fix: The 'warn' method is deprecated (#11105)

* The 'warn' method is deprecated

* fix test

src/transformers/file_utils.py

@@ -194,7 +194,7 @@ if (
     and "PYTORCH_TRANSFORMERS_CACHE" not in os.environ
     and "TRANSFORMERS_CACHE" not in os.environ
 ):
-    logger.warn(
+    logger.warning(
         "In Transformers v4.0.0, the default path to cache downloaded models changed from "
         "'~/.cache/torch/transformers' to '~/.cache/huggingface/transformers'. Since you don't seem to have overridden "
         "and '~/.cache/torch/transformers' is a directory that exists, we're moving it to "

src/transformers/integrations.py

@@ -54,7 +54,7 @@ from .trainer_utils import PREFIX_CHECKPOINT_DIR, BestRun, IntervalStrategy  # n
 def is_wandb_available():
     # any value of WANDB_DISABLED disables wandb
     if os.getenv("WANDB_DISABLED", "").upper() in ENV_VARS_TRUE_VALUES:
-        logger.warn(
+        logger.warning(
             "Using the `WAND_DISABLED` environment variable is deprecated and will be removed in v5. Use the "
             "--report_to flag to control the integrations used for logging result (for instance --report_to none)."
         )

src/transformers/modeling_tf_utils.py

@@ -290,7 +290,7 @@ def booleans_processing(config, **kwargs):
             or kwargs["output_hidden_states"] is not None
             or ("use_cache" in kwargs and kwargs["use_cache"] is not None)
         ):
-            tf_logger.warn(
+            tf_logger.warning(
                 "The parameters `output_attentions`, `output_hidden_states` and `use_cache` cannot be updated when calling a model."
                 "They have to be set to True/False in the config object (i.e.: `config=XConfig.from_pretrained('name', output_attentions=True)`)."
             )
@@ -299,7 +299,9 @@ def booleans_processing(config, **kwargs):
         final_booleans["output_hidden_states"] = config.output_hidden_states
 
         if kwargs["return_dict"] is not None:
-            tf_logger.warn("The parameter `return_dict` cannot be set in graph mode and will always be set to `True`.")
+            tf_logger.warning(
+                "The parameter `return_dict` cannot be set in graph mode and will always be set to `True`."
+            )
         final_booleans["return_dict"] = True
 
         if "use_cache" in kwargs:
@@ -398,7 +400,7 @@ def input_processing(func, config, input_ids, **kwargs):
             if isinstance(v, allowed_types) or v is None:
                 output[k] = v
             elif k not in parameter_names and "args" not in parameter_names:
-                logger.warn(
+                logger.warning(
                     f"The parameter {k} does not belongs to the parameter list {parameter_names} and will be ignored."
                 )
                 continue

src/transformers/models/auto/tokenization_auto.py

@@ -409,7 +409,7 @@ class AutoTokenizer:
         # if model is an encoder decoder, the encoder tokenizer class is used by default
         if isinstance(config, EncoderDecoderConfig):
             if type(config.decoder) is not type(config.encoder):  # noqa: E721
-                logger.warn(
+                logger.warning(
                     f"The encoder model config class: {config.encoder.__class__} is different from the decoder model "
                     f"config class: {config.decoder.__class}. It is not recommended to use the "
                     "`AutoTokenizer.from_pretrained()` method in this case. Please use the encoder and decoder "

src/transformers/models/bart/modeling_bart.py

@@ -1011,7 +1011,7 @@ class BartDecoder(BartPretrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/bert/modeling_bert.py

@@ -544,7 +544,7 @@ class BertEncoder(nn.Module):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/bert_generation/modeling_bert_generation.py

@@ -450,7 +450,7 @@ class BertGenerationDecoder(BertGenerationPreTrainedModel):
         super().__init__(config)
 
         if not config.is_decoder:
-            logger.warn("If you want to use `BertGenerationDecoder` as a standalone, add `is_decoder=True.`")
+            logger.warning("If you want to use `BertGenerationDecoder` as a standalone, add `is_decoder=True.`")
 
         self.bert = BertGenerationEncoder(config)
         self.lm_head = BertGenerationOnlyLMHead(config)

src/transformers/models/big_bird/modeling_big_bird.py

@@ -1586,7 +1586,7 @@ class BigBirdEncoder(nn.Module):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/blenderbot/modeling_blenderbot.py

@@ -973,7 +973,7 @@ class BlenderbotDecoder(BlenderbotPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/blenderbot_small/modeling_blenderbot_small.py

@@ -974,7 +974,7 @@ class BlenderbotSmallDecoder(BlenderbotSmallPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/electra/modeling_electra.py

@@ -541,7 +541,7 @@ class ElectraEncoder(nn.Module):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/gpt2/modeling_gpt2.py

@@ -726,7 +726,7 @@ class GPT2Model(GPT2PreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/gpt_neo/modeling_gpt_neo.py

@@ -823,7 +823,7 @@ class GPTNeoModel(GPTNeoPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/layoutlm/modeling_layoutlm.py

@@ -470,7 +470,7 @@ class LayoutLMEncoder(nn.Module):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/led/modeling_led.py

@@ -2070,7 +2070,7 @@ class LEDDecoder(LEDPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/m2m_100/modeling_m2m_100.py

@@ -968,7 +968,7 @@ class M2M100Decoder(M2M100PreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/marian/modeling_marian.py

@@ -981,7 +981,7 @@ class MarianDecoder(MarianPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/mbart/modeling_mbart.py

@@ -1020,7 +1020,7 @@ class MBartDecoder(MBartPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/pegasus/modeling_pegasus.py

@@ -987,7 +987,7 @@ class PegasusDecoder(PegasusPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )

src/transformers/models/prophetnet/modeling_prophetnet.py

@@ -1475,7 +1475,7 @@ class ProphetNetDecoder(ProphetNetPreTrainedModel):
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn(
+                    logger.warning(
                         "`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
                         "`use_cache=False`..."
                     )