This product is not supported for your selected Datadog site. ().
This page is not yet available in Spanish. We are working on its translation.
If you have any questions or feedback about our current translation project, feel free to reach out to us!

aws_sagemaker_inferencerecommendationjob

account_id

Type: STRING

completion_time

Type: TIMESTAMP
Provider name: CompletionTime
Description: A timestamp that shows when the job completed.

creation_time

Type: TIMESTAMP
Provider name: CreationTime
Description: A timestamp that shows when the job was created.

endpoint_performances

Type: UNORDERED_LIST_STRUCT
Provider name: EndpointPerformances
Description: The performance results from running an Inference Recommender job on an existing endpoint.

  • endpoint_info
    Type: STRUCT
    Provider name: EndpointInfo
    • endpoint_name
      Type: STRING
      Provider name: EndpointName
      Description: The name of a customer’s endpoint.
  • metrics
    Type: STRUCT
    Provider name: Metrics
    Description: The metrics for an existing endpoint.
    • max_invocations
      Type: INT32
      Provider name: MaxInvocations
      Description: The expected maximum number of requests per minute for the instance.
    • model_latency
      Type: INT32
      Provider name: ModelLatency
      Description: The expected model latency at maximum invocations per minute for the instance.

failure_reason

Type: STRING
Provider name: FailureReason
Description: If the job fails, provides information why the job failed.

inference_recommendations

Type: UNORDERED_LIST_STRUCT
Provider name: InferenceRecommendations
Description: The recommendations made by Inference Recommender.

  • endpoint_configuration
    Type: STRUCT
    Provider name: EndpointConfiguration
    Description: Defines the endpoint configuration parameters.
    • endpoint_name
      Type: STRING
      Provider name: EndpointName
      Description: The name of the endpoint made during a recommendation job.
    • initial_instance_count
      Type: INT32
      Provider name: InitialInstanceCount
      Description: The number of instances recommended to launch initially.
    • instance_type
      Type: STRING
      Provider name: InstanceType
      Description: The instance type recommended by Amazon SageMaker Inference Recommender.
    • serverless_config
      Type: STRUCT
      Provider name: ServerlessConfig
      • max_concurrency
        Type: INT32
        Provider name: MaxConcurrency
        Description: The maximum number of concurrent invocations your serverless endpoint can process.
      • memory_size_in_mb
        Type: INT32
        Provider name: MemorySizeInMB
        Description: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
      • provisioned_concurrency
        Type: INT32
        Provider name: ProvisionedConcurrency
        Description: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency. This field is not supported for serverless endpoint recommendations for Inference Recommender jobs. For more information about creating an Inference Recommender job, see CreateInferenceRecommendationsJobs.
    • variant_name
      Type: STRING
      Provider name: VariantName
      Description: The name of the production variant (deployed model) made during a recommendation job.
  • invocation_end_time
    Type: TIMESTAMP
    Provider name: InvocationEndTime
    Description: A timestamp that shows when the benchmark completed.
  • invocation_start_time
    Type: TIMESTAMP
    Provider name: InvocationStartTime
    Description: A timestamp that shows when the benchmark started.
  • metrics
    Type: STRUCT
    Provider name: Metrics
    Description: The metrics used to decide what recommendation to make.
    • cost_per_hour
      Type: FLOAT
      Provider name: CostPerHour
      Description: Defines the cost per hour for the instance.
    • cost_per_inference
      Type: FLOAT
      Provider name: CostPerInference
      Description: Defines the cost per inference for the instance .
    • cpu_utilization
      Type: FLOAT
      Provider name: CpuUtilization
      Description: The expected CPU utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available.
    • max_invocations
      Type: INT32
      Provider name: MaxInvocations
      Description: The expected maximum number of requests per minute for the instance.
    • memory_utilization
      Type: FLOAT
      Provider name: MemoryUtilization
      Description: The expected memory utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available.
    • model_latency
      Type: INT32
      Provider name: ModelLatency
      Description: The expected model latency at maximum invocation per minute for the instance.
    • model_setup_time
      Type: INT32
      Provider name: ModelSetupTime
      Description: The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container. NaN indicates that the value is not available.
  • model_configuration
    Type: STRUCT
    Provider name: ModelConfiguration
    Description: Defines the model configuration.
    • compilation_job_name
      Type: STRING
      Provider name: CompilationJobName
      Description: The name of the compilation job used to create the recommended model artifacts.
    • environment_parameters
      Type: UNORDERED_LIST_STRUCT
      Provider name: EnvironmentParameters
      Description: Defines the environment parameters that includes key, value types, and values.
      • key
        Type: STRING
        Provider name: Key
        Description: The environment key suggested by the Amazon SageMaker Inference Recommender.
      • value
        Type: STRING
        Provider name: Value
        Description: The value suggested by the Amazon SageMaker Inference Recommender.
      • value_type
        Type: STRING
        Provider name: ValueType
        Description: The value type suggested by the Amazon SageMaker Inference Recommender.
    • inference_specification_name
      Type: STRING
      Provider name: InferenceSpecificationName
      Description: The inference specification name in the model package version.
  • recommendation_id
    Type: STRING
    Provider name: RecommendationId
    Description: The recommendation ID which uniquely identifies each recommendation.

input_config

Type: STRUCT
Provider name: InputConfig
Description: Returns information about the versioned model package Amazon Resource Name (ARN), the traffic pattern, and endpoint configurations you provided when you initiated the job.

  • container_config
    Type: STRUCT
    Provider name: ContainerConfig
    Description: Specifies mandatory fields for running an Inference Recommender job. The fields specified in ContainerConfig override the corresponding fields in the model package.
    • data_input_config
      Type: STRING
      Provider name: DataInputConfig
      Description: Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. This field is used for optimizing your model using SageMaker Neo. For more information, see DataInputConfig.
    • domain
      Type: STRING
      Provider name: Domain
      Description: The machine learning domain of the model and its components. Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING
    • framework
      Type: STRING
      Provider name: Framework
      Description: The machine learning framework of the container image. Valid Values: TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN
    • framework_version
      Type: STRING
      Provider name: FrameworkVersion
      Description: The framework version of the container image.
    • nearest_model_name
      Type: STRING
      Provider name: NearestModelName
      Description: The name of a pre-trained machine learning model benchmarked by Amazon SageMaker Inference Recommender that matches your model. Valid Values: efficientnetb7 | unet | xgboost | faster-rcnn-resnet101 | nasnetlarge | vgg16 | inception-v3 | mask-rcnn | sagemaker-scikit-learn | densenet201-gluon | resnet18v2-gluon | xception | densenet201 | yolov4 | resnet152 | bert-base-cased | xceptionV1-keras | resnet50 | retinanet
    • payload_config
      Type: STRUCT
      Provider name: PayloadConfig
      Description: Specifies the SamplePayloadUrl and all other sample payload-related fields.
      • sample_payload_url
        Type: STRING
        Provider name: SamplePayloadUrl
        Description: The Amazon Simple Storage Service (Amazon S3) path where the sample payload is stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
      • supported_content_types
        Type: UNORDERED_LIST_STRING
        Provider name: SupportedContentTypes
        Description: The supported MIME types for the input data.
    • supported_endpoint_type
      Type: STRING
      Provider name: SupportedEndpointType
      Description: The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.
    • supported_instance_types
      Type: UNORDERED_LIST_STRING
      Provider name: SupportedInstanceTypes
      Description: A list of the instance types that are used to generate inferences in real-time.
    • supported_response_mime_types
      Type: UNORDERED_LIST_STRING
      Provider name: SupportedResponseMIMETypes
      Description: The supported MIME types for the output data.
    • task
      Type: STRING
      Provider name: Task
      Description: The machine learning task that the model accomplishes. Valid Values: IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER
  • endpoint_configurations
    Type: UNORDERED_LIST_STRUCT
    Provider name: EndpointConfigurations
    Description: Specifies the endpoint configuration to use for a job.
    • environment_parameter_ranges
      Type: STRUCT
      Provider name: EnvironmentParameterRanges
      Description: The parameter you want to benchmark against.
      • categorical_parameter_ranges
        Type: UNORDERED_LIST_STRUCT
        Provider name: CategoricalParameterRanges
        Description: Specified a list of parameters for each category.
        • name
          Type: STRING
          Provider name: Name
          Description: The Name of the environment variable.
        • value
          Type: UNORDERED_LIST_STRING
          Provider name: Value
          Description: The list of values you can pass.
    • inference_specification_name
      Type: STRING
      Provider name: InferenceSpecificationName
      Description: The inference specification name in the model package version.
    • instance_type
      Type: STRING
      Provider name: InstanceType
      Description: The instance types to use for the load test.
    • serverless_config
      Type: STRUCT
      Provider name: ServerlessConfig
      • max_concurrency
        Type: INT32
        Provider name: MaxConcurrency
        Description: The maximum number of concurrent invocations your serverless endpoint can process.
      • memory_size_in_mb
        Type: INT32
        Provider name: MemorySizeInMB
        Description: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
      • provisioned_concurrency
        Type: INT32
        Provider name: ProvisionedConcurrency
        Description: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency. This field is not supported for serverless endpoint recommendations for Inference Recommender jobs. For more information about creating an Inference Recommender job, see CreateInferenceRecommendationsJobs.
  • endpoints
    Type: UNORDERED_LIST_STRUCT
    Provider name: Endpoints
    Description: Existing customer endpoints on which to run an Inference Recommender job.
    • endpoint_name
      Type: STRING
      Provider name: EndpointName
      Description: The name of a customer’s endpoint.
  • job_duration_in_seconds
    Type: INT32
    Provider name: JobDurationInSeconds
    Description: Specifies the maximum duration of the job, in seconds. The maximum value is 18,000 seconds.
  • model_name
    Type: STRING
    Provider name: ModelName
    Description: The name of the created model.
  • model_package_version_arn
    Type: STRING
    Provider name: ModelPackageVersionArn
    Description: The Amazon Resource Name (ARN) of a versioned model package.
  • resource_limit
    Type: STRUCT
    Provider name: ResourceLimit
    Description: Defines the resource limit of the job.
    • max_number_of_tests
      Type: INT32
      Provider name: MaxNumberOfTests
      Description: Defines the maximum number of load tests.
    • max_parallel_of_tests
      Type: INT32
      Provider name: MaxParallelOfTests
      Description: Defines the maximum number of parallel load tests.
  • traffic_pattern
    Type: STRUCT
    Provider name: TrafficPattern
    Description: Specifies the traffic pattern of the job.
    • phases
      Type: UNORDERED_LIST_STRUCT
      Provider name: Phases
      Description: Defines the phases traffic specification.
      • duration_in_seconds
        Type: INT32
        Provider name: DurationInSeconds
        Description: Specifies how long a traffic phase should be. For custom load tests, the value should be between 120 and 3600. This value should not exceed JobDurationInSeconds.
      • initial_number_of_users
        Type: INT32
        Provider name: InitialNumberOfUsers
        Description: Specifies how many concurrent users to start with. The value should be between 1 and 3.
      • spawn_rate
        Type: INT32
        Provider name: SpawnRate
        Description: Specified how many new users to spawn in a minute.
    • stairs
      Type: STRUCT
      Provider name: Stairs
      Description: Defines the stairs traffic pattern.
      • duration_in_seconds
        Type: INT32
        Provider name: DurationInSeconds
        Description: Defines how long each traffic step should be.
      • number_of_steps
        Type: INT32
        Provider name: NumberOfSteps
        Description: Specifies how many steps to perform during traffic.
      • users_per_step
        Type: INT32
        Provider name: UsersPerStep
        Description: Specifies how many new users to spawn in each step.
    • traffic_type
      Type: STRING
      Provider name: TrafficType
      Description: Defines the traffic patterns. Choose either PHASES or STAIRS.
  • volume_kms_key_id
    Type: STRING
    Provider name: VolumeKmsKeyId
    Description: The Amazon Resource Name (ARN) of a Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint. This key will be passed to SageMaker Hosting for endpoint creation. The SageMaker execution role must have kms:CreateGrant permission in order to encrypt data on the storage volume of the endpoints created for inference recommendation. The inference recommendation job will fail asynchronously during endpoint configuration creation if the role passed does not have kms:CreateGrant permission. The KmsKeyId can be any of the following formats:
    • // KMS Key ID “1234abcd-12ab-34cd-56ef-1234567890ab”
    • // Amazon Resource Name (ARN) of a KMS Key “arn:aws:kms:<region>:<account>:key/<key-id-12ab-34cd-56ef-1234567890ab>"
    • // KMS Key Alias “alias/ExampleAlias”
    • // Amazon Resource Name (ARN) of a KMS Key Alias “arn:aws:kms:<region>:<account>:alias/<ExampleAlias>"
    For more information about key identifiers, see Key identifiers (KeyID) in the Amazon Web Services Key Management Service (Amazon Web Services KMS) documentation.
  • vpc_config
    Type: STRUCT
    Provider name: VpcConfig
    Description: Inference Recommender provisions SageMaker endpoints with access to VPC in the inference recommendation job.
    • security_group_ids
      Type: UNORDERED_LIST_STRING
      Provider name: SecurityGroupIds
      Description: The VPC security group IDs. IDs have the form of sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
    • subnets
      Type: UNORDERED_LIST_STRING
      Provider name: Subnets
      Description: The ID of the subnets in the VPC to which you want to connect your model.

job_arn

Type: STRING
Provider name: JobArn
Description: The Amazon Resource Name (ARN) of the job.

job_description

Type: STRING
Provider name: JobDescription
Description: The job description that you provided when you initiated the job.

job_name

Type: STRING
Provider name: JobName
Description: The name of the job. The name must be unique within an Amazon Web Services Region in the Amazon Web Services account.

job_type

Type: STRING
Provider name: JobType
Description: The job type that you provided when you initiated the job.

last_modified_time

Type: TIMESTAMP
Provider name: LastModifiedTime
Description: A timestamp that shows when the job was last modified.

role_arn

Type: STRING
Provider name: RoleArn
Description: The Amazon Resource Name (ARN) of the Amazon Web Services Identity and Access Management (IAM) role you provided when you initiated the job.

status

Type: STRING
Provider name: Status
Description: The status of the job.

stopping_conditions

Type: STRUCT
Provider name: StoppingConditions
Description: The stopping conditions that you provided when you initiated the job.

  • flat_invocations
    Type: STRING
    Provider name: FlatInvocations
    Description: Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.
  • max_invocations
    Type: INT32
    Provider name: MaxInvocations
    Description: The maximum number of requests per minute expected for the endpoint.
  • model_latency_thresholds
    Type: UNORDERED_LIST_STRUCT
    Provider name: ModelLatencyThresholds
    Description: The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.
    • percentile
      Type: STRING
      Provider name: Percentile
      Description: The model latency percentile threshold. Acceptable values are P95 and P99. For custom load tests, specify the value as P95.
    • value_in_milliseconds
      Type: INT32
      Provider name: ValueInMilliseconds
      Description: The model latency percentile value in milliseconds.

tags

Type: UNORDERED_LIST_STRING