diff --git a/src/open_r1/grpo.py b/src/open_r1/grpo.py index 1970f8ef..f9a07e2c 100644 --- a/src/open_r1/grpo.py +++ b/src/open_r1/grpo.py @@ -99,7 +99,7 @@ class GRPOScriptArguments(ScriptArguments): SYSTEM_PROMPT = ( - "A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant " + "A conversation between user and assistant. The user asks a question, and the assistant solves it. The assistant " "first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning " "process and answer are enclosed within and tags, respectively, i.e., " " reasoning process here answer here "