Use FutureWarning to deprecate (#6111)

src/transformers/modeling_albert.py

@@ -823,7 +823,7 @@ class AlbertForMaskedLM(AlbertPreTrainedModel):
         if "masked_lm_labels" in kwargs:
             warnings.warn(
                 "The `masked_lm_labels` argument is deprecated and will be removed in a future version, use `labels` instead.",
-                DeprecationWarning,
+                FutureWarning,
             )
             labels = kwargs.pop("masked_lm_labels")
         assert kwargs == {}, f"Unexpected keyword arguments: {list(kwargs.keys())}."

src/transformers/tokenization_utils_base.py

@@ -1466,7 +1466,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin):
                     "use `padding='max_length'` to pad to a max length. In this case, you can give a specific "
                     "length with `max_length` (e.g. `max_length=45`) or leave max_length to None to pad to the "
                     "maximal input size of the model (e.g. 512 for Bert).",
-                    DeprecationWarning,
+                    FutureWarning,
                 )
             if max_length is None:
                 padding_strategy = PaddingStrategy.LONGEST
@@ -1492,7 +1492,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin):
                     "`truncation='only_first'` (will only truncate the first sentence in the pairs) "
                     "`truncation='only_second'` (will only truncate the second sentence in the pairs) "
                     "or `truncation='longest_first'` (will iteratively remove tokens from the longest sentence in the pairs).",
-                    DeprecationWarning,
+                    FutureWarning,
                 )
             truncation_strategy = TruncationStrategy(old_truncation_strategy)
         elif truncation is not False: