2023-10-16 19:41:39,866 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(32001, 768) (position_embeddings): Embedding(512, 768) (token_type_embeddings): Embedding(2, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): BertSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 MultiCorpus: 1085 train + 148 dev + 364 test sentences - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Train: 1085 sentences 2023-10-16 19:41:39,867 (train_with_dev=False, train_with_test=False) 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Training Params: 2023-10-16 19:41:39,867 - learning_rate: "3e-05" 2023-10-16 19:41:39,867 - mini_batch_size: "4" 2023-10-16 19:41:39,867 - max_epochs: "10" 2023-10-16 19:41:39,867 - shuffle: "True" 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Plugins: 2023-10-16 19:41:39,867 - LinearScheduler | warmup_fraction: '0.1' 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Final evaluation on model from best epoch (best-model.pt) 2023-10-16 19:41:39,867 - metric: "('micro avg', 'f1-score')" 2023-10-16 19:41:39,867 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,867 Computation: 2023-10-16 19:41:39,867 - compute on device: cuda:0 2023-10-16 19:41:39,867 - embedding storage: none 2023-10-16 19:41:39,868 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,868 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-16 19:41:39,868 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:39,868 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:41,668 epoch 1 - iter 27/272 - loss 3.04057792 - time (sec): 1.80 - samples/sec: 3488.66 - lr: 0.000003 - momentum: 0.000000 2023-10-16 19:41:43,128 epoch 1 - iter 54/272 - loss 2.72238985 - time (sec): 3.26 - samples/sec: 3362.51 - lr: 0.000006 - momentum: 0.000000 2023-10-16 19:41:44,623 epoch 1 - iter 81/272 - loss 2.12940151 - time (sec): 4.75 - samples/sec: 3384.70 - lr: 0.000009 - momentum: 0.000000 2023-10-16 19:41:46,156 epoch 1 - iter 108/272 - loss 1.75711148 - time (sec): 6.29 - samples/sec: 3316.36 - lr: 0.000012 - momentum: 0.000000 2023-10-16 19:41:47,862 epoch 1 - iter 135/272 - loss 1.46487207 - time (sec): 7.99 - samples/sec: 3304.13 - lr: 0.000015 - momentum: 0.000000 2023-10-16 19:41:49,429 epoch 1 - iter 162/272 - loss 1.28960596 - time (sec): 9.56 - samples/sec: 3305.75 - lr: 0.000018 - momentum: 0.000000 2023-10-16 19:41:51,075 epoch 1 - iter 189/272 - loss 1.13468045 - time (sec): 11.21 - samples/sec: 3345.50 - lr: 0.000021 - momentum: 0.000000 2023-10-16 19:41:52,592 epoch 1 - iter 216/272 - loss 1.04586991 - time (sec): 12.72 - samples/sec: 3294.89 - lr: 0.000024 - momentum: 0.000000 2023-10-16 19:41:54,223 epoch 1 - iter 243/272 - loss 0.96986172 - time (sec): 14.35 - samples/sec: 3259.73 - lr: 0.000027 - momentum: 0.000000 2023-10-16 19:41:55,991 epoch 1 - iter 270/272 - loss 0.90362345 - time (sec): 16.12 - samples/sec: 3202.49 - lr: 0.000030 - momentum: 0.000000 2023-10-16 19:41:56,121 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:56,121 EPOCH 1 done: loss 0.9000 - lr: 0.000030 2023-10-16 19:41:57,268 DEV : loss 0.17124275863170624 - f1-score (micro avg) 0.6407 2023-10-16 19:41:57,273 saving best model 2023-10-16 19:41:57,710 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:41:59,416 epoch 2 - iter 27/272 - loss 0.16607614 - time (sec): 1.70 - samples/sec: 3155.34 - lr: 0.000030 - momentum: 0.000000 2023-10-16 19:42:01,169 epoch 2 - iter 54/272 - loss 0.16049108 - time (sec): 3.46 - samples/sec: 3150.41 - lr: 0.000029 - momentum: 0.000000 2023-10-16 19:42:03,073 epoch 2 - iter 81/272 - loss 0.16338692 - time (sec): 5.36 - samples/sec: 3221.47 - lr: 0.000029 - momentum: 0.000000 2023-10-16 19:42:04,801 epoch 2 - iter 108/272 - loss 0.17411210 - time (sec): 7.09 - samples/sec: 3138.75 - lr: 0.000029 - momentum: 0.000000 2023-10-16 19:42:06,360 epoch 2 - iter 135/272 - loss 0.17518551 - time (sec): 8.65 - samples/sec: 3103.12 - lr: 0.000028 - momentum: 0.000000 2023-10-16 19:42:08,005 epoch 2 - iter 162/272 - loss 0.16738460 - time (sec): 10.29 - samples/sec: 3111.22 - lr: 0.000028 - momentum: 0.000000 2023-10-16 19:42:09,542 epoch 2 - iter 189/272 - loss 0.16655385 - time (sec): 11.83 - samples/sec: 3067.92 - lr: 0.000028 - momentum: 0.000000 2023-10-16 19:42:11,189 epoch 2 - iter 216/272 - loss 0.15624382 - time (sec): 13.48 - samples/sec: 3131.93 - lr: 0.000027 - momentum: 0.000000 2023-10-16 19:42:12,694 epoch 2 - iter 243/272 - loss 0.15627730 - time (sec): 14.98 - samples/sec: 3110.53 - lr: 0.000027 - momentum: 0.000000 2023-10-16 19:42:14,304 epoch 2 - iter 270/272 - loss 0.15603499 - time (sec): 16.59 - samples/sec: 3109.70 - lr: 0.000027 - momentum: 0.000000 2023-10-16 19:42:14,439 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:14,440 EPOCH 2 done: loss 0.1554 - lr: 0.000027 2023-10-16 19:42:15,902 DEV : loss 0.10554348677396774 - f1-score (micro avg) 0.763 2023-10-16 19:42:15,907 saving best model 2023-10-16 19:42:16,452 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:18,054 epoch 3 - iter 27/272 - loss 0.10392696 - time (sec): 1.60 - samples/sec: 3355.97 - lr: 0.000026 - momentum: 0.000000 2023-10-16 19:42:19,712 epoch 3 - iter 54/272 - loss 0.10890746 - time (sec): 3.26 - samples/sec: 3313.26 - lr: 0.000026 - momentum: 0.000000 2023-10-16 19:42:21,067 epoch 3 - iter 81/272 - loss 0.10086706 - time (sec): 4.61 - samples/sec: 3274.70 - lr: 0.000026 - momentum: 0.000000 2023-10-16 19:42:22,742 epoch 3 - iter 108/272 - loss 0.09780563 - time (sec): 6.29 - samples/sec: 3247.84 - lr: 0.000025 - momentum: 0.000000 2023-10-16 19:42:24,396 epoch 3 - iter 135/272 - loss 0.10021849 - time (sec): 7.94 - samples/sec: 3219.47 - lr: 0.000025 - momentum: 0.000000 2023-10-16 19:42:25,911 epoch 3 - iter 162/272 - loss 0.09720403 - time (sec): 9.46 - samples/sec: 3237.74 - lr: 0.000025 - momentum: 0.000000 2023-10-16 19:42:27,360 epoch 3 - iter 189/272 - loss 0.09662984 - time (sec): 10.90 - samples/sec: 3204.15 - lr: 0.000024 - momentum: 0.000000 2023-10-16 19:42:28,951 epoch 3 - iter 216/272 - loss 0.09189039 - time (sec): 12.50 - samples/sec: 3262.50 - lr: 0.000024 - momentum: 0.000000 2023-10-16 19:42:30,509 epoch 3 - iter 243/272 - loss 0.08816254 - time (sec): 14.05 - samples/sec: 3272.51 - lr: 0.000024 - momentum: 0.000000 2023-10-16 19:42:32,346 epoch 3 - iter 270/272 - loss 0.08535618 - time (sec): 15.89 - samples/sec: 3254.24 - lr: 0.000023 - momentum: 0.000000 2023-10-16 19:42:32,451 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:32,452 EPOCH 3 done: loss 0.0850 - lr: 0.000023 2023-10-16 19:42:33,920 DEV : loss 0.12464497238397598 - f1-score (micro avg) 0.7804 2023-10-16 19:42:33,925 saving best model 2023-10-16 19:42:34,466 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:36,154 epoch 4 - iter 27/272 - loss 0.05096666 - time (sec): 1.69 - samples/sec: 2912.70 - lr: 0.000023 - momentum: 0.000000 2023-10-16 19:42:37,750 epoch 4 - iter 54/272 - loss 0.05596561 - time (sec): 3.28 - samples/sec: 2826.09 - lr: 0.000023 - momentum: 0.000000 2023-10-16 19:42:39,690 epoch 4 - iter 81/272 - loss 0.06377073 - time (sec): 5.22 - samples/sec: 2841.32 - lr: 0.000022 - momentum: 0.000000 2023-10-16 19:42:41,408 epoch 4 - iter 108/272 - loss 0.05733990 - time (sec): 6.94 - samples/sec: 2887.32 - lr: 0.000022 - momentum: 0.000000 2023-10-16 19:42:43,042 epoch 4 - iter 135/272 - loss 0.05884014 - time (sec): 8.57 - samples/sec: 2922.45 - lr: 0.000022 - momentum: 0.000000 2023-10-16 19:42:44,622 epoch 4 - iter 162/272 - loss 0.05374785 - time (sec): 10.15 - samples/sec: 2978.84 - lr: 0.000021 - momentum: 0.000000 2023-10-16 19:42:46,425 epoch 4 - iter 189/272 - loss 0.05327700 - time (sec): 11.96 - samples/sec: 2977.07 - lr: 0.000021 - momentum: 0.000000 2023-10-16 19:42:48,339 epoch 4 - iter 216/272 - loss 0.05113520 - time (sec): 13.87 - samples/sec: 2960.29 - lr: 0.000021 - momentum: 0.000000 2023-10-16 19:42:50,077 epoch 4 - iter 243/272 - loss 0.04944726 - time (sec): 15.61 - samples/sec: 2958.44 - lr: 0.000020 - momentum: 0.000000 2023-10-16 19:42:51,797 epoch 4 - iter 270/272 - loss 0.04935030 - time (sec): 17.33 - samples/sec: 2994.60 - lr: 0.000020 - momentum: 0.000000 2023-10-16 19:42:51,895 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:51,895 EPOCH 4 done: loss 0.0502 - lr: 0.000020 2023-10-16 19:42:53,362 DEV : loss 0.13258929550647736 - f1-score (micro avg) 0.7653 2023-10-16 19:42:53,367 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:42:54,971 epoch 5 - iter 27/272 - loss 0.02364095 - time (sec): 1.60 - samples/sec: 2831.61 - lr: 0.000020 - momentum: 0.000000 2023-10-16 19:42:56,597 epoch 5 - iter 54/272 - loss 0.02260480 - time (sec): 3.23 - samples/sec: 2967.66 - lr: 0.000019 - momentum: 0.000000 2023-10-16 19:42:58,320 epoch 5 - iter 81/272 - loss 0.02465063 - time (sec): 4.95 - samples/sec: 3063.40 - lr: 0.000019 - momentum: 0.000000 2023-10-16 19:43:00,000 epoch 5 - iter 108/272 - loss 0.02741689 - time (sec): 6.63 - samples/sec: 3103.35 - lr: 0.000019 - momentum: 0.000000 2023-10-16 19:43:01,706 epoch 5 - iter 135/272 - loss 0.02512919 - time (sec): 8.34 - samples/sec: 3071.33 - lr: 0.000018 - momentum: 0.000000 2023-10-16 19:43:03,345 epoch 5 - iter 162/272 - loss 0.03049677 - time (sec): 9.98 - samples/sec: 3105.01 - lr: 0.000018 - momentum: 0.000000 2023-10-16 19:43:05,128 epoch 5 - iter 189/272 - loss 0.03343267 - time (sec): 11.76 - samples/sec: 3086.84 - lr: 0.000018 - momentum: 0.000000 2023-10-16 19:43:06,775 epoch 5 - iter 216/272 - loss 0.03294967 - time (sec): 13.41 - samples/sec: 3096.49 - lr: 0.000017 - momentum: 0.000000 2023-10-16 19:43:08,424 epoch 5 - iter 243/272 - loss 0.03334278 - time (sec): 15.06 - samples/sec: 3078.80 - lr: 0.000017 - momentum: 0.000000 2023-10-16 19:43:10,071 epoch 5 - iter 270/272 - loss 0.03395116 - time (sec): 16.70 - samples/sec: 3089.94 - lr: 0.000017 - momentum: 0.000000 2023-10-16 19:43:10,180 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:10,180 EPOCH 5 done: loss 0.0341 - lr: 0.000017 2023-10-16 19:43:11,658 DEV : loss 0.13392110168933868 - f1-score (micro avg) 0.7877 2023-10-16 19:43:11,665 saving best model 2023-10-16 19:43:12,154 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:13,763 epoch 6 - iter 27/272 - loss 0.03778512 - time (sec): 1.61 - samples/sec: 3168.40 - lr: 0.000016 - momentum: 0.000000 2023-10-16 19:43:15,374 epoch 6 - iter 54/272 - loss 0.02722681 - time (sec): 3.22 - samples/sec: 3206.30 - lr: 0.000016 - momentum: 0.000000 2023-10-16 19:43:16,848 epoch 6 - iter 81/272 - loss 0.02809537 - time (sec): 4.69 - samples/sec: 3251.07 - lr: 0.000016 - momentum: 0.000000 2023-10-16 19:43:18,290 epoch 6 - iter 108/272 - loss 0.02507468 - time (sec): 6.13 - samples/sec: 3230.08 - lr: 0.000015 - momentum: 0.000000 2023-10-16 19:43:19,863 epoch 6 - iter 135/272 - loss 0.02724857 - time (sec): 7.71 - samples/sec: 3296.89 - lr: 0.000015 - momentum: 0.000000 2023-10-16 19:43:21,484 epoch 6 - iter 162/272 - loss 0.02825793 - time (sec): 9.33 - samples/sec: 3335.91 - lr: 0.000015 - momentum: 0.000000 2023-10-16 19:43:23,031 epoch 6 - iter 189/272 - loss 0.02674067 - time (sec): 10.87 - samples/sec: 3349.13 - lr: 0.000014 - momentum: 0.000000 2023-10-16 19:43:24,758 epoch 6 - iter 216/272 - loss 0.02551610 - time (sec): 12.60 - samples/sec: 3350.01 - lr: 0.000014 - momentum: 0.000000 2023-10-16 19:43:26,259 epoch 6 - iter 243/272 - loss 0.02385448 - time (sec): 14.10 - samples/sec: 3348.26 - lr: 0.000014 - momentum: 0.000000 2023-10-16 19:43:27,780 epoch 6 - iter 270/272 - loss 0.02470491 - time (sec): 15.62 - samples/sec: 3322.18 - lr: 0.000013 - momentum: 0.000000 2023-10-16 19:43:27,864 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:27,864 EPOCH 6 done: loss 0.0248 - lr: 0.000013 2023-10-16 19:43:29,321 DEV : loss 0.14046281576156616 - f1-score (micro avg) 0.8 2023-10-16 19:43:29,326 saving best model 2023-10-16 19:43:29,947 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:31,708 epoch 7 - iter 27/272 - loss 0.00860986 - time (sec): 1.76 - samples/sec: 3047.31 - lr: 0.000013 - momentum: 0.000000 2023-10-16 19:43:33,205 epoch 7 - iter 54/272 - loss 0.01502937 - time (sec): 3.25 - samples/sec: 3087.39 - lr: 0.000013 - momentum: 0.000000 2023-10-16 19:43:34,844 epoch 7 - iter 81/272 - loss 0.01762492 - time (sec): 4.89 - samples/sec: 3264.70 - lr: 0.000012 - momentum: 0.000000 2023-10-16 19:43:36,281 epoch 7 - iter 108/272 - loss 0.02130141 - time (sec): 6.33 - samples/sec: 3192.36 - lr: 0.000012 - momentum: 0.000000 2023-10-16 19:43:37,828 epoch 7 - iter 135/272 - loss 0.01919742 - time (sec): 7.88 - samples/sec: 3163.69 - lr: 0.000012 - momentum: 0.000000 2023-10-16 19:43:39,439 epoch 7 - iter 162/272 - loss 0.01892265 - time (sec): 9.49 - samples/sec: 3243.27 - lr: 0.000011 - momentum: 0.000000 2023-10-16 19:43:41,107 epoch 7 - iter 189/272 - loss 0.01706367 - time (sec): 11.16 - samples/sec: 3282.93 - lr: 0.000011 - momentum: 0.000000 2023-10-16 19:43:42,766 epoch 7 - iter 216/272 - loss 0.01961053 - time (sec): 12.81 - samples/sec: 3272.44 - lr: 0.000011 - momentum: 0.000000 2023-10-16 19:43:44,301 epoch 7 - iter 243/272 - loss 0.01988748 - time (sec): 14.35 - samples/sec: 3269.06 - lr: 0.000010 - momentum: 0.000000 2023-10-16 19:43:45,857 epoch 7 - iter 270/272 - loss 0.01967655 - time (sec): 15.91 - samples/sec: 3261.43 - lr: 0.000010 - momentum: 0.000000 2023-10-16 19:43:45,938 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:45,938 EPOCH 7 done: loss 0.0196 - lr: 0.000010 2023-10-16 19:43:47,701 DEV : loss 0.15851223468780518 - f1-score (micro avg) 0.8296 2023-10-16 19:43:47,706 saving best model 2023-10-16 19:43:48,144 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:43:49,737 epoch 8 - iter 27/272 - loss 0.00730779 - time (sec): 1.59 - samples/sec: 3356.08 - lr: 0.000010 - momentum: 0.000000 2023-10-16 19:43:51,346 epoch 8 - iter 54/272 - loss 0.01329991 - time (sec): 3.20 - samples/sec: 3283.33 - lr: 0.000009 - momentum: 0.000000 2023-10-16 19:43:52,910 epoch 8 - iter 81/272 - loss 0.01513609 - time (sec): 4.76 - samples/sec: 3232.24 - lr: 0.000009 - momentum: 0.000000 2023-10-16 19:43:54,423 epoch 8 - iter 108/272 - loss 0.01642677 - time (sec): 6.28 - samples/sec: 3279.86 - lr: 0.000009 - momentum: 0.000000 2023-10-16 19:43:55,951 epoch 8 - iter 135/272 - loss 0.01633534 - time (sec): 7.80 - samples/sec: 3248.26 - lr: 0.000008 - momentum: 0.000000 2023-10-16 19:43:57,780 epoch 8 - iter 162/272 - loss 0.01601286 - time (sec): 9.63 - samples/sec: 3295.91 - lr: 0.000008 - momentum: 0.000000 2023-10-16 19:43:59,225 epoch 8 - iter 189/272 - loss 0.01457084 - time (sec): 11.08 - samples/sec: 3283.86 - lr: 0.000008 - momentum: 0.000000 2023-10-16 19:44:00,755 epoch 8 - iter 216/272 - loss 0.01424786 - time (sec): 12.61 - samples/sec: 3295.96 - lr: 0.000007 - momentum: 0.000000 2023-10-16 19:44:02,216 epoch 8 - iter 243/272 - loss 0.01473901 - time (sec): 14.07 - samples/sec: 3267.45 - lr: 0.000007 - momentum: 0.000000 2023-10-16 19:44:03,955 epoch 8 - iter 270/272 - loss 0.01629383 - time (sec): 15.81 - samples/sec: 3280.70 - lr: 0.000007 - momentum: 0.000000 2023-10-16 19:44:04,041 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:04,042 EPOCH 8 done: loss 0.0163 - lr: 0.000007 2023-10-16 19:44:05,481 DEV : loss 0.1702307164669037 - f1-score (micro avg) 0.8185 2023-10-16 19:44:05,485 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:07,344 epoch 9 - iter 27/272 - loss 0.01425725 - time (sec): 1.86 - samples/sec: 3673.07 - lr: 0.000006 - momentum: 0.000000 2023-10-16 19:44:08,891 epoch 9 - iter 54/272 - loss 0.01007186 - time (sec): 3.40 - samples/sec: 3473.96 - lr: 0.000006 - momentum: 0.000000 2023-10-16 19:44:10,403 epoch 9 - iter 81/272 - loss 0.01074541 - time (sec): 4.92 - samples/sec: 3349.36 - lr: 0.000006 - momentum: 0.000000 2023-10-16 19:44:11,931 epoch 9 - iter 108/272 - loss 0.01073820 - time (sec): 6.44 - samples/sec: 3369.06 - lr: 0.000005 - momentum: 0.000000 2023-10-16 19:44:13,587 epoch 9 - iter 135/272 - loss 0.01165407 - time (sec): 8.10 - samples/sec: 3351.69 - lr: 0.000005 - momentum: 0.000000 2023-10-16 19:44:15,139 epoch 9 - iter 162/272 - loss 0.01157834 - time (sec): 9.65 - samples/sec: 3307.49 - lr: 0.000005 - momentum: 0.000000 2023-10-16 19:44:16,667 epoch 9 - iter 189/272 - loss 0.01155416 - time (sec): 11.18 - samples/sec: 3328.55 - lr: 0.000004 - momentum: 0.000000 2023-10-16 19:44:18,214 epoch 9 - iter 216/272 - loss 0.01153189 - time (sec): 12.73 - samples/sec: 3300.75 - lr: 0.000004 - momentum: 0.000000 2023-10-16 19:44:19,737 epoch 9 - iter 243/272 - loss 0.01160906 - time (sec): 14.25 - samples/sec: 3308.12 - lr: 0.000004 - momentum: 0.000000 2023-10-16 19:44:21,191 epoch 9 - iter 270/272 - loss 0.01116786 - time (sec): 15.70 - samples/sec: 3300.45 - lr: 0.000003 - momentum: 0.000000 2023-10-16 19:44:21,271 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:21,271 EPOCH 9 done: loss 0.0111 - lr: 0.000003 2023-10-16 19:44:22,704 DEV : loss 0.1694680005311966 - f1-score (micro avg) 0.8231 2023-10-16 19:44:22,708 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:24,190 epoch 10 - iter 27/272 - loss 0.01260807 - time (sec): 1.48 - samples/sec: 3696.73 - lr: 0.000003 - momentum: 0.000000 2023-10-16 19:44:25,500 epoch 10 - iter 54/272 - loss 0.00936227 - time (sec): 2.79 - samples/sec: 3440.58 - lr: 0.000003 - momentum: 0.000000 2023-10-16 19:44:27,074 epoch 10 - iter 81/272 - loss 0.00640857 - time (sec): 4.36 - samples/sec: 3416.96 - lr: 0.000002 - momentum: 0.000000 2023-10-16 19:44:28,554 epoch 10 - iter 108/272 - loss 0.00757260 - time (sec): 5.84 - samples/sec: 3438.35 - lr: 0.000002 - momentum: 0.000000 2023-10-16 19:44:30,020 epoch 10 - iter 135/272 - loss 0.00855156 - time (sec): 7.31 - samples/sec: 3436.34 - lr: 0.000002 - momentum: 0.000000 2023-10-16 19:44:31,751 epoch 10 - iter 162/272 - loss 0.00838144 - time (sec): 9.04 - samples/sec: 3406.32 - lr: 0.000001 - momentum: 0.000000 2023-10-16 19:44:33,309 epoch 10 - iter 189/272 - loss 0.00867403 - time (sec): 10.60 - samples/sec: 3403.41 - lr: 0.000001 - momentum: 0.000000 2023-10-16 19:44:34,793 epoch 10 - iter 216/272 - loss 0.00894913 - time (sec): 12.08 - samples/sec: 3383.57 - lr: 0.000001 - momentum: 0.000000 2023-10-16 19:44:36,325 epoch 10 - iter 243/272 - loss 0.00909194 - time (sec): 13.62 - samples/sec: 3365.60 - lr: 0.000000 - momentum: 0.000000 2023-10-16 19:44:37,949 epoch 10 - iter 270/272 - loss 0.00844017 - time (sec): 15.24 - samples/sec: 3399.90 - lr: 0.000000 - momentum: 0.000000 2023-10-16 19:44:38,030 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:38,030 EPOCH 10 done: loss 0.0084 - lr: 0.000000 2023-10-16 19:44:39,488 DEV : loss 0.17159999907016754 - f1-score (micro avg) 0.8185 2023-10-16 19:44:39,915 ---------------------------------------------------------------------------------------------------- 2023-10-16 19:44:39,917 Loading model from best epoch ... 2023-10-16 19:44:41,460 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG 2023-10-16 19:44:43,901 Results: - F-score (micro) 0.7683 - F-score (macro) 0.7159 - Accuracy 0.6392 By class: precision recall f1-score support LOC 0.7867 0.8750 0.8285 312 PER 0.6579 0.8413 0.7384 208 ORG 0.5556 0.3636 0.4396 55 HumanProd 0.7778 0.9545 0.8571 22 micro avg 0.7234 0.8191 0.7683 597 macro avg 0.6945 0.7586 0.7159 597 weighted avg 0.7202 0.8191 0.7623 597 2023-10-16 19:44:43,901 ----------------------------------------------------------------------------------------------------