2023-10-16 20:21:36,765 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,766 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 20:21:36,766 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 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 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Train: 1085 sentences 2023-10-16 20:21:36,767 (train_with_dev=False, train_with_test=False) 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Training Params: 2023-10-16 20:21:36,767 - learning_rate: "3e-05" 2023-10-16 20:21:36,767 - mini_batch_size: "4" 2023-10-16 20:21:36,767 - max_epochs: "10" 2023-10-16 20:21:36,767 - shuffle: "True" 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Plugins: 2023-10-16 20:21:36,767 - LinearScheduler | warmup_fraction: '0.1' 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Final evaluation on model from best epoch (best-model.pt) 2023-10-16 20:21:36,767 - metric: "('micro avg', 'f1-score')" 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Computation: 2023-10-16 20:21:36,767 - compute on device: cuda:0 2023-10-16 20:21:36,767 - embedding storage: none 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:36,767 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:38,339 epoch 1 - iter 27/272 - loss 2.78403560 - time (sec): 1.57 - samples/sec: 3229.32 - lr: 0.000003 - momentum: 0.000000 2023-10-16 20:21:40,094 epoch 1 - iter 54/272 - loss 2.40057045 - time (sec): 3.33 - samples/sec: 3248.68 - lr: 0.000006 - momentum: 0.000000 2023-10-16 20:21:41,731 epoch 1 - iter 81/272 - loss 1.82624760 - time (sec): 4.96 - samples/sec: 3345.86 - lr: 0.000009 - momentum: 0.000000 2023-10-16 20:21:43,315 epoch 1 - iter 108/272 - loss 1.52858521 - time (sec): 6.55 - samples/sec: 3282.52 - lr: 0.000012 - momentum: 0.000000 2023-10-16 20:21:44,848 epoch 1 - iter 135/272 - loss 1.32380649 - time (sec): 8.08 - samples/sec: 3297.07 - lr: 0.000015 - momentum: 0.000000 2023-10-16 20:21:46,418 epoch 1 - iter 162/272 - loss 1.18197180 - time (sec): 9.65 - samples/sec: 3300.84 - lr: 0.000018 - momentum: 0.000000 2023-10-16 20:21:47,884 epoch 1 - iter 189/272 - loss 1.05227075 - time (sec): 11.12 - samples/sec: 3314.13 - lr: 0.000021 - momentum: 0.000000 2023-10-16 20:21:49,438 epoch 1 - iter 216/272 - loss 0.95821963 - time (sec): 12.67 - samples/sec: 3311.69 - lr: 0.000024 - momentum: 0.000000 2023-10-16 20:21:50,892 epoch 1 - iter 243/272 - loss 0.89248220 - time (sec): 14.12 - samples/sec: 3299.70 - lr: 0.000027 - momentum: 0.000000 2023-10-16 20:21:52,460 epoch 1 - iter 270/272 - loss 0.82752649 - time (sec): 15.69 - samples/sec: 3304.71 - lr: 0.000030 - momentum: 0.000000 2023-10-16 20:21:52,549 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:52,550 EPOCH 1 done: loss 0.8257 - lr: 0.000030 2023-10-16 20:21:53,648 DEV : loss 0.20883718132972717 - f1-score (micro avg) 0.5635 2023-10-16 20:21:53,653 saving best model 2023-10-16 20:21:54,009 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:21:55,510 epoch 2 - iter 27/272 - loss 0.23865211 - time (sec): 1.50 - samples/sec: 3012.03 - lr: 0.000030 - momentum: 0.000000 2023-10-16 20:21:57,145 epoch 2 - iter 54/272 - loss 0.21111499 - time (sec): 3.13 - samples/sec: 2990.38 - lr: 0.000029 - momentum: 0.000000 2023-10-16 20:21:58,855 epoch 2 - iter 81/272 - loss 0.18236592 - time (sec): 4.84 - samples/sec: 3134.51 - lr: 0.000029 - momentum: 0.000000 2023-10-16 20:22:00,503 epoch 2 - iter 108/272 - loss 0.16340264 - time (sec): 6.49 - samples/sec: 3219.69 - lr: 0.000029 - momentum: 0.000000 2023-10-16 20:22:01,918 epoch 2 - iter 135/272 - loss 0.17367697 - time (sec): 7.91 - samples/sec: 3226.50 - lr: 0.000028 - momentum: 0.000000 2023-10-16 20:22:03,448 epoch 2 - iter 162/272 - loss 0.16437164 - time (sec): 9.44 - samples/sec: 3253.57 - lr: 0.000028 - momentum: 0.000000 2023-10-16 20:22:05,013 epoch 2 - iter 189/272 - loss 0.16007430 - time (sec): 11.00 - samples/sec: 3234.67 - lr: 0.000028 - momentum: 0.000000 2023-10-16 20:22:06,521 epoch 2 - iter 216/272 - loss 0.15664843 - time (sec): 12.51 - samples/sec: 3289.42 - lr: 0.000027 - momentum: 0.000000 2023-10-16 20:22:08,169 epoch 2 - iter 243/272 - loss 0.16161312 - time (sec): 14.16 - samples/sec: 3267.43 - lr: 0.000027 - momentum: 0.000000 2023-10-16 20:22:09,760 epoch 2 - iter 270/272 - loss 0.15717506 - time (sec): 15.75 - samples/sec: 3288.18 - lr: 0.000027 - momentum: 0.000000 2023-10-16 20:22:09,865 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:09,865 EPOCH 2 done: loss 0.1566 - lr: 0.000027 2023-10-16 20:22:11,292 DEV : loss 0.11095353215932846 - f1-score (micro avg) 0.7437 2023-10-16 20:22:11,299 saving best model 2023-10-16 20:22:11,759 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:13,277 epoch 3 - iter 27/272 - loss 0.11749999 - time (sec): 1.52 - samples/sec: 2858.87 - lr: 0.000026 - momentum: 0.000000 2023-10-16 20:22:14,910 epoch 3 - iter 54/272 - loss 0.11281766 - time (sec): 3.15 - samples/sec: 3016.40 - lr: 0.000026 - momentum: 0.000000 2023-10-16 20:22:16,349 epoch 3 - iter 81/272 - loss 0.10816546 - time (sec): 4.59 - samples/sec: 3086.19 - lr: 0.000026 - momentum: 0.000000 2023-10-16 20:22:17,971 epoch 3 - iter 108/272 - loss 0.09957259 - time (sec): 6.21 - samples/sec: 3190.98 - lr: 0.000025 - momentum: 0.000000 2023-10-16 20:22:19,509 epoch 3 - iter 135/272 - loss 0.09598081 - time (sec): 7.75 - samples/sec: 3248.08 - lr: 0.000025 - momentum: 0.000000 2023-10-16 20:22:21,106 epoch 3 - iter 162/272 - loss 0.09855270 - time (sec): 9.35 - samples/sec: 3319.72 - lr: 0.000025 - momentum: 0.000000 2023-10-16 20:22:22,721 epoch 3 - iter 189/272 - loss 0.09542228 - time (sec): 10.96 - samples/sec: 3281.50 - lr: 0.000024 - momentum: 0.000000 2023-10-16 20:22:24,159 epoch 3 - iter 216/272 - loss 0.09125236 - time (sec): 12.40 - samples/sec: 3244.45 - lr: 0.000024 - momentum: 0.000000 2023-10-16 20:22:25,925 epoch 3 - iter 243/272 - loss 0.09163871 - time (sec): 14.16 - samples/sec: 3249.55 - lr: 0.000024 - momentum: 0.000000 2023-10-16 20:22:27,581 epoch 3 - iter 270/272 - loss 0.09515133 - time (sec): 15.82 - samples/sec: 3269.62 - lr: 0.000023 - momentum: 0.000000 2023-10-16 20:22:27,698 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:27,698 EPOCH 3 done: loss 0.0950 - lr: 0.000023 2023-10-16 20:22:29,168 DEV : loss 0.1084960475564003 - f1-score (micro avg) 0.7687 2023-10-16 20:22:29,173 saving best model 2023-10-16 20:22:29,660 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:31,232 epoch 4 - iter 27/272 - loss 0.08673095 - time (sec): 1.57 - samples/sec: 3367.90 - lr: 0.000023 - momentum: 0.000000 2023-10-16 20:22:32,904 epoch 4 - iter 54/272 - loss 0.06096268 - time (sec): 3.24 - samples/sec: 3366.04 - lr: 0.000023 - momentum: 0.000000 2023-10-16 20:22:34,929 epoch 4 - iter 81/272 - loss 0.05277234 - time (sec): 5.27 - samples/sec: 3191.79 - lr: 0.000022 - momentum: 0.000000 2023-10-16 20:22:36,440 epoch 4 - iter 108/272 - loss 0.05214582 - time (sec): 6.78 - samples/sec: 3170.65 - lr: 0.000022 - momentum: 0.000000 2023-10-16 20:22:37,846 epoch 4 - iter 135/272 - loss 0.05275227 - time (sec): 8.18 - samples/sec: 3140.46 - lr: 0.000022 - momentum: 0.000000 2023-10-16 20:22:39,337 epoch 4 - iter 162/272 - loss 0.05294019 - time (sec): 9.68 - samples/sec: 3194.65 - lr: 0.000021 - momentum: 0.000000 2023-10-16 20:22:40,847 epoch 4 - iter 189/272 - loss 0.05256511 - time (sec): 11.19 - samples/sec: 3191.38 - lr: 0.000021 - momentum: 0.000000 2023-10-16 20:22:42,403 epoch 4 - iter 216/272 - loss 0.05388890 - time (sec): 12.74 - samples/sec: 3187.35 - lr: 0.000021 - momentum: 0.000000 2023-10-16 20:22:43,889 epoch 4 - iter 243/272 - loss 0.05397102 - time (sec): 14.23 - samples/sec: 3216.73 - lr: 0.000020 - momentum: 0.000000 2023-10-16 20:22:45,507 epoch 4 - iter 270/272 - loss 0.05116201 - time (sec): 15.85 - samples/sec: 3274.71 - lr: 0.000020 - momentum: 0.000000 2023-10-16 20:22:45,590 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:45,590 EPOCH 4 done: loss 0.0511 - lr: 0.000020 2023-10-16 20:22:47,042 DEV : loss 0.11970058083534241 - f1-score (micro avg) 0.7956 2023-10-16 20:22:47,047 saving best model 2023-10-16 20:22:47,506 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:22:49,124 epoch 5 - iter 27/272 - loss 0.02705900 - time (sec): 1.62 - samples/sec: 3193.66 - lr: 0.000020 - momentum: 0.000000 2023-10-16 20:22:50,547 epoch 5 - iter 54/272 - loss 0.02506314 - time (sec): 3.04 - samples/sec: 3127.97 - lr: 0.000019 - momentum: 0.000000 2023-10-16 20:22:52,155 epoch 5 - iter 81/272 - loss 0.03031274 - time (sec): 4.65 - samples/sec: 3124.88 - lr: 0.000019 - momentum: 0.000000 2023-10-16 20:22:53,730 epoch 5 - iter 108/272 - loss 0.03097207 - time (sec): 6.22 - samples/sec: 3159.63 - lr: 0.000019 - momentum: 0.000000 2023-10-16 20:22:55,225 epoch 5 - iter 135/272 - loss 0.02985994 - time (sec): 7.72 - samples/sec: 3242.28 - lr: 0.000018 - momentum: 0.000000 2023-10-16 20:22:56,755 epoch 5 - iter 162/272 - loss 0.03208358 - time (sec): 9.25 - samples/sec: 3243.43 - lr: 0.000018 - momentum: 0.000000 2023-10-16 20:22:58,587 epoch 5 - iter 189/272 - loss 0.03465943 - time (sec): 11.08 - samples/sec: 3296.53 - lr: 0.000018 - momentum: 0.000000 2023-10-16 20:23:00,310 epoch 5 - iter 216/272 - loss 0.03639915 - time (sec): 12.80 - samples/sec: 3304.91 - lr: 0.000017 - momentum: 0.000000 2023-10-16 20:23:01,828 epoch 5 - iter 243/272 - loss 0.03542833 - time (sec): 14.32 - samples/sec: 3266.68 - lr: 0.000017 - momentum: 0.000000 2023-10-16 20:23:03,373 epoch 5 - iter 270/272 - loss 0.03755505 - time (sec): 15.87 - samples/sec: 3259.66 - lr: 0.000017 - momentum: 0.000000 2023-10-16 20:23:03,466 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:03,466 EPOCH 5 done: loss 0.0374 - lr: 0.000017 2023-10-16 20:23:04,927 DEV : loss 0.1268547922372818 - f1-score (micro avg) 0.7971 2023-10-16 20:23:04,931 saving best model 2023-10-16 20:23:05,417 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:07,117 epoch 6 - iter 27/272 - loss 0.00811967 - time (sec): 1.70 - samples/sec: 3380.93 - lr: 0.000016 - momentum: 0.000000 2023-10-16 20:23:08,639 epoch 6 - iter 54/272 - loss 0.01425739 - time (sec): 3.22 - samples/sec: 3222.56 - lr: 0.000016 - momentum: 0.000000 2023-10-16 20:23:10,127 epoch 6 - iter 81/272 - loss 0.01768857 - time (sec): 4.71 - samples/sec: 3212.83 - lr: 0.000016 - momentum: 0.000000 2023-10-16 20:23:11,760 epoch 6 - iter 108/272 - loss 0.02554340 - time (sec): 6.34 - samples/sec: 3228.81 - lr: 0.000015 - momentum: 0.000000 2023-10-16 20:23:13,459 epoch 6 - iter 135/272 - loss 0.02481300 - time (sec): 8.04 - samples/sec: 3216.75 - lr: 0.000015 - momentum: 0.000000 2023-10-16 20:23:14,910 epoch 6 - iter 162/272 - loss 0.02810161 - time (sec): 9.49 - samples/sec: 3189.64 - lr: 0.000015 - momentum: 0.000000 2023-10-16 20:23:16,351 epoch 6 - iter 189/272 - loss 0.02581547 - time (sec): 10.93 - samples/sec: 3166.18 - lr: 0.000014 - momentum: 0.000000 2023-10-16 20:23:17,969 epoch 6 - iter 216/272 - loss 0.02439654 - time (sec): 12.55 - samples/sec: 3191.87 - lr: 0.000014 - momentum: 0.000000 2023-10-16 20:23:19,576 epoch 6 - iter 243/272 - loss 0.02443384 - time (sec): 14.16 - samples/sec: 3219.27 - lr: 0.000014 - momentum: 0.000000 2023-10-16 20:23:21,284 epoch 6 - iter 270/272 - loss 0.02556831 - time (sec): 15.87 - samples/sec: 3253.43 - lr: 0.000013 - momentum: 0.000000 2023-10-16 20:23:21,383 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:21,383 EPOCH 6 done: loss 0.0254 - lr: 0.000013 2023-10-16 20:23:22,856 DEV : loss 0.15687650442123413 - f1-score (micro avg) 0.8 2023-10-16 20:23:22,860 saving best model 2023-10-16 20:23:23,331 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:25,063 epoch 7 - iter 27/272 - loss 0.01894596 - time (sec): 1.73 - samples/sec: 3546.75 - lr: 0.000013 - momentum: 0.000000 2023-10-16 20:23:26,630 epoch 7 - iter 54/272 - loss 0.01748641 - time (sec): 3.30 - samples/sec: 3316.07 - lr: 0.000013 - momentum: 0.000000 2023-10-16 20:23:28,014 epoch 7 - iter 81/272 - loss 0.02121757 - time (sec): 4.68 - samples/sec: 3177.52 - lr: 0.000012 - momentum: 0.000000 2023-10-16 20:23:29,587 epoch 7 - iter 108/272 - loss 0.02299563 - time (sec): 6.25 - samples/sec: 3206.07 - lr: 0.000012 - momentum: 0.000000 2023-10-16 20:23:31,102 epoch 7 - iter 135/272 - loss 0.02088311 - time (sec): 7.77 - samples/sec: 3207.48 - lr: 0.000012 - momentum: 0.000000 2023-10-16 20:23:32,693 epoch 7 - iter 162/272 - loss 0.01951963 - time (sec): 9.36 - samples/sec: 3182.35 - lr: 0.000011 - momentum: 0.000000 2023-10-16 20:23:34,322 epoch 7 - iter 189/272 - loss 0.01987080 - time (sec): 10.99 - samples/sec: 3220.45 - lr: 0.000011 - momentum: 0.000000 2023-10-16 20:23:36,323 epoch 7 - iter 216/272 - loss 0.02118412 - time (sec): 12.99 - samples/sec: 3197.06 - lr: 0.000011 - momentum: 0.000000 2023-10-16 20:23:37,912 epoch 7 - iter 243/272 - loss 0.02066351 - time (sec): 14.58 - samples/sec: 3201.54 - lr: 0.000010 - momentum: 0.000000 2023-10-16 20:23:39,484 epoch 7 - iter 270/272 - loss 0.02156439 - time (sec): 16.15 - samples/sec: 3210.50 - lr: 0.000010 - momentum: 0.000000 2023-10-16 20:23:39,569 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:39,569 EPOCH 7 done: loss 0.0215 - lr: 0.000010 2023-10-16 20:23:41,023 DEV : loss 0.14880990982055664 - f1-score (micro avg) 0.8177 2023-10-16 20:23:41,028 saving best model 2023-10-16 20:23:41,490 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:43,041 epoch 8 - iter 27/272 - loss 0.02885847 - time (sec): 1.55 - samples/sec: 3406.76 - lr: 0.000010 - momentum: 0.000000 2023-10-16 20:23:44,729 epoch 8 - iter 54/272 - loss 0.02025245 - time (sec): 3.24 - samples/sec: 3261.21 - lr: 0.000009 - momentum: 0.000000 2023-10-16 20:23:46,167 epoch 8 - iter 81/272 - loss 0.01914734 - time (sec): 4.68 - samples/sec: 3213.83 - lr: 0.000009 - momentum: 0.000000 2023-10-16 20:23:47,822 epoch 8 - iter 108/272 - loss 0.01626159 - time (sec): 6.33 - samples/sec: 3259.52 - lr: 0.000009 - momentum: 0.000000 2023-10-16 20:23:49,237 epoch 8 - iter 135/272 - loss 0.01407233 - time (sec): 7.75 - samples/sec: 3303.45 - lr: 0.000008 - momentum: 0.000000 2023-10-16 20:23:50,883 epoch 8 - iter 162/272 - loss 0.01494253 - time (sec): 9.39 - samples/sec: 3278.17 - lr: 0.000008 - momentum: 0.000000 2023-10-16 20:23:52,476 epoch 8 - iter 189/272 - loss 0.01366276 - time (sec): 10.99 - samples/sec: 3228.69 - lr: 0.000008 - momentum: 0.000000 2023-10-16 20:23:54,141 epoch 8 - iter 216/272 - loss 0.01370213 - time (sec): 12.65 - samples/sec: 3285.37 - lr: 0.000007 - momentum: 0.000000 2023-10-16 20:23:55,686 epoch 8 - iter 243/272 - loss 0.01409608 - time (sec): 14.19 - samples/sec: 3286.25 - lr: 0.000007 - momentum: 0.000000 2023-10-16 20:23:57,435 epoch 8 - iter 270/272 - loss 0.01362443 - time (sec): 15.94 - samples/sec: 3254.98 - lr: 0.000007 - momentum: 0.000000 2023-10-16 20:23:57,523 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:23:57,524 EPOCH 8 done: loss 0.0136 - lr: 0.000007 2023-10-16 20:23:58,981 DEV : loss 0.16685882210731506 - f1-score (micro avg) 0.8103 2023-10-16 20:23:58,988 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:24:00,624 epoch 9 - iter 27/272 - loss 0.00599380 - time (sec): 1.63 - samples/sec: 3348.82 - lr: 0.000006 - momentum: 0.000000 2023-10-16 20:24:02,276 epoch 9 - iter 54/272 - loss 0.01311148 - time (sec): 3.29 - samples/sec: 3429.61 - lr: 0.000006 - momentum: 0.000000 2023-10-16 20:24:03,891 epoch 9 - iter 81/272 - loss 0.01123314 - time (sec): 4.90 - samples/sec: 3443.51 - lr: 0.000006 - momentum: 0.000000 2023-10-16 20:24:05,413 epoch 9 - iter 108/272 - loss 0.01353945 - time (sec): 6.42 - samples/sec: 3323.39 - lr: 0.000005 - momentum: 0.000000 2023-10-16 20:24:07,043 epoch 9 - iter 135/272 - loss 0.01225708 - time (sec): 8.05 - samples/sec: 3282.12 - lr: 0.000005 - momentum: 0.000000 2023-10-16 20:24:08,759 epoch 9 - iter 162/272 - loss 0.01190655 - time (sec): 9.77 - samples/sec: 3230.90 - lr: 0.000005 - momentum: 0.000000 2023-10-16 20:24:10,412 epoch 9 - iter 189/272 - loss 0.01157508 - time (sec): 11.42 - samples/sec: 3213.24 - lr: 0.000004 - momentum: 0.000000 2023-10-16 20:24:11,943 epoch 9 - iter 216/272 - loss 0.01177737 - time (sec): 12.95 - samples/sec: 3230.00 - lr: 0.000004 - momentum: 0.000000 2023-10-16 20:24:13,506 epoch 9 - iter 243/272 - loss 0.01213604 - time (sec): 14.52 - samples/sec: 3218.45 - lr: 0.000004 - momentum: 0.000000 2023-10-16 20:24:14,983 epoch 9 - iter 270/272 - loss 0.01161932 - time (sec): 15.99 - samples/sec: 3226.42 - lr: 0.000003 - momentum: 0.000000 2023-10-16 20:24:15,106 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:24:15,106 EPOCH 9 done: loss 0.0115 - lr: 0.000003 2023-10-16 20:24:16,622 DEV : loss 0.16301465034484863 - f1-score (micro avg) 0.8327 2023-10-16 20:24:16,627 saving best model 2023-10-16 20:24:17,102 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:24:18,760 epoch 10 - iter 27/272 - loss 0.01320646 - time (sec): 1.66 - samples/sec: 2935.45 - lr: 0.000003 - momentum: 0.000000 2023-10-16 20:24:20,380 epoch 10 - iter 54/272 - loss 0.01195513 - time (sec): 3.28 - samples/sec: 3000.55 - lr: 0.000003 - momentum: 0.000000 2023-10-16 20:24:22,050 epoch 10 - iter 81/272 - loss 0.01072011 - time (sec): 4.95 - samples/sec: 3165.10 - lr: 0.000002 - momentum: 0.000000 2023-10-16 20:24:23,640 epoch 10 - iter 108/272 - loss 0.01026115 - time (sec): 6.54 - samples/sec: 3232.53 - lr: 0.000002 - momentum: 0.000000 2023-10-16 20:24:25,083 epoch 10 - iter 135/272 - loss 0.01064150 - time (sec): 7.98 - samples/sec: 3247.32 - lr: 0.000002 - momentum: 0.000000 2023-10-16 20:24:26,612 epoch 10 - iter 162/272 - loss 0.00997044 - time (sec): 9.51 - samples/sec: 3235.87 - lr: 0.000001 - momentum: 0.000000 2023-10-16 20:24:28,274 epoch 10 - iter 189/272 - loss 0.01040692 - time (sec): 11.17 - samples/sec: 3250.02 - lr: 0.000001 - momentum: 0.000000 2023-10-16 20:24:30,075 epoch 10 - iter 216/272 - loss 0.00966299 - time (sec): 12.97 - samples/sec: 3285.20 - lr: 0.000001 - momentum: 0.000000 2023-10-16 20:24:31,522 epoch 10 - iter 243/272 - loss 0.00976536 - time (sec): 14.42 - samples/sec: 3264.05 - lr: 0.000000 - momentum: 0.000000 2023-10-16 20:24:32,976 epoch 10 - iter 270/272 - loss 0.00978654 - time (sec): 15.87 - samples/sec: 3252.31 - lr: 0.000000 - momentum: 0.000000 2023-10-16 20:24:33,097 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:24:33,097 EPOCH 10 done: loss 0.0097 - lr: 0.000000 2023-10-16 20:24:34,795 DEV : loss 0.1661917269229889 - f1-score (micro avg) 0.8155 2023-10-16 20:24:35,171 ---------------------------------------------------------------------------------------------------- 2023-10-16 20:24:35,172 Loading model from best epoch ... 2023-10-16 20:24:36,716 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 20:24:38,779 Results: - F-score (micro) 0.7838 - F-score (macro) 0.7384 - Accuracy 0.6582 By class: precision recall f1-score support LOC 0.8138 0.8686 0.8403 312 PER 0.6914 0.8510 0.7629 208 ORG 0.5217 0.4364 0.4752 55 HumanProd 0.8077 0.9545 0.8750 22 micro avg 0.7458 0.8258 0.7838 597 macro avg 0.7087 0.7776 0.7384 597 weighted avg 0.7440 0.8258 0.7810 597 2023-10-16 20:24:38,779 ----------------------------------------------------------------------------------------------------