Request Syntax Request Parameters Response Syntax Response Elements Errors See Also

CreateOptimizationJob

Creates a job that optimizes a model for inference performance. To create the job, you provide the location of a source model, and you provide the settings for the optimization techniques that you want the job to apply. When the job completes successfully, SageMaker uploads the new optimized model to the output destination that you specify.

For more information about how to use this action, and about the supported optimization techniques, see Optimize model inference with Amazon SageMaker.

Request Syntax


{
   "DeploymentInstanceType": "string",
   "ModelSource": { 
      "S3": { 
         "ModelAccessConfig": { 
            "AcceptEula": boolean
         },
         "S3Uri": "string"
      }
   },
   "OptimizationConfigs": [ 
      { ... }
   ],
   "OptimizationEnvironment": { 
      "string" : "string" 
   },
   "OptimizationJobName": "string",
   "OutputConfig": { 
      "KmsKeyId": "string",
      "S3OutputLocation": "string"
   },
   "RoleArn": "string",
   "StoppingCondition": { 
      "MaxPendingTimeInSeconds": number,
      "MaxRuntimeInSeconds": number,
      "MaxWaitTimeInSeconds": number
   },
   "Tags": [ 
      { 
         "Key": "string",
         "Value": "string"
      }
   ],
   "VpcConfig": { 
      "SecurityGroupIds": [ "string" ],
      "Subnets": [ "string" ]
   }
}

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

DeploymentInstanceType

The type of instance that hosts the optimized model that you create with the optimization job.

Type: String

Required: Yes

ModelSource

The location of the source model to optimize with an optimization job.

Type: OptimizationJobModelSource object

Required: Yes

OptimizationConfigs

Settings for each of the optimization techniques that the job applies.

Type: Array of OptimizationConfig objects

Array Members: Maximum number of 10 items.

Required: Yes

OptimizationEnvironment

The environment variables to set in the model container.

Type: String to string map

Map Entries: Maximum number of 25 items.

Key Length Constraints: Maximum length of 256.

Key Pattern: ^(?!\s*$).+

Value Length Constraints: Maximum length of 256.

Required: No

OptimizationJobName

A custom name for the new optimization job.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 63.

Pattern: ^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$

Required: Yes

OutputConfig

Details for where to store the optimized model that you create with the optimization job.

Type: OptimizationJobOutputConfig object

Required: Yes

RoleArn

The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker to perform tasks on your behalf.

During model optimization, Amazon SageMaker needs your permission to:

Read input data from an S3 bucket
Write model artifacts to an S3 bucket
Write logs to Amazon CloudWatch Logs
Publish metrics to Amazon CloudWatch

You grant permissions for all of these tasks to an IAM role. To pass this role to Amazon SageMaker, the caller of this API must have the iam:PassRole permission. For more information, see Amazon SageMaker Roles.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: ^arn:aws[a-z\-]*:iam::\d{12}:role/?[a-zA-Z_0-9+=,.@\-_/]+$

Required: Yes

StoppingCondition

Specifies a limit to how long a job can run. When the job reaches the time limit, SageMaker ends the job. Use this API to cap costs.

To stop a training job, SageMaker sends the algorithm the SIGTERM signal, which delays job termination for 120 seconds. Algorithms can use this 120-second window to save the model artifacts, so the results of training are not lost.

The training algorithms provided by SageMaker automatically save the intermediate results of a model training job when possible. This attempt to save artifacts is only a best effort case as model might not be in a state from which it can be saved. For example, if training has just started, the model might not be ready to save. When saved, this intermediate data is a valid model artifact. You can use it to create a model with CreateModel.

Note

The Neural Topic Model (NTM) currently does not support saving intermediate model artifacts. When training NTMs, make sure that the maximum runtime is sufficient for the training job to complete.

Type: StoppingCondition object

Required: Yes

Tags