diff --git a/environments/gsm8k_server.py b/environments/gsm8k_server.py index 6809f381..21d3c696 100644 --- a/environments/gsm8k_server.py +++ b/environments/gsm8k_server.py @@ -122,7 +122,7 @@ class GSM8kEnv(BaseEnv): async def rollout_and_score_eval(self, question: str, answer: str) -> dict: """Rollout and score evaluation with detailed sample data collection.""" - + async with self.server.managed_server(tokenizer=self.tokenizer) as managed: completion = await managed.chat_completion( messages=[