Evaluator
- reward_model (BaseRewardModel): A reward model to evaluate messages.
init
evaluate
- messages (List[Dict[str, str]]): A list of messages where each message is a dictionary with ‘role’ and ‘content’.
filter_data
- messages (List[Dict[str, str]]): A list of messages where each message is a dictionary with ‘role’ and ‘content’.
- thresholds (Dict[str, float]): A dictionary mapping score types to their values.