Add better logging defaults for GRPO

setup.py

@@ -116,7 +116,7 @@ def deps_list(*pkgs):
     deps["transformers"],
     deps["trl"],
     deps["wandb"],
-    deps["async-lru"]
+    deps["async-lru"],
 ]
 
 setup(

src/open_r1/configs.py

@@ -136,15 +136,22 @@ class GRPOConfig(trl.GRPOConfig):
         metadata={"help": "The callbacks to run during training."},
     )
     chat_template: Optional[str] = field(default=None, metadata={"help": "The chat template to use."})
-    system_prompt: Optional[str] = field(
-        default=None,
-        metadata={"help": "The optional system prompt to use."},
-    )
     hub_model_revision: Optional[str] = field(
         default="main", metadata={"help": "The Hub model branch to push the model to."}
     )
+    num_completions_to_print: int = field(default=0, metadata={"help": "Number of completions to print."})
     overwrite_hub_revision: bool = field(default=False, metadata={"help": "Whether to overwrite the Hub revision."})
     push_to_hub_revision: bool = field(default=False, metadata={"help": "Whether to push to a Hub revision/branch."})
+    system_prompt: Optional[str] = field(
+        default=None,
+        metadata={"help": "The optional system prompt to use."},
+    )
+    wandb_log_unique_prompts: bool = field(
+        default=True,
+        metadata={
+            "help": ("Whether to log the unique prompts to wandb. This will create a new run for each unique prompt.")
+        },
+    )
     wandb_entity: Optional[str] = field(
         default=None,
         metadata={"help": ("The entity to store runs under.")},

src/open_r1/utils/competitive_programming/cf_scoring.py

@@ -61,6 +61,7 @@ async def get_generated_contest_tests(contest_id: str) -> list[dict]:
 
     import aiofiles
     import aiofiles.os
+
     tests_folder = os.environ.get("CF_TESTS_FOLDER", None)
     if not tests_folder:
         raise ValueError(