| Column Name | Column Data Type |
|---|
job_name Required Input Column
The name of the job. The name must be unique within an Amazon Web Services Region in the Amazon Web Services account. | VARCHAR |
_aws_profile Input Column
The AWS profile defines the AWS identity used. It can be defined via credentials or by assuming a IAM role. | STRUCT(
"type" VARCHAR,
"name" VARCHAR,
"account_id" VARCHAR,
"via_profile_name" VARCHAR,
"assumed_role_arn" VARCHAR,
"organization" STRUCT(
"account_name" VARCHAR,
"id" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[],
"master_account" STRUCT(
"id" VARCHAR,
"email" VARCHAR
),
"parents" STRUCT(
"type" VARCHAR,
"id" VARCHAR,
"name" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[]
)[]
)
) |
Show child fields- _aws_profile.account_id
The AWS account id - _aws_profile.assumed_role_arn
The ARN of the assumed role - _aws_profile.name
The unique name of the profile. - _aws_profile.organization
Information about this profile's membership in the AWS organization. Show child fields- _aws_profile.organization.account_name
The name of account speciifed by the organization - _aws_profile.organization.id
The organization id - _aws_profile.organization.master_account
Show child fields- _aws_profile.organization.master_account.email
The organization master account email address - _aws_profile.organization.master_account.id
The organization master account id
- _aws_profile.organization.parents[]
Show child fields- _aws_profile.organization.parents[].id
The id of the parent - _aws_profile.organization.parents[].name
The name of the parent - _aws_profile.organization.parents[].tags[]
Show child fields- _aws_profile.organization.parents[].tags[].key
- _aws_profile.organization.parents[].tags[].value
- _aws_profile.organization.parents[].type
The type of parent can be an organization unit or a root
- _aws_profile.organization.tags[]
Show child fields- _aws_profile.organization.tags[].key
- _aws_profile.organization.tags[].value
- _aws_profile.type
The type of profile, either 'credentials' or 'assumed_role' - _aws_profile.via_profile_name
This IAM role for this profile is assumed by first utilizing another profile with this name to obtain credentials.
|
completion_time
A timestamp that shows when the job completed. | TIMESTAMP_S |
creation_time
A timestamp that shows when the job was created. | TIMESTAMP_S |
endpoint_performances
The performance results from running an Inference Recommender job on an existing endpoint. | STRUCT(
"metrics" STRUCT(
"max_invocations" BIGINT,
"model_latency" BIGINT
),
"endpoint_info" STRUCT(
"endpoint_name" VARCHAR
)
)[] |
Show child fields- endpoint_performances[]
Show child fields- endpoint_performances[].endpoint_info
Details about a customer endpoint that was compared in an Inference Recommender job. Show child fields- endpoint_performances[].endpoint_info.endpoint_name
The name of a customer's endpoint.
- endpoint_performances[].metrics
The metrics for an existing endpoint. Show child fields- endpoint_performances[].metrics.max_invocations
The expected maximum number of requests per minute for the instance. - endpoint_performances[].metrics.model_latency
The expected model latency at maximum invocations per minute for the instance.
|
failure_reason
If the job fails, provides information why the job failed. | VARCHAR |
inference_recommendations
The recommendations made by Inference Recommender. | STRUCT(
"recommendation_id" VARCHAR,
"metrics" STRUCT(
"cost_per_hour" DOUBLE,
"cost_per_inference" DOUBLE,
"max_invocations" BIGINT,
"model_latency" BIGINT,
"cpu_utilization" DOUBLE,
"memory_utilization" DOUBLE,
"model_setup_time" BIGINT
),
"endpoint_configuration" STRUCT(
"endpoint_name" VARCHAR,
"variant_name" VARCHAR,
"instance_type" VARCHAR,
"initial_instance_count" BIGINT,
"serverless_config" STRUCT(
"memory_size_in_mb" BIGINT,
"max_concurrency" BIGINT,
"provisioned_concurrency" BIGINT
)
),
"model_configuration" STRUCT(
"inference_specification_name" VARCHAR,
"environment_parameters" STRUCT(
"key" VARCHAR,
"value_type" VARCHAR,
"value" VARCHAR
)[],
"compilation_job_name" VARCHAR
),
"invocation_end_time" TIMESTAMP_S,
"invocation_start_time" TIMESTAMP_S
)[] |
Show child fields- inference_recommendations[]
Show child fields- inference_recommendations[].endpoint_configuration
Defines the endpoint configuration parameters. Show child fields- inference_recommendations[].endpoint_configuration.endpoint_name
The name of the endpoint made during a recommendation job. - inference_recommendations[].endpoint_configuration.initial_instance_count
The number of instances recommended to launch initially. - inference_recommendations[].endpoint_configuration.instance_type
The instance type recommended by Amazon SageMaker Inference Recommender. - inference_recommendations[].endpoint_configuration.serverless_config
Specifies the serverless configuration for an endpoint variant. Show child fields- inference_recommendations[].endpoint_configuration.serverless_config.max_concurrency
The maximum number of concurrent invocations your serverless endpoint can process. - inference_recommendations[].endpoint_configuration.serverless_config.memory_size_in_mb
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. - inference_recommendations[].endpoint_configuration.serverless_config.provisioned_concurrency
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.
- inference_recommendations[].endpoint_configuration.variant_name
The name of the production variant (deployed model) made during a recommendation job.
- inference_recommendations[].invocation_end_time
A timestamp that shows when the benchmark completed. - inference_recommendations[].invocation_start_time
A timestamp that shows when the benchmark started. - inference_recommendations[].metrics
The metrics used to decide what recommendation to make. Show child fields- inference_recommendations[].metrics.cost_per_hour
Defines the cost per hour for the instance. - inference_recommendations[].metrics.cost_per_inference
Defines the cost per inference for the instance . - inference_recommendations[].metrics.cpu_utilization
The expected CPU utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available. - inference_recommendations[].metrics.max_invocations
The expected maximum number of requests per minute for the instance. - inference_recommendations[].metrics.memory_utilization
The expected memory utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available. - inference_recommendations[].metrics.model_latency
The expected model latency at maximum invocation per minute for the instance. - inference_recommendations[].metrics.model_setup_time
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.
- inference_recommendations[].model_configuration
Defines the model configuration. Show child fields- inference_recommendations[].model_configuration.compilation_job_name
The name of the compilation job used to create the recommended model artifacts. - inference_recommendations[].model_configuration.environment_parameters[]
Show child fields- inference_recommendations[].model_configuration.environment_parameters[].key
The environment key suggested by the Amazon SageMaker Inference Recommender. - inference_recommendations[].model_configuration.environment_parameters[].value
The value suggested by the Amazon SageMaker Inference Recommender. - inference_recommendations[].model_configuration.environment_parameters[].value_type
The value type suggested by the Amazon SageMaker Inference Recommender.
- inference_recommendations[].model_configuration.inference_specification_name
The inference specification name in the model package version.
- inference_recommendations[].recommendation_id
The recommendation ID which uniquely identifies each recommendation.
|
input_config
Returns information about the versioned model package Amazon Resource Name (ARN), the traffic pattern, and endpoint configurations you provided when you initiated the job. | STRUCT(
"model_package_version_arn" VARCHAR,
"model_name" VARCHAR,
"job_duration_in_seconds" BIGINT,
"traffic_pattern" STRUCT(
"traffic_type" VARCHAR,
"phases" STRUCT(
"initial_number_of_users" BIGINT,
"spawn_rate" BIGINT,
"duration_in_seconds" BIGINT
)[],
"stairs" STRUCT(
"duration_in_seconds" BIGINT,
"number_of_steps" BIGINT,
"users_per_step" BIGINT
)
),
"resource_limit" STRUCT(
"max_number_of_tests" BIGINT,
"max_parallel_of_tests" BIGINT
),
"endpoint_configurations" STRUCT(
"instance_type" VARCHAR,
"serverless_config" STRUCT(
"memory_size_in_mb" BIGINT,
"max_concurrency" BIGINT,
"provisioned_concurrency" BIGINT
),
"inference_specification_name" VARCHAR,
"environment_parameter_ranges" STRUCT(
"categorical_parameter_ranges" STRUCT(
"name" VARCHAR,
"value" VARCHAR[]
)[]
)
)[],
"volume_kms_key_id" VARCHAR,
"container_config" STRUCT(
"domain" VARCHAR,
"task" VARCHAR,
"framework" VARCHAR,
"framework_version" VARCHAR,
"payload_config" STRUCT(
"sample_payload_url" VARCHAR,
"supported_content_types" VARCHAR[]
),
"nearest_model_name" VARCHAR,
"supported_instance_types" VARCHAR[],
"supported_endpoint_type" VARCHAR,
"data_input_config" VARCHAR,
"supported_response_mime_types" VARCHAR[]
),
"endpoints" STRUCT(
"endpoint_name" VARCHAR
)[],
"vpc_config" STRUCT(
"security_group_ids" VARCHAR[],
"subnets" VARCHAR[]
)
) |
Show child fields- input_config.container_config
Specifies mandatory fields for running an Inference Recommender job. The fields specified in ContainerConfig override the corresponding fields in the model package. Show child fields- input_config.container_config.data_input_config
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. - input_config.container_config.domain
The machine learning domain of the model and its components. Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING - input_config.container_config.framework
The machine learning framework of the container image. Valid Values: TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN - input_config.container_config.framework_version
The framework version of the container image. - input_config.container_config.nearest_model_name
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 - input_config.container_config.payload_config
Specifies the SamplePayloadUrl and all other sample payload-related fields. Show child fields- input_config.container_config.payload_config.sample_payload_url
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). - input_config.container_config.payload_config.supported_content_types[]
- input_config.container_config.supported_endpoint_type
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. - input_config.container_config.supported_instance_types[]
- input_config.container_config.supported_response_mime_types[]
- input_config.container_config.task
The machine learning task that the model accomplishes. Valid Values: IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER
- input_config.endpoint_configurations[]
Show child fields- input_config.endpoint_configurations[].environment_parameter_ranges
The parameter you want to benchmark against. Show child fields- input_config.endpoint_configurations[].environment_parameter_ranges.categorical_parameter_ranges[]
Show child fields- input_config.endpoint_configurations[].environment_parameter_ranges.categorical_parameter_ranges[].name
The Name of the environment variable. - input_config.endpoint_configurations[].environment_parameter_ranges.categorical_parameter_ranges[].value[]
- input_config.endpoint_configurations[].inference_specification_name
The inference specification name in the model package version. - input_config.endpoint_configurations[].instance_type
The instance types to use for the load test. - input_config.endpoint_configurations[].serverless_config
Specifies the serverless configuration for an endpoint variant. Show child fields- input_config.endpoint_configurations[].serverless_config.max_concurrency
The maximum number of concurrent invocations your serverless endpoint can process. - input_config.endpoint_configurations[].serverless_config.memory_size_in_mb
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. - input_config.endpoint_configurations[].serverless_config.provisioned_concurrency
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.
- input_config.endpoints[]
Show child fields- input_config.endpoints[].endpoint_name
The name of a customer's endpoint.
- input_config.job_duration_in_seconds
Specifies the maximum duration of the job, in seconds. The maximum value is 18,000 seconds. - input_config.model_name
The name of the created model. - input_config.model_package_version_arn
The Amazon Resource Name (ARN) of a versioned model package. - input_config.resource_limit
Defines the resource limit of the job. Show child fields- input_config.resource_limit.max_number_of_tests
Defines the maximum number of load tests. - input_config.resource_limit.max_parallel_of_tests
Defines the maximum number of parallel load tests.
- input_config.traffic_pattern
Specifies the traffic pattern of the job. Show child fields- input_config.traffic_pattern.phases[]
Show child fields- input_config.traffic_pattern.phases[].duration_in_seconds
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. - input_config.traffic_pattern.phases[].initial_number_of_users
Specifies how many concurrent users to start with. The value should be between 1 and 3. - input_config.traffic_pattern.phases[].spawn_rate
Specified how many new users to spawn in a minute.
- input_config.traffic_pattern.stairs
Defines the stairs traffic pattern. Show child fields- input_config.traffic_pattern.stairs.duration_in_seconds
Defines how long each traffic step should be. - input_config.traffic_pattern.stairs.number_of_steps
Specifies how many steps to perform during traffic. - input_config.traffic_pattern.stairs.users_per_step
Specifies how many new users to spawn in each step.
- input_config.traffic_pattern.traffic_type
Defines the traffic patterns. Choose either PHASES or STAIRS.
- input_config.volume_kms_key_id
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. - input_config.vpc_config
Inference Recommender provisions SageMaker endpoints with access to VPC in the inference recommendation job. Show child fields- input_config.vpc_config.security_group_ids[]
- input_config.vpc_config.subnets[]
|
job_arn
The Amazon Resource Name (ARN) of the job. | VARCHAR |
job_description
The job description that you provided when you initiated the job. | VARCHAR |
job_type
The job type that you provided when you initiated the job. | VARCHAR |
last_modified_time
A timestamp that shows when the job was last modified. | TIMESTAMP_S |
role_arn
The Amazon Resource Name (ARN) of the Amazon Web Services Identity and Access Management (IAM) role you provided when you initiated the job. | VARCHAR |
status
The status of the job. | VARCHAR |
stopping_conditions
The stopping conditions that you provided when you initiated the job. | STRUCT(
"max_invocations" BIGINT,
"model_latency_thresholds" STRUCT(
"percentile" VARCHAR,
"value_in_milliseconds" BIGINT
)[],
"flat_invocations" VARCHAR
) |
Show child fields- stopping_conditions.flat_invocations
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. - stopping_conditions.max_invocations
The maximum number of requests per minute expected for the endpoint. - stopping_conditions.model_latency_thresholds[]
Show child fields- stopping_conditions.model_latency_thresholds[].percentile
The model latency percentile threshold. Acceptable values are P95 and P99. For custom load tests, specify the value as P95. - stopping_conditions.model_latency_thresholds[].value_in_milliseconds
The model latency percentile value in milliseconds.
|