fix tf doc bug (#10570)

src/transformers/models/bert/modeling_tf_bert.py

@@ -959,6 +959,19 @@ class TFBertForPreTraining(TFBertPreTrainedModel, TFBertPreTrainingLoss):
         **kwargs,
     ) -> Union[TFBertForPreTrainingOutput, Tuple[tf.Tensor]]:
         r"""
+        labels (:obj:`torch.LongTensor` of shape ``(batch_size, sequence_length)``, `optional`):
+            Labels for computing the masked language modeling loss. Indices should be in ``[-100, 0, ...,
+            config.vocab_size]`` (see ``input_ids`` docstring) Tokens with indices set to ``-100`` are ignored
+            (masked), the loss is only computed for the tokens with labels in ``[0, ..., config.vocab_size]``
+        next_sentence_label (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`):
+            Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair
+            (see :obj:`input_ids` docstring) Indices should be in ``[0, 1]``:
+
+            - 0 indicates sequence B is a continuation of sequence A,
+            - 1 indicates sequence B is a random sequence.
+        kwargs (:obj:`Dict[str, any]`, optional, defaults to `{}`):
+            Used to hide legacy arguments that have been deprecated.
+
         Return:
 
         Examples::