec): 78.32 - samples/sec: 2834.50 - lr: 0.000012 - momentum: 0.000000 2023-10-16 11:08:08,823 epoch 8 - iter 1780/1786 - loss 0.02208015 - time (sec): 87.23 - samples/sec: 2842.31 - lr: 0.000011 - momentum: 0.000000 2023-10-16 11:08:09,133 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:08:09,133 EPOCH 8 done: loss 0.0221 - lr: 0.000011 2023-10-16 11:08:13,486 DEV : loss 0.19474762678146362 - f1-score (micro avg) 0.796 2023-10-16 11:08:13,506 saving best model 2023-10-16 11:08:14,028 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:08:23,840 epoch 9 - iter 178/1786 - loss 0.01798579 - time (sec): 9.81 - samples/sec: 2549.51 - lr: 0.000011 - momentum: 0.000000 2023-10-16 11:08:32,940 epoch 9 - iter 356/1786 - loss 0.01872623 - time (sec): 18.91 - samples/sec: 2662.25 - lr: 0.000010 - momentum: 0.000000 2023-10-16 11:08:42,168 epoch 9 - iter 534/1786 - loss 0.01727464 - time (sec): 28.14 - samples/sec: 2677.48 - lr: 0.000009 - momentum: 0.000000 2023-10-16 11:08:50,782 epoch 9 - iter 712/1786 - loss 0.01690762 - time (sec): 36.75 - samples/sec: 2698.90 - lr: 0.000009 - momentum: 0.000000 2023-10-16 11:08:59,465 epoch 9 - iter 890/1786 - loss 0.01729150 - time (sec): 45.43 - samples/sec: 2718.02 - lr: 0.000008 - momentum: 0.000000 2023-10-16 11:09:08,235 epoch 9 - iter 1068/1786 - loss 0.01759655 - time (sec): 54.20 - samples/sec: 2743.24 - lr: 0.000008 - momentum: 0.000000 2023-10-16 11:09:17,081 epoch 9 - iter 1246/1786 - loss 0.01836818 - time (sec): 63.05 - samples/sec: 2762.68 - lr: 0.000007 - momentum: 0.000000 2023-10-16 11:09:25,811 epoch 9 - iter 1424/1786 - loss 0.01880668 - time (sec): 71.78 - samples/sec: 2792.07 - lr: 0.000007 - momentum: 0.000000 2023-10-16 11:09:34,295 epoch 9 - iter 1602/1786 - loss 0.01846836 - time (sec): 80.26 - samples/sec: 2780.26 - lr: 0.000006 - momentum: 0.000000 2023-10-16 11:09:43,041 epoch 9 - iter 1780/1786 - loss 0.01794289 - time (sec): 89.01 - samples/sec: 2784.51 - lr: 0.000006 - momentum: 0.000000 2023-10-16 11:09:43,337 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:09:43,338 EPOCH 9 done: loss 0.0180 - lr: 0.000006 2023-10-16 11:09:48,154 DEV : loss 0.1844618022441864 - f1-score (micro avg) 0.8048 2023-10-16 11:09:48,181 saving best model 2023-10-16 11:09:48,726 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:09:58,642 epoch 10 - iter 178/1786 - loss 0.01185496 - time (sec): 9.91 - samples/sec: 2381.04 - lr: 0.000005 - momentum: 0.000000 2023-10-16 11:10:08,696 epoch 10 - iter 356/1786 - loss 0.01135159 - time (sec): 19.97 - samples/sec: 2548.54 - lr: 0.000004 - momentum: 0.000000 2023-10-16 11:10:18,592 epoch 10 - iter 534/1786 - loss 0.01376928 - time (sec): 29.86 - samples/sec: 2545.00 - lr: 0.000004 - momentum: 0.000000 2023-10-16 11:10:28,392 epoch 10 - iter 712/1786 - loss 0.01268921 - time (sec): 39.66 - samples/sec: 2517.19 - lr: 0.000003 - momentum: 0.000000 2023-10-16 11:10:38,278 epoch 10 - iter 890/1786 - loss 0.01251690 - time (sec): 49.55 - samples/sec: 2514.27 - lr: 0.000003 - momentum: 0.000000 2023-10-16 11:10:48,164 epoch 10 - iter 1068/1786 - loss 0.01347864 - time (sec): 59.44 - samples/sec: 2506.01 - lr: 0.000002 - momentum: 0.000000 2023-10-16 11:10:58,148 epoch 10 - iter 1246/1786 - loss 0.01278922 - time (sec): 69.42 - samples/sec: 2507.14 - lr: 0.000002 - momentum: 0.000000 2023-10-16 11:11:07,753 epoch 10 - iter 1424/1786 - loss 0.01267902 - time (sec): 79.02 - samples/sec: 2494.79 - lr: 0.000001 - momentum: 0.000000 2023-10-16 11:11:17,680 epoch 10 - iter 1602/1786 - loss 0.01194308 - time (sec): 88.95 - samples/sec: 2510.87 - lr: 0.000001 - momentum: 0.000000 2023-10-16 11:11:27,393 epoch 10 - iter 1780/1786 - loss 0.01186500 - time (sec): 98.66 - samples/sec: 2515.20 - lr: 0.000000 - momentum: 0.000000 2023-10-16 11:11:27,704 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:11:27,704 EPOCH 10 done: loss 0.0118 - lr: 0.000000 2023-10-16 11:11:32,731 DEV : loss 0.18512549996376038 - f1-score (micro avg) 0.8024 2023-10-16 11:11:33,164 ---------------------------------------------------------------------------------------------------- 2023-10-16 11:11:33,165 Loading model from best epoch ... 2023-10-16 11:11:34,828 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-16 11:11:44,735 Results: - F-score (micro) 0.6916 - F-score (macro) 0.5961 - Accuracy 0.5475 By class: precision recall f1-score support LOC 0.6627 0.7196 0.6900 1095 PER 0.7735 0.7628 0.7682 1012 ORG 0.5198 0.5154 0.5176 357 HumanProd 0.3167 0.5758 0.4086 33 micro avg 0.6778 0.7060 0.6916 2497 macro avg 0.5682 0.6434 0.5961 2497 weighted avg 0.6826 0.7060 0.6933 2497 2023-10-16 11:11:44,735 ----------------------------------------------------------------------------------------------------