2023-10-14 22:53:22,080 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,081 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=13, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-14 22:53:22,081 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,081 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator 2023-10-14 22:53:22,081 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,081 Train: 14465 sentences 2023-10-14 22:53:22,081 (train_with_dev=False, train_with_test=False) 2023-10-14 22:53:22,081 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,081 Training Params: 2023-10-14 22:53:22,081 - learning_rate: "3e-05" 2023-10-14 22:53:22,081 - mini_batch_size: "8" 2023-10-14 22:53:22,081 - max_epochs: "10" 2023-10-14 22:53:22,081 - shuffle: "True" 2023-10-14 22:53:22,081 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,081 Plugins: 2023-10-14 22:53:22,081 - LinearScheduler | warmup_fraction: '0.1' 2023-10-14 22:53:22,082 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,082 Final evaluation on model from best epoch (best-model.pt) 2023-10-14 22:53:22,082 - metric: "('micro avg', 'f1-score')" 2023-10-14 22:53:22,082 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,082 Computation: 2023-10-14 22:53:22,082 - compute on device: cuda:0 2023-10-14 22:53:22,082 - embedding storage: none 2023-10-14 22:53:22,082 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,082 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-14 22:53:22,082 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:22,082 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:53:33,152 epoch 1 - iter 180/1809 - loss 1.67027407 - time (sec): 11.07 - samples/sec: 3457.13 - lr: 0.000003 - momentum: 0.000000 2023-10-14 22:53:44,247 epoch 1 - iter 360/1809 - loss 0.96696948 - time (sec): 22.16 - samples/sec: 3425.79 - lr: 0.000006 - momentum: 0.000000 2023-10-14 22:53:55,940 epoch 1 - iter 540/1809 - loss 0.70638013 - time (sec): 33.86 - samples/sec: 3331.88 - lr: 0.000009 - momentum: 0.000000 2023-10-14 22:54:07,179 epoch 1 - iter 720/1809 - loss 0.55894456 - time (sec): 45.10 - samples/sec: 3377.37 - lr: 0.000012 - momentum: 0.000000 2023-10-14 22:54:18,106 epoch 1 - iter 900/1809 - loss 0.47409400 - time (sec): 56.02 - samples/sec: 3391.19 - lr: 0.000015 - momentum: 0.000000 2023-10-14 22:54:29,388 epoch 1 - iter 1080/1809 - loss 0.41428178 - time (sec): 67.31 - samples/sec: 3405.66 - lr: 0.000018 - momentum: 0.000000 2023-10-14 22:54:40,232 epoch 1 - iter 1260/1809 - loss 0.37349997 - time (sec): 78.15 - samples/sec: 3406.85 - lr: 0.000021 - momentum: 0.000000 2023-10-14 22:54:51,158 epoch 1 - iter 1440/1809 - loss 0.34066974 - time (sec): 89.08 - samples/sec: 3410.54 - lr: 0.000024 - momentum: 0.000000 2023-10-14 22:55:02,254 epoch 1 - iter 1620/1809 - loss 0.31439415 - time (sec): 100.17 - samples/sec: 3403.63 - lr: 0.000027 - momentum: 0.000000 2023-10-14 22:55:13,151 epoch 1 - iter 1800/1809 - loss 0.29381810 - time (sec): 111.07 - samples/sec: 3406.22 - lr: 0.000030 - momentum: 0.000000 2023-10-14 22:55:13,661 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:55:13,661 EPOCH 1 done: loss 0.2930 - lr: 0.000030 2023-10-14 22:55:19,299 DEV : loss 0.10940668731927872 - f1-score (micro avg) 0.604 2023-10-14 22:55:19,334 saving best model 2023-10-14 22:55:19,823 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:55:30,992 epoch 2 - iter 180/1809 - loss 0.08979228 - time (sec): 11.17 - samples/sec: 3317.64 - lr: 0.000030 - momentum: 0.000000 2023-10-14 22:55:42,224 epoch 2 - iter 360/1809 - loss 0.08989058 - time (sec): 22.40 - samples/sec: 3360.44 - lr: 0.000029 - momentum: 0.000000 2023-10-14 22:55:53,269 epoch 2 - iter 540/1809 - loss 0.08901176 - time (sec): 33.44 - samples/sec: 3395.78 - lr: 0.000029 - momentum: 0.000000 2023-10-14 22:56:04,648 epoch 2 - iter 720/1809 - loss 0.08769618 - time (sec): 44.82 - samples/sec: 3400.92 - lr: 0.000029 - momentum: 0.000000 2023-10-14 22:56:15,731 epoch 2 - iter 900/1809 - loss 0.08657795 - time (sec): 55.91 - samples/sec: 3423.49 - lr: 0.000028 - momentum: 0.000000 2023-10-14 22:56:26,940 epoch 2 - iter 1080/1809 - loss 0.08614963 - time (sec): 67.11 - samples/sec: 3412.98 - lr: 0.000028 - momentum: 0.000000 2023-10-14 22:56:37,915 epoch 2 - iter 1260/1809 - loss 0.08650169 - time (sec): 78.09 - samples/sec: 3409.66 - lr: 0.000028 - momentum: 0.000000 2023-10-14 22:56:48,753 epoch 2 - iter 1440/1809 - loss 0.08591524 - time (sec): 88.93 - samples/sec: 3397.15 - lr: 0.000027 - momentum: 0.000000 2023-10-14 22:57:00,131 epoch 2 - iter 1620/1809 - loss 0.08467002 - time (sec): 100.31 - samples/sec: 3398.25 - lr: 0.000027 - momentum: 0.000000 2023-10-14 22:57:10,944 epoch 2 - iter 1800/1809 - loss 0.08346842 - time (sec): 111.12 - samples/sec: 3402.53 - lr: 0.000027 - momentum: 0.000000 2023-10-14 22:57:11,479 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:57:11,479 EPOCH 2 done: loss 0.0833 - lr: 0.000027 2023-10-14 22:57:18,912 DEV : loss 0.12328627705574036 - f1-score (micro avg) 0.6436 2023-10-14 22:57:18,946 saving best model 2023-10-14 22:57:19,426 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:57:31,144 epoch 3 - iter 180/1809 - loss 0.05050900 - time (sec): 11.72 - samples/sec: 3299.37 - lr: 0.000026 - momentum: 0.000000 2023-10-14 22:57:42,023 epoch 3 - iter 360/1809 - loss 0.05640218 - time (sec): 22.59 - samples/sec: 3385.87 - lr: 0.000026 - momentum: 0.000000 2023-10-14 22:57:52,973 epoch 3 - iter 540/1809 - loss 0.05884620 - time (sec): 33.54 - samples/sec: 3385.83 - lr: 0.000026 - momentum: 0.000000 2023-10-14 22:58:03,993 epoch 3 - iter 720/1809 - loss 0.05715791 - time (sec): 44.57 - samples/sec: 3417.03 - lr: 0.000025 - momentum: 0.000000 2023-10-14 22:58:15,316 epoch 3 - iter 900/1809 - loss 0.05631954 - time (sec): 55.89 - samples/sec: 3394.29 - lr: 0.000025 - momentum: 0.000000 2023-10-14 22:58:26,071 epoch 3 - iter 1080/1809 - loss 0.05690696 - time (sec): 66.64 - samples/sec: 3409.30 - lr: 0.000025 - momentum: 0.000000 2023-10-14 22:58:37,282 epoch 3 - iter 1260/1809 - loss 0.05623779 - time (sec): 77.85 - samples/sec: 3404.87 - lr: 0.000024 - momentum: 0.000000 2023-10-14 22:58:48,305 epoch 3 - iter 1440/1809 - loss 0.05612202 - time (sec): 88.88 - samples/sec: 3399.30 - lr: 0.000024 - momentum: 0.000000 2023-10-14 22:58:59,489 epoch 3 - iter 1620/1809 - loss 0.05782234 - time (sec): 100.06 - samples/sec: 3403.20 - lr: 0.000024 - momentum: 0.000000 2023-10-14 22:59:10,384 epoch 3 - iter 1800/1809 - loss 0.05647561 - time (sec): 110.96 - samples/sec: 3408.09 - lr: 0.000023 - momentum: 0.000000 2023-10-14 22:59:11,005 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:59:11,005 EPOCH 3 done: loss 0.0563 - lr: 0.000023 2023-10-14 22:59:16,771 DEV : loss 0.1787535846233368 - f1-score (micro avg) 0.6304 2023-10-14 22:59:16,818 ---------------------------------------------------------------------------------------------------- 2023-10-14 22:59:28,293 epoch 4 - iter 180/1809 - loss 0.03058125 - time (sec): 11.47 - samples/sec: 3393.40 - lr: 0.000023 - momentum: 0.000000 2023-10-14 22:59:40,346 epoch 4 - iter 360/1809 - loss 0.03335145 - time (sec): 23.53 - samples/sec: 3247.71 - lr: 0.000023 - momentum: 0.000000 2023-10-14 22:59:51,427 epoch 4 - iter 540/1809 - loss 0.03771304 - time (sec): 34.61 - samples/sec: 3305.71 - lr: 0.000022 - momentum: 0.000000 2023-10-14 23:00:02,403 epoch 4 - iter 720/1809 - loss 0.03909361 - time (sec): 45.58 - samples/sec: 3315.77 - lr: 0.000022 - momentum: 0.000000 2023-10-14 23:00:13,244 epoch 4 - iter 900/1809 - loss 0.03854045 - time (sec): 56.42 - samples/sec: 3339.92 - lr: 0.000022 - momentum: 0.000000 2023-10-14 23:00:24,493 epoch 4 - iter 1080/1809 - loss 0.03909550 - time (sec): 67.67 - samples/sec: 3349.27 - lr: 0.000021 - momentum: 0.000000 2023-10-14 23:00:35,558 epoch 4 - iter 1260/1809 - loss 0.03949444 - time (sec): 78.74 - samples/sec: 3361.35 - lr: 0.000021 - momentum: 0.000000 2023-10-14 23:00:46,652 epoch 4 - iter 1440/1809 - loss 0.03909637 - time (sec): 89.83 - samples/sec: 3374.67 - lr: 0.000021 - momentum: 0.000000 2023-10-14 23:00:57,583 epoch 4 - iter 1620/1809 - loss 0.03977330 - time (sec): 100.76 - samples/sec: 3381.39 - lr: 0.000020 - momentum: 0.000000 2023-10-14 23:01:08,579 epoch 4 - iter 1800/1809 - loss 0.04051474 - time (sec): 111.76 - samples/sec: 3382.87 - lr: 0.000020 - momentum: 0.000000 2023-10-14 23:01:09,100 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:01:09,100 EPOCH 4 done: loss 0.0407 - lr: 0.000020 2023-10-14 23:01:14,916 DEV : loss 0.212530717253685 - f1-score (micro avg) 0.6394 2023-10-14 23:01:14,965 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:01:26,608 epoch 5 - iter 180/1809 - loss 0.03110605 - time (sec): 11.64 - samples/sec: 3244.49 - lr: 0.000020 - momentum: 0.000000 2023-10-14 23:01:37,407 epoch 5 - iter 360/1809 - loss 0.02633661 - time (sec): 22.44 - samples/sec: 3367.39 - lr: 0.000019 - momentum: 0.000000 2023-10-14 23:01:48,476 epoch 5 - iter 540/1809 - loss 0.02512481 - time (sec): 33.51 - samples/sec: 3381.73 - lr: 0.000019 - momentum: 0.000000 2023-10-14 23:01:59,358 epoch 5 - iter 720/1809 - loss 0.02642180 - time (sec): 44.39 - samples/sec: 3378.28 - lr: 0.000019 - momentum: 0.000000 2023-10-14 23:02:10,472 epoch 5 - iter 900/1809 - loss 0.02681334 - time (sec): 55.51 - samples/sec: 3383.01 - lr: 0.000018 - momentum: 0.000000 2023-10-14 23:02:21,350 epoch 5 - iter 1080/1809 - loss 0.02711812 - time (sec): 66.38 - samples/sec: 3387.39 - lr: 0.000018 - momentum: 0.000000 2023-10-14 23:02:31,971 epoch 5 - iter 1260/1809 - loss 0.02724187 - time (sec): 77.00 - samples/sec: 3399.19 - lr: 0.000018 - momentum: 0.000000 2023-10-14 23:02:43,223 epoch 5 - iter 1440/1809 - loss 0.02806269 - time (sec): 88.26 - samples/sec: 3411.19 - lr: 0.000017 - momentum: 0.000000 2023-10-14 23:02:55,040 epoch 5 - iter 1620/1809 - loss 0.02837556 - time (sec): 100.07 - samples/sec: 3395.44 - lr: 0.000017 - momentum: 0.000000 2023-10-14 23:03:06,144 epoch 5 - iter 1800/1809 - loss 0.02959314 - time (sec): 111.18 - samples/sec: 3402.73 - lr: 0.000017 - momentum: 0.000000 2023-10-14 23:03:06,663 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:03:06,663 EPOCH 5 done: loss 0.0297 - lr: 0.000017 2023-10-14 23:03:12,415 DEV : loss 0.30899283289909363 - f1-score (micro avg) 0.6383 2023-10-14 23:03:12,460 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:03:23,454 epoch 6 - iter 180/1809 - loss 0.01975153 - time (sec): 10.99 - samples/sec: 3268.70 - lr: 0.000016 - momentum: 0.000000 2023-10-14 23:03:34,423 epoch 6 - iter 360/1809 - loss 0.02159189 - time (sec): 21.96 - samples/sec: 3373.45 - lr: 0.000016 - momentum: 0.000000 2023-10-14 23:03:45,156 epoch 6 - iter 540/1809 - loss 0.02205122 - time (sec): 32.69 - samples/sec: 3395.68 - lr: 0.000016 - momentum: 0.000000 2023-10-14 23:03:55,922 epoch 6 - iter 720/1809 - loss 0.02227128 - time (sec): 43.46 - samples/sec: 3422.32 - lr: 0.000015 - momentum: 0.000000 2023-10-14 23:04:06,988 epoch 6 - iter 900/1809 - loss 0.02215978 - time (sec): 54.53 - samples/sec: 3437.87 - lr: 0.000015 - momentum: 0.000000 2023-10-14 23:04:18,180 epoch 6 - iter 1080/1809 - loss 0.02229865 - time (sec): 65.72 - samples/sec: 3431.52 - lr: 0.000015 - momentum: 0.000000 2023-10-14 23:04:29,141 epoch 6 - iter 1260/1809 - loss 0.02131826 - time (sec): 76.68 - samples/sec: 3450.76 - lr: 0.000014 - momentum: 0.000000 2023-10-14 23:04:40,072 epoch 6 - iter 1440/1809 - loss 0.02100046 - time (sec): 87.61 - samples/sec: 3471.36 - lr: 0.000014 - momentum: 0.000000 2023-10-14 23:04:50,521 epoch 6 - iter 1620/1809 - loss 0.02171985 - time (sec): 98.06 - samples/sec: 3468.48 - lr: 0.000014 - momentum: 0.000000 2023-10-14 23:05:01,563 epoch 6 - iter 1800/1809 - loss 0.02103705 - time (sec): 109.10 - samples/sec: 3465.50 - lr: 0.000013 - momentum: 0.000000 2023-10-14 23:05:02,125 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:05:02,125 EPOCH 6 done: loss 0.0211 - lr: 0.000013 2023-10-14 23:05:09,525 DEV : loss 0.3297453224658966 - f1-score (micro avg) 0.6349 2023-10-14 23:05:09,564 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:05:21,406 epoch 7 - iter 180/1809 - loss 0.01552725 - time (sec): 11.84 - samples/sec: 3136.20 - lr: 0.000013 - momentum: 0.000000 2023-10-14 23:05:32,981 epoch 7 - iter 360/1809 - loss 0.01402831 - time (sec): 23.42 - samples/sec: 3263.96 - lr: 0.000013 - momentum: 0.000000 2023-10-14 23:05:44,453 epoch 7 - iter 540/1809 - loss 0.01360336 - time (sec): 34.89 - samples/sec: 3314.74 - lr: 0.000012 - momentum: 0.000000 2023-10-14 23:05:55,765 epoch 7 - iter 720/1809 - loss 0.01494343 - time (sec): 46.20 - samples/sec: 3294.49 - lr: 0.000012 - momentum: 0.000000 2023-10-14 23:06:06,988 epoch 7 - iter 900/1809 - loss 0.01605299 - time (sec): 57.42 - samples/sec: 3310.58 - lr: 0.000012 - momentum: 0.000000 2023-10-14 23:06:17,896 epoch 7 - iter 1080/1809 - loss 0.01580151 - time (sec): 68.33 - samples/sec: 3335.50 - lr: 0.000011 - momentum: 0.000000 2023-10-14 23:06:29,114 epoch 7 - iter 1260/1809 - loss 0.01590065 - time (sec): 79.55 - samples/sec: 3352.47 - lr: 0.000011 - momentum: 0.000000 2023-10-14 23:06:39,900 epoch 7 - iter 1440/1809 - loss 0.01510279 - time (sec): 90.33 - samples/sec: 3348.18 - lr: 0.000011 - momentum: 0.000000 2023-10-14 23:06:51,240 epoch 7 - iter 1620/1809 - loss 0.01461003 - time (sec): 101.67 - samples/sec: 3346.97 - lr: 0.000010 - momentum: 0.000000 2023-10-14 23:07:02,417 epoch 7 - iter 1800/1809 - loss 0.01467349 - time (sec): 112.85 - samples/sec: 3351.90 - lr: 0.000010 - momentum: 0.000000 2023-10-14 23:07:02,945 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:07:02,945 EPOCH 7 done: loss 0.0146 - lr: 0.000010 2023-10-14 23:07:10,634 DEV : loss 0.3628890812397003 - f1-score (micro avg) 0.6504 2023-10-14 23:07:10,675 saving best model 2023-10-14 23:07:11,201 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:07:22,863 epoch 8 - iter 180/1809 - loss 0.00662021 - time (sec): 11.66 - samples/sec: 3155.29 - lr: 0.000010 - momentum: 0.000000 2023-10-14 23:07:34,630 epoch 8 - iter 360/1809 - loss 0.00795343 - time (sec): 23.43 - samples/sec: 3215.56 - lr: 0.000009 - momentum: 0.000000 2023-10-14 23:07:46,178 epoch 8 - iter 540/1809 - loss 0.00814355 - time (sec): 34.97 - samples/sec: 3244.02 - lr: 0.000009 - momentum: 0.000000 2023-10-14 23:07:57,360 epoch 8 - iter 720/1809 - loss 0.00832031 - time (sec): 46.16 - samples/sec: 3271.35 - lr: 0.000009 - momentum: 0.000000 2023-10-14 23:08:08,704 epoch 8 - iter 900/1809 - loss 0.00816301 - time (sec): 57.50 - samples/sec: 3270.22 - lr: 0.000008 - momentum: 0.000000 2023-10-14 23:08:20,051 epoch 8 - iter 1080/1809 - loss 0.00860007 - time (sec): 68.85 - samples/sec: 3288.75 - lr: 0.000008 - momentum: 0.000000 2023-10-14 23:08:31,136 epoch 8 - iter 1260/1809 - loss 0.00904243 - time (sec): 79.93 - samples/sec: 3313.67 - lr: 0.000008 - momentum: 0.000000 2023-10-14 23:08:42,429 epoch 8 - iter 1440/1809 - loss 0.00953422 - time (sec): 91.23 - samples/sec: 3313.24 - lr: 0.000007 - momentum: 0.000000 2023-10-14 23:08:53,796 epoch 8 - iter 1620/1809 - loss 0.01000057 - time (sec): 102.59 - samples/sec: 3308.69 - lr: 0.000007 - momentum: 0.000000 2023-10-14 23:09:05,437 epoch 8 - iter 1800/1809 - loss 0.01005559 - time (sec): 114.23 - samples/sec: 3312.91 - lr: 0.000007 - momentum: 0.000000 2023-10-14 23:09:05,941 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:09:05,941 EPOCH 8 done: loss 0.0100 - lr: 0.000007 2023-10-14 23:09:13,141 DEV : loss 0.37255582213401794 - f1-score (micro avg) 0.6496 2023-10-14 23:09:13,188 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:09:24,752 epoch 9 - iter 180/1809 - loss 0.00494447 - time (sec): 11.56 - samples/sec: 3303.26 - lr: 0.000006 - momentum: 0.000000 2023-10-14 23:09:36,272 epoch 9 - iter 360/1809 - loss 0.00585614 - time (sec): 23.08 - samples/sec: 3278.56 - lr: 0.000006 - momentum: 0.000000 2023-10-14 23:09:47,503 epoch 9 - iter 540/1809 - loss 0.00614073 - time (sec): 34.31 - samples/sec: 3302.47 - lr: 0.000006 - momentum: 0.000000 2023-10-14 23:09:58,681 epoch 9 - iter 720/1809 - loss 0.00551232 - time (sec): 45.49 - samples/sec: 3340.65 - lr: 0.000005 - momentum: 0.000000 2023-10-14 23:10:09,760 epoch 9 - iter 900/1809 - loss 0.00625027 - time (sec): 56.57 - samples/sec: 3357.66 - lr: 0.000005 - momentum: 0.000000 2023-10-14 23:10:20,942 epoch 9 - iter 1080/1809 - loss 0.00619889 - time (sec): 67.75 - samples/sec: 3379.13 - lr: 0.000005 - momentum: 0.000000 2023-10-14 23:10:31,916 epoch 9 - iter 1260/1809 - loss 0.00604495 - time (sec): 78.73 - samples/sec: 3390.61 - lr: 0.000004 - momentum: 0.000000 2023-10-14 23:10:42,708 epoch 9 - iter 1440/1809 - loss 0.00630439 - time (sec): 89.52 - samples/sec: 3391.73 - lr: 0.000004 - momentum: 0.000000 2023-10-14 23:10:53,793 epoch 9 - iter 1620/1809 - loss 0.00656510 - time (sec): 100.60 - samples/sec: 3397.99 - lr: 0.000004 - momentum: 0.000000 2023-10-14 23:11:04,500 epoch 9 - iter 1800/1809 - loss 0.00635203 - time (sec): 111.31 - samples/sec: 3397.12 - lr: 0.000003 - momentum: 0.000000 2023-10-14 23:11:05,069 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:11:05,069 EPOCH 9 done: loss 0.0063 - lr: 0.000003 2023-10-14 23:11:10,696 DEV : loss 0.38722819089889526 - f1-score (micro avg) 0.6478 2023-10-14 23:11:10,731 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:11:23,051 epoch 10 - iter 180/1809 - loss 0.00392312 - time (sec): 12.32 - samples/sec: 3093.81 - lr: 0.000003 - momentum: 0.000000 2023-10-14 23:11:33,944 epoch 10 - iter 360/1809 - loss 0.00404755 - time (sec): 23.21 - samples/sec: 3274.69 - lr: 0.000003 - momentum: 0.000000 2023-10-14 23:11:44,860 epoch 10 - iter 540/1809 - loss 0.00406751 - time (sec): 34.13 - samples/sec: 3311.50 - lr: 0.000002 - momentum: 0.000000 2023-10-14 23:11:55,986 epoch 10 - iter 720/1809 - loss 0.00488523 - time (sec): 45.25 - samples/sec: 3346.71 - lr: 0.000002 - momentum: 0.000000 2023-10-14 23:12:07,005 epoch 10 - iter 900/1809 - loss 0.00447546 - time (sec): 56.27 - samples/sec: 3372.90 - lr: 0.000002 - momentum: 0.000000 2023-10-14 23:12:17,916 epoch 10 - iter 1080/1809 - loss 0.00409456 - time (sec): 67.18 - samples/sec: 3382.70 - lr: 0.000001 - momentum: 0.000000 2023-10-14 23:12:29,157 epoch 10 - iter 1260/1809 - loss 0.00427865 - time (sec): 78.42 - samples/sec: 3377.11 - lr: 0.000001 - momentum: 0.000000 2023-10-14 23:12:40,344 epoch 10 - iter 1440/1809 - loss 0.00393300 - time (sec): 89.61 - samples/sec: 3387.40 - lr: 0.000001 - momentum: 0.000000 2023-10-14 23:12:51,215 epoch 10 - iter 1620/1809 - loss 0.00442583 - time (sec): 100.48 - samples/sec: 3373.72 - lr: 0.000000 - momentum: 0.000000 2023-10-14 23:13:02,697 epoch 10 - iter 1800/1809 - loss 0.00442660 - time (sec): 111.96 - samples/sec: 3379.21 - lr: 0.000000 - momentum: 0.000000 2023-10-14 23:13:03,201 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:13:03,201 EPOCH 10 done: loss 0.0044 - lr: 0.000000 2023-10-14 23:13:08,887 DEV : loss 0.39746981859207153 - f1-score (micro avg) 0.6532 2023-10-14 23:13:08,933 saving best model 2023-10-14 23:13:09,734 ---------------------------------------------------------------------------------------------------- 2023-10-14 23:13:09,736 Loading model from best epoch ... 2023-10-14 23:13:11,362 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org 2023-10-14 23:13:20,771 Results: - F-score (micro) 0.6532 - F-score (macro) 0.5047 - Accuracy 0.5013 By class: precision recall f1-score support loc 0.6327 0.7986 0.7061 591 pers 0.5670 0.7703 0.6532 357 org 0.1746 0.1392 0.1549 79 micro avg 0.5858 0.7381 0.6532 1027 macro avg 0.4581 0.5694 0.5047 1027 weighted avg 0.5746 0.7381 0.6453 1027 2023-10-14 23:13:20,771 ----------------------------------------------------------------------------------------------------