diff --git a/src/transformers/file_utils.py b/src/transformers/file_utils.py
index de169198d5b..5f522a440c6 100644
--- a/src/transformers/file_utils.py
+++ b/src/transformers/file_utils.py
@@ -816,7 +816,7 @@ def _prepare_output_docstrings(output_type, config_class):
         >>> choice1 = "It is eaten while held in the hand."
         >>> labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1
 
-        >>> encoding = tokenizer([[prompt, prompt], [choice0, choice1]], return_tensors='pt', padding=True)
+        >>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors='pt', padding=True)
         >>> outputs = model(**{{k: v.unsqueeze(0) for k,v in encoding.items()}}, labels=labels)  # batch size is 1
 
         >>> # the linear classifier still needs to be trained