RftConfig

Configuration settings for reinforcement fine-tuning (RFT), including grader configuration and training hyperparameters.

Types

Configuration for the grader that evaluates model responses and provides reward signals during RFT training.

Hyperparameters that control the reinforcement fine-tuning training process, including learning rate, batch size, and epoch count.

open operator override fun equals(other: Any?): Boolean

open override fun hashCode(): Int

open override fun toString(): String