2022-01-16 18:38:17,520 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,523 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): RobertaModel(
      (embeddings): RobertaEmbeddings(
        (word_embeddings): Embedding(32768, 768, padding_idx=1)
        (position_embeddings): Embedding(514, 768, padding_idx=1)
        (token_type_embeddings): Embedding(1, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): RobertaEncoder(
        (layer): ModuleList(
          (0): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (1): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (2): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (3): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (4): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (5): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (6): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (7): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (8): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (9): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (10): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (11): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (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): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): RobertaPooler(
        (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=51, bias=True)
  (beta): 1.0
  (weights): None
  (weight_tensor) None
)"
2022-01-16 18:38:17,526 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,526 Corpus: "Corpus: 5642 train + 195 dev + 649 test sentences"
2022-01-16 18:38:17,526 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,527 Parameters:
2022-01-16 18:38:17,527  - learning_rate: "5e-06"
2022-01-16 18:38:17,527  - mini_batch_size: "32"
2022-01-16 18:38:17,527  - patience: "3"
2022-01-16 18:38:17,528  - anneal_factor: "0.5"
2022-01-16 18:38:17,528  - max_epochs: "10"
2022-01-16 18:38:17,528  - shuffle: "True"
2022-01-16 18:38:17,528  - train_with_dev: "False"
2022-01-16 18:38:17,529  - batch_growth_annealing: "False"
2022-01-16 18:38:17,529 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,529 Model training base path: "resources/taggers/pos-transformer"
2022-01-16 18:38:17,530 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,530 Device: cuda:0
2022-01-16 18:38:17,530 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:17,530 Embeddings storage mode: none
2022-01-16 18:38:17,534 ----------------------------------------------------------------------------------------------------
2022-01-16 18:38:34,359 epoch 1 - iter 17/177 - loss 4.21719545 - samples/sec: 32.34 - lr: 0.000000
2022-01-16 18:38:49,400 epoch 1 - iter 34/177 - loss 4.19345430 - samples/sec: 36.17 - lr: 0.000001
2022-01-16 18:39:05,256 epoch 1 - iter 51/177 - loss 4.15633603 - samples/sec: 34.31 - lr: 0.000001
2022-01-16 18:39:19,936 epoch 1 - iter 68/177 - loss 4.11811385 - samples/sec: 37.07 - lr: 0.000002
2022-01-16 18:39:35,631 epoch 1 - iter 85/177 - loss 4.06705216 - samples/sec: 34.68 - lr: 0.000002
2022-01-16 18:39:49,539 epoch 1 - iter 102/177 - loss 4.01162833 - samples/sec: 39.12 - lr: 0.000003
2022-01-16 18:40:04,517 epoch 1 - iter 119/177 - loss 3.95117440 - samples/sec: 36.33 - lr: 0.000003
2022-01-16 18:40:18,637 epoch 1 - iter 136/177 - loss 3.88391044 - samples/sec: 38.53 - lr: 0.000004
2022-01-16 18:40:34,602 epoch 1 - iter 153/177 - loss 3.78662706 - samples/sec: 34.08 - lr: 0.000004
2022-01-16 18:40:50,297 epoch 1 - iter 170/177 - loss 3.66565316 - samples/sec: 34.67 - lr: 0.000005
2022-01-16 18:40:55,405 ----------------------------------------------------------------------------------------------------
2022-01-16 18:40:55,406 EPOCH 1 done: loss 3.6331 - lr 0.0000050
2022-01-16 18:41:01,071 DEV : loss 2.0775277614593506 - f1-score (micro avg)  0.5698
2022-01-16 18:41:01,073 BAD EPOCHS (no improvement): 4
2022-01-16 18:41:01,075 ----------------------------------------------------------------------------------------------------
2022-01-16 18:41:14,873 epoch 2 - iter 17/177 - loss 2.20805337 - samples/sec: 39.44 - lr: 0.000005
2022-01-16 18:41:29,867 epoch 2 - iter 34/177 - loss 1.96658974 - samples/sec: 36.29 - lr: 0.000005
2022-01-16 18:41:45,607 epoch 2 - iter 51/177 - loss 1.75508128 - samples/sec: 34.57 - lr: 0.000005
2022-01-16 18:42:01,386 epoch 2 - iter 68/177 - loss 1.58575541 - samples/sec: 34.48 - lr: 0.000005
2022-01-16 18:42:16,804 epoch 2 - iter 85/177 - loss 1.45429547 - samples/sec: 35.29 - lr: 0.000005
2022-01-16 18:42:32,178 epoch 2 - iter 102/177 - loss 1.34526502 - samples/sec: 35.39 - lr: 0.000005
2022-01-16 18:42:48,735 epoch 2 - iter 119/177 - loss 1.23724431 - samples/sec: 32.86 - lr: 0.000005
2022-01-16 18:43:03,310 epoch 2 - iter 136/177 - loss 1.16223838 - samples/sec: 37.33 - lr: 0.000005
2022-01-16 18:43:18,304 epoch 2 - iter 153/177 - loss 1.09870495 - samples/sec: 36.29 - lr: 0.000005
2022-01-16 18:43:34,956 epoch 2 - iter 170/177 - loss 1.03855466 - samples/sec: 32.67 - lr: 0.000004
2022-01-16 18:43:40,722 ----------------------------------------------------------------------------------------------------
2022-01-16 18:43:40,723 EPOCH 2 done: loss 1.0198 - lr 0.0000044
2022-01-16 18:43:46,405 DEV : loss 0.23464356362819672 - f1-score (micro avg)  0.9443
2022-01-16 18:43:46,407 BAD EPOCHS (no improvement): 4
2022-01-16 18:43:46,408 ----------------------------------------------------------------------------------------------------
2022-01-16 18:44:01,387 epoch 3 - iter 17/177 - loss 0.46476740 - samples/sec: 36.33 - lr: 0.000004
2022-01-16 18:44:17,394 epoch 3 - iter 34/177 - loss 0.46233323 - samples/sec: 33.99 - lr: 0.000004
2022-01-16 18:44:32,304 epoch 3 - iter 51/177 - loss 0.45235428 - samples/sec: 36.49 - lr: 0.000004
2022-01-16 18:44:46,826 epoch 3 - iter 68/177 - loss 0.44547326 - samples/sec: 37.47 - lr: 0.000004
2022-01-16 18:45:03,857 epoch 3 - iter 85/177 - loss 0.43503033 - samples/sec: 31.95 - lr: 0.000004
2022-01-16 18:45:20,043 epoch 3 - iter 102/177 - loss 0.42734805 - samples/sec: 33.63 - lr: 0.000004
2022-01-16 18:45:36,060 epoch 3 - iter 119/177 - loss 0.42237100 - samples/sec: 33.97 - lr: 0.000004
2022-01-16 18:45:51,576 epoch 3 - iter 136/177 - loss 0.41700412 - samples/sec: 35.07 - lr: 0.000004
2022-01-16 18:46:07,252 epoch 3 - iter 153/177 - loss 0.41455352 - samples/sec: 34.71 - lr: 0.000004
2022-01-16 18:46:23,597 epoch 3 - iter 170/177 - loss 0.41134424 - samples/sec: 33.29 - lr: 0.000004
2022-01-16 18:46:29,222 ----------------------------------------------------------------------------------------------------
2022-01-16 18:46:29,223 EPOCH 3 done: loss 0.4103 - lr 0.0000039
2022-01-16 18:46:34,899 DEV : loss 0.140821173787117 - f1-score (micro avg)  0.9632
2022-01-16 18:46:34,901 BAD EPOCHS (no improvement): 4
2022-01-16 18:46:34,902 ----------------------------------------------------------------------------------------------------
2022-01-16 18:46:49,649 epoch 4 - iter 17/177 - loss 0.34770276 - samples/sec: 36.90 - lr: 0.000004
2022-01-16 18:47:05,137 epoch 4 - iter 34/177 - loss 0.34449519 - samples/sec: 35.13 - lr: 0.000004
2022-01-16 18:47:20,666 epoch 4 - iter 51/177 - loss 0.35038471 - samples/sec: 35.04 - lr: 0.000004
2022-01-16 18:47:35,593 epoch 4 - iter 68/177 - loss 0.34965167 - samples/sec: 36.45 - lr: 0.000004
2022-01-16 18:47:51,537 epoch 4 - iter 85/177 - loss 0.35074386 - samples/sec: 34.13 - lr: 0.000004
2022-01-16 18:48:06,575 epoch 4 - iter 102/177 - loss 0.34919573 - samples/sec: 36.18 - lr: 0.000004
2022-01-16 18:48:22,671 epoch 4 - iter 119/177 - loss 0.34906482 - samples/sec: 33.80 - lr: 0.000004
2022-01-16 18:48:38,152 epoch 4 - iter 136/177 - loss 0.34645574 - samples/sec: 35.15 - lr: 0.000003
2022-01-16 18:48:53,425 epoch 4 - iter 153/177 - loss 0.34515747 - samples/sec: 35.63 - lr: 0.000003
2022-01-16 18:49:08,614 epoch 4 - iter 170/177 - loss 0.34411478 - samples/sec: 35.82 - lr: 0.000003
2022-01-16 18:49:14,556 ----------------------------------------------------------------------------------------------------
2022-01-16 18:49:14,557 EPOCH 4 done: loss 0.3430 - lr 0.0000033
2022-01-16 18:49:20,294 DEV : loss 0.11640190333127975 - f1-score (micro avg)  0.9703
2022-01-16 18:49:20,297 BAD EPOCHS (no improvement): 4
2022-01-16 18:49:20,297 ----------------------------------------------------------------------------------------------------
2022-01-16 18:49:36,057 epoch 5 - iter 17/177 - loss 0.31027747 - samples/sec: 34.53 - lr: 0.000003
2022-01-16 18:49:51,823 epoch 5 - iter 34/177 - loss 0.31176440 - samples/sec: 34.51 - lr: 0.000003
2022-01-16 18:50:06,630 epoch 5 - iter 51/177 - loss 0.31452075 - samples/sec: 36.75 - lr: 0.000003
2022-01-16 18:50:22,294 epoch 5 - iter 68/177 - loss 0.31209996 - samples/sec: 34.73 - lr: 0.000003
2022-01-16 18:50:36,301 epoch 5 - iter 85/177 - loss 0.31357991 - samples/sec: 38.85 - lr: 0.000003
2022-01-16 18:50:52,962 epoch 5 - iter 102/177 - loss 0.31496866 - samples/sec: 32.66 - lr: 0.000003
2022-01-16 18:51:08,260 epoch 5 - iter 119/177 - loss 0.31294977 - samples/sec: 35.57 - lr: 0.000003
2022-01-16 18:51:24,158 epoch 5 - iter 136/177 - loss 0.31189665 - samples/sec: 34.22 - lr: 0.000003
2022-01-16 18:51:39,145 epoch 5 - iter 153/177 - loss 0.31138881 - samples/sec: 36.31 - lr: 0.000003
2022-01-16 18:51:54,700 epoch 5 - iter 170/177 - loss 0.30960234 - samples/sec: 34.98 - lr: 0.000003
2022-01-16 18:51:59,742 ----------------------------------------------------------------------------------------------------
2022-01-16 18:51:59,743 EPOCH 5 done: loss 0.3098 - lr 0.0000028
2022-01-16 18:52:05,466 DEV : loss 0.10135460644960403 - f1-score (micro avg)  0.9729
2022-01-16 18:52:05,468 BAD EPOCHS (no improvement): 4
2022-01-16 18:52:05,469 ----------------------------------------------------------------------------------------------------
2022-01-16 18:52:20,458 epoch 6 - iter 17/177 - loss 0.30154787 - samples/sec: 36.30 - lr: 0.000003
2022-01-16 18:52:34,917 epoch 6 - iter 34/177 - loss 0.30197436 - samples/sec: 37.63 - lr: 0.000003
2022-01-16 18:52:49,618 epoch 6 - iter 51/177 - loss 0.30167136 - samples/sec: 37.01 - lr: 0.000003
2022-01-16 18:53:04,988 epoch 6 - iter 68/177 - loss 0.30196611 - samples/sec: 35.40 - lr: 0.000003
2022-01-16 18:53:20,297 epoch 6 - iter 85/177 - loss 0.30182940 - samples/sec: 35.54 - lr: 0.000003
2022-01-16 18:53:35,734 epoch 6 - iter 102/177 - loss 0.30003109 - samples/sec: 35.25 - lr: 0.000002
2022-01-16 18:53:51,701 epoch 6 - iter 119/177 - loss 0.30091205 - samples/sec: 34.08 - lr: 0.000002
2022-01-16 18:54:06,831 epoch 6 - iter 136/177 - loss 0.30099483 - samples/sec: 35.96 - lr: 0.000002
2022-01-16 18:54:22,486 epoch 6 - iter 153/177 - loss 0.29848715 - samples/sec: 34.76 - lr: 0.000002
2022-01-16 18:54:37,203 epoch 6 - iter 170/177 - loss 0.29689481 - samples/sec: 36.97 - lr: 0.000002
2022-01-16 18:54:44,337 ----------------------------------------------------------------------------------------------------
2022-01-16 18:54:44,338 EPOCH 6 done: loss 0.2966 - lr 0.0000022
2022-01-16 18:54:49,620 DEV : loss 0.09480294585227966 - f1-score (micro avg)  0.974
2022-01-16 18:54:49,623 BAD EPOCHS (no improvement): 4
2022-01-16 18:54:49,623 ----------------------------------------------------------------------------------------------------
2022-01-16 18:55:05,515 epoch 7 - iter 17/177 - loss 0.28239213 - samples/sec: 34.24 - lr: 0.000002
2022-01-16 18:55:20,295 epoch 7 - iter 34/177 - loss 0.28557506 - samples/sec: 36.81 - lr: 0.000002
2022-01-16 18:55:35,660 epoch 7 - iter 51/177 - loss 0.28541785 - samples/sec: 35.41 - lr: 0.000002
2022-01-16 18:55:51,758 epoch 7 - iter 68/177 - loss 0.29320767 - samples/sec: 33.80 - lr: 0.000002
2022-01-16 18:56:06,783 epoch 7 - iter 85/177 - loss 0.29339894 - samples/sec: 36.21 - lr: 0.000002
2022-01-16 18:56:22,815 epoch 7 - iter 102/177 - loss 0.29253486 - samples/sec: 33.94 - lr: 0.000002
2022-01-16 18:56:39,028 epoch 7 - iter 119/177 - loss 0.29145637 - samples/sec: 33.56 - lr: 0.000002
2022-01-16 18:56:54,361 epoch 7 - iter 136/177 - loss 0.29111952 - samples/sec: 35.49 - lr: 0.000002
2022-01-16 18:57:09,548 epoch 7 - iter 153/177 - loss 0.29113036 - samples/sec: 35.83 - lr: 0.000002
2022-01-16 18:57:23,584 epoch 7 - iter 170/177 - loss 0.29066532 - samples/sec: 38.76 - lr: 0.000002
2022-01-16 18:57:29,584 ----------------------------------------------------------------------------------------------------
2022-01-16 18:57:29,585 EPOCH 7 done: loss 0.2896 - lr 0.0000017
2022-01-16 18:57:34,894 DEV : loss 0.09033482521772385 - f1-score (micro avg)  0.9743
2022-01-16 18:57:34,896 BAD EPOCHS (no improvement): 4
2022-01-16 18:57:34,898 ----------------------------------------------------------------------------------------------------
2022-01-16 18:57:50,623 epoch 8 - iter 17/177 - loss 0.28329047 - samples/sec: 34.60 - lr: 0.000002
2022-01-16 18:58:06,213 epoch 8 - iter 34/177 - loss 0.28096448 - samples/sec: 34.90 - lr: 0.000002
2022-01-16 18:58:22,737 epoch 8 - iter 51/177 - loss 0.28201738 - samples/sec: 32.93 - lr: 0.000002
2022-01-16 18:58:37,507 epoch 8 - iter 68/177 - loss 0.28137267 - samples/sec: 36.84 - lr: 0.000001
2022-01-16 18:58:52,962 epoch 8 - iter 85/177 - loss 0.28405564 - samples/sec: 35.21 - lr: 0.000001
2022-01-16 18:59:08,711 epoch 8 - iter 102/177 - loss 0.28496531 - samples/sec: 34.55 - lr: 0.000001
2022-01-16 18:59:23,238 epoch 8 - iter 119/177 - loss 0.28466528 - samples/sec: 37.46 - lr: 0.000001
2022-01-16 18:59:38,520 epoch 8 - iter 136/177 - loss 0.28246598 - samples/sec: 35.60 - lr: 0.000001
2022-01-16 18:59:53,789 epoch 8 - iter 153/177 - loss 0.28078088 - samples/sec: 35.63 - lr: 0.000001
2022-01-16 19:00:09,934 epoch 8 - iter 170/177 - loss 0.28075535 - samples/sec: 33.70 - lr: 0.000001
2022-01-16 19:00:15,100 ----------------------------------------------------------------------------------------------------
2022-01-16 19:00:15,101 EPOCH 8 done: loss 0.2814 - lr 0.0000011
2022-01-16 19:00:20,403 DEV : loss 0.08581043034791946 - f1-score (micro avg)  0.9745
2022-01-16 19:00:20,406 BAD EPOCHS (no improvement): 4
2022-01-16 19:00:20,406 ----------------------------------------------------------------------------------------------------
2022-01-16 19:00:36,469 epoch 9 - iter 17/177 - loss 0.27366042 - samples/sec: 33.87 - lr: 0.000001
2022-01-16 19:00:51,042 epoch 9 - iter 34/177 - loss 0.27417563 - samples/sec: 37.34 - lr: 0.000001
2022-01-16 19:01:06,968 epoch 9 - iter 51/177 - loss 0.27908066 - samples/sec: 34.16 - lr: 0.000001
2022-01-16 19:01:21,551 epoch 9 - iter 68/177 - loss 0.27815091 - samples/sec: 37.31 - lr: 0.000001
2022-01-16 19:01:38,409 epoch 9 - iter 85/177 - loss 0.27855783 - samples/sec: 32.28 - lr: 0.000001
2022-01-16 19:01:53,547 epoch 9 - iter 102/177 - loss 0.28336618 - samples/sec: 35.94 - lr: 0.000001
2022-01-16 19:02:09,188 epoch 9 - iter 119/177 - loss 0.28196400 - samples/sec: 34.79 - lr: 0.000001
2022-01-16 19:02:25,112 epoch 9 - iter 136/177 - loss 0.28112997 - samples/sec: 34.17 - lr: 0.000001
2022-01-16 19:02:41,122 epoch 9 - iter 153/177 - loss 0.28271008 - samples/sec: 33.99 - lr: 0.000001
2022-01-16 19:02:57,003 epoch 9 - iter 170/177 - loss 0.28254205 - samples/sec: 34.26 - lr: 0.000001
2022-01-16 19:03:02,602 ----------------------------------------------------------------------------------------------------
2022-01-16 19:03:02,603 EPOCH 9 done: loss 0.2826 - lr 0.0000006
2022-01-16 19:03:08,344 DEV : loss 0.08502506464719772 - f1-score (micro avg)  0.974
2022-01-16 19:03:08,347 BAD EPOCHS (no improvement): 4
2022-01-16 19:03:08,348 ----------------------------------------------------------------------------------------------------
2022-01-16 19:03:22,683 epoch 10 - iter 17/177 - loss 0.29810598 - samples/sec: 37.96 - lr: 0.000001
2022-01-16 19:03:38,044 epoch 10 - iter 34/177 - loss 0.29633129 - samples/sec: 35.42 - lr: 0.000000
2022-01-16 19:03:54,399 epoch 10 - iter 51/177 - loss 0.28500408 - samples/sec: 33.27 - lr: 0.000000
2022-01-16 19:04:09,802 epoch 10 - iter 68/177 - loss 0.28305573 - samples/sec: 35.32 - lr: 0.000000
2022-01-16 19:04:25,641 epoch 10 - iter 85/177 - loss 0.28663575 - samples/sec: 34.35 - lr: 0.000000
2022-01-16 19:04:40,354 epoch 10 - iter 102/177 - loss 0.28653115 - samples/sec: 36.98 - lr: 0.000000
2022-01-16 19:04:56,702 epoch 10 - iter 119/177 - loss 0.28579694 - samples/sec: 33.28 - lr: 0.000000
2022-01-16 19:05:12,070 epoch 10 - iter 136/177 - loss 0.28590446 - samples/sec: 35.40 - lr: 0.000000
2022-01-16 19:05:27,377 epoch 10 - iter 153/177 - loss 0.28533742 - samples/sec: 35.55 - lr: 0.000000
2022-01-16 19:05:42,603 epoch 10 - iter 170/177 - loss 0.28333786 - samples/sec: 35.73 - lr: 0.000000
2022-01-16 19:05:48,443 ----------------------------------------------------------------------------------------------------
2022-01-16 19:05:48,444 EPOCH 10 done: loss 0.2832 - lr 0.0000000
2022-01-16 19:05:54,211 DEV : loss 0.08448906987905502 - f1-score (micro avg)  0.974
2022-01-16 19:05:54,214 BAD EPOCHS (no improvement): 4
2022-01-16 19:05:55,439 ----------------------------------------------------------------------------------------------------
2022-01-16 19:05:55,440 Testing using last state of model ...
2022-01-16 19:06:15,179 0.9788	0.9788	0.9788	0.9788
2022-01-16 19:06:15,180 
Results:
- F-score (micro) 0.9788
- F-score (macro) 0.7527
- Accuracy 0.9788

By class:
              precision    recall  f1-score   support

      NOMcom     0.9850    0.9840    0.9845      2130
      VERcjg     0.9974    0.9954    0.9964      1535
      PROper     0.9912    0.9920    0.9916      1368
      PONfbl     1.0000    0.9993    0.9996      1341
         PRE     0.9881    0.9955    0.9918      1331
      ADVgen     0.9713    0.9263    0.9483       841
      PONfrt     0.9895    1.0000    0.9947       662
      DETdef     0.9983    0.9983    0.9983       606
      ADJqua     0.9259    0.9500    0.9378       500
      VERinf     0.9920    1.0000    0.9960       497
      DETpos     1.0000    0.9957    0.9979       469
      CONcoo     0.9957    0.9935    0.9946       465
      CONsub     0.9337    0.9409    0.9373       389
      VERppe     0.9659    0.9720    0.9689       321
      ADVneg     0.9476    1.0000    0.9731       271
      PROrel     0.9194    0.9296    0.9245       270
      NOMpro     0.9634    0.9925    0.9777       265
      DETndf     0.9958    0.9715    0.9835       246
      PROind     0.9526    0.9628    0.9577       188
  PRE.DETdef     0.9785    0.9945    0.9864       183
      DETdem     1.0000    0.9806    0.9902       155
      PROdem     0.9675    1.0000    0.9835       119
      PROadv     0.9083    0.9820    0.9437       111
      DETind     0.9223    0.9694    0.9453        98
      VERppa     0.9683    0.9104    0.9385        67
      PROimp     0.8333    0.8333    0.8333        54
      DETcar     0.7381    1.0000    0.8493        31
         INJ     1.0000    0.8571    0.9231        35
      ADJind     0.9310    0.9000    0.9153        30
      PROint     0.6957    0.7273    0.7111        22
      ADJcar     0.8333    0.4762    0.6061        21
      PROcar     0.7333    0.6111    0.6667        18
      PONpga     1.0000    1.0000    1.0000        16
      PROpos     0.9231    0.8571    0.8889        14
      DETrel     0.6364    0.4375    0.5185        16
      DETint     0.4706    0.8000    0.5926        10
      PONpdr     1.0000    1.0000    1.0000        13
      ADJord     0.8889    0.5000    0.6400        16
      ADVint     1.0000    0.8000    0.8889         5
      PONpxx     0.0000    0.0000    0.0000         6
  PRE.PROrel     0.0000    0.0000    0.0000         2
       latin     0.0000    0.0000    0.0000         2
      PROord     0.0000    0.0000    0.0000         1
  PRE.PROdem     0.0000    0.0000    0.0000         1
  PRE.NOMcom     0.0000    0.0000    0.0000         1
         ETR     0.0000    0.0000    0.0000         1
      ADVsub     0.0000    0.0000    0.0000         1

   micro avg     0.9788    0.9788    0.9788     14744
   macro avg     0.7647    0.7497    0.7527     14744
weighted avg     0.9781    0.9788    0.9782     14744
 samples avg     0.9788    0.9788    0.9788     14744

2022-01-16 19:06:15,180 ----------------------------------------------------------------------------------------------------