diff --git a/src/transformers/data/data_collator.py b/src/transformers/data/data_collator.py
index b7dc4346d2c24a..3279117e6dfe94 100644
--- a/src/transformers/data/data_collator.py
+++ b/src/transformers/data/data_collator.py
@@ -445,8 +445,10 @@ def _whole_word_mask(self, input_tokens: List[str], max_predictions=512):
         Get 0/1 labels for masked tokens with whole word mask proxy
         """
         if not isinstance(self.tokenizer, (BertTokenizer, BertTokenizerFast)):
-            warnings.warn("DataCollatorForWholeWordMask is only suitable for BertTokenizer-like tokenizers."
-                          "Please refer to the documentation for more information.")
+            warnings.warn(
+                "DataCollatorForWholeWordMask is only suitable for BertTokenizer-like tokenizers."
+                "Please refer to the documentation for more information."
+            )
 
         cand_indexes = []
         for (i, token) in enumerate(input_tokens):