Validate Reward Parameters
@Serializable
Parameters for the validate_reward method.
Validates a reinforcement tuning reward configuration against a sample response and example before creating a reinforcement tuning job.
Constructors
Link copied to clipboard
constructor(parent: String? = null, sampleResponse: Content? = null, example: ReinforcementTuningExample? = null, singleRewardConfig: SingleReinforcementTuningRewardConfig? = null, compositeRewardConfig: CompositeReinforcementTuningRewardConfig? = null, config: ValidateRewardConfig? = null)
Properties
Link copied to clipboard
Composite reward function configuration for reinforcement tuning. Mutually exclusive with single_reward_config.
Link copied to clipboard
Optional parameters for the request.
Link copied to clipboard
Required. The example to validate the reward configuration.
Link copied to clipboard
Required. The sample response for validating the reward configuration.
Link copied to clipboard
Single reward function configuration for reinforcement tuning. Mutually exclusive with composite_reward_config.