Pass datasets trust_remote_code (#31406)

* Pass datasets trust_remote_code

* Pass trust_remote_code in more tests

* Add trust_remote_dataset_code arg to some tests

* Revert "Temporarily pin datasets upper version to fix CI"

This reverts commit b7672826ca.

* Pass trust_remote_code in librispeech_asr_dummy docstrings

* Revert "Pin datasets<2.20.0 for examples"

This reverts commit 833fc17a3e.

* Pass trust_remote_code to all examples

* Revert "Add trust_remote_dataset_code arg to some tests" to research_projects

* Pass trust_remote_code to tests

* Pass trust_remote_code to docstrings

* Fix flax examples tests requirements

* Pass trust_remote_dataset_code arg to tests

* Replace trust_remote_dataset_code with trust_remote_code in one example

* Fix duplicate trust_remote_code

* Replace args.trust_remote_dataset_code with args.trust_remote_code

* Replace trust_remote_dataset_code with trust_remote_code in parser

* Replace trust_remote_dataset_code with trust_remote_code in dataclasses

* Replace trust_remote_dataset_code with trust_remote_code arg

examples/pytorch/image-pretraining/run_mae.py

@@ -63,6 +63,16 @@ class DataTrainingArguments:
     dataset_config_name: Optional[str] = field(
         default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
     )
+    trust_remote_code: bool = field(
+        default=False,
+        metadata={
+            "help": (
+                "Whether to trust the execution of code from datasets/models defined on the Hub."
+                " This option should only be set to `True` for repositories you trust and in which you have read the"
+                " code, as it will execute code present on the Hub on your local machine."
+            )
+        },
+    )
     image_column_name: Optional[str] = field(
         default=None, metadata={"help": "The column name of the images in the files."}
     )
@@ -225,6 +235,7 @@ def main():
         data_files=data_args.data_files,
         cache_dir=model_args.cache_dir,
         token=model_args.token,
+        trust_remote_code=data_args.trust_remote_code,
     )
 
     # If we don't have a validation split, split off a percentage of train as validation.

examples/pytorch/image-pretraining/run_mim.py

@@ -166,9 +166,9 @@ class ModelArguments:
         default=False,
         metadata={
             "help": (
-                "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option "
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
-                "execute code present on the Hub on your local machine."
+                "Whether to trust the execution of code from datasets/models defined on the Hub."
+                " This option should only be set to `True` for repositories you trust and in which you have read the"
+                " code, as it will execute code present on the Hub on your local machine."
             )
         },
     )
@@ -299,6 +299,7 @@ def main():
         data_files=data_args.data_files,
         cache_dir=model_args.cache_dir,
         token=model_args.token,
+        trust_remote_code=model_args.trust_remote_code,
     )
 
     # If we don't have a validation split, split off a percentage of train as validation.

examples/pytorch/image-pretraining/run_mim_no_trainer.py

@@ -197,12 +197,11 @@ def parse_args():
     )
     parser.add_argument(
         "--trust_remote_code",
-        type=bool,
-        default=False,
+        action="store_true",
         help=(
-            "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option "
-            "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
-            "execute code present on the Hub on your local machine."
+            "Whether to trust the execution of code from datasets/models defined on the Hub."
+            " This option should only be set to `True` for repositories you trust and in which you have read the"
+            " code, as it will execute code present on the Hub on your local machine."
         ),
     )
     parser.add_argument(
@@ -441,6 +440,7 @@ def main():
         data_files=args.data_files,
         cache_dir=args.cache_dir,
         token=args.token,
+        trust_remote_code=args.trust_remote_code,
     )
 
     # If we don't have a validation split, split off a percentage of train as validation.