SageMaker Inference Experiment

Docs > DDSQL Reference > Data Directory > SageMaker Inference Experiment

SageMaker Inference Experiment is an AWS resource that allows you to compare the performance of different machine learning model variants in real-time. It helps you safely test new models against production traffic by routing a portion of requests to each variant and collecting metrics such as accuracy, latency, and cost. This enables data-driven decisions when promoting models to production.

aws.sagemaker_inference_experiment

Fields

ID	Type	Data Type	Description
_key	core	string
account_id	core	string
arn	core	string	The ARN of the inference experiment being described.
completion_time	core	timestamp	The timestamp at which the inference experiment was completed.
creation_time	core	timestamp	The timestamp at which you created the inference experiment.
data_storage_config	core	json	The Amazon S3 location and configuration for storing inference request and response data.
description	core	string	The description of the inference experiment.
endpoint_metadata	core	json	The metadata of the endpoint on which the inference experiment ran.
last_modified_time	core	timestamp	The timestamp at which you last modified the inference experiment.
model_variants	core	json	An array of ModelVariantConfigSummary objects. There is one for each variant in the inference experiment. Each ModelVariantConfigSummary object in the array describes the infrastructure configuration for deploying the corresponding variant.
name	core	string	The name of the inference experiment.
role_arn	core	string	The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and container images, and manage Amazon SageMaker Inference endpoints for model deployment.
schedule	core	json	The duration for which the inference experiment ran or will run.
shadow_mode_config	core	json	The configuration of ShadowMode inference experiment type, which shows the production variant that takes all the inference requests, and the shadow variant to which Amazon SageMaker replicates a percentage of the inference requests. For the shadow variant it also shows the percentage of requests that Amazon SageMaker replicates.
status	core	string	The status of the inference experiment. The following are the possible statuses for an inference experiment: Creating - Amazon SageMaker is creating your experiment. Created - Amazon SageMaker has finished the creation of your experiment and will begin the experiment at the scheduled time. Updating - When you make changes to your experiment, your experiment shows as updating. Starting - Amazon SageMaker is beginning your experiment. Running - Your experiment is in progress. Stopping - Amazon SageMaker is stopping your experiment. Completed - Your experiment has completed. Cancelled - When you conclude your experiment early using the StopInferenceExperiment API, or if any operation fails with an unexpected error, it shows as cancelled.
status_reason	core	string	The error message or client-specified Reason from the StopInferenceExperiment API, that explains the status of the inference experiment.
tags	core	hstore
type	core	string	The type of the inference experiment.