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/language-modeling/run_clm.py

@@ -124,9 +124,9 @@ 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."
             )
         },
     )
@@ -312,6 +312,7 @@ def main():
             cache_dir=model_args.cache_dir,
             token=model_args.token,
             streaming=data_args.streaming,
+            trust_remote_code=model_args.trust_remote_code,
         )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
@@ -321,6 +322,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 data_args.dataset_name,
@@ -329,6 +331,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -195,12 +195,11 @@ def parse_args():
     parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.")
     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(
@@ -327,17 +326,21 @@ def main():
     # download the dataset.
     if args.dataset_name is not None:
         # Downloading and loading a dataset from the hub.
-        raw_datasets = load_dataset(args.dataset_name, args.dataset_config_name)
+        raw_datasets = load_dataset(
+            args.dataset_name, args.dataset_config_name, trust_remote_code=args.trust_remote_code
+        )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[:{args.validation_split_percentage}%]",
+                trust_remote_code=args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[{args.validation_split_percentage}%:]",
+                trust_remote_code=args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_fim.py

@@ -127,9 +127,9 @@ 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."
             )
         },
     )
@@ -382,6 +382,7 @@ def main():
             cache_dir=model_args.cache_dir,
             token=model_args.token,
             streaming=data_args.streaming,
+            trust_remote_code=model_args.trust_remote_code,
         )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
@@ -391,6 +392,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 data_args.dataset_name,
@@ -399,6 +401,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_fim_no_trainer.py

@@ -257,12 +257,11 @@ def parse_args():
     parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.")
     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(
@@ -395,17 +394,21 @@ def main():
     # download the dataset.
     if args.dataset_name is not None:
         # Downloading and loading a dataset from the hub.
-        raw_datasets = load_dataset(args.dataset_name, args.dataset_config_name)
+        raw_datasets = load_dataset(
+            args.dataset_name, args.dataset_config_name, trust_remote_code=args.trust_remote_code
+        )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[:{args.validation_split_percentage}%]",
+                trust_remote_code=args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[{args.validation_split_percentage}%:]",
+                trust_remote_code=args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_mlm.py

@@ -121,9 +121,9 @@ 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."
             )
         },
     )
@@ -324,6 +324,7 @@ def main():
             cache_dir=model_args.cache_dir,
             token=model_args.token,
             streaming=data_args.streaming,
+            trust_remote_code=model_args.trust_remote_code,
         )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
@@ -333,6 +334,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 data_args.dataset_name,
@@ -341,6 +343,7 @@ def main():
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
                 streaming=data_args.streaming,
+                trust_remote_code=model_args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -202,12 +202,11 @@ def parse_args():
     parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.")
     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(
@@ -334,17 +333,21 @@ def main():
     # download the dataset.
     if args.dataset_name is not None:
         # Downloading and loading a dataset from the hub.
-        raw_datasets = load_dataset(args.dataset_name, args.dataset_config_name)
+        raw_datasets = load_dataset(
+            args.dataset_name, args.dataset_config_name, trust_remote_code=args.trust_remote_code
+        )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[:{args.validation_split_percentage}%]",
+                trust_remote_code=args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 args.dataset_name,
                 args.dataset_config_name,
                 split=f"train[{args.validation_split_percentage}%:]",
+                trust_remote_code=args.trust_remote_code,
             )
     else:
         data_files = {}

examples/pytorch/language-modeling/run_plm.py

@@ -133,6 +133,16 @@ 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."
+            )
+        },
+    )
     train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
     validation_file: Optional[str] = field(
         default=None,
@@ -292,6 +302,7 @@ def main():
             data_args.dataset_config_name,
             cache_dir=model_args.cache_dir,
             token=model_args.token,
+            trust_remote_code=data_args.trust_remote_code,
         )
         if "validation" not in raw_datasets.keys():
             raw_datasets["validation"] = load_dataset(
@@ -300,6 +311,7 @@ def main():
                 split=f"train[:{data_args.validation_split_percentage}%]",
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
+                trust_remote_code=data_args.trust_remote_code,
             )
             raw_datasets["train"] = load_dataset(
                 data_args.dataset_name,
@@ -307,6 +319,7 @@ def main():
                 split=f"train[{data_args.validation_split_percentage}%:]",
                 cache_dir=model_args.cache_dir,
                 token=model_args.token,
+                trust_remote_code=data_args.trust_remote_code,
             )
     else:
         data_files = {}