['__call__', '__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattr__', '__getattribute__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__setstate__', '__sizeof__', '__str__', '__subclasshook__', '__weakref__', '_apply', '_backend', '_backward_hooks', '_buffers', '_forward_hooks', '_forward_pre_hooks', '_get_name', '_load_from_state_dict', '_load_state_dict_pre_hooks', '_modules', '_named_members', '_parameters', '_register_load_state_dict_pre_hook', '_register_state_dict_hook', '_slow_forward', '_state_dict_hooks', '_tracing_name', '_version', 'add_module', 'apply', 'buffers', 'children', 'cpu', 'cuda', 'device_ids', 'dim', 'double', 'dump_patches', 'eval', 'extra_repr', 'float', 'forward', 'gather', 'half', 'load_state_dict', 'module', 'modules', 'named_buffers', 'named_children', 'named_modules', 'named_parameters', 'output_device', 'parallel_apply', 'parameters', 'register_backward_hook', 'register_buffer', 'register_forward_hook', 'register_forward_pre_hook', 'register_parameter', 'replicate', 'scatter', 'share_memory', 'state_dict', 'to', 'train', 'training', 'type', 'zero_grad']
<bound method Module.__dir__ of DataParallel(
  (module): BertForMultiLabelSequenceClassification(
    (bert): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(30522, 768)
        (position_embeddings): Embedding(512, 768)
        (token_type_embeddings): Embedding(2, 768)
        (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1)
      )
      (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
          (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)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
    (dropout): Dropout(p=0.1)
    (classifier): Linear(in_features=768, out_features=50, bias=True)
  )
)>