2022-10-26 19:45:19,393 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,398 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(35000, 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)
  (embedding2nn): Linear(in_features=768, out_features=768, bias=True)
  (rnn): LSTM(768, 256, batch_first=True, bidirectional=True)
  (linear): Linear(in_features=512, out_features=15, bias=True)
  (loss_function): ViterbiLoss()
  (crf): CRF()
)"
2022-10-26 19:45:19,409 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,415 Corpus: "Corpus: 8551 train + 1425 dev + 1425 test sentences"
2022-10-26 19:45:19,418 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,425 Parameters:
2022-10-26 19:45:19,429  - learning_rate: "0.010000"
2022-10-26 19:45:19,436  - mini_batch_size: "8"
2022-10-26 19:45:19,441  - patience: "3"
2022-10-26 19:45:19,446  - anneal_factor: "0.5"
2022-10-26 19:45:19,447  - max_epochs: "10"
2022-10-26 19:45:19,466  - shuffle: "True"
2022-10-26 19:45:19,470  - train_with_dev: "False"
2022-10-26 19:45:19,475  - batch_growth_annealing: "False"
2022-10-26 19:45:19,476 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,479 Model training base path: "/content/model/mono_ner"
2022-10-26 19:45:19,480 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,484 Device: cuda:0
2022-10-26 19:45:19,489 ----------------------------------------------------------------------------------------------------
2022-10-26 19:45:19,491 Embeddings storage mode: none
2022-10-26 19:45:19,496 ----------------------------------------------------------------------------------------------------
2022-10-26 19:46:27,364 epoch 1 - iter 106/1069 - loss 0.49979466 - samples/sec: 12.50 - lr: 0.010000
2022-10-26 19:47:29,408 epoch 1 - iter 212/1069 - loss 0.36858293 - samples/sec: 13.67 - lr: 0.010000
2022-10-26 19:48:32,710 epoch 1 - iter 318/1069 - loss 0.31288040 - samples/sec: 13.40 - lr: 0.010000
2022-10-26 19:49:36,271 epoch 1 - iter 424/1069 - loss 0.27906252 - samples/sec: 13.34 - lr: 0.010000
2022-10-26 19:50:40,278 epoch 1 - iter 530/1069 - loss 0.25802546 - samples/sec: 13.25 - lr: 0.010000
2022-10-26 19:51:45,008 epoch 1 - iter 636/1069 - loss 0.24111842 - samples/sec: 13.10 - lr: 0.010000
2022-10-26 19:52:47,602 epoch 1 - iter 742/1069 - loss 0.22829427 - samples/sec: 13.55 - lr: 0.010000
2022-10-26 19:53:50,115 epoch 1 - iter 848/1069 - loss 0.21731094 - samples/sec: 13.57 - lr: 0.010000
2022-10-26 19:54:53,793 epoch 1 - iter 954/1069 - loss 0.20876564 - samples/sec: 13.32 - lr: 0.010000
2022-10-26 19:55:55,252 epoch 1 - iter 1060/1069 - loss 0.20166716 - samples/sec: 13.80 - lr: 0.010000
2022-10-26 19:56:00,400 ----------------------------------------------------------------------------------------------------
2022-10-26 19:56:00,402 EPOCH 1 done: loss 0.2008 - lr 0.010000
2022-10-26 19:57:09,701 Evaluating as a multi-label problem: False
2022-10-26 19:57:09,740 DEV : loss 0.09606283158063889 - f1-score (micro avg)  0.7526
2022-10-26 19:57:09,783 BAD EPOCHS (no improvement): 0
2022-10-26 19:57:09,785 saving best model
2022-10-26 19:57:11,433 ----------------------------------------------------------------------------------------------------
2022-10-26 19:58:18,467 epoch 2 - iter 106/1069 - loss 0.12276787 - samples/sec: 12.65 - lr: 0.010000
2022-10-26 19:59:24,322 epoch 2 - iter 212/1069 - loss 0.12231755 - samples/sec: 12.88 - lr: 0.010000
2022-10-26 20:00:41,700 epoch 2 - iter 318/1069 - loss 0.12435630 - samples/sec: 10.96 - lr: 0.010000
2022-10-26 20:01:46,059 epoch 2 - iter 424/1069 - loss 0.12564768 - samples/sec: 13.18 - lr: 0.010000
2022-10-26 20:02:49,678 epoch 2 - iter 530/1069 - loss 0.12512958 - samples/sec: 13.33 - lr: 0.010000
2022-10-26 20:04:05,654 epoch 2 - iter 636/1069 - loss 0.12238487 - samples/sec: 11.16 - lr: 0.010000
2022-10-26 20:05:09,552 epoch 2 - iter 742/1069 - loss 0.12010170 - samples/sec: 13.27 - lr: 0.010000
2022-10-26 20:06:14,022 epoch 2 - iter 848/1069 - loss 0.11967127 - samples/sec: 13.16 - lr: 0.010000
2022-10-26 20:07:19,659 epoch 2 - iter 954/1069 - loss 0.11888882 - samples/sec: 12.92 - lr: 0.010000
2022-10-26 20:08:29,253 epoch 2 - iter 1060/1069 - loss 0.11866747 - samples/sec: 12.19 - lr: 0.010000
2022-10-26 20:08:34,370 ----------------------------------------------------------------------------------------------------
2022-10-26 20:08:34,372 EPOCH 2 done: loss 0.1185 - lr 0.010000
2022-10-26 20:09:47,920 Evaluating as a multi-label problem: False
2022-10-26 20:09:47,955 DEV : loss 0.07920133322477341 - f1-score (micro avg)  0.8155
2022-10-26 20:09:47,998 BAD EPOCHS (no improvement): 0
2022-10-26 20:09:48,000 saving best model
2022-10-26 20:09:49,587 ----------------------------------------------------------------------------------------------------
2022-10-26 20:10:53,964 epoch 3 - iter 106/1069 - loss 0.10166018 - samples/sec: 13.18 - lr: 0.010000
2022-10-26 20:11:56,797 epoch 3 - iter 212/1069 - loss 0.10111216 - samples/sec: 13.50 - lr: 0.010000
2022-10-26 20:13:03,180 epoch 3 - iter 318/1069 - loss 0.10239146 - samples/sec: 12.78 - lr: 0.010000
2022-10-26 20:14:08,543 epoch 3 - iter 424/1069 - loss 0.10173990 - samples/sec: 12.98 - lr: 0.010000
2022-10-26 20:15:13,145 epoch 3 - iter 530/1069 - loss 0.10135509 - samples/sec: 13.13 - lr: 0.010000
2022-10-26 20:16:19,356 epoch 3 - iter 636/1069 - loss 0.10020505 - samples/sec: 12.81 - lr: 0.010000
2022-10-26 20:17:21,470 epoch 3 - iter 742/1069 - loss 0.10033292 - samples/sec: 13.65 - lr: 0.010000
2022-10-26 20:18:25,712 epoch 3 - iter 848/1069 - loss 0.09965180 - samples/sec: 13.20 - lr: 0.010000
2022-10-26 20:19:32,123 epoch 3 - iter 954/1069 - loss 0.09942363 - samples/sec: 12.77 - lr: 0.010000
2022-10-26 20:20:37,362 epoch 3 - iter 1060/1069 - loss 0.09818458 - samples/sec: 13.00 - lr: 0.010000
2022-10-26 20:20:42,922 ----------------------------------------------------------------------------------------------------
2022-10-26 20:20:42,923 EPOCH 3 done: loss 0.0981 - lr 0.010000
2022-10-26 20:21:56,678 Evaluating as a multi-label problem: False
2022-10-26 20:21:56,717 DEV : loss 0.07603894919157028 - f1-score (micro avg)  0.8361
2022-10-26 20:21:56,759 BAD EPOCHS (no improvement): 0
2022-10-26 20:21:56,761 saving best model
2022-10-26 20:21:58,329 ----------------------------------------------------------------------------------------------------
2022-10-26 20:23:02,865 epoch 4 - iter 106/1069 - loss 0.08581557 - samples/sec: 13.14 - lr: 0.010000
2022-10-26 20:24:06,558 epoch 4 - iter 212/1069 - loss 0.08690126 - samples/sec: 13.32 - lr: 0.010000
2022-10-26 20:25:11,549 epoch 4 - iter 318/1069 - loss 0.08740134 - samples/sec: 13.05 - lr: 0.010000
2022-10-26 20:26:16,171 epoch 4 - iter 424/1069 - loss 0.08691255 - samples/sec: 13.12 - lr: 0.010000
2022-10-26 20:27:21,108 epoch 4 - iter 530/1069 - loss 0.08743159 - samples/sec: 13.06 - lr: 0.010000
2022-10-26 20:28:26,306 epoch 4 - iter 636/1069 - loss 0.08700733 - samples/sec: 13.01 - lr: 0.010000
2022-10-26 20:29:28,907 epoch 4 - iter 742/1069 - loss 0.08700591 - samples/sec: 13.55 - lr: 0.010000
2022-10-26 20:30:34,735 epoch 4 - iter 848/1069 - loss 0.08615337 - samples/sec: 12.88 - lr: 0.010000
2022-10-26 20:32:03,266 epoch 4 - iter 954/1069 - loss 0.08562659 - samples/sec: 9.58 - lr: 0.010000
2022-10-26 20:33:59,270 epoch 4 - iter 1060/1069 - loss 0.08544457 - samples/sec: 7.31 - lr: 0.010000
2022-10-26 20:34:09,369 ----------------------------------------------------------------------------------------------------
2022-10-26 20:34:09,371 EPOCH 4 done: loss 0.0853 - lr 0.010000
2022-10-26 20:37:53,248 Evaluating as a multi-label problem: False
2022-10-26 20:37:53,283 DEV : loss 0.07134225219488144 - f1-score (micro avg)  0.8336
2022-10-26 20:37:53,326 BAD EPOCHS (no improvement): 1
2022-10-26 20:37:53,328 ----------------------------------------------------------------------------------------------------
2022-10-26 20:39:45,902 epoch 5 - iter 106/1069 - loss 0.07612726 - samples/sec: 7.53 - lr: 0.010000
2022-10-26 20:41:42,470 epoch 5 - iter 212/1069 - loss 0.07932025 - samples/sec: 7.28 - lr: 0.010000
2022-10-26 20:43:01,451 epoch 5 - iter 318/1069 - loss 0.07766485 - samples/sec: 10.74 - lr: 0.010000
2022-10-26 20:44:06,242 epoch 5 - iter 424/1069 - loss 0.07782655 - samples/sec: 13.09 - lr: 0.010000
2022-10-26 20:45:10,011 epoch 5 - iter 530/1069 - loss 0.07797363 - samples/sec: 13.30 - lr: 0.010000
2022-10-26 20:46:18,444 epoch 5 - iter 636/1069 - loss 0.07784710 - samples/sec: 12.39 - lr: 0.010000
2022-10-26 20:47:22,712 epoch 5 - iter 742/1069 - loss 0.07764170 - samples/sec: 13.20 - lr: 0.010000
2022-10-26 20:48:26,544 epoch 5 - iter 848/1069 - loss 0.07765970 - samples/sec: 13.29 - lr: 0.010000
2022-10-26 20:49:32,065 epoch 5 - iter 954/1069 - loss 0.07726613 - samples/sec: 12.94 - lr: 0.010000
2022-10-26 20:50:36,714 epoch 5 - iter 1060/1069 - loss 0.07692019 - samples/sec: 13.12 - lr: 0.010000
2022-10-26 20:50:41,823 ----------------------------------------------------------------------------------------------------
2022-10-26 20:50:41,825 EPOCH 5 done: loss 0.0771 - lr 0.010000
2022-10-26 20:51:56,635 Evaluating as a multi-label problem: False
2022-10-26 20:51:56,681 DEV : loss 0.06873895972967148 - f1-score (micro avg)  0.848
2022-10-26 20:51:56,730 BAD EPOCHS (no improvement): 0
2022-10-26 20:51:56,732 saving best model
2022-10-26 20:51:58,276 ----------------------------------------------------------------------------------------------------
2022-10-26 20:53:04,269 epoch 6 - iter 106/1069 - loss 0.07259857 - samples/sec: 12.85 - lr: 0.010000
2022-10-26 20:54:08,435 epoch 6 - iter 212/1069 - loss 0.06894409 - samples/sec: 13.22 - lr: 0.010000
2022-10-26 20:55:15,290 epoch 6 - iter 318/1069 - loss 0.06918623 - samples/sec: 12.69 - lr: 0.010000
2022-10-26 20:56:20,441 epoch 6 - iter 424/1069 - loss 0.06917844 - samples/sec: 13.02 - lr: 0.010000
2022-10-26 20:57:24,834 epoch 6 - iter 530/1069 - loss 0.06940973 - samples/sec: 13.17 - lr: 0.010000
2022-10-26 20:58:31,661 epoch 6 - iter 636/1069 - loss 0.06932249 - samples/sec: 12.69 - lr: 0.010000
2022-10-26 20:59:37,057 epoch 6 - iter 742/1069 - loss 0.06858729 - samples/sec: 12.97 - lr: 0.010000
2022-10-26 21:00:42,037 epoch 6 - iter 848/1069 - loss 0.06850174 - samples/sec: 13.05 - lr: 0.010000
2022-10-26 21:01:48,234 epoch 6 - iter 954/1069 - loss 0.06855966 - samples/sec: 12.81 - lr: 0.010000
2022-10-26 21:02:54,530 epoch 6 - iter 1060/1069 - loss 0.06812598 - samples/sec: 12.79 - lr: 0.010000
2022-10-26 21:03:00,480 ----------------------------------------------------------------------------------------------------
2022-10-26 21:03:00,482 EPOCH 6 done: loss 0.0680 - lr 0.010000
2022-10-26 21:04:16,435 Evaluating as a multi-label problem: False
2022-10-26 21:04:16,476 DEV : loss 0.05917559936642647 - f1-score (micro avg)  0.8775
2022-10-26 21:04:16,522 BAD EPOCHS (no improvement): 0
2022-10-26 21:04:16,526 saving best model
2022-10-26 21:04:18,071 ----------------------------------------------------------------------------------------------------
2022-10-26 21:05:24,303 epoch 7 - iter 106/1069 - loss 0.06352705 - samples/sec: 12.81 - lr: 0.010000
2022-10-26 21:06:30,784 epoch 7 - iter 212/1069 - loss 0.06166309 - samples/sec: 12.76 - lr: 0.010000
2022-10-26 21:07:35,118 epoch 7 - iter 318/1069 - loss 0.06134693 - samples/sec: 13.18 - lr: 0.010000
2022-10-26 21:08:39,228 epoch 7 - iter 424/1069 - loss 0.06161759 - samples/sec: 13.23 - lr: 0.010000
2022-10-26 21:10:15,880 epoch 7 - iter 530/1069 - loss 0.06137938 - samples/sec: 8.77 - lr: 0.010000
2022-10-26 21:12:14,808 epoch 7 - iter 636/1069 - loss 0.06149529 - samples/sec: 7.13 - lr: 0.010000
2022-10-26 21:14:13,856 epoch 7 - iter 742/1069 - loss 0.06173201 - samples/sec: 7.12 - lr: 0.010000
2022-10-26 21:15:51,294 epoch 7 - iter 848/1069 - loss 0.06166752 - samples/sec: 8.70 - lr: 0.010000
2022-10-26 21:16:59,785 epoch 7 - iter 954/1069 - loss 0.06152770 - samples/sec: 12.38 - lr: 0.010000
2022-10-26 21:18:05,005 epoch 7 - iter 1060/1069 - loss 0.06131402 - samples/sec: 13.00 - lr: 0.010000
2022-10-26 21:18:10,767 ----------------------------------------------------------------------------------------------------
2022-10-26 21:18:10,769 EPOCH 7 done: loss 0.0613 - lr 0.010000
2022-10-26 21:19:27,868 Evaluating as a multi-label problem: False
2022-10-26 21:19:27,905 DEV : loss 0.061052411794662476 - f1-score (micro avg)  0.8814
2022-10-26 21:19:27,952 BAD EPOCHS (no improvement): 0
2022-10-26 21:19:27,954 saving best model
2022-10-26 21:19:29,378 ----------------------------------------------------------------------------------------------------
2022-10-26 21:20:36,789 epoch 8 - iter 106/1069 - loss 0.05390116 - samples/sec: 12.58 - lr: 0.010000
2022-10-26 21:21:41,786 epoch 8 - iter 212/1069 - loss 0.05771654 - samples/sec: 13.05 - lr: 0.010000
2022-10-26 21:22:48,800 epoch 8 - iter 318/1069 - loss 0.05630827 - samples/sec: 12.66 - lr: 0.010000
2022-10-26 21:23:54,308 epoch 8 - iter 424/1069 - loss 0.05571937 - samples/sec: 12.95 - lr: 0.010000
2022-10-26 21:25:00,994 epoch 8 - iter 530/1069 - loss 0.05600622 - samples/sec: 12.72 - lr: 0.010000
2022-10-26 21:26:05,543 epoch 8 - iter 636/1069 - loss 0.05638838 - samples/sec: 13.14 - lr: 0.010000
2022-10-26 21:27:11,826 epoch 8 - iter 742/1069 - loss 0.05616568 - samples/sec: 12.80 - lr: 0.010000
2022-10-26 21:28:18,954 epoch 8 - iter 848/1069 - loss 0.05584409 - samples/sec: 12.64 - lr: 0.010000
2022-10-26 21:29:25,542 epoch 8 - iter 954/1069 - loss 0.05561947 - samples/sec: 12.74 - lr: 0.010000
2022-10-26 21:30:30,533 epoch 8 - iter 1060/1069 - loss 0.05524983 - samples/sec: 13.05 - lr: 0.010000
2022-10-26 21:30:35,751 ----------------------------------------------------------------------------------------------------
2022-10-26 21:30:35,755 EPOCH 8 done: loss 0.0553 - lr 0.010000
2022-10-26 21:31:53,000 Evaluating as a multi-label problem: False
2022-10-26 21:31:53,038 DEV : loss 0.06685522198677063 - f1-score (micro avg)  0.8808
2022-10-26 21:31:53,088 BAD EPOCHS (no improvement): 1
2022-10-26 21:31:53,092 ----------------------------------------------------------------------------------------------------
2022-10-26 21:33:00,202 epoch 9 - iter 106/1069 - loss 0.04591263 - samples/sec: 12.64 - lr: 0.010000
2022-10-26 21:34:05,608 epoch 9 - iter 212/1069 - loss 0.04753505 - samples/sec: 12.97 - lr: 0.010000
2022-10-26 21:35:08,841 epoch 9 - iter 318/1069 - loss 0.04983626 - samples/sec: 13.41 - lr: 0.010000
2022-10-26 21:36:15,599 epoch 9 - iter 424/1069 - loss 0.04851610 - samples/sec: 12.70 - lr: 0.010000
2022-10-26 21:37:22,043 epoch 9 - iter 530/1069 - loss 0.04882362 - samples/sec: 12.77 - lr: 0.010000
2022-10-26 21:38:26,514 epoch 9 - iter 636/1069 - loss 0.04925004 - samples/sec: 13.16 - lr: 0.010000
2022-10-26 21:39:34,184 epoch 9 - iter 742/1069 - loss 0.04945580 - samples/sec: 12.53 - lr: 0.010000
2022-10-26 21:40:39,778 epoch 9 - iter 848/1069 - loss 0.04945835 - samples/sec: 12.93 - lr: 0.010000
2022-10-26 21:41:44,710 epoch 9 - iter 954/1069 - loss 0.04953811 - samples/sec: 13.06 - lr: 0.010000
2022-10-26 21:42:52,682 epoch 9 - iter 1060/1069 - loss 0.04944091 - samples/sec: 12.48 - lr: 0.010000
2022-10-26 21:42:57,825 ----------------------------------------------------------------------------------------------------
2022-10-26 21:42:57,826 EPOCH 9 done: loss 0.0497 - lr 0.010000
2022-10-26 21:44:13,770 Evaluating as a multi-label problem: False
2022-10-26 21:44:13,809 DEV : loss 0.057355064898729324 - f1-score (micro avg)  0.8922
2022-10-26 21:44:13,856 BAD EPOCHS (no improvement): 0
2022-10-26 21:44:13,859 saving best model
2022-10-26 21:44:15,333 ----------------------------------------------------------------------------------------------------
2022-10-26 21:45:22,992 epoch 10 - iter 106/1069 - loss 0.03999971 - samples/sec: 12.54 - lr: 0.010000
2022-10-26 21:46:28,166 epoch 10 - iter 212/1069 - loss 0.04223290 - samples/sec: 13.01 - lr: 0.010000
2022-10-26 21:47:34,530 epoch 10 - iter 318/1069 - loss 0.04233629 - samples/sec: 12.78 - lr: 0.010000
2022-10-26 21:49:21,523 epoch 10 - iter 424/1069 - loss 0.04293457 - samples/sec: 7.93 - lr: 0.010000
2022-10-26 21:51:20,933 epoch 10 - iter 530/1069 - loss 0.04261612 - samples/sec: 7.10 - lr: 0.010000
2022-10-26 21:53:16,486 epoch 10 - iter 636/1069 - loss 0.04316492 - samples/sec: 7.34 - lr: 0.010000
2022-10-26 21:55:14,355 epoch 10 - iter 742/1069 - loss 0.04313719 - samples/sec: 7.20 - lr: 0.010000
2022-10-26 21:57:14,471 epoch 10 - iter 848/1069 - loss 0.04345674 - samples/sec: 7.06 - lr: 0.010000
2022-10-26 21:59:14,125 epoch 10 - iter 954/1069 - loss 0.04368164 - samples/sec: 7.09 - lr: 0.010000
2022-10-26 22:01:02,494 epoch 10 - iter 1060/1069 - loss 0.04413420 - samples/sec: 7.83 - lr: 0.010000
2022-10-26 22:01:08,438 ----------------------------------------------------------------------------------------------------
2022-10-26 22:01:08,440 EPOCH 10 done: loss 0.0440 - lr 0.010000
2022-10-26 22:02:22,434 Evaluating as a multi-label problem: False
2022-10-26 22:02:22,472 DEV : loss 0.06379110366106033 - f1-score (micro avg)  0.8877
2022-10-26 22:02:22,522 BAD EPOCHS (no improvement): 1
2022-10-26 22:02:23,953 ----------------------------------------------------------------------------------------------------
2022-10-26 22:02:23,963 loading file /content/model/mono_ner/best-model.pt
2022-10-26 22:02:26,538 SequenceTagger predicts: Dictionary with 15 tags: O, S-PER, B-PER, E-PER, I-PER, S-MISC, B-MISC, E-MISC, I-MISC, S-LOC, B-LOC, E-LOC, I-LOC, <START>, <STOP>
2022-10-26 22:03:39,014 Evaluating as a multi-label problem: False
2022-10-26 22:03:39,054 0.8798	0.8959	0.8878	0.8324
2022-10-26 22:03:39,056 
Results:
- F-score (micro) 0.8878
- F-score (macro) 0.8574
- Accuracy 0.8324

By class:
              precision    recall  f1-score   support

         PER     0.9124    0.9445    0.9282      2127
        MISC     0.8092    0.8317    0.8203       933
         LOC     0.8686    0.7835    0.8238       388

   micro avg     0.8798    0.8959    0.8878      3448
   macro avg     0.8634    0.8533    0.8574      3448
weighted avg     0.8795    0.8959    0.8872      3448

2022-10-26 22:03:39,059 ----------------------------------------------------------------------------------------------------