update examples after ruff being updated (#36972)

* update

* update

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

examples/pytorch/language-modeling/run_clm.py

@@ -438,7 +438,7 @@ def main():
     else:
         model = AutoModelForCausalLM.from_config(config, trust_remote_code=model_args.trust_remote_code)
         n_params = sum({p.data_ptr(): p.numel() for p in model.parameters()}.values())
-        logger.info(f"Training new model from scratch - Total size={n_params/2**20:.2f}M params")
+        logger.info(f"Training new model from scratch - Total size={n_params / 2**20:.2f}M params")
 
     # We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch
     # on a small vocab and want a smaller embedding size, remove this test.

examples/pytorch/language-modeling/run_fim.py

@@ -265,8 +265,7 @@ class DataTrainingArguments:
         default="<fim_pad>",
         metadata={
             "help": (
-                "Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. "
-                "Defaults to '<fim_pad>'."
+                "Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. Defaults to '<fim_pad>'."
             )
         },
     )
@@ -514,7 +513,7 @@ def main():
             attn_implementation=model_args.attn_implementation,
         )
         n_params = sum({p.data_ptr(): p.numel() for p in model.parameters()}.values())
-        logger.info(f"Training new model from scratch - Total size={n_params/2**20:.2f}M params")
+        logger.info(f"Training new model from scratch - Total size={n_params / 2**20:.2f}M params")
 
     # Add the new FIM tokens to the tokenizer and resize model's vocab embeddings
     special_tokens = [data_args.fim_prefix_token, data_args.fim_middle_token, data_args.fim_suffix_token]

examples/pytorch/language-modeling/run_fim_no_trainer.py

@@ -234,9 +234,7 @@ def parse_args():
         "--fim_pad_token",
         type=str,
         default="<fim_pad>",
-        help=(
-            "Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True." " Defaults to '<fim_pad>'."
-        ),
+        help=("Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. Defaults to '<fim_pad>'."),
     )
     parser.add_argument(
         "--preprocessing_num_workers",

examples/pytorch/speech-recognition/run_speech_recognition_ctc.py

@@ -491,7 +491,7 @@ def main():
     # E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
     # that could be easily picked up by the model
     chars_to_ignore_regex = (
-        f'[{"".join(data_args.chars_to_ignore)}]' if data_args.chars_to_ignore is not None else None
+        f"[{''.join(data_args.chars_to_ignore)}]" if data_args.chars_to_ignore is not None else None
     )
     text_column_name = data_args.text_column_name
 

examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py

@@ -471,7 +471,7 @@ def main():
     # E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
     # that could be easily picked up by the model
     chars_to_ignore_regex = (
-        f'[{"".join(data_args.chars_to_ignore)}]' if data_args.chars_to_ignore is not None else None
+        f"[{''.join(data_args.chars_to_ignore)}]" if data_args.chars_to_ignore is not None else None
     )
     text_column_name = data_args.text_column_name
 

examples/pytorch/summarization/run_summarization.py

@@ -505,9 +505,9 @@ def main():
         return
 
     if isinstance(tokenizer, tuple(MULTILINGUAL_TOKENIZERS)):
-        assert (
-            data_args.lang is not None
-        ), f"{tokenizer.__class__.__name__} is a multilingual tokenizer which requires --lang argument"
+        assert data_args.lang is not None, (
+            f"{tokenizer.__class__.__name__} is a multilingual tokenizer which requires --lang argument"
+        )
 
         tokenizer.src_lang = data_args.lang
         tokenizer.tgt_lang = data_args.lang

examples/pytorch/text-classification/run_classification.py

@@ -199,9 +199,9 @@ class DataTrainingArguments:
             train_extension = self.train_file.split(".")[-1]
             assert train_extension in ["csv", "json"], "`train_file` should be a csv or a json file."
             validation_extension = self.validation_file.split(".")[-1]
-            assert (
-                validation_extension == train_extension
-            ), "`validation_file` should have the same extension (csv or json) as `train_file`."
+            assert validation_extension == train_extension, (
+                "`validation_file` should have the same extension (csv or json) as `train_file`."
+            )
 
 
 @dataclass
@@ -357,9 +357,9 @@ def main():
             if data_args.test_file is not None:
                 train_extension = data_args.train_file.split(".")[-1]
                 test_extension = data_args.test_file.split(".")[-1]
-                assert (
-                    test_extension == train_extension
-                ), "`test_file` should have the same extension (csv or json) as `train_file`."
+                assert test_extension == train_extension, (
+                    "`test_file` should have the same extension (csv or json) as `train_file`."
+                )
                 data_files["test"] = data_args.test_file
             else:
                 raise ValueError("Need either a dataset name or a test file for `do_predict`.")

examples/pytorch/text-classification/run_glue.py

@@ -156,9 +156,9 @@ class DataTrainingArguments:
             train_extension = self.train_file.split(".")[-1]
             assert train_extension in ["csv", "json"], "`train_file` should be a csv or a json file."
             validation_extension = self.validation_file.split(".")[-1]
-            assert (
-                validation_extension == train_extension
-            ), "`validation_file` should have the same extension (csv or json) as `train_file`."
+            assert validation_extension == train_extension, (
+                "`validation_file` should have the same extension (csv or json) as `train_file`."
+            )
 
 
 @dataclass
@@ -313,9 +313,9 @@ def main():
             if data_args.test_file is not None:
                 train_extension = data_args.train_file.split(".")[-1]
                 test_extension = data_args.test_file.split(".")[-1]
-                assert (
-                    test_extension == train_extension
-                ), "`test_file` should have the same extension (csv or json) as `train_file`."
+                assert test_extension == train_extension, (
+                    "`test_file` should have the same extension (csv or json) as `train_file`."
+                )
                 data_files["test"] = data_args.test_file
             else:
                 raise ValueError("Need either a GLUE task or a test file for `do_predict`.")

examples/pytorch/text-generation/run_generation.py

@@ -322,7 +322,7 @@ def main():
     parser.add_argument(
         "--use_cpu",
         action="store_true",
-        help="Whether or not to use cpu. If set to False, " "we will use gpu/npu or mps device if available",
+        help="Whether or not to use cpu. If set to False, we will use gpu/npu or mps device if available",
     )
     parser.add_argument("--num_return_sequences", type=int, default=1, help="The number of samples to generate.")
     parser.add_argument(

examples/pytorch/text-generation/run_generation_contrastive_search.py

@@ -68,7 +68,7 @@ def main():
     parser.add_argument(
         "--use_cpu",
         action="store_true",
-        help="Whether or not to use cpu. If set to False, " "we will use gpu/npu or mps device if available",
+        help="Whether or not to use cpu. If set to False, we will use gpu/npu or mps device if available",
     )
     parser.add_argument(
         "--fp16",

examples/pytorch/translation/run_translation_no_trainer.py

@@ -436,9 +436,9 @@ def main():
 
     # Set decoder_start_token_id
     if model.config.decoder_start_token_id is None and isinstance(tokenizer, (MBartTokenizer, MBartTokenizerFast)):
-        assert (
-            args.target_lang is not None and args.source_lang is not None
-        ), "mBart requires --target_lang and --source_lang"
+        assert args.target_lang is not None and args.source_lang is not None, (
+            "mBart requires --target_lang and --source_lang"
+        )
         if isinstance(tokenizer, MBartTokenizer):
             model.config.decoder_start_token_id = tokenizer.lang_code_to_id[args.target_lang]
         else: