Corrected typo: maked → masked (#7703)

src/transformers/modeling_bert.py

@@ -667,7 +667,7 @@ BERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
@@ -781,7 +781,7 @@ class BertModel(BertPreTrainedModel):
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
         """
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (
@@ -1012,7 +1012,7 @@ class BertLMHeadModel(BertPreTrainedModel):
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the left-to-right language modeling loss (next word prediction).
             Indices should be in ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)