Fix input data file extension in examples (#28741)

examples/tensorflow/multiple-choice/run_swag.py

@@ -320,9 +320,10 @@ def main():
         data_files = {}
         if data_args.train_file is not None:
             data_files["train"] = data_args.train_file
+            extension = data_args.train_file.split(".")[-1]
         if data_args.validation_file is not None:
             data_files["validation"] = data_args.validation_file
-        extension = data_args.train_file.split(".")[-1]
+            extension = data_args.validation_file.split(".")[-1]
         raw_datasets = load_dataset(
             extension,
             data_files=data_files,

examples/tensorflow/token-classification/run_ner.py

@@ -260,9 +260,10 @@ def main():
         data_files = {}
         if data_args.train_file is not None:
             data_files["train"] = data_args.train_file
+            extension = data_args.train_file.split(".")[-1]
         if data_args.validation_file is not None:
             data_files["validation"] = data_args.validation_file
-        extension = data_args.train_file.split(".")[-1]
+            extension = data_args.validation_file.split(".")[-1]
         raw_datasets = load_dataset(
             extension,
             data_files=data_files,

templates/adding_a_new_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py

@@ -730,9 +730,10 @@ def main():
         data_files = {}
         if args.train_file is not None:
             data_files["train"] = args.train_file
+            extension = args.train_file.split(".")[-1]
         if args.validation_file is not None:
             data_files["validation"] = args.validation_file
-        extension = args.train_file.split(".")[-1]
+            extension = args.validation_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files)
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
     # https://huggingface.co/docs/datasets/loading_datasets.