Make docstring match args (#4711)

src/transformers/modeling_bart.py

@@ -904,7 +904,7 @@ class BartForConditionalGeneration(PretrainedBartModel):
         **unused
     ):
         r"""
-        masked_lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
             Labels for computing the masked language modeling loss.
             Indices should either be in ``[0, ..., config.vocab_size]`` or -100 (see ``input_ids`` docstring).
             Tokens with indices set to ``-100`` are ignored (masked), the loss is only computed for the tokens
@@ -913,7 +913,7 @@ class BartForConditionalGeneration(PretrainedBartModel):
 
     Returns:
         :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
-        masked_lm_loss (`optional`, returned when ``masked_lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
+        masked_lm_loss (`optional`, returned when ``lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
             Masked language modeling loss.
         prediction_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

src/transformers/modeling_gpt2.py

@@ -554,7 +554,7 @@ class GPT2LMHeadModel(GPT2PreTrainedModel):
         r"""
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
             Labels for language modeling.
-            Note that the labels **are shifted** inside the model, i.e. you can set ``lm_labels = input_ids``
+            Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``
             All labels set to ``-100`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``

src/transformers/modeling_openai.py

@@ -491,7 +491,7 @@ class OpenAIGPTLMHeadModel(OpenAIGPTPreTrainedModel):
         r"""
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
             Labels for language modeling.
-            Note that the labels **are shifted** inside the model, i.e. you can set ``lm_labels = input_ids``
+            Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``
             All labels set to ``-100`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``

src/transformers/modeling_transfo_xl.py

@@ -852,7 +852,7 @@ class TransfoXLLMHeadModel(TransfoXLPreTrainedModel):
         r"""
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
             Labels for language modeling.
-            Note that the labels **are shifted** inside the model, i.e. you can set ``lm_labels = input_ids``
+            Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``
             All labels set to ``-100`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``

src/transformers/modeling_xlm.py

@@ -640,7 +640,7 @@ class XLMWithLMHeadModel(XLMPreTrainedModel):
         r"""
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
             Labels for language modeling.
-            Note that the labels **are shifted** inside the model, i.e. you can set ``lm_labels = input_ids``
+            Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``
             All labels set to ``-100`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``