The first token in this vocab.

Args: trn_data: dev_data: save_dir: batch_size: epochs: transformer:

Args: trn_data: Training set. dev_data: Development set. save_dir: The directory to save trained compone

Fit component to training set. Args: trn_data: Training set. dev_data: Development set. save_dir: The dir

Args: trn_data: Path to training set. dev_data: Path to dev set. save_dir: The directory to save trained

Fit to data, triggers the training procedure. For training set and dev set, they shall be local or remote files. Args: tr

Fit onto a dataloader. Args: trn: Training set. criterion: Loss function. optimizer: Optimizer.

`input_ids_shape` is expected to be [bsz x seqlen].

Input shape: Batch x Time x Channel

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)` attention_mask (

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence toke

r""" Args: input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence toke

r""" labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing the masked language mo

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for position (index) of the start of the la

r""" Args: input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence toke

r""" Args: scores (~torch.Tensor): ``[batch_size, seq_len, seq_len]``. Scores of all possible constituents.

r""" Args: x (~torch.FloatTensor): ``[batch_size, seq_len, hidden_dim]``. Hidden states from encoder. Ret

r""" Args: batch (~dict): Batch of input data. Returns: ~torch.Tensor, ~torch.Tensor:

r""" Args: x (torch.Tensor): ``[batch_size, seq_len, n_in]``. y (torch.Tensor): ``[batch_size, seq_len, n_in]``.

r""" Args: x (~torch.Tensor): The size of each input feature is `n_in`. Returns: A tensor wit