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: