2021-08-28 02:06:15,858 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,862 Model: "TARSTagger(
  (tars_model): SequenceTagger(
    (embeddings): TransformerWordEmbeddings(
      (model): RobertaModel(
        (embeddings): RobertaEmbeddings(
          (word_embeddings): Embedding(50265, 1024, padding_idx=1)
          (position_embeddings): Embedding(514, 1024, padding_idx=1)
          (token_type_embeddings): Embedding(1, 1024)
          (LayerNorm): LayerNorm((1024,), 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=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (1): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (2): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (3): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (4): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (5): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (6): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (7): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (8): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (9): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (10): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (11): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (12): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (13): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (14): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (15): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (16): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (17): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (18): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (19): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (20): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (21): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (22): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (23): RobertaLayer(
              (attention): RobertaAttention(
                (self): RobertaSelfAttention(
                  (query): Linear(in_features=1024, out_features=1024, bias=True)
                  (key): Linear(in_features=1024, out_features=1024, bias=True)
                  (value): Linear(in_features=1024, out_features=1024, bias=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
                (output): RobertaSelfOutput(
                  (dense): Linear(in_features=1024, out_features=1024, bias=True)
                  (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                  (dropout): Dropout(p=0.1, inplace=False)
                )
              )
              (intermediate): RobertaIntermediate(
                (dense): Linear(in_features=1024, out_features=4096, bias=True)
              )
              (output): RobertaOutput(
                (dense): Linear(in_features=4096, out_features=1024, bias=True)
                (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
          )
        )
        (pooler): RobertaPooler(
          (dense): Linear(in_features=1024, out_features=1024, bias=True)
          (activation): Tanh()
        )
      )
    )
    (word_dropout): WordDropout(p=0.05)
    (locked_dropout): LockedDropout(p=0.5)
    (linear): Linear(in_features=1024, out_features=5, bias=True)
  )
)"
2021-08-28 02:06:15,864 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,864 Corpus: "Corpus: 14987 train + 3466 dev + 3684 test sentences"
2021-08-28 02:06:15,864 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,864 Parameters:
2021-08-28 02:06:15,864  - learning_rate: "5e-06"
2021-08-28 02:06:15,864  - mini_batch_size: "4"
2021-08-28 02:06:15,864  - patience: "3"
2021-08-28 02:06:15,864  - anneal_factor: "0.5"
2021-08-28 02:06:15,864  - max_epochs: "3"
2021-08-28 02:06:15,864  - shuffle: "True"
2021-08-28 02:06:15,864  - train_with_dev: "True"
2021-08-28 02:06:15,864  - batch_growth_annealing: "False"
2021-08-28 02:06:15,864 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,864 Model training base path: "resources/taggers/few-shot-sequence-tagger-all-entities-with-long-roberta-large-mbz-2/short-conll-3"
2021-08-28 02:06:15,865 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,865 Device: cuda:2
2021-08-28 02:06:15,865 ----------------------------------------------------------------------------------------------------
2021-08-28 02:06:15,865 Embeddings storage mode: none
2021-08-28 02:06:15,870 ----------------------------------------------------------------------------------------------------
2021-08-28 02:07:54,916 epoch 1 - iter 461/4614 - loss 0.04115386 - samples/sec: 18.63 - lr: 0.000005
2021-08-28 02:09:31,352 epoch 1 - iter 922/4614 - loss 0.03811590 - samples/sec: 19.13 - lr: 0.000005
2021-08-28 02:11:00,393 epoch 1 - iter 1383/4614 - loss 0.03731959 - samples/sec: 20.71 - lr: 0.000005
2021-08-28 02:12:30,899 epoch 1 - iter 1844/4614 - loss 0.03724935 - samples/sec: 20.38 - lr: 0.000005
2021-08-28 02:14:09,588 epoch 1 - iter 2305/4614 - loss 0.03622093 - samples/sec: 18.69 - lr: 0.000005
2021-08-28 02:15:47,357 epoch 1 - iter 2766/4614 - loss 0.03669202 - samples/sec: 18.87 - lr: 0.000005
2021-08-28 02:17:28,241 epoch 1 - iter 3227/4614 - loss 0.03672819 - samples/sec: 18.28 - lr: 0.000005
2021-08-28 02:19:08,959 epoch 1 - iter 3688/4614 - loss 0.03660902 - samples/sec: 18.31 - lr: 0.000005
2021-08-28 02:20:49,032 epoch 1 - iter 4149/4614 - loss 0.03606340 - samples/sec: 18.43 - lr: 0.000005
2021-08-28 02:22:32,671 epoch 1 - iter 4610/4614 - loss 0.03575037 - samples/sec: 17.80 - lr: 0.000005
2021-08-28 02:22:33,416 ----------------------------------------------------------------------------------------------------
2021-08-28 02:22:33,416 EPOCH 1 done: loss 0.0357 - lr 0.0000050
2021-08-28 02:22:33,416 BAD EPOCHS (no improvement): 0
2021-08-28 02:22:33,419 ----------------------------------------------------------------------------------------------------
2021-08-28 02:24:13,051 epoch 2 - iter 461/4614 - loss 0.03170887 - samples/sec: 18.52 - lr: 0.000005
2021-08-28 02:25:51,305 epoch 2 - iter 922/4614 - loss 0.03231392 - samples/sec: 18.77 - lr: 0.000005
2021-08-28 02:27:29,419 epoch 2 - iter 1383/4614 - loss 0.03237881 - samples/sec: 18.80 - lr: 0.000005
2021-08-28 02:29:08,708 epoch 2 - iter 1844/4614 - loss 0.03253567 - samples/sec: 18.58 - lr: 0.000005
2021-08-28 02:30:47,243 epoch 2 - iter 2305/4614 - loss 0.03299843 - samples/sec: 18.72 - lr: 0.000005
2021-08-28 02:32:25,259 epoch 2 - iter 2766/4614 - loss 0.03296455 - samples/sec: 18.82 - lr: 0.000005
2021-08-28 02:34:04,594 epoch 2 - iter 3227/4614 - loss 0.03287460 - samples/sec: 18.57 - lr: 0.000005
2021-08-28 02:35:43,744 epoch 2 - iter 3688/4614 - loss 0.03304968 - samples/sec: 18.60 - lr: 0.000005
2021-08-28 02:37:21,953 epoch 2 - iter 4149/4614 - loss 0.03302461 - samples/sec: 18.78 - lr: 0.000005
2021-08-28 02:39:01,436 epoch 2 - iter 4610/4614 - loss 0.03288710 - samples/sec: 18.54 - lr: 0.000005
2021-08-28 02:39:02,140 ----------------------------------------------------------------------------------------------------
2021-08-28 02:39:02,141 EPOCH 2 done: loss 0.0329 - lr 0.0000050
2021-08-28 02:39:02,141 BAD EPOCHS (no improvement): 0
2021-08-28 02:39:02,144 ----------------------------------------------------------------------------------------------------
2021-08-28 02:40:43,583 epoch 3 - iter 461/4614 - loss 0.03113382 - samples/sec: 18.19 - lr: 0.000005
2021-08-28 02:42:22,011 epoch 3 - iter 922/4614 - loss 0.03137606 - samples/sec: 18.74 - lr: 0.000005
2021-08-28 02:44:01,059 epoch 3 - iter 1383/4614 - loss 0.03222867 - samples/sec: 18.62 - lr: 0.000005
2021-08-28 02:45:38,279 epoch 3 - iter 1844/4614 - loss 0.03152823 - samples/sec: 18.97 - lr: 0.000005
2021-08-28 02:47:17,054 epoch 3 - iter 2305/4614 - loss 0.03129660 - samples/sec: 18.67 - lr: 0.000005
2021-08-28 02:48:54,027 epoch 3 - iter 2766/4614 - loss 0.03114759 - samples/sec: 19.02 - lr: 0.000005
2021-08-28 02:50:32,327 epoch 3 - iter 3227/4614 - loss 0.03117330 - samples/sec: 18.76 - lr: 0.000005
2021-08-28 02:52:11,082 epoch 3 - iter 3688/4614 - loss 0.03114697 - samples/sec: 18.68 - lr: 0.000005
2021-08-28 02:53:49,543 epoch 3 - iter 4149/4614 - loss 0.03111803 - samples/sec: 18.73 - lr: 0.000005
2021-08-28 02:55:27,619 epoch 3 - iter 4610/4614 - loss 0.03130476 - samples/sec: 18.81 - lr: 0.000005
2021-08-28 02:55:28,495 ----------------------------------------------------------------------------------------------------
2021-08-28 02:55:28,495 EPOCH 3 done: loss 0.0313 - lr 0.0000050
2021-08-28 02:55:28,495 BAD EPOCHS (no improvement): 0
2021-08-28 02:55:59,472 ----------------------------------------------------------------------------------------------------
2021-08-28 02:56:00,988 Testing using last state of model ...
2021-08-28 03:00:45,584 0.9282	0.9338	0.931	0.8972
2021-08-28 03:00:45,585 
Results:
- F-score (micro) 0.931
- F-score (macro) 0.9173
- Accuracy 0.8972

By class:
               precision    recall  f1-score   support

 organization     0.9036    0.9368    0.9199      1661
     location     0.9507    0.9371    0.9438      1668
       person     0.9751    0.9691    0.9721      1617
miscellaneous     0.8293    0.8376    0.8335       702

    micro avg     0.9282    0.9338    0.9310      5648
    macro avg     0.9147    0.9201    0.9173      5648
 weighted avg     0.9288    0.9338    0.9312      5648
  samples avg     0.8972    0.8972    0.8972      5648

2021-08-28 03:00:45,585 ----------------------------------------------------------------------------------------------------