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

* The 'warn' method is deprecated

* fix test

examples/language-modeling/run_clm.py

@@ -330,14 +330,14 @@ def main():
     if data_args.block_size is None:
         block_size = tokenizer.model_max_length
         if block_size > 1024:
-            logger.warn(
+            logger.warning(
                 f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). "
                 "Picking 1024 instead. You can change that default value by passing --block_size xxx."
             )
         block_size = 1024
     else:
         if data_args.block_size > tokenizer.model_max_length:
-            logger.warn(
+            logger.warning(
                 f"The block_size passed ({data_args.block_size}) is larger than the maximum length for the model"
                 f"({tokenizer.model_max_length}). Using block_size={tokenizer.model_max_length}."
             )

examples/language-modeling/run_clm_no_trainer.py

@@ -305,14 +305,14 @@ def main():
     if args.block_size is None:
         block_size = tokenizer.model_max_length
         if block_size > 1024:
-            logger.warn(
+            logger.warning(
                 f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). "
                 "Picking 1024 instead. You can change that default value by passing --block_size xxx."
             )
         block_size = 1024
     else:
         if args.block_size > tokenizer.model_max_length:
-            logger.warn(
+            logger.warning(
                 f"The block_size passed ({args.block_size}) is larger than the maximum length for the model"
                 f"({tokenizer.model_max_length}). Using block_size={tokenizer.model_max_length}."
             )

examples/language-modeling/run_mlm.py

@@ -324,14 +324,14 @@ def main():
     if data_args.max_seq_length is None:
         max_seq_length = tokenizer.model_max_length
         if max_seq_length > 1024:
-            logger.warn(
+            logger.warning(
                 f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). "
                 "Picking 1024 instead. You can change that default value by passing --max_seq_length xxx."
             )
             max_seq_length = 1024
     else:
         if data_args.max_seq_length > tokenizer.model_max_length:
-            logger.warn(
+            logger.warning(
                 f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
                 f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
             )

examples/language-modeling/run_mlm_no_trainer.py

@@ -308,14 +308,14 @@ def main():
     if args.max_seq_length is None:
         max_seq_length = tokenizer.model_max_length
         if max_seq_length > 1024:
-            logger.warn(
+            logger.warning(
                 f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). "
                 "Picking 1024 instead. You can change that default value by passing --max_seq_length xxx."
             )
             max_seq_length = 1024
     else:
         if args.max_seq_length > tokenizer.model_max_length:
-            logger.warn(
+            logger.warning(
                 f"The max_seq_length passed ({args.max_seq_length}) is larger than the maximum length for the"
                 f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
             )

examples/language-modeling/run_plm.py

@@ -319,7 +319,7 @@ def main():
     text_column_name = "text" if "text" in column_names else column_names[0]
 
     if data_args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/legacy/question-answering/run_squad.py

@@ -436,7 +436,7 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
                 raise ImportError("If not data_dir is specified, tensorflow_datasets needs to be installed.")
 
             if args.version_2_with_negative:
-                logger.warn("tensorflow_datasets does not handle version 2 of SQuAD.")
+                logger.warning("tensorflow_datasets does not handle version 2 of SQuAD.")
 
             tfds_examples = tfds.load("squad")
             examples = SquadV1Processor().get_examples_from_dataset(tfds_examples, evaluate=evaluate)

examples/legacy/seq2seq/seq2seq_trainer.py

@@ -73,7 +73,7 @@ class Seq2SeqTrainer(Trainer):
             ), "Make sure that `config.pad_token_id` is correcly defined when ignoring `pad_token` for loss calculation or doing label smoothing."
 
         if self.config.pad_token_id is None and self.config.eos_token_id is not None:
-            logger.warn(
+            logger.warning(
                 f"The `config.pad_token_id` is `None`. Using `config.eos_token_id` = {self.config.eos_token_id} for padding.."
             )
 
@@ -127,7 +127,7 @@ class Seq2SeqTrainer(Trainer):
         if self.lr_scheduler is None:
             self.lr_scheduler = self._get_lr_scheduler(num_training_steps)
         else:  # ignoring --lr_scheduler
-            logger.warn("scheduler is passed to `Seq2SeqTrainer`, `--lr_scheduler` arg is ignored.")
+            logger.warning("scheduler is passed to `Seq2SeqTrainer`, `--lr_scheduler` arg is ignored.")
 
     def _get_lr_scheduler(self, num_training_steps):
         schedule_func = arg_to_scheduler[self.args.lr_scheduler]

examples/multiple-choice/run_swag.py

@@ -310,14 +310,14 @@ def main():
     if data_args.max_seq_length is None:
         max_seq_length = tokenizer.model_max_length
         if max_seq_length > 1024:
-            logger.warn(
+            logger.warning(
                 f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). "
                 "Picking 1024 instead. You can change that default value by passing --max_seq_length xxx."
             )
             max_seq_length = 1024
     else:
         if data_args.max_seq_length > tokenizer.model_max_length:
-            logger.warn(
+            logger.warning(
                 f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
                 f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
             )

examples/question-answering/run_qa.py

@@ -324,7 +324,7 @@ def main():
     pad_on_right = tokenizer.padding_side == "right"
 
     if data_args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/question-answering/run_qa_beam_search.py

@@ -313,7 +313,7 @@ def main():
     pad_on_right = tokenizer.padding_side == "right"
 
     if data_args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/question-answering/run_qa_beam_search_no_trainer.py

@@ -291,7 +291,7 @@ def main():
     pad_on_right = tokenizer.padding_side == "right"
 
     if args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/question-answering/run_qa_no_trainer.py

@@ -343,7 +343,7 @@ def main():
     pad_on_right = tokenizer.padding_side == "right"
 
     if args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/question-answering/run_tf_squad.py

@@ -181,7 +181,7 @@ def main():
     # Get datasets
     if data_args.use_tfds:
         if data_args.version_2_with_negative:
-            logger.warn("tensorflow_datasets does not handle version 2 of SQuAD. Switch to version 1 automatically")
+            logger.warning("tensorflow_datasets does not handle version 2 of SQuAD. Switch to version 1 automatically")
 
         try:
             import tensorflow_datasets as tfds

examples/research_projects/movement-pruning/masked_run_squad.py

@@ -629,7 +629,7 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
                 raise ImportError("If not data_dir is specified, tensorflow_datasets needs to be installed.")
 
             if args.version_2_with_negative:
-                logger.warn("tensorflow_datasets does not handle version 2 of SQuAD.")
+                logger.warning("tensorflow_datasets does not handle version 2 of SQuAD.")
 
             tfds_examples = tfds.load("squad")
             examples = SquadV1Processor().get_examples_from_dataset(tfds_examples, evaluate=evaluate)

examples/seq2seq/run_summarization.py

@@ -394,7 +394,7 @@ def main():
     padding = "max_length" if data_args.pad_to_max_length else False
 
     if training_args.label_smoothing_factor > 0 and not hasattr(model, "prepare_decoder_input_ids_from_labels"):
-        logger.warn(
+        logger.warning(
             "label_smoothing is enabled but the `prepare_decoder_input_ids_from_labels` method is not defined for"
             f"`{model.__class__.__name__}`. This will lead to loss being calculated twice and will take up more memory"
         )

examples/seq2seq/run_translation.py

@@ -367,7 +367,7 @@ def main():
     padding = "max_length" if data_args.pad_to_max_length else False
 
     if training_args.label_smoothing_factor > 0 and not hasattr(model, "prepare_decoder_input_ids_from_labels"):
-        logger.warn(
+        logger.warning(
             "label_smoothing is enabled but the `prepare_decoder_input_ids_from_labels` method is not defined for"
             f"`{model.__class__.__name__}`. This will lead to loss being calculated twice and will take up more memory"
         )

examples/text-classification/run_glue.py

@@ -351,7 +351,7 @@ def main():
         if list(sorted(label_name_to_id.keys())) == list(sorted(label_list)):
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
-            logger.warn(
+            logger.warning(
                 "Your model seems to have been trained with labels, but they don't match the dataset: ",
                 f"model labels: {list(sorted(label_name_to_id.keys()))}, dataset labels: {list(sorted(label_list))}."
                 "\nIgnoring the model labels as a result.",
@@ -360,7 +360,7 @@ def main():
         label_to_id = {v: i for i, v in enumerate(label_list)}
 
     if data_args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

examples/text-classification/run_glue_no_trainer.py

@@ -274,7 +274,7 @@ def main():
             )
             label_to_id = {i: label_name_to_id[label_list[i]] for i in range(num_labels)}
         else:
-            logger.warn(
+            logger.warning(
                 "Your model seems to have been trained with labels, but they don't match the dataset: ",
                 f"model labels: {list(sorted(label_name_to_id.keys()))}, dataset labels: {list(sorted(label_list))}."
                 "\nIgnoring the model labels as a result.",

src/transformers/configuration_utils.py

@@ -262,7 +262,7 @@ class PretrainedConfig(object):
 
         # TPU arguments
         if kwargs.pop("xla_device", None) is not None:
-            logger.warn(
+            logger.warning(
                 "The `xla_device` argument has been deprecated in v4.4.0 of Transformers. It is ignored and you can "
                 "safely remove it from your `config.json` file."
             )

src/transformers/data/datasets/squad.py

@@ -152,7 +152,7 @@ class SquadDataset(Dataset):
                 )
 
                 if self.dataset is None or self.examples is None:
-                    logger.warn(
+                    logger.warning(
                         f"Deleting cached file {cached_features_file} will allow dataset and examples to be cached in future run"
                     )
             else:

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`..."
                     )

src/transformers/models/roberta/modeling_roberta.py

@@ -484,7 +484,7 @@ class RobertaEncoder(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/speech_to_text/modeling_speech_to_text.py

@@ -1015,7 +1015,7 @@ class Speech2TextDecoder(Speech2TextPreTrainedModel):
             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`..."
                     )
                     use_cache = False

src/transformers/models/wav2vec2/convert_wav2vec2_original_pytorch_checkpoint_to_pytorch.py

@@ -111,7 +111,7 @@ def recursively_load_weights(fairseq_model, hf_model, is_finetuned):
         if not is_used:
             unused_weights.append(name)
 
-    logger.warn(f"Unused weights: {unused_weights}")
+    logger.warning(f"Unused weights: {unused_weights}")
 
 
 def load_conv_layer(full_name, value, feature_extractor, unused_weights, use_group_norm):

src/transformers/models/xlm/modeling_tf_xlm.py

@@ -1140,7 +1140,7 @@ class TFXLMForMultipleChoice(TFXLMPreTrainedModel, TFMultipleChoiceLoss):
         )
 
         if inputs["lengths"] is not None:
-            logger.warn(
+            logger.warning(
                 "The `lengths` parameter cannot be used with the XLM multiple choice models. Please use the "
                 "attention mask instead.",
             )

src/transformers/models/xlm/modeling_xlm.py

@@ -1232,7 +1232,7 @@ class XLMForMultipleChoice(XLMPreTrainedModel):
         )
 
         if lengths is not None:
-            logger.warn(
+            logger.warning(
                 "The `lengths` parameter cannot be used with the XLM multiple choice models. Please use the "
                 "attention mask instead."
             )

src/transformers/pipelines/zero_shot_classification.py

@@ -142,7 +142,7 @@ class ZeroShotClassificationPipeline(Pipeline):
         """
         if "multi_class" in kwargs and kwargs["multi_class"] is not None:
             multi_label = kwargs.pop("multi_class")
-            logger.warn(
+            logger.warning(
                 "The `multi_class` argument has been deprecated and renamed to `multi_label`. "
                 "`multi_class` will be removed in a future version of Transformers."
             )

src/transformers/trainer_callback.py

@@ -289,7 +289,7 @@ class CallbackHandler(TrainerCallback):
         self.eval_dataloader = None
 
         if not any(isinstance(cb, DefaultFlowCallback) for cb in self.callbacks):
-            logger.warn(
+            logger.warning(
                 "The Trainer will not work properly if you don't have a `DefaultFlowCallback` in its callbacks. You\n"
                 + "should add one before training with `trainer.add_callback(DefaultFlowCallback). The current list of"
                 + "callbacks is\n:"
@@ -300,7 +300,7 @@ class CallbackHandler(TrainerCallback):
         cb = callback() if isinstance(callback, type) else callback
         cb_class = callback if isinstance(callback, type) else callback.__class__
         if cb_class in [c.__class__ for c in self.callbacks]:
-            logger.warn(
+            logger.warning(
                 f"You are adding a {cb_class} to the callbacks of this Trainer, but there is already one. The current"
                 + "list of callbacks is\n:"
                 + self.callback_list

src/transformers/trainer_pt_utils.py

@@ -391,7 +391,7 @@ class DistributedTensorGatherer:
         if self._storage is None:
             return
         if self._offsets[0] != self.process_length:
-            logger.warn("Not all data has been set. Are you sure you passed all values?")
+            logger.warning("Not all data has been set. Are you sure you passed all values?")
         return nested_truncate(self._storage, self.num_samples)
 
 
@@ -589,7 +589,7 @@ def _get_learning_rate(self):
             last_lr = self.lr_scheduler.get_last_lr()[0]
         except AssertionError as e:
             if "need to call step" in str(e):
-                logger.warn("tried to get lr value before scheduler/optimizer started stepping, returning lr=0")
+                logger.warning("tried to get lr value before scheduler/optimizer started stepping, returning lr=0")
                 last_lr = 0
             else:
                 raise

templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py

@@ -531,7 +531,7 @@ class {{cookiecutter.camelcase_modelname}}Encoder(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`..."
                     )
@@ -2512,7 +2512,7 @@ class {{cookiecutter.camelcase_modelname}}Decoder({{cookiecutter.camelcase_model
             if getattr(self.config, "gradient_checkpointing", False) and self.training:
 
                 if use_cache:
-                    logger.warn("`use_cache = True` is incompatible with `config.gradient_checkpointing = True`. Setting `use_cache = False`...")
+                    logger.warning("`use_cache = True` is incompatible with `config.gradient_checkpointing = True`. Setting `use_cache = False`...")
                     use_cache = False
 
                 def create_custom_forward(module):

tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py

@@ -353,7 +353,7 @@ def main():
         if list(sorted(label_name_to_id.keys())) == list(sorted(label_list)):
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
-            logger.warn(
+            logger.warning(
                 "Your model seems to have been trained with labels, but they don't match the dataset: ",
                 f"model labels: {list(sorted(label_name_to_id.keys()))}, dataset labels: {list(sorted(label_list))}."
                 "\nIgnoring the model labels as a result.",
@@ -362,7 +362,7 @@ def main():
         label_to_id = {v: i for i, v in enumerate(label_list)}
 
     if data_args.max_seq_length > tokenizer.model_max_length:
-        logger.warn(
+        logger.warning(
             f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )

tests/test_logging.py

@@ -51,7 +51,7 @@ class HfArgumentParserTest(unittest.TestCase):
         # should be able to log warnings (if default settings weren't overridden by `pytest --log-level-all`)
         if level_origin <= logging.WARNING:
             with CaptureLogger(logger) as cl:
-                logger.warn(msg)
+                logger.warning(msg)
             self.assertEqual(cl.out, msg + "\n")
 
         # this is setting the level for all of `transformers.*` loggers
@@ -59,7 +59,7 @@ class HfArgumentParserTest(unittest.TestCase):
 
         # should not be able to log warnings
         with CaptureLogger(logger) as cl:
-            logger.warn(msg)
+            logger.warning(msg)
         self.assertEqual(cl.out, "")
 
         # should be able to log warnings again

tests/test_trainer_callback.py

@@ -234,7 +234,7 @@ class TrainerCallbackTest(unittest.TestCase):
         self.assertEqual(events, self.get_expected_events(trainer))
 
         # warning should be emitted for duplicated callbacks
-        with unittest.mock.patch("transformers.trainer_callback.logger.warn") as warn_mock:
+        with unittest.mock.patch("transformers.trainer_callback.logger.warning") as warn_mock:
             trainer = self.get_trainer(
                 callbacks=[MyTestTrainerCallback, MyTestTrainerCallback],
             )