LambdaGraderConfig
Configuration for using an AWS Lambda function to grade model responses during reinforcement fine-tuning training.
Contents
- lambdaArn
-
ARN of the AWS Lambda function that will evaluate model responses and return reward scores for RFT training.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 512.
Pattern:
arn:(aws[a-zA-Z-]*)?:lambda:[a-z]{2}(-gov)?-[a-z]+-\d{1}:\d{12}:function:[a-zA-Z0-9-_\.]+(:(\$LATEST|[a-zA-Z0-9-_]+))?Required: Yes
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: