2022-05-09 23:40:59,402 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,404 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(28996, 768, padding_idx=0)
        (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()
      )
    )
  )
  (word_dropout): WordDropout(p=0.05)
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=768, out_features=17, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2022-05-09 23:40:59,408 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,408 Corpus: "Corpus: 14987 train + 3466 dev + 3684 test sentences"
2022-05-09 23:40:59,408 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,408 Parameters:
2022-05-09 23:40:59,408  - learning_rate: "0.000050"
2022-05-09 23:40:59,408  - mini_batch_size: "16"
2022-05-09 23:40:59,408  - patience: "3"
2022-05-09 23:40:59,409  - anneal_factor: "0.5"
2022-05-09 23:40:59,409  - max_epochs: "10"
2022-05-09 23:40:59,409  - shuffle: "True"
2022-05-09 23:40:59,409  - train_with_dev: "False"
2022-05-09 23:40:59,409  - batch_growth_annealing: "False"
2022-05-09 23:40:59,409 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,409 Model training base path: "resources\taggers\ner"
2022-05-09 23:40:59,409 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,409 Device: cuda:0
2022-05-09 23:40:59,410 ----------------------------------------------------------------------------------------------------
2022-05-09 23:40:59,410 Embeddings storage mode: none
2022-05-09 23:40:59,410 ----------------------------------------------------------------------------------------------------
2022-05-09 23:41:15,820 epoch 1 - iter 93/937 - loss 2.04152065 - samples/sec: 90.73 - lr: 0.000005
2022-05-09 23:41:31,406 epoch 1 - iter 186/937 - loss 1.48569545 - samples/sec: 95.52 - lr: 0.000010
2022-05-09 23:41:46,603 epoch 1 - iter 279/937 - loss 1.18645416 - samples/sec: 97.92 - lr: 0.000015
2022-05-09 23:42:01,525 epoch 1 - iter 372/937 - loss 1.01481547 - samples/sec: 99.74 - lr: 0.000020
2022-05-09 23:42:16,869 epoch 1 - iter 465/937 - loss 0.86894115 - samples/sec: 97.01 - lr: 0.000025
2022-05-09 23:42:32,505 epoch 1 - iter 558/937 - loss 0.75848951 - samples/sec: 95.21 - lr: 0.000030
2022-05-09 23:42:48,889 epoch 1 - iter 651/937 - loss 0.68004440 - samples/sec: 90.87 - lr: 0.000035
2022-05-09 23:43:05,305 epoch 1 - iter 744/937 - loss 0.62468227 - samples/sec: 90.67 - lr: 0.000040
2022-05-09 23:43:22,552 epoch 1 - iter 837/937 - loss 0.57575609 - samples/sec: 86.33 - lr: 0.000045
2022-05-09 23:43:40,505 epoch 1 - iter 930/937 - loss 0.53467358 - samples/sec: 82.91 - lr: 0.000050
2022-05-09 23:43:41,669 ----------------------------------------------------------------------------------------------------
2022-05-09 23:43:41,670 EPOCH 1 done: loss 0.5328 - lr 0.000050
2022-05-09 23:44:01,944 Evaluating as a multi-label problem: False
2022-05-09 23:44:01,998 DEV : loss 0.08702843636274338 - f1-score (micro avg)  0.9042
2022-05-09 23:44:02,088 BAD EPOCHS (no improvement): 4
2022-05-09 23:44:02,089 ----------------------------------------------------------------------------------------------------
2022-05-09 23:44:19,412 epoch 2 - iter 93/937 - loss 0.21171218 - samples/sec: 85.94 - lr: 0.000049
2022-05-09 23:44:39,339 epoch 2 - iter 186/937 - loss 0.20667256 - samples/sec: 74.71 - lr: 0.000049
2022-05-09 23:44:57,325 epoch 2 - iter 279/937 - loss 0.20359662 - samples/sec: 82.76 - lr: 0.000048
2022-05-09 23:45:15,903 epoch 2 - iter 372/937 - loss 0.20181902 - samples/sec: 80.11 - lr: 0.000048
2022-05-09 23:45:33,625 epoch 2 - iter 465/937 - loss 0.20239195 - samples/sec: 84.00 - lr: 0.000047
2022-05-09 23:45:51,983 epoch 2 - iter 558/937 - loss 0.20029145 - samples/sec: 81.07 - lr: 0.000047
2022-05-09 23:46:10,178 epoch 2 - iter 651/937 - loss 0.19802516 - samples/sec: 81.82 - lr: 0.000046
2022-05-09 23:46:27,567 epoch 2 - iter 744/937 - loss 0.19751023 - samples/sec: 85.60 - lr: 0.000046
2022-05-09 23:46:46,030 epoch 2 - iter 837/937 - loss 0.19578745 - samples/sec: 80.62 - lr: 0.000045
2022-05-09 23:47:03,838 epoch 2 - iter 930/937 - loss 0.19400286 - samples/sec: 83.60 - lr: 0.000044
2022-05-09 23:47:05,067 ----------------------------------------------------------------------------------------------------
2022-05-09 23:47:05,067 EPOCH 2 done: loss 0.1938 - lr 0.000044
2022-05-09 23:47:24,009 Evaluating as a multi-label problem: False
2022-05-09 23:47:24,058 DEV : loss 0.06405811011791229 - f1-score (micro avg)  0.9361
2022-05-09 23:47:24,143 BAD EPOCHS (no improvement): 4
2022-05-09 23:47:24,144 ----------------------------------------------------------------------------------------------------
2022-05-09 23:47:43,087 epoch 3 - iter 93/937 - loss 0.17145472 - samples/sec: 78.59 - lr: 0.000044
2022-05-09 23:48:02,729 epoch 3 - iter 186/937 - loss 0.16975910 - samples/sec: 75.78 - lr: 0.000043
2022-05-09 23:48:22,058 epoch 3 - iter 279/937 - loss 0.16698979 - samples/sec: 77.00 - lr: 0.000043
2022-05-09 23:48:42,011 epoch 3 - iter 372/937 - loss 0.16408423 - samples/sec: 74.60 - lr: 0.000042
2022-05-09 23:49:02,832 epoch 3 - iter 465/937 - loss 0.16405058 - samples/sec: 71.49 - lr: 0.000042
2022-05-09 23:49:24,164 epoch 3 - iter 558/937 - loss 0.16308247 - samples/sec: 69.79 - lr: 0.000041
2022-05-09 23:49:44,385 epoch 3 - iter 651/937 - loss 0.16211092 - samples/sec: 73.61 - lr: 0.000041
2022-05-09 23:50:05,176 epoch 3 - iter 744/937 - loss 0.16230919 - samples/sec: 71.59 - lr: 0.000040
2022-05-09 23:50:24,259 epoch 3 - iter 837/937 - loss 0.16223568 - samples/sec: 78.01 - lr: 0.000039
2022-05-09 23:50:42,702 epoch 3 - iter 930/937 - loss 0.16166223 - samples/sec: 80.71 - lr: 0.000039
2022-05-09 23:50:43,928 ----------------------------------------------------------------------------------------------------
2022-05-09 23:50:43,928 EPOCH 3 done: loss 0.1620 - lr 0.000039
2022-05-09 23:51:01,357 Evaluating as a multi-label problem: False
2022-05-09 23:51:01,410 DEV : loss 0.06513667851686478 - f1-score (micro avg)  0.9462
2022-05-09 23:51:01,494 BAD EPOCHS (no improvement): 4
2022-05-09 23:51:01,495 ----------------------------------------------------------------------------------------------------
2022-05-09 23:51:19,373 epoch 4 - iter 93/937 - loss 0.14617156 - samples/sec: 83.28 - lr: 0.000038
2022-05-09 23:51:39,862 epoch 4 - iter 186/937 - loss 0.15318927 - samples/sec: 72.64 - lr: 0.000038
2022-05-09 23:51:58,633 epoch 4 - iter 279/937 - loss 0.15311397 - samples/sec: 79.31 - lr: 0.000037
2022-05-09 23:52:17,782 epoch 4 - iter 372/937 - loss 0.15237270 - samples/sec: 77.73 - lr: 0.000037
2022-05-09 23:52:37,756 epoch 4 - iter 465/937 - loss 0.15252893 - samples/sec: 74.51 - lr: 0.000036
2022-05-09 23:52:57,040 epoch 4 - iter 558/937 - loss 0.15296964 - samples/sec: 77.19 - lr: 0.000036
2022-05-09 23:53:17,120 epoch 4 - iter 651/937 - loss 0.15177070 - samples/sec: 74.12 - lr: 0.000035
2022-05-09 23:53:36,789 epoch 4 - iter 744/937 - loss 0.15212670 - samples/sec: 75.67 - lr: 0.000034
2022-05-09 23:53:55,789 epoch 4 - iter 837/937 - loss 0.15188826 - samples/sec: 78.35 - lr: 0.000034
2022-05-09 23:54:15,078 epoch 4 - iter 930/937 - loss 0.15158585 - samples/sec: 77.16 - lr: 0.000033
2022-05-09 23:54:16,427 ----------------------------------------------------------------------------------------------------
2022-05-09 23:54:16,428 EPOCH 4 done: loss 0.1514 - lr 0.000033
2022-05-09 23:54:37,613 Evaluating as a multi-label problem: False
2022-05-09 23:54:37,666 DEV : loss 0.0851067453622818 - f1-score (micro avg)  0.9445
2022-05-09 23:54:37,758 BAD EPOCHS (no improvement): 4
2022-05-09 23:54:37,759 ----------------------------------------------------------------------------------------------------
2022-05-09 23:54:57,548 epoch 5 - iter 93/937 - loss 0.13786995 - samples/sec: 75.23 - lr: 0.000033
2022-05-09 23:55:17,232 epoch 5 - iter 186/937 - loss 0.14230070 - samples/sec: 75.62 - lr: 0.000032
2022-05-09 23:55:36,628 epoch 5 - iter 279/937 - loss 0.14258916 - samples/sec: 76.74 - lr: 0.000032
2022-05-09 23:55:56,340 epoch 5 - iter 372/937 - loss 0.14284130 - samples/sec: 75.52 - lr: 0.000031
2022-05-09 23:56:15,854 epoch 5 - iter 465/937 - loss 0.14169986 - samples/sec: 76.27 - lr: 0.000031
2022-05-09 23:56:34,410 epoch 5 - iter 558/937 - loss 0.14100332 - samples/sec: 80.21 - lr: 0.000030
2022-05-09 23:56:53,730 epoch 5 - iter 651/937 - loss 0.14139534 - samples/sec: 77.04 - lr: 0.000029
2022-05-09 23:57:12,846 epoch 5 - iter 744/937 - loss 0.14072810 - samples/sec: 77.88 - lr: 0.000029
2022-05-09 23:57:32,509 epoch 5 - iter 837/937 - loss 0.13972343 - samples/sec: 75.72 - lr: 0.000028
2022-05-09 23:57:51,218 epoch 5 - iter 930/937 - loss 0.14088149 - samples/sec: 79.56 - lr: 0.000028
2022-05-09 23:57:52,684 ----------------------------------------------------------------------------------------------------
2022-05-09 23:57:52,685 EPOCH 5 done: loss 0.1408 - lr 0.000028
2022-05-09 23:58:11,005 Evaluating as a multi-label problem: False
2022-05-09 23:58:11,060 DEV : loss 0.07939312607049942 - f1-score (micro avg)  0.9502
2022-05-09 23:58:11,147 BAD EPOCHS (no improvement): 4
2022-05-09 23:58:11,148 ----------------------------------------------------------------------------------------------------
2022-05-09 23:58:29,830 epoch 6 - iter 93/937 - loss 0.13587072 - samples/sec: 79.69 - lr: 0.000027
2022-05-09 23:58:48,422 epoch 6 - iter 186/937 - loss 0.13733201 - samples/sec: 80.06 - lr: 0.000027
2022-05-09 23:59:06,303 epoch 6 - iter 279/937 - loss 0.14061270 - samples/sec: 83.23 - lr: 0.000026
2022-05-09 23:59:24,586 epoch 6 - iter 372/937 - loss 0.13957657 - samples/sec: 81.44 - lr: 0.000026
2022-05-09 23:59:43,413 epoch 6 - iter 465/937 - loss 0.13980319 - samples/sec: 79.05 - lr: 0.000025
2022-05-10 00:00:01,871 epoch 6 - iter 558/937 - loss 0.13997926 - samples/sec: 80.63 - lr: 0.000024
2022-05-10 00:00:19,776 epoch 6 - iter 651/937 - loss 0.13934109 - samples/sec: 83.13 - lr: 0.000024
2022-05-10 00:00:38,921 epoch 6 - iter 744/937 - loss 0.13935470 - samples/sec: 77.75 - lr: 0.000023
2022-05-10 00:00:57,515 epoch 6 - iter 837/937 - loss 0.13944998 - samples/sec: 80.07 - lr: 0.000023
2022-05-10 00:01:15,467 epoch 6 - iter 930/937 - loss 0.13962343 - samples/sec: 82.92 - lr: 0.000022
2022-05-10 00:01:16,715 ----------------------------------------------------------------------------------------------------
2022-05-10 00:01:16,715 EPOCH 6 done: loss 0.1396 - lr 0.000022
2022-05-10 00:01:40,529 Evaluating as a multi-label problem: False
2022-05-10 00:01:40,579 DEV : loss 0.08579559624195099 - f1-score (micro avg)  0.9497
2022-05-10 00:01:40,666 BAD EPOCHS (no improvement): 4
2022-05-10 00:01:40,667 ----------------------------------------------------------------------------------------------------
2022-05-10 00:01:59,831 epoch 7 - iter 93/937 - loss 0.13534539 - samples/sec: 77.69 - lr: 0.000022
2022-05-10 00:02:18,246 epoch 7 - iter 186/937 - loss 0.13551684 - samples/sec: 80.83 - lr: 0.000021
2022-05-10 00:02:36,156 epoch 7 - iter 279/937 - loss 0.13584534 - samples/sec: 83.13 - lr: 0.000021
2022-05-10 00:02:55,093 epoch 7 - iter 372/937 - loss 0.13345388 - samples/sec: 78.60 - lr: 0.000020
2022-05-10 00:03:13,968 epoch 7 - iter 465/937 - loss 0.13357006 - samples/sec: 78.85 - lr: 0.000019
2022-05-10 00:03:33,833 epoch 7 - iter 558/937 - loss 0.13346607 - samples/sec: 74.94 - lr: 0.000019
2022-05-10 00:03:52,609 epoch 7 - iter 651/937 - loss 0.13318798 - samples/sec: 79.29 - lr: 0.000018
2022-05-10 00:04:11,143 epoch 7 - iter 744/937 - loss 0.13297235 - samples/sec: 80.32 - lr: 0.000018
2022-05-10 00:04:29,324 epoch 7 - iter 837/937 - loss 0.13294986 - samples/sec: 81.87 - lr: 0.000017
2022-05-10 00:04:48,227 epoch 7 - iter 930/937 - loss 0.13304211 - samples/sec: 78.74 - lr: 0.000017
2022-05-10 00:04:49,540 ----------------------------------------------------------------------------------------------------
2022-05-10 00:04:49,540 EPOCH 7 done: loss 0.1331 - lr 0.000017
2022-05-10 00:05:07,897 Evaluating as a multi-label problem: False
2022-05-10 00:05:07,956 DEV : loss 0.09259101003408432 - f1-score (micro avg)  0.9515
2022-05-10 00:05:08,048 BAD EPOCHS (no improvement): 4
2022-05-10 00:05:08,049 ----------------------------------------------------------------------------------------------------
2022-05-10 00:05:26,187 epoch 8 - iter 93/937 - loss 0.13287977 - samples/sec: 82.08 - lr: 0.000016
2022-05-10 00:05:46,292 epoch 8 - iter 186/937 - loss 0.13409706 - samples/sec: 74.04 - lr: 0.000016
2022-05-10 00:06:04,623 epoch 8 - iter 279/937 - loss 0.13270913 - samples/sec: 81.19 - lr: 0.000015
2022-05-10 00:06:23,601 epoch 8 - iter 372/937 - loss 0.13243728 - samples/sec: 78.43 - lr: 0.000014
2022-05-10 00:06:42,643 epoch 8 - iter 465/937 - loss 0.13287784 - samples/sec: 78.17 - lr: 0.000014
2022-05-10 00:07:02,185 epoch 8 - iter 558/937 - loss 0.13373988 - samples/sec: 76.17 - lr: 0.000013
2022-05-10 00:07:20,122 epoch 8 - iter 651/937 - loss 0.13402409 - samples/sec: 82.98 - lr: 0.000013
2022-05-10 00:07:39,327 epoch 8 - iter 744/937 - loss 0.13327101 - samples/sec: 77.50 - lr: 0.000012
2022-05-10 00:07:57,782 epoch 8 - iter 837/937 - loss 0.13355020 - samples/sec: 80.65 - lr: 0.000012
2022-05-10 00:08:16,804 epoch 8 - iter 930/937 - loss 0.13294805 - samples/sec: 78.25 - lr: 0.000011
2022-05-10 00:08:18,099 ----------------------------------------------------------------------------------------------------
2022-05-10 00:08:18,099 EPOCH 8 done: loss 0.1327 - lr 0.000011
2022-05-10 00:08:36,160 Evaluating as a multi-label problem: False
2022-05-10 00:08:36,214 DEV : loss 0.09469996392726898 - f1-score (micro avg)  0.9505
2022-05-10 00:08:36,300 BAD EPOCHS (no improvement): 4
2022-05-10 00:08:36,301 ----------------------------------------------------------------------------------------------------
2022-05-10 00:08:54,628 epoch 9 - iter 93/937 - loss 0.13256573 - samples/sec: 81.23 - lr: 0.000011
2022-05-10 00:09:13,253 epoch 9 - iter 186/937 - loss 0.13218317 - samples/sec: 79.94 - lr: 0.000010
2022-05-10 00:09:31,322 epoch 9 - iter 279/937 - loss 0.13240640 - samples/sec: 82.40 - lr: 0.000009
2022-05-10 00:09:49,199 epoch 9 - iter 372/937 - loss 0.13118429 - samples/sec: 83.28 - lr: 0.000009
2022-05-10 00:10:06,958 epoch 9 - iter 465/937 - loss 0.13128632 - samples/sec: 83.83 - lr: 0.000008
2022-05-10 00:10:25,134 epoch 9 - iter 558/937 - loss 0.12936261 - samples/sec: 81.90 - lr: 0.000008
2022-05-10 00:10:43,680 epoch 9 - iter 651/937 - loss 0.12973987 - samples/sec: 80.27 - lr: 0.000007
2022-05-10 00:11:01,678 epoch 9 - iter 744/937 - loss 0.12968500 - samples/sec: 82.71 - lr: 0.000007
2022-05-10 00:11:19,484 epoch 9 - iter 837/937 - loss 0.12985020 - samples/sec: 83.59 - lr: 0.000006
2022-05-10 00:11:37,340 epoch 9 - iter 930/937 - loss 0.12947938 - samples/sec: 83.36 - lr: 0.000006
2022-05-10 00:11:38,689 ----------------------------------------------------------------------------------------------------
2022-05-10 00:11:38,689 EPOCH 9 done: loss 0.1294 - lr 0.000006
2022-05-10 00:11:56,867 Evaluating as a multi-label problem: False
2022-05-10 00:11:56,918 DEV : loss 0.09501232951879501 - f1-score (micro avg)  0.9504
2022-05-10 00:11:57,003 BAD EPOCHS (no improvement): 4
2022-05-10 00:11:57,004 ----------------------------------------------------------------------------------------------------
2022-05-10 00:12:15,701 epoch 10 - iter 93/937 - loss 0.12882436 - samples/sec: 79.62 - lr: 0.000005
2022-05-10 00:12:34,784 epoch 10 - iter 186/937 - loss 0.12932802 - samples/sec: 78.02 - lr: 0.000004
2022-05-10 00:12:53,563 epoch 10 - iter 279/937 - loss 0.12935565 - samples/sec: 79.27 - lr: 0.000004
2022-05-10 00:13:12,428 epoch 10 - iter 372/937 - loss 0.13016513 - samples/sec: 78.91 - lr: 0.000003
2022-05-10 00:13:31,484 epoch 10 - iter 465/937 - loss 0.13001423 - samples/sec: 78.12 - lr: 0.000003
2022-05-10 00:13:50,860 epoch 10 - iter 558/937 - loss 0.12967414 - samples/sec: 76.82 - lr: 0.000002
2022-05-10 00:14:10,036 epoch 10 - iter 651/937 - loss 0.13044245 - samples/sec: 77.61 - lr: 0.000002
2022-05-10 00:14:29,046 epoch 10 - iter 744/937 - loss 0.13049319 - samples/sec: 78.30 - lr: 0.000001
2022-05-10 00:14:47,934 epoch 10 - iter 837/937 - loss 0.12970693 - samples/sec: 78.83 - lr: 0.000001
2022-05-10 00:15:06,881 epoch 10 - iter 930/937 - loss 0.12987301 - samples/sec: 78.57 - lr: 0.000000
2022-05-10 00:15:08,384 ----------------------------------------------------------------------------------------------------
2022-05-10 00:15:08,384 EPOCH 10 done: loss 0.1298 - lr 0.000000
2022-05-10 00:15:27,169 Evaluating as a multi-label problem: False
2022-05-10 00:15:27,221 DEV : loss 0.09416753053665161 - f1-score (micro avg)  0.9513
2022-05-10 00:15:27,303 BAD EPOCHS (no improvement): 4
2022-05-10 00:15:28,112 ----------------------------------------------------------------------------------------------------
2022-05-10 00:15:28,113 Testing using last state of model ...
2022-05-10 00:15:47,035 Evaluating as a multi-label problem: False
2022-05-10 00:15:47,087 0.9117	0.9212	0.9164	0.879
2022-05-10 00:15:47,087 
Results:
- F-score (micro) 0.9164
- F-score (macro) 0.9024
- Accuracy 0.879

By class:
              precision    recall  f1-score   support

         ORG     0.8893    0.9097    0.8994      1661
         LOC     0.9301    0.9335    0.9318      1668
         PER     0.9699    0.9579    0.9639      1617
        MISC     0.7951    0.8348    0.8145       702

   micro avg     0.9117    0.9212    0.9164      5648
   macro avg     0.8961    0.9090    0.9024      5648
weighted avg     0.9127    0.9212    0.9169      5648

2022-05-10 00:15:47,088 ----------------------------------------------------------------------------------------------------