Evaluating your trained model

An evaluation recipe is a YAML configuration file that defines how Amazon Nova model evaluation jobs are executed. This process allows you to assess the performance of either base or customized models against standard benchmarks or your own custom datasets. The evaluation generates quantitative metrics that help determine if additional model customization is needed, with results that can be stored in Amazon S3 or visualized in TensorBoard.

For more information about evaluating your trained Amazon Nova on SageMaker HyperPod, see the Evaluating your model topic from the Amazon Nova User Guide.