RFTConfig
Configuration settings for reinforcement fine-tuning (RFT), including grader configuration and training hyperparameters.
Contents
- graderConfig
-
Configuration for the grader that evaluates model responses and provides reward signals during RFT training.
Type: GraderConfig object
Note: This object is a Union. Only one member of this object can be specified or returned.
Required: No
- hyperParameters
-
Hyperparameters that control the reinforcement fine-tuning training process, including learning rate, batch size, and epoch count.
Type: RFTHyperParameters object
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
