2023-10-13 11:10:18,371 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,372 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=25, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-13 11:10:18,372 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,372 MultiCorpus: 966 train + 219 dev + 204 test sentences
 - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-13 11:10:18,372 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,372 Train:  966 sentences
2023-10-13 11:10:18,372         (train_with_dev=False, train_with_test=False)
2023-10-13 11:10:18,372 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,372 Training Params:
2023-10-13 11:10:18,372  - learning_rate: "3e-05" 
2023-10-13 11:10:18,372  - mini_batch_size: "8"
2023-10-13 11:10:18,372  - max_epochs: "10"
2023-10-13 11:10:18,372  - shuffle: "True"
2023-10-13 11:10:18,372 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,373 Plugins:
2023-10-13 11:10:18,373  - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 11:10:18,373 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,373 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 11:10:18,373  - metric: "('micro avg', 'f1-score')"
2023-10-13 11:10:18,373 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,373 Computation:
2023-10-13 11:10:18,373  - compute on device: cuda:0
2023-10-13 11:10:18,373  - embedding storage: none
2023-10-13 11:10:18,373 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,373 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-13 11:10:18,373 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:18,373 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:19,028 epoch 1 - iter 12/121 - loss 3.23686547 - time (sec): 0.65 - samples/sec: 3357.97 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:10:19,789 epoch 1 - iter 24/121 - loss 3.08356686 - time (sec): 1.42 - samples/sec: 3404.65 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:10:20,522 epoch 1 - iter 36/121 - loss 2.75565966 - time (sec): 2.15 - samples/sec: 3356.65 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:10:21,260 epoch 1 - iter 48/121 - loss 2.22033244 - time (sec): 2.89 - samples/sec: 3445.03 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:10:22,022 epoch 1 - iter 60/121 - loss 1.90687504 - time (sec): 3.65 - samples/sec: 3413.67 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:10:22,689 epoch 1 - iter 72/121 - loss 1.70068116 - time (sec): 4.31 - samples/sec: 3377.30 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:10:23,464 epoch 1 - iter 84/121 - loss 1.54601736 - time (sec): 5.09 - samples/sec: 3371.31 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:10:24,156 epoch 1 - iter 96/121 - loss 1.42977512 - time (sec): 5.78 - samples/sec: 3382.42 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:10:24,867 epoch 1 - iter 108/121 - loss 1.33870901 - time (sec): 6.49 - samples/sec: 3365.58 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:10:25,655 epoch 1 - iter 120/121 - loss 1.23639310 - time (sec): 7.28 - samples/sec: 3361.78 - lr: 0.000030 - momentum: 0.000000
2023-10-13 11:10:25,726 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:25,726 EPOCH 1 done: loss 1.2258 - lr: 0.000030
2023-10-13 11:10:26,644 DEV : loss 0.36207425594329834 - f1-score (micro avg)  0.3053
2023-10-13 11:10:26,649 saving best model
2023-10-13 11:10:27,006 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:27,700 epoch 2 - iter 12/121 - loss 0.39607246 - time (sec): 0.69 - samples/sec: 3726.90 - lr: 0.000030 - momentum: 0.000000
2023-10-13 11:10:28,463 epoch 2 - iter 24/121 - loss 0.36432721 - time (sec): 1.46 - samples/sec: 3571.66 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:10:29,135 epoch 2 - iter 36/121 - loss 0.36955311 - time (sec): 2.13 - samples/sec: 3459.37 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:10:29,904 epoch 2 - iter 48/121 - loss 0.34687311 - time (sec): 2.90 - samples/sec: 3426.17 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:10:30,617 epoch 2 - iter 60/121 - loss 0.32491719 - time (sec): 3.61 - samples/sec: 3393.44 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:10:31,369 epoch 2 - iter 72/121 - loss 0.30750715 - time (sec): 4.36 - samples/sec: 3381.87 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:10:32,148 epoch 2 - iter 84/121 - loss 0.29997426 - time (sec): 5.14 - samples/sec: 3362.05 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:10:32,881 epoch 2 - iter 96/121 - loss 0.29230878 - time (sec): 5.87 - samples/sec: 3367.92 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:10:33,606 epoch 2 - iter 108/121 - loss 0.27725347 - time (sec): 6.60 - samples/sec: 3375.32 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:10:34,301 epoch 2 - iter 120/121 - loss 0.26927054 - time (sec): 7.29 - samples/sec: 3378.13 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:10:34,350 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:34,350 EPOCH 2 done: loss 0.2695 - lr: 0.000027
2023-10-13 11:10:35,153 DEV : loss 0.16814236342906952 - f1-score (micro avg)  0.6962
2023-10-13 11:10:35,159 saving best model
2023-10-13 11:10:35,771 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:36,503 epoch 3 - iter 12/121 - loss 0.15819860 - time (sec): 0.73 - samples/sec: 3394.19 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:10:37,304 epoch 3 - iter 24/121 - loss 0.16309934 - time (sec): 1.53 - samples/sec: 3229.87 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:10:38,024 epoch 3 - iter 36/121 - loss 0.15355893 - time (sec): 2.25 - samples/sec: 3108.45 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:10:38,805 epoch 3 - iter 48/121 - loss 0.14476800 - time (sec): 3.03 - samples/sec: 3151.69 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:10:39,562 epoch 3 - iter 60/121 - loss 0.15856289 - time (sec): 3.79 - samples/sec: 3198.34 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:10:40,321 epoch 3 - iter 72/121 - loss 0.15967065 - time (sec): 4.55 - samples/sec: 3238.68 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:10:41,049 epoch 3 - iter 84/121 - loss 0.15280106 - time (sec): 5.27 - samples/sec: 3290.71 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:10:41,787 epoch 3 - iter 96/121 - loss 0.15638849 - time (sec): 6.01 - samples/sec: 3282.68 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:10:42,441 epoch 3 - iter 108/121 - loss 0.15090289 - time (sec): 6.66 - samples/sec: 3289.20 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:10:43,180 epoch 3 - iter 120/121 - loss 0.14357302 - time (sec): 7.40 - samples/sec: 3309.23 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:10:43,232 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:43,232 EPOCH 3 done: loss 0.1423 - lr: 0.000023
2023-10-13 11:10:44,149 DEV : loss 0.126093789935112 - f1-score (micro avg)  0.8055
2023-10-13 11:10:44,157 saving best model
2023-10-13 11:10:44,687 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:45,522 epoch 4 - iter 12/121 - loss 0.08458435 - time (sec): 0.83 - samples/sec: 2905.79 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:10:46,450 epoch 4 - iter 24/121 - loss 0.09228534 - time (sec): 1.76 - samples/sec: 2859.11 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:10:47,240 epoch 4 - iter 36/121 - loss 0.09097094 - time (sec): 2.55 - samples/sec: 2886.20 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:10:48,030 epoch 4 - iter 48/121 - loss 0.09573211 - time (sec): 3.34 - samples/sec: 2936.27 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:10:48,873 epoch 4 - iter 60/121 - loss 0.09409124 - time (sec): 4.18 - samples/sec: 2961.19 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:10:49,726 epoch 4 - iter 72/121 - loss 0.09645539 - time (sec): 5.04 - samples/sec: 2968.80 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:10:50,507 epoch 4 - iter 84/121 - loss 0.09356465 - time (sec): 5.82 - samples/sec: 2970.75 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:10:51,306 epoch 4 - iter 96/121 - loss 0.09865829 - time (sec): 6.62 - samples/sec: 2949.74 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:10:52,131 epoch 4 - iter 108/121 - loss 0.10045796 - time (sec): 7.44 - samples/sec: 2944.22 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:10:53,065 epoch 4 - iter 120/121 - loss 0.09623331 - time (sec): 8.38 - samples/sec: 2938.18 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:10:53,130 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:53,130 EPOCH 4 done: loss 0.0959 - lr: 0.000020
2023-10-13 11:10:53,958 DEV : loss 0.11419466882944107 - f1-score (micro avg)  0.814
2023-10-13 11:10:53,963 saving best model
2023-10-13 11:10:54,443 ----------------------------------------------------------------------------------------------------
2023-10-13 11:10:55,252 epoch 5 - iter 12/121 - loss 0.07157336 - time (sec): 0.80 - samples/sec: 3282.21 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:10:55,972 epoch 5 - iter 24/121 - loss 0.07611632 - time (sec): 1.52 - samples/sec: 3279.00 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:10:56,678 epoch 5 - iter 36/121 - loss 0.06427848 - time (sec): 2.23 - samples/sec: 3257.32 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:10:57,412 epoch 5 - iter 48/121 - loss 0.07273777 - time (sec): 2.96 - samples/sec: 3296.01 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:10:58,115 epoch 5 - iter 60/121 - loss 0.07213143 - time (sec): 3.67 - samples/sec: 3344.49 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:10:58,831 epoch 5 - iter 72/121 - loss 0.06897480 - time (sec): 4.38 - samples/sec: 3370.17 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:10:59,579 epoch 5 - iter 84/121 - loss 0.06830377 - time (sec): 5.13 - samples/sec: 3398.16 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:11:00,354 epoch 5 - iter 96/121 - loss 0.06639599 - time (sec): 5.91 - samples/sec: 3361.63 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:11:01,097 epoch 5 - iter 108/121 - loss 0.06645515 - time (sec): 6.65 - samples/sec: 3375.34 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:11:01,778 epoch 5 - iter 120/121 - loss 0.06438298 - time (sec): 7.33 - samples/sec: 3356.46 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:11:01,827 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:01,827 EPOCH 5 done: loss 0.0645 - lr: 0.000017
2023-10-13 11:11:02,675 DEV : loss 0.14454086124897003 - f1-score (micro avg)  0.8054
2023-10-13 11:11:02,681 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:03,442 epoch 6 - iter 12/121 - loss 0.05954669 - time (sec): 0.76 - samples/sec: 3410.58 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:11:04,204 epoch 6 - iter 24/121 - loss 0.05911514 - time (sec): 1.52 - samples/sec: 3345.39 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:11:04,960 epoch 6 - iter 36/121 - loss 0.05197972 - time (sec): 2.28 - samples/sec: 3380.01 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:11:05,619 epoch 6 - iter 48/121 - loss 0.04652385 - time (sec): 2.94 - samples/sec: 3340.33 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:11:06,487 epoch 6 - iter 60/121 - loss 0.04783989 - time (sec): 3.80 - samples/sec: 3284.27 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:11:07,249 epoch 6 - iter 72/121 - loss 0.04450554 - time (sec): 4.57 - samples/sec: 3267.21 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:11:07,951 epoch 6 - iter 84/121 - loss 0.04614645 - time (sec): 5.27 - samples/sec: 3238.91 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:11:08,678 epoch 6 - iter 96/121 - loss 0.04321518 - time (sec): 6.00 - samples/sec: 3235.98 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:11:09,424 epoch 6 - iter 108/121 - loss 0.04354754 - time (sec): 6.74 - samples/sec: 3240.25 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:11:10,213 epoch 6 - iter 120/121 - loss 0.04690223 - time (sec): 7.53 - samples/sec: 3267.09 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:11:10,263 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:10,263 EPOCH 6 done: loss 0.0480 - lr: 0.000013
2023-10-13 11:11:11,090 DEV : loss 0.15227191150188446 - f1-score (micro avg)  0.818
2023-10-13 11:11:11,095 saving best model
2023-10-13 11:11:11,576 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:12,332 epoch 7 - iter 12/121 - loss 0.03956377 - time (sec): 0.75 - samples/sec: 3394.79 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:11:13,065 epoch 7 - iter 24/121 - loss 0.03515716 - time (sec): 1.48 - samples/sec: 3401.61 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:11:13,747 epoch 7 - iter 36/121 - loss 0.03182407 - time (sec): 2.17 - samples/sec: 3397.80 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:11:14,454 epoch 7 - iter 48/121 - loss 0.03351245 - time (sec): 2.87 - samples/sec: 3392.40 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:11:15,166 epoch 7 - iter 60/121 - loss 0.03833087 - time (sec): 3.59 - samples/sec: 3410.52 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:11:15,953 epoch 7 - iter 72/121 - loss 0.03730157 - time (sec): 4.37 - samples/sec: 3389.92 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:11:16,675 epoch 7 - iter 84/121 - loss 0.03774702 - time (sec): 5.09 - samples/sec: 3400.29 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:11:17,403 epoch 7 - iter 96/121 - loss 0.03950572 - time (sec): 5.82 - samples/sec: 3361.81 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:11:18,156 epoch 7 - iter 108/121 - loss 0.03913401 - time (sec): 6.58 - samples/sec: 3360.69 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:11:18,941 epoch 7 - iter 120/121 - loss 0.03782988 - time (sec): 7.36 - samples/sec: 3333.14 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:11:18,999 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:18,999 EPOCH 7 done: loss 0.0375 - lr: 0.000010
2023-10-13 11:11:19,763 DEV : loss 0.1678510457277298 - f1-score (micro avg)  0.8238
2023-10-13 11:11:19,768 saving best model
2023-10-13 11:11:20,230 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:21,029 epoch 8 - iter 12/121 - loss 0.02579330 - time (sec): 0.79 - samples/sec: 3386.12 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:11:21,760 epoch 8 - iter 24/121 - loss 0.02880649 - time (sec): 1.53 - samples/sec: 3406.78 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:11:22,597 epoch 8 - iter 36/121 - loss 0.02842207 - time (sec): 2.36 - samples/sec: 3260.17 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:11:23,347 epoch 8 - iter 48/121 - loss 0.02926475 - time (sec): 3.11 - samples/sec: 3281.81 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:11:24,083 epoch 8 - iter 60/121 - loss 0.02641771 - time (sec): 3.85 - samples/sec: 3333.45 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:11:24,829 epoch 8 - iter 72/121 - loss 0.02717774 - time (sec): 4.59 - samples/sec: 3308.41 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:11:25,566 epoch 8 - iter 84/121 - loss 0.02823503 - time (sec): 5.33 - samples/sec: 3278.29 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:11:26,274 epoch 8 - iter 96/121 - loss 0.02818844 - time (sec): 6.04 - samples/sec: 3280.47 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:11:26,975 epoch 8 - iter 108/121 - loss 0.02864591 - time (sec): 6.74 - samples/sec: 3317.23 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:11:27,685 epoch 8 - iter 120/121 - loss 0.02846050 - time (sec): 7.45 - samples/sec: 3309.76 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:11:27,732 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:27,733 EPOCH 8 done: loss 0.0284 - lr: 0.000007
2023-10-13 11:11:28,644 DEV : loss 0.16501988470554352 - f1-score (micro avg)  0.8385
2023-10-13 11:11:28,649 saving best model
2023-10-13 11:11:29,116 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:29,884 epoch 9 - iter 12/121 - loss 0.02637404 - time (sec): 0.77 - samples/sec: 3175.23 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:11:30,600 epoch 9 - iter 24/121 - loss 0.03206035 - time (sec): 1.48 - samples/sec: 3432.23 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:11:31,365 epoch 9 - iter 36/121 - loss 0.03177588 - time (sec): 2.25 - samples/sec: 3456.53 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:11:32,041 epoch 9 - iter 48/121 - loss 0.02688614 - time (sec): 2.92 - samples/sec: 3368.96 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:11:32,715 epoch 9 - iter 60/121 - loss 0.02569866 - time (sec): 3.60 - samples/sec: 3340.67 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:11:33,423 epoch 9 - iter 72/121 - loss 0.02485426 - time (sec): 4.31 - samples/sec: 3368.02 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:11:34,161 epoch 9 - iter 84/121 - loss 0.02371548 - time (sec): 5.04 - samples/sec: 3413.07 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:11:34,953 epoch 9 - iter 96/121 - loss 0.02197400 - time (sec): 5.84 - samples/sec: 3361.81 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:11:35,638 epoch 9 - iter 108/121 - loss 0.02375103 - time (sec): 6.52 - samples/sec: 3341.96 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:11:36,449 epoch 9 - iter 120/121 - loss 0.02309117 - time (sec): 7.33 - samples/sec: 3355.78 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:11:36,497 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:36,497 EPOCH 9 done: loss 0.0232 - lr: 0.000004
2023-10-13 11:11:37,265 DEV : loss 0.17005358636379242 - f1-score (micro avg)  0.8306
2023-10-13 11:11:37,269 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:37,953 epoch 10 - iter 12/121 - loss 0.01774069 - time (sec): 0.68 - samples/sec: 3559.64 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:11:38,720 epoch 10 - iter 24/121 - loss 0.02065838 - time (sec): 1.45 - samples/sec: 3574.69 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:11:39,427 epoch 10 - iter 36/121 - loss 0.02086100 - time (sec): 2.16 - samples/sec: 3450.79 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:11:40,124 epoch 10 - iter 48/121 - loss 0.02031963 - time (sec): 2.85 - samples/sec: 3362.98 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:11:40,892 epoch 10 - iter 60/121 - loss 0.02096082 - time (sec): 3.62 - samples/sec: 3451.73 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:11:41,615 epoch 10 - iter 72/121 - loss 0.02132037 - time (sec): 4.34 - samples/sec: 3421.31 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:11:42,362 epoch 10 - iter 84/121 - loss 0.02130246 - time (sec): 5.09 - samples/sec: 3374.54 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:11:43,063 epoch 10 - iter 96/121 - loss 0.02273356 - time (sec): 5.79 - samples/sec: 3353.51 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:11:43,822 epoch 10 - iter 108/121 - loss 0.02075952 - time (sec): 6.55 - samples/sec: 3344.69 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:11:44,676 epoch 10 - iter 120/121 - loss 0.02007672 - time (sec): 7.41 - samples/sec: 3316.90 - lr: 0.000000 - momentum: 0.000000
2023-10-13 11:11:44,728 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:44,728 EPOCH 10 done: loss 0.0199 - lr: 0.000000
2023-10-13 11:11:45,491 DEV : loss 0.1679229587316513 - f1-score (micro avg)  0.8362
2023-10-13 11:11:45,859 ----------------------------------------------------------------------------------------------------
2023-10-13 11:11:45,860 Loading model from best epoch ...
2023-10-13 11:11:47,203 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-13 11:11:47,847 
Results:
- F-score (micro) 0.8267
- F-score (macro) 0.5381
- Accuracy 0.7284

By class:
              precision    recall  f1-score   support

        pers     0.8696    0.8633    0.8664       139
       scope     0.8273    0.8915    0.8582       129
        work     0.7053    0.8375    0.7657        80
         loc     1.0000    0.1111    0.2000         9
        date     0.0000    0.0000    0.0000         3

   micro avg     0.8123    0.8417    0.8267       360
   macro avg     0.6804    0.5407    0.5381       360
weighted avg     0.8139    0.8417    0.8172       360

2023-10-13 11:11:47,848 ----------------------------------------------------------------------------------------------------