2023-10-25 15:38:47,008 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(64001, 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): 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)
            )
          )
          (1): 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)
            )
          )
          (2): 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)
            )
          )
          (3): 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)
            )
          )
          (4): 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)
            )
          )
          (5): 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)
            )
          )
          (6): 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)
            )
          )
          (7): 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)
            )
          )
          (8): 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)
            )
          )
          (9): 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)
            )
          )
          (10): 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)
            )
          )
          (11): 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()
)"
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
 - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Train:  14465 sentences
2023-10-25 15:38:47,009         (train_with_dev=False, train_with_test=False)
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Training Params:
2023-10-25 15:38:47,009  - learning_rate: "3e-05" 
2023-10-25 15:38:47,009  - mini_batch_size: "4"
2023-10-25 15:38:47,009  - max_epochs: "10"
2023-10-25 15:38:47,009  - shuffle: "True"
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Plugins:
2023-10-25 15:38:47,009  - TensorboardLogger
2023-10-25 15:38:47,009  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 15:38:47,009  - metric: "('micro avg', 'f1-score')"
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Computation:
2023-10-25 15:38:47,009  - compute on device: cuda:0
2023-10-25 15:38:47,009  - embedding storage: none
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 ----------------------------------------------------------------------------------------------------
2023-10-25 15:38:47,009 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 15:39:09,553 epoch 1 - iter 361/3617 - loss 1.19886281 - time (sec): 22.54 - samples/sec: 1661.18 - lr: 0.000003 - momentum: 0.000000
2023-10-25 15:39:32,433 epoch 1 - iter 722/3617 - loss 0.68831441 - time (sec): 45.42 - samples/sec: 1682.42 - lr: 0.000006 - momentum: 0.000000
2023-10-25 15:39:54,936 epoch 1 - iter 1083/3617 - loss 0.51170947 - time (sec): 67.93 - samples/sec: 1667.26 - lr: 0.000009 - momentum: 0.000000
2023-10-25 15:40:17,679 epoch 1 - iter 1444/3617 - loss 0.41162390 - time (sec): 90.67 - samples/sec: 1675.46 - lr: 0.000012 - momentum: 0.000000
2023-10-25 15:40:40,401 epoch 1 - iter 1805/3617 - loss 0.35326768 - time (sec): 113.39 - samples/sec: 1674.11 - lr: 0.000015 - momentum: 0.000000
2023-10-25 15:41:03,110 epoch 1 - iter 2166/3617 - loss 0.31329417 - time (sec): 136.10 - samples/sec: 1682.14 - lr: 0.000018 - momentum: 0.000000
2023-10-25 15:41:25,626 epoch 1 - iter 2527/3617 - loss 0.28535492 - time (sec): 158.62 - samples/sec: 1680.30 - lr: 0.000021 - momentum: 0.000000
2023-10-25 15:41:48,351 epoch 1 - iter 2888/3617 - loss 0.26499215 - time (sec): 181.34 - samples/sec: 1682.04 - lr: 0.000024 - momentum: 0.000000
2023-10-25 15:42:10,950 epoch 1 - iter 3249/3617 - loss 0.24775587 - time (sec): 203.94 - samples/sec: 1678.70 - lr: 0.000027 - momentum: 0.000000
2023-10-25 15:42:33,298 epoch 1 - iter 3610/3617 - loss 0.23447570 - time (sec): 226.29 - samples/sec: 1675.45 - lr: 0.000030 - momentum: 0.000000
2023-10-25 15:42:33,748 ----------------------------------------------------------------------------------------------------
2023-10-25 15:42:33,748 EPOCH 1 done: loss 0.2341 - lr: 0.000030
2023-10-25 15:42:38,729 DEV : loss 0.12141559273004532 - f1-score (micro avg)  0.6425
2023-10-25 15:42:38,752 saving best model
2023-10-25 15:42:39,301 ----------------------------------------------------------------------------------------------------
2023-10-25 15:43:02,256 epoch 2 - iter 361/3617 - loss 0.10229911 - time (sec): 22.95 - samples/sec: 1700.22 - lr: 0.000030 - momentum: 0.000000
2023-10-25 15:43:24,847 epoch 2 - iter 722/3617 - loss 0.10119859 - time (sec): 45.55 - samples/sec: 1678.69 - lr: 0.000029 - momentum: 0.000000
2023-10-25 15:43:47,602 epoch 2 - iter 1083/3617 - loss 0.10115542 - time (sec): 68.30 - samples/sec: 1671.77 - lr: 0.000029 - momentum: 0.000000
2023-10-25 15:44:10,203 epoch 2 - iter 1444/3617 - loss 0.10048881 - time (sec): 90.90 - samples/sec: 1676.55 - lr: 0.000029 - momentum: 0.000000
2023-10-25 15:44:32,710 epoch 2 - iter 1805/3617 - loss 0.09969364 - time (sec): 113.41 - samples/sec: 1664.78 - lr: 0.000028 - momentum: 0.000000
2023-10-25 15:44:55,757 epoch 2 - iter 2166/3617 - loss 0.09899570 - time (sec): 136.45 - samples/sec: 1680.19 - lr: 0.000028 - momentum: 0.000000
2023-10-25 15:45:18,336 epoch 2 - iter 2527/3617 - loss 0.09812338 - time (sec): 159.03 - samples/sec: 1675.61 - lr: 0.000028 - momentum: 0.000000
2023-10-25 15:45:40,866 epoch 2 - iter 2888/3617 - loss 0.09881509 - time (sec): 181.56 - samples/sec: 1674.82 - lr: 0.000027 - momentum: 0.000000
2023-10-25 15:46:03,446 epoch 2 - iter 3249/3617 - loss 0.09818580 - time (sec): 204.14 - samples/sec: 1678.00 - lr: 0.000027 - momentum: 0.000000
2023-10-25 15:46:26,000 epoch 2 - iter 3610/3617 - loss 0.09912199 - time (sec): 226.70 - samples/sec: 1673.03 - lr: 0.000027 - momentum: 0.000000
2023-10-25 15:46:26,427 ----------------------------------------------------------------------------------------------------
2023-10-25 15:46:26,427 EPOCH 2 done: loss 0.0991 - lr: 0.000027
2023-10-25 15:46:31,155 DEV : loss 0.10703670233488083 - f1-score (micro avg)  0.5748
2023-10-25 15:46:31,178 ----------------------------------------------------------------------------------------------------
2023-10-25 15:46:54,123 epoch 3 - iter 361/3617 - loss 0.06451220 - time (sec): 22.94 - samples/sec: 1635.94 - lr: 0.000026 - momentum: 0.000000
2023-10-25 15:47:17,018 epoch 3 - iter 722/3617 - loss 0.07071297 - time (sec): 45.84 - samples/sec: 1661.24 - lr: 0.000026 - momentum: 0.000000
2023-10-25 15:47:39,779 epoch 3 - iter 1083/3617 - loss 0.07369259 - time (sec): 68.60 - samples/sec: 1671.64 - lr: 0.000026 - momentum: 0.000000
2023-10-25 15:48:02,401 epoch 3 - iter 1444/3617 - loss 0.07364717 - time (sec): 91.22 - samples/sec: 1660.50 - lr: 0.000025 - momentum: 0.000000
2023-10-25 15:48:25,138 epoch 3 - iter 1805/3617 - loss 0.07368861 - time (sec): 113.96 - samples/sec: 1661.84 - lr: 0.000025 - momentum: 0.000000
2023-10-25 15:48:47,723 epoch 3 - iter 2166/3617 - loss 0.07186830 - time (sec): 136.54 - samples/sec: 1669.15 - lr: 0.000025 - momentum: 0.000000
2023-10-25 15:49:10,464 epoch 3 - iter 2527/3617 - loss 0.07251865 - time (sec): 159.28 - samples/sec: 1672.41 - lr: 0.000024 - momentum: 0.000000
2023-10-25 15:49:32,837 epoch 3 - iter 2888/3617 - loss 0.07304301 - time (sec): 181.66 - samples/sec: 1667.81 - lr: 0.000024 - momentum: 0.000000
2023-10-25 15:49:55,910 epoch 3 - iter 3249/3617 - loss 0.07314916 - time (sec): 204.73 - samples/sec: 1669.74 - lr: 0.000024 - momentum: 0.000000
2023-10-25 15:50:18,464 epoch 3 - iter 3610/3617 - loss 0.07317717 - time (sec): 227.28 - samples/sec: 1667.96 - lr: 0.000023 - momentum: 0.000000
2023-10-25 15:50:18,929 ----------------------------------------------------------------------------------------------------
2023-10-25 15:50:18,929 EPOCH 3 done: loss 0.0731 - lr: 0.000023
2023-10-25 15:50:23,703 DEV : loss 0.22103023529052734 - f1-score (micro avg)  0.6461
2023-10-25 15:50:23,726 saving best model
2023-10-25 15:50:24,448 ----------------------------------------------------------------------------------------------------
2023-10-25 15:50:47,337 epoch 4 - iter 361/3617 - loss 0.04349179 - time (sec): 22.89 - samples/sec: 1687.96 - lr: 0.000023 - momentum: 0.000000
2023-10-25 15:51:09,914 epoch 4 - iter 722/3617 - loss 0.04765068 - time (sec): 45.47 - samples/sec: 1697.83 - lr: 0.000023 - momentum: 0.000000
2023-10-25 15:51:32,736 epoch 4 - iter 1083/3617 - loss 0.04598577 - time (sec): 68.29 - samples/sec: 1696.69 - lr: 0.000022 - momentum: 0.000000
2023-10-25 15:51:55,386 epoch 4 - iter 1444/3617 - loss 0.04854533 - time (sec): 90.94 - samples/sec: 1670.10 - lr: 0.000022 - momentum: 0.000000
2023-10-25 15:52:17,964 epoch 4 - iter 1805/3617 - loss 0.05057207 - time (sec): 113.51 - samples/sec: 1665.68 - lr: 0.000022 - momentum: 0.000000
2023-10-25 15:52:40,951 epoch 4 - iter 2166/3617 - loss 0.05016728 - time (sec): 136.50 - samples/sec: 1678.27 - lr: 0.000021 - momentum: 0.000000
2023-10-25 15:53:03,727 epoch 4 - iter 2527/3617 - loss 0.05059513 - time (sec): 159.28 - samples/sec: 1678.58 - lr: 0.000021 - momentum: 0.000000
2023-10-25 15:53:26,318 epoch 4 - iter 2888/3617 - loss 0.05293486 - time (sec): 181.87 - samples/sec: 1675.87 - lr: 0.000021 - momentum: 0.000000
2023-10-25 15:53:49,399 epoch 4 - iter 3249/3617 - loss 0.05285239 - time (sec): 204.95 - samples/sec: 1669.80 - lr: 0.000020 - momentum: 0.000000
2023-10-25 15:54:11,936 epoch 4 - iter 3610/3617 - loss 0.05260123 - time (sec): 227.49 - samples/sec: 1666.60 - lr: 0.000020 - momentum: 0.000000
2023-10-25 15:54:12,392 ----------------------------------------------------------------------------------------------------
2023-10-25 15:54:12,392 EPOCH 4 done: loss 0.0525 - lr: 0.000020
2023-10-25 15:54:17,149 DEV : loss 0.24151772260665894 - f1-score (micro avg)  0.6262
2023-10-25 15:54:17,172 ----------------------------------------------------------------------------------------------------
2023-10-25 15:54:39,932 epoch 5 - iter 361/3617 - loss 0.02889314 - time (sec): 22.76 - samples/sec: 1633.70 - lr: 0.000020 - momentum: 0.000000
2023-10-25 15:55:02,383 epoch 5 - iter 722/3617 - loss 0.02845671 - time (sec): 45.21 - samples/sec: 1640.80 - lr: 0.000019 - momentum: 0.000000
2023-10-25 15:55:25,074 epoch 5 - iter 1083/3617 - loss 0.02905149 - time (sec): 67.90 - samples/sec: 1652.84 - lr: 0.000019 - momentum: 0.000000
2023-10-25 15:55:47,562 epoch 5 - iter 1444/3617 - loss 0.03106635 - time (sec): 90.39 - samples/sec: 1657.09 - lr: 0.000019 - momentum: 0.000000
2023-10-25 15:56:10,156 epoch 5 - iter 1805/3617 - loss 0.03395971 - time (sec): 112.98 - samples/sec: 1662.83 - lr: 0.000018 - momentum: 0.000000
2023-10-25 15:56:32,681 epoch 5 - iter 2166/3617 - loss 0.03439912 - time (sec): 135.51 - samples/sec: 1657.17 - lr: 0.000018 - momentum: 0.000000
2023-10-25 15:56:55,301 epoch 5 - iter 2527/3617 - loss 0.03516551 - time (sec): 158.13 - samples/sec: 1655.70 - lr: 0.000018 - momentum: 0.000000
2023-10-25 15:57:18,303 epoch 5 - iter 2888/3617 - loss 0.03540794 - time (sec): 181.13 - samples/sec: 1670.73 - lr: 0.000017 - momentum: 0.000000
2023-10-25 15:57:40,862 epoch 5 - iter 3249/3617 - loss 0.03667999 - time (sec): 203.69 - samples/sec: 1666.12 - lr: 0.000017 - momentum: 0.000000
2023-10-25 15:58:03,741 epoch 5 - iter 3610/3617 - loss 0.03647650 - time (sec): 226.57 - samples/sec: 1674.18 - lr: 0.000017 - momentum: 0.000000
2023-10-25 15:58:04,146 ----------------------------------------------------------------------------------------------------
2023-10-25 15:58:04,146 EPOCH 5 done: loss 0.0365 - lr: 0.000017
2023-10-25 15:58:09,429 DEV : loss 0.27911558747291565 - f1-score (micro avg)  0.6411
2023-10-25 15:58:09,452 ----------------------------------------------------------------------------------------------------
2023-10-25 15:58:32,153 epoch 6 - iter 361/3617 - loss 0.01844611 - time (sec): 22.70 - samples/sec: 1684.49 - lr: 0.000016 - momentum: 0.000000
2023-10-25 15:58:54,997 epoch 6 - iter 722/3617 - loss 0.01909398 - time (sec): 45.54 - samples/sec: 1660.35 - lr: 0.000016 - momentum: 0.000000
2023-10-25 15:59:18,007 epoch 6 - iter 1083/3617 - loss 0.02262065 - time (sec): 68.55 - samples/sec: 1690.87 - lr: 0.000016 - momentum: 0.000000
2023-10-25 15:59:40,435 epoch 6 - iter 1444/3617 - loss 0.02337790 - time (sec): 90.98 - samples/sec: 1680.22 - lr: 0.000015 - momentum: 0.000000
2023-10-25 16:00:03,256 epoch 6 - iter 1805/3617 - loss 0.02294877 - time (sec): 113.80 - samples/sec: 1686.69 - lr: 0.000015 - momentum: 0.000000
2023-10-25 16:00:25,717 epoch 6 - iter 2166/3617 - loss 0.02260980 - time (sec): 136.26 - samples/sec: 1685.27 - lr: 0.000015 - momentum: 0.000000
2023-10-25 16:00:48,516 epoch 6 - iter 2527/3617 - loss 0.02245400 - time (sec): 159.06 - samples/sec: 1682.99 - lr: 0.000014 - momentum: 0.000000
2023-10-25 16:01:11,169 epoch 6 - iter 2888/3617 - loss 0.02342671 - time (sec): 181.72 - samples/sec: 1678.37 - lr: 0.000014 - momentum: 0.000000
2023-10-25 16:01:33,582 epoch 6 - iter 3249/3617 - loss 0.02358711 - time (sec): 204.13 - samples/sec: 1671.21 - lr: 0.000014 - momentum: 0.000000
2023-10-25 16:01:56,285 epoch 6 - iter 3610/3617 - loss 0.02404475 - time (sec): 226.83 - samples/sec: 1671.46 - lr: 0.000013 - momentum: 0.000000
2023-10-25 16:01:56,730 ----------------------------------------------------------------------------------------------------
2023-10-25 16:01:56,730 EPOCH 6 done: loss 0.0240 - lr: 0.000013
2023-10-25 16:02:02,029 DEV : loss 0.30914661288261414 - f1-score (micro avg)  0.6277
2023-10-25 16:02:02,052 ----------------------------------------------------------------------------------------------------
2023-10-25 16:02:24,697 epoch 7 - iter 361/3617 - loss 0.01518405 - time (sec): 22.64 - samples/sec: 1682.07 - lr: 0.000013 - momentum: 0.000000
2023-10-25 16:02:47,369 epoch 7 - iter 722/3617 - loss 0.01696119 - time (sec): 45.32 - samples/sec: 1686.25 - lr: 0.000013 - momentum: 0.000000
2023-10-25 16:03:10,138 epoch 7 - iter 1083/3617 - loss 0.01811277 - time (sec): 68.08 - samples/sec: 1679.52 - lr: 0.000012 - momentum: 0.000000
2023-10-25 16:03:33,026 epoch 7 - iter 1444/3617 - loss 0.01753427 - time (sec): 90.97 - samples/sec: 1687.97 - lr: 0.000012 - momentum: 0.000000
2023-10-25 16:03:55,497 epoch 7 - iter 1805/3617 - loss 0.01779560 - time (sec): 113.44 - samples/sec: 1678.37 - lr: 0.000012 - momentum: 0.000000
2023-10-25 16:04:18,296 epoch 7 - iter 2166/3617 - loss 0.01660255 - time (sec): 136.24 - samples/sec: 1684.12 - lr: 0.000011 - momentum: 0.000000
2023-10-25 16:04:40,932 epoch 7 - iter 2527/3617 - loss 0.01698618 - time (sec): 158.88 - samples/sec: 1684.01 - lr: 0.000011 - momentum: 0.000000
2023-10-25 16:05:03,601 epoch 7 - iter 2888/3617 - loss 0.01728988 - time (sec): 181.55 - samples/sec: 1677.49 - lr: 0.000011 - momentum: 0.000000
2023-10-25 16:05:26,391 epoch 7 - iter 3249/3617 - loss 0.01721398 - time (sec): 204.34 - samples/sec: 1672.88 - lr: 0.000010 - momentum: 0.000000
2023-10-25 16:05:48,951 epoch 7 - iter 3610/3617 - loss 0.01693395 - time (sec): 226.90 - samples/sec: 1671.22 - lr: 0.000010 - momentum: 0.000000
2023-10-25 16:05:49,404 ----------------------------------------------------------------------------------------------------
2023-10-25 16:05:49,404 EPOCH 7 done: loss 0.0169 - lr: 0.000010
2023-10-25 16:05:54,703 DEV : loss 0.35005614161491394 - f1-score (micro avg)  0.6476
2023-10-25 16:05:54,726 saving best model
2023-10-25 16:05:55,436 ----------------------------------------------------------------------------------------------------
2023-10-25 16:06:18,101 epoch 8 - iter 361/3617 - loss 0.01402887 - time (sec): 22.66 - samples/sec: 1711.01 - lr: 0.000010 - momentum: 0.000000
2023-10-25 16:06:40,840 epoch 8 - iter 722/3617 - loss 0.01326071 - time (sec): 45.40 - samples/sec: 1682.72 - lr: 0.000009 - momentum: 0.000000
2023-10-25 16:07:03,485 epoch 8 - iter 1083/3617 - loss 0.01183986 - time (sec): 68.05 - samples/sec: 1685.05 - lr: 0.000009 - momentum: 0.000000
2023-10-25 16:07:26,172 epoch 8 - iter 1444/3617 - loss 0.01108027 - time (sec): 90.74 - samples/sec: 1677.66 - lr: 0.000009 - momentum: 0.000000
2023-10-25 16:07:48,816 epoch 8 - iter 1805/3617 - loss 0.01123144 - time (sec): 113.38 - samples/sec: 1672.07 - lr: 0.000008 - momentum: 0.000000
2023-10-25 16:08:11,441 epoch 8 - iter 2166/3617 - loss 0.01079378 - time (sec): 136.00 - samples/sec: 1672.45 - lr: 0.000008 - momentum: 0.000000
2023-10-25 16:08:34,072 epoch 8 - iter 2527/3617 - loss 0.01078423 - time (sec): 158.63 - samples/sec: 1670.37 - lr: 0.000008 - momentum: 0.000000
2023-10-25 16:08:56,585 epoch 8 - iter 2888/3617 - loss 0.01037040 - time (sec): 181.15 - samples/sec: 1664.64 - lr: 0.000007 - momentum: 0.000000
2023-10-25 16:09:19,603 epoch 8 - iter 3249/3617 - loss 0.01027725 - time (sec): 204.17 - samples/sec: 1671.72 - lr: 0.000007 - momentum: 0.000000
2023-10-25 16:09:42,381 epoch 8 - iter 3610/3617 - loss 0.01022367 - time (sec): 226.94 - samples/sec: 1671.16 - lr: 0.000007 - momentum: 0.000000
2023-10-25 16:09:42,798 ----------------------------------------------------------------------------------------------------
2023-10-25 16:09:42,799 EPOCH 8 done: loss 0.0102 - lr: 0.000007
2023-10-25 16:09:47,567 DEV : loss 0.3698480725288391 - f1-score (micro avg)  0.6525
2023-10-25 16:09:47,591 saving best model
2023-10-25 16:09:48,302 ----------------------------------------------------------------------------------------------------
2023-10-25 16:10:11,572 epoch 9 - iter 361/3617 - loss 0.00763808 - time (sec): 23.27 - samples/sec: 1670.63 - lr: 0.000006 - momentum: 0.000000
2023-10-25 16:10:34,042 epoch 9 - iter 722/3617 - loss 0.00979704 - time (sec): 45.74 - samples/sec: 1646.34 - lr: 0.000006 - momentum: 0.000000
2023-10-25 16:10:56,797 epoch 9 - iter 1083/3617 - loss 0.00817557 - time (sec): 68.49 - samples/sec: 1662.63 - lr: 0.000006 - momentum: 0.000000
2023-10-25 16:11:19,697 epoch 9 - iter 1444/3617 - loss 0.00803821 - time (sec): 91.39 - samples/sec: 1664.55 - lr: 0.000005 - momentum: 0.000000
2023-10-25 16:11:42,445 epoch 9 - iter 1805/3617 - loss 0.00799518 - time (sec): 114.14 - samples/sec: 1674.93 - lr: 0.000005 - momentum: 0.000000
2023-10-25 16:12:04,911 epoch 9 - iter 2166/3617 - loss 0.00724524 - time (sec): 136.61 - samples/sec: 1664.75 - lr: 0.000005 - momentum: 0.000000
2023-10-25 16:12:27,624 epoch 9 - iter 2527/3617 - loss 0.00774410 - time (sec): 159.32 - samples/sec: 1659.46 - lr: 0.000004 - momentum: 0.000000
2023-10-25 16:12:50,435 epoch 9 - iter 2888/3617 - loss 0.00794723 - time (sec): 182.13 - samples/sec: 1665.12 - lr: 0.000004 - momentum: 0.000000
2023-10-25 16:13:13,176 epoch 9 - iter 3249/3617 - loss 0.00789576 - time (sec): 204.87 - samples/sec: 1665.74 - lr: 0.000004 - momentum: 0.000000
2023-10-25 16:13:35,910 epoch 9 - iter 3610/3617 - loss 0.00792795 - time (sec): 227.61 - samples/sec: 1666.40 - lr: 0.000003 - momentum: 0.000000
2023-10-25 16:13:36,335 ----------------------------------------------------------------------------------------------------
2023-10-25 16:13:36,335 EPOCH 9 done: loss 0.0080 - lr: 0.000003
2023-10-25 16:13:41,094 DEV : loss 0.3735716640949249 - f1-score (micro avg)  0.6539
2023-10-25 16:13:41,117 saving best model
2023-10-25 16:13:41,777 ----------------------------------------------------------------------------------------------------
2023-10-25 16:14:04,798 epoch 10 - iter 361/3617 - loss 0.00287944 - time (sec): 23.02 - samples/sec: 1742.64 - lr: 0.000003 - momentum: 0.000000
2023-10-25 16:14:27,220 epoch 10 - iter 722/3617 - loss 0.00450426 - time (sec): 45.44 - samples/sec: 1693.31 - lr: 0.000003 - momentum: 0.000000
2023-10-25 16:14:49,716 epoch 10 - iter 1083/3617 - loss 0.00489107 - time (sec): 67.94 - samples/sec: 1682.68 - lr: 0.000002 - momentum: 0.000000
2023-10-25 16:15:12,220 epoch 10 - iter 1444/3617 - loss 0.00465774 - time (sec): 90.44 - samples/sec: 1677.15 - lr: 0.000002 - momentum: 0.000000
2023-10-25 16:15:34,869 epoch 10 - iter 1805/3617 - loss 0.00452385 - time (sec): 113.09 - samples/sec: 1671.53 - lr: 0.000002 - momentum: 0.000000
2023-10-25 16:15:57,676 epoch 10 - iter 2166/3617 - loss 0.00459334 - time (sec): 135.90 - samples/sec: 1678.53 - lr: 0.000001 - momentum: 0.000000
2023-10-25 16:16:20,440 epoch 10 - iter 2527/3617 - loss 0.00459891 - time (sec): 158.66 - samples/sec: 1677.78 - lr: 0.000001 - momentum: 0.000000
2023-10-25 16:16:43,162 epoch 10 - iter 2888/3617 - loss 0.00448095 - time (sec): 181.38 - samples/sec: 1681.58 - lr: 0.000001 - momentum: 0.000000
2023-10-25 16:17:06,066 epoch 10 - iter 3249/3617 - loss 0.00453443 - time (sec): 204.29 - samples/sec: 1671.10 - lr: 0.000000 - momentum: 0.000000
2023-10-25 16:17:28,567 epoch 10 - iter 3610/3617 - loss 0.00449270 - time (sec): 226.79 - samples/sec: 1672.45 - lr: 0.000000 - momentum: 0.000000
2023-10-25 16:17:28,984 ----------------------------------------------------------------------------------------------------
2023-10-25 16:17:28,985 EPOCH 10 done: loss 0.0045 - lr: 0.000000
2023-10-25 16:17:33,739 DEV : loss 0.4017893970012665 - f1-score (micro avg)  0.6536
2023-10-25 16:17:34,312 ----------------------------------------------------------------------------------------------------
2023-10-25 16:17:34,312 Loading model from best epoch ...
2023-10-25 16:17:36,078 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
2023-10-25 16:17:41,702 
Results:
- F-score (micro) 0.6735
- F-score (macro) 0.5491
- Accuracy 0.5216

By class:
              precision    recall  f1-score   support

         loc     0.6490    0.7885    0.7120       591
        pers     0.5944    0.7759    0.6731       357
         org     0.3721    0.2025    0.2623        79

   micro avg     0.6186    0.7390    0.6735      1027
   macro avg     0.5385    0.5890    0.5491      1027
weighted avg     0.6087    0.7390    0.6639      1027

2023-10-25 16:17:41,702 ----------------------------------------------------------------------------------------------------