Skip to content
AWS for Query.Farm

aws.sagemaker.describe_auto_ml_job_v2

Example SQL Queries

SELECT * FROM
aws.sagemaker.describe_auto_ml_job_v2
WHERE
"auto_ml_job_name" = 'VALUE';

Description

Returns information about an AutoML job created by calling CreateAutoMLJobV2 or CreateAutoMLJob.

Table Definition

Column NameColumn Data Type
auto_ml_job_name Required Input Column

Returns the name of the AutoML job V2.

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.

auto_ml_compute_config

The compute configuration used for the AutoML job V2.

STRUCT(
    "emr_serverless_compute_config" STRUCT(
        "execution_role_arn" VARCHAR
    )
)
Show child fields
auto_ml_compute_config.emr_serverless_compute_config

The configuration for using EMR Serverless to run the AutoML job V2.

To allow your AutoML job V2 to automatically initiate a remote job on EMR Serverless when additional compute resources are needed to process large datasets, you need to provide an EmrServerlessComputeConfig object, which includes an ExecutionRoleARN attribute, to the AutoMLComputeConfig of the AutoML job V2 input request.

By seamlessly transitioning to EMR Serverless when required, the AutoML job can handle datasets that would otherwise exceed the initially provisioned resources, without any manual intervention from you.

EMR Serverless is available for the tabular and time series problem types. We recommend setting up this option for tabular datasets larger than 5 GB and time series datasets larger than 30 GB.

Show child fields
auto_ml_compute_config.emr_serverless_compute_config.execution_role_arn

The ARN of the IAM role granting the AutoML job V2 the necessary permissions access policies to list, connect to, or manage EMR Serverless jobs. For detailed information about the required permissions of this role, see "How to configure AutoML to initiate a remote job on EMR Serverless for large datasets" in Create a regression or classification job for tabular data using the AutoML API or Create an AutoML job for time-series forecasting using the API.

auto_ml_job_arn

Returns the Amazon Resource Name (ARN) of the AutoML job V2.

VARCHAR
auto_ml_job_artifacts

The artifacts that are generated during an AutoML job.

STRUCT(
    "candidate_definition_notebook_location" VARCHAR,
    "data_exploration_notebook_location" VARCHAR
)
Show child fields
auto_ml_job_artifacts.candidate_definition_notebook_location

The URL of the notebook location.

auto_ml_job_artifacts.data_exploration_notebook_location

The URL of the notebook location.

auto_ml_job_input_data_config

Returns an array of channel objects describing the input data and their location.

STRUCT(
    "channel_type" VARCHAR,
    "content_type" VARCHAR,
    "compression_type" VARCHAR,
    "data_source" STRUCT(
        "s3_data_source" STRUCT(
            "s3_data_type" VARCHAR,
            "s3_uri" VARCHAR
        )
    )
)[]
Show child fields
auto_ml_job_input_data_config[]
Show child fields
auto_ml_job_input_data_config[].channel_type

The type of channel. Defines whether the data are used for training or validation. The default value is training. Channels for training and validation must share the same ContentType

The type of channel defaults to training for the time-series forecasting problem type.

auto_ml_job_input_data_config[].compression_type

The allowed compression types depend on the input format and problem type. We allow the compression type Gzip for S3Prefix inputs on tabular data only. For all other inputs, the compression type should be None. If no compression type is provided, we default to None.

auto_ml_job_input_data_config[].content_type

The content type of the data from the input source. The following are the allowed content types for different problems:

  • For tabular problem types: text/csv;header=present or x-application/vnd.amazon+parquet. The default value is text/csv;header=present.

  • For image classification: image/png, image/jpeg, or image/*. The default value is image/*.

  • For text classification: text/csv;header=present or x-application/vnd.amazon+parquet. The default value is text/csv;header=present.

  • For time-series forecasting: text/csv;header=present or x-application/vnd.amazon+parquet. The default value is text/csv;header=present.

  • For text generation (LLMs fine-tuning): text/csv;header=present or x-application/vnd.amazon+parquet. The default value is text/csv;header=present.

auto_ml_job_input_data_config[].data_source

The data source for an AutoML channel (Required).

Show child fields
auto_ml_job_input_data_config[].data_source.s3_data_source

The Amazon S3 location of the input data.

Show child fields
auto_ml_job_input_data_config[].data_source.s3_data_source.s3_data_type

The data type.

  • If you choose S3Prefix, S3Uri identifies a key name prefix. SageMaker uses all objects that match the specified key name prefix for model training.

    The S3Prefix should have the following format:

    s3://DOC-EXAMPLE-BUCKET/DOC-EXAMPLE-FOLDER-OR-FILE

  • If you choose ManifestFile, S3Uri identifies an object that is a manifest file containing a list of object keys that you want SageMaker to use for model training.

    A ManifestFile should have the format shown below:

    [ {"prefix": "s3://DOC-EXAMPLE-BUCKET/DOC-EXAMPLE-FOLDER/DOC-EXAMPLE-PREFIX/"},

    "DOC-EXAMPLE-RELATIVE-PATH/DOC-EXAMPLE-FOLDER/DATA-1",

    "DOC-EXAMPLE-RELATIVE-PATH/DOC-EXAMPLE-FOLDER/DATA-2",

    ... "DOC-EXAMPLE-RELATIVE-PATH/DOC-EXAMPLE-FOLDER/DATA-N" ]

  • If you choose AugmentedManifestFile, S3Uri identifies an object that is an augmented manifest file in JSON lines format. This file contains the data you want to use for model training. AugmentedManifestFile is available for V2 API jobs only (for example, for jobs created by calling CreateAutoMLJobV2).

    Here is a minimal, single-record example of an AugmentedManifestFile:

    {"source-ref": "s3://DOC-EXAMPLE-BUCKET/DOC-EXAMPLE-FOLDER/cats/cat.jpg",

    "label-metadata": {"class-name": "cat" }

    For more information on AugmentedManifestFile, see Provide Dataset Metadata to Training Jobs with an Augmented Manifest File.

auto_ml_job_input_data_config[].data_source.s3_data_source.s3_uri

The URL to the Amazon S3 data source. The Uri refers to the Amazon S3 prefix or ManifestFile depending on the data type.

auto_ml_job_objective

Returns the job's objective.

STRUCT(
    "metric_name" VARCHAR
)
Show child fields
auto_ml_job_objective.metric_name

The name of the objective metric used to measure the predictive quality of a machine learning system. During training, the model's parameters are updated iteratively to optimize its performance based on the feedback provided by the objective metric when evaluating the model on the validation dataset.

The list of available metrics supported by Autopilot and the default metric applied when you do not specify a metric name explicitly depend on the problem type.

  • For tabular problem types:

    • List of available metrics:

      • Regression: MAE, MSE, R2, RMSE

      • Binary classification: Accuracy, AUC, BalancedAccuracy, F1, Precision, Recall

      • Multiclass classification: Accuracy, BalancedAccuracy, F1macro, PrecisionMacro, RecallMacro

      For a description of each metric, see Autopilot metrics for classification and regression.

    • Default objective metrics:

      • Regression: MSE.

      • Binary classification: F1.

      • Multiclass classification: Accuracy.

  • For image or text classification problem types:

  • For time-series forecasting problem types:

  • For text generation problem types (LLMs fine-tuning): Fine-tuning language models in Autopilot does not require setting the AutoMLJobObjective field. Autopilot fine-tunes LLMs without requiring multiple candidates to be trained and evaluated. Instead, using your dataset, Autopilot directly fine-tunes your target model to enhance a default objective metric, the cross-entropy loss. After fine-tuning a language model, you can evaluate the quality of its generated text using different metrics. For a list of the available metrics, see Metrics for fine-tuning LLMs in Autopilot.

auto_ml_job_secondary_status

Returns the secondary status of the AutoML job V2.

VARCHAR
auto_ml_job_status

Returns the status of the AutoML job V2.

VARCHAR
auto_ml_problem_type_config

Returns the configuration settings of the problem type set for the AutoML job V2.

STRUCT(
    "image_classification_job_config" STRUCT(
        "completion_criteria" STRUCT(
            "max_candidates" BIGINT,
            "max_runtime_per_training_job_in_seconds" BIGINT,
            "max_auto_ml_job_runtime_in_seconds" BIGINT
        )
    ),
    "text_classification_job_config" STRUCT(
        "completion_criteria" STRUCT(
            "max_candidates" BIGINT,
            "max_runtime_per_training_job_in_seconds" BIGINT,
            "max_auto_ml_job_runtime_in_seconds" BIGINT
        ),
        "content_column" VARCHAR,
        "target_label_column" VARCHAR
    ),
    "time_series_forecasting_job_config" STRUCT(
        "feature_specification_s3_uri" VARCHAR,
        "completion_criteria" STRUCT(
            "max_candidates" BIGINT,
            "max_runtime_per_training_job_in_seconds" BIGINT,
            "max_auto_ml_job_runtime_in_seconds" BIGINT
        ),
        "forecast_frequency" VARCHAR,
        "forecast_horizon" BIGINT,
        "forecast_quantiles" VARCHAR[],
        "transformations" STRUCT(
            "filling" MAP(VARCHAR, MAP(VARCHAR, VARCHAR)),
            "aggregation" MAP(VARCHAR, VARCHAR)
        ),
        "time_series_config" STRUCT(
            "target_attribute_name" VARCHAR,
            "timestamp_attribute_name" VARCHAR,
            "item_identifier_attribute_name" VARCHAR,
            "grouping_attribute_names" VARCHAR[]
        ),
        "holiday_config" STRUCT(
            "country_code" VARCHAR
        )[],
        "candidate_generation_config" STRUCT(
            "algorithms_config" STRUCT(
                "auto_ml_algorithms" VARCHAR[]
            )[]
        )
    ),
    "tabular_job_config" STRUCT(
        "candidate_generation_config" STRUCT(
            "algorithms_config" STRUCT(
                "auto_ml_algorithms" VARCHAR[]
            )[]
        ),
        "completion_criteria" STRUCT(
            "max_candidates" BIGINT,
            "max_runtime_per_training_job_in_seconds" BIGINT,
            "max_auto_ml_job_runtime_in_seconds" BIGINT
        ),
        "feature_specification_s3_uri" VARCHAR,
        "mode" VARCHAR,
        "generate_candidate_definitions_only" BOOLEAN,
        "problem_type" VARCHAR,
        "target_attribute_name" VARCHAR,
        "sample_weight_attribute_name" VARCHAR
    ),
    "text_generation_job_config" STRUCT(
        "completion_criteria" STRUCT(
            "max_candidates" BIGINT,
            "max_runtime_per_training_job_in_seconds" BIGINT,
            "max_auto_ml_job_runtime_in_seconds" BIGINT
        ),
        "base_model_name" VARCHAR,
        "text_generation_hyper_parameters" MAP(VARCHAR, VARCHAR),
        "model_access_config" STRUCT(
            "accept_eula" BOOLEAN
        )
    )
)
Show child fields
auto_ml_problem_type_config.image_classification_job_config

Settings used to configure an AutoML job V2 for the image classification problem type.

Show child fields
auto_ml_problem_type_config.image_classification_job_config.completion_criteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.

Show child fields
auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

auto_ml_problem_type_config.tabular_job_config

Settings used to configure an AutoML job V2 for the tabular problem type (regression, classification).

Show child fields
auto_ml_problem_type_config.tabular_job_config.candidate_generation_config

The configuration information of how model candidates are generated.

Show child fields
auto_ml_problem_type_config.tabular_job_config.candidate_generation_config.algorithms_config[]
Show child fields
auto_ml_problem_type_config.tabular_job_config.candidate_generation_config.algorithms_config[].auto_ml_algorithms[]
auto_ml_problem_type_config.tabular_job_config.completion_criteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.

Show child fields
auto_ml_problem_type_config.tabular_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

auto_ml_problem_type_config.tabular_job_config.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

auto_ml_problem_type_config.tabular_job_config.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

auto_ml_problem_type_config.tabular_job_config.feature_specification_s3_uri

A URL to the Amazon S3 data source containing selected features from the input data source to run an Autopilot job V2. You can input FeatureAttributeNames (optional) in JSON format as shown below:

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format shown below:

{ "FeatureDataTypes":{"col1":"numeric", "col2":"categorical" ... } }

These column keys may not include the target column.

In ensembling mode, Autopilot only supports the following data types: numeric, categorical, text, and datetime. In HPO mode, Autopilot can support numeric, categorical, text, datetime, and sequence.

If only FeatureDataTypes is provided, the column keys (col1, col2,..) should be a subset of the column names in the input data.

If both FeatureDataTypes and FeatureAttributeNames are provided, then the column keys should be a subset of the column names provided in FeatureAttributeNames.

The key name FeatureAttributeNames is fixed. The values listed in ["col1", "col2", ...] are case sensitive and should be a list of strings containing unique values that are a subset of the column names in the input data. The list of columns provided must not include the target column.

auto_ml_problem_type_config.tabular_job_config.generate_candidate_definitions_only

Generates possible candidates without training the models. A model candidate is a combination of data preprocessors, algorithms, and algorithm parameter settings.

auto_ml_problem_type_config.tabular_job_config.mode

The method that Autopilot uses to train the data. You can either specify the mode manually or let Autopilot choose for you based on the dataset size by selecting AUTO. In AUTO mode, Autopilot chooses ENSEMBLING for datasets smaller than 100 MB, and HYPERPARAMETER_TUNING for larger ones.

The ENSEMBLING mode uses a multi-stack ensemble model to predict classification and regression tasks directly from your dataset. This machine learning mode combines several base models to produce an optimal predictive model. It then uses a stacking ensemble method to combine predictions from contributing members. A multi-stack ensemble model can provide better performance over a single model by combining the predictive capabilities of multiple models. See Autopilot algorithm support for a list of algorithms supported by ENSEMBLING mode.

The HYPERPARAMETER_TUNING (HPO) mode uses the best hyperparameters to train the best version of a model. HPO automatically selects an algorithm for the type of problem you want to solve. Then HPO finds the best hyperparameters according to your objective metric. See Autopilot algorithm support for a list of algorithms supported by HYPERPARAMETER_TUNING mode.

auto_ml_problem_type_config.tabular_job_config.problem_type

The type of supervised learning problem available for the model candidates of the AutoML job V2. For more information, see SageMaker Autopilot problem types.

You must either specify the type of supervised learning problem in ProblemType and provide the AutoMLJobObjective metric, or none at all.

auto_ml_problem_type_config.tabular_job_config.sample_weight_attribute_name

If specified, this column name indicates which column of the dataset should be treated as sample weights for use by the objective metric during the training, evaluation, and the selection of the best model. This column is not considered as a predictive feature. For more information on Autopilot metrics, see Metrics and validation.

Sample weights should be numeric, non-negative, with larger values indicating which rows are more important than others. Data points that have invalid or no weight value are excluded.

Support for sample weights is available in Ensembling mode only.

auto_ml_problem_type_config.tabular_job_config.target_attribute_name

The name of the target variable in supervised learning, usually represented by 'y'.

auto_ml_problem_type_config.text_classification_job_config

Settings used to configure an AutoML job V2 for the text classification problem type.

Show child fields
auto_ml_problem_type_config.text_classification_job_config.completion_criteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.

Show child fields
auto_ml_problem_type_config.text_classification_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

auto_ml_problem_type_config.text_classification_job_config.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

auto_ml_problem_type_config.text_classification_job_config.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

auto_ml_problem_type_config.text_classification_job_config.content_column

The name of the column used to provide the sentences to be classified. It should not be the same as the target column.

auto_ml_problem_type_config.text_classification_job_config.target_label_column

The name of the column used to provide the class labels. It should not be same as the content column.

auto_ml_problem_type_config.text_generation_job_config

Settings used to configure an AutoML job V2 for the text generation (LLMs fine-tuning) problem type.

The text generation models that support fine-tuning in Autopilot are currently accessible exclusively in regions supported by Canvas. Refer to the documentation of Canvas for the full list of its supported Regions.

Show child fields
auto_ml_problem_type_config.text_generation_job_config.base_model_name

The name of the base model to fine-tune. Autopilot supports fine-tuning a variety of large language models. For information on the list of supported models, see Text generation models supporting fine-tuning in Autopilot. If no BaseModelName is provided, the default model used is Falcon7BInstruct.

auto_ml_problem_type_config.text_generation_job_config.completion_criteria

How long a fine-tuning job is allowed to run. For TextGenerationJobConfig problem types, the MaxRuntimePerTrainingJobInSeconds attribute of AutoMLJobCompletionCriteria defaults to 72h (259200s).

Show child fields
auto_ml_problem_type_config.text_generation_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

auto_ml_problem_type_config.text_generation_job_config.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

auto_ml_problem_type_config.text_generation_job_config.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

auto_ml_problem_type_config.text_generation_job_config.model_access_config

The access configuration file to control access to the ML model. You can explicitly accept the model end-user license agreement (EULA) within the ModelAccessConfig.

Show child fields
auto_ml_problem_type_config.text_generation_job_config.model_access_config.accept_eula

Specifies agreement to the model end-user license agreement (EULA). The AcceptEula value must be explicitly defined as True in order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.

auto_ml_problem_type_config.text_generation_job_config.text_generation_hyper_parameters

The hyperparameters used to configure and optimize the learning process of the base model. You can set any combination of the following hyperparameters for all base models. For more information on each supported hyperparameter, see Optimize the learning process of your text generation models with hyperparameters.

  • "epochCount": The number of times the model goes through the entire training dataset. Its value should be a string containing an integer value within the range of "1" to "10".

  • "batchSize": The number of data samples used in each iteration of training. Its value should be a string containing an integer value within the range of "1" to "64".

  • "learningRate": The step size at which a model's parameters are updated during training. Its value should be a string containing a floating-point value within the range of "0" to "1".

  • "learningRateWarmupSteps": The number of training steps during which the learning rate gradually increases before reaching its target or maximum value. Its value should be a string containing an integer value within the range of "0" to "250".

Here is an example where all four hyperparameters are configured.

{ "epochCount":"5", "learningRate":"0.5", "batchSize": "32", "learningRateWarmupSteps": "10" }

auto_ml_problem_type_config.time_series_forecasting_job_config

Settings used to configure an AutoML job V2 for the time-series forecasting problem type.

Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.candidate_generation_config

Stores the configuration information for how model candidates are generated using an AutoML job V2.

Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.candidate_generation_config.algorithms_config[]
Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.candidate_generation_config.algorithms_config[].auto_ml_algorithms[]
auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.

Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

auto_ml_problem_type_config.time_series_forecasting_job_config.feature_specification_s3_uri

A URL to the Amazon S3 data source containing additional selected features that complement the target, itemID, timestamp, and grouped columns set in TimeSeriesConfig. When not provided, the AutoML job V2 includes all the columns from the original dataset that are not already declared in TimeSeriesConfig. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

You can input FeatureAttributeNames (optional) in JSON format as shown below:

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format shown below:

{ "FeatureDataTypes":{"col1":"numeric", "col2":"categorical" ... } }

Autopilot supports the following data types: numeric, categorical, text, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_frequency

The frequency of predictions in a forecast.

Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, 1D indicates every day and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

  • Minute - 1-59

  • Hour - 1-23

  • Day - 1-6

  • Week - 1-4

  • Month - 1-11

  • Year - 1

auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_horizon

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_quantiles[]
auto_ml_problem_type_config.time_series_forecasting_job_config.holiday_config[]
Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.holiday_config[].country_code

The country code for the holiday calendar.

For the list of public holiday calendars supported by AutoML job V2, see Country Codes. Use the country code corresponding to the country of your choice.

auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config

The collection of components that defines the time-series.

Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.grouping_attribute_names[]
auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.item_identifier_attribute_name

The name of the column that represents the set of item identifiers for which you want to predict the target value.

auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.target_attribute_name

The name of the column representing the target variable that you want to predict for each item in your dataset. The data type of the target variable must be numerical.

auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.timestamp_attribute_name

The name of the column indicating a point in time at which the target value of a given item is recorded.

auto_ml_problem_type_config.time_series_forecasting_job_config.transformations

The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Show child fields
auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.aggregation

A key value pair defining the aggregation method for a column, where the key is the column name and the value is the aggregation method.

The supported aggregation methods are sum (default), avg, first, min, max.

Aggregation is only supported for the target column.

auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.filling

A key value pair defining the filling method for a column, where the key is the column name and the value is an object which defines the filling logic. You can specify multiple filling methods for a single column.

The supported filling methods and their corresponding options are:

  • frontfill: none (Supported only for target column)

  • middlefill: zero, value, median, mean, min, max

  • backfill: zero, value, median, mean, min, max

  • futurefill: zero, value, median, mean, min, max

To set a filling method to a specific value, set the fill parameter to the chosen filling method value (for example "backfill" : "value"), and define the filling value in an additional parameter prefixed with "_value". For example, to set backfill to a value of 2, you must include two parameters: "backfill": "value" and "backfill_value":"2".

auto_ml_problem_type_config_name

Returns the name of the problem type configuration set for the AutoML job V2.

VARCHAR
best_candidate

Information about the candidate produced by an AutoML training job V2, including its status, steps, and other properties.

STRUCT(
    "candidate_name" VARCHAR,
    "final_auto_ml_job_objective_metric" STRUCT(
        "type" VARCHAR,
        "metric_name" VARCHAR,
        "value" DOUBLE,
        "standard_metric_name" VARCHAR
    ),
    "objective_status" VARCHAR,
    "candidate_steps" STRUCT(
        "candidate_step_type" VARCHAR,
        "candidate_step_arn" VARCHAR,
        "candidate_step_name" VARCHAR
    )[],
    "candidate_status" VARCHAR,
    "inference_containers" STRUCT(
        "image" VARCHAR,
        "model_data_url" VARCHAR,
        "environment" MAP(VARCHAR, VARCHAR)
    )[],
    "creation_time" TIMESTAMP_S,
    "end_time" TIMESTAMP_S,
    "last_modified_time" TIMESTAMP_S,
    "failure_reason" VARCHAR,
    "candidate_properties" STRUCT(
        "candidate_artifact_locations" STRUCT(
            "explainability" VARCHAR,
            "model_insights" VARCHAR,
            "backtest_results" VARCHAR
        ),
        "candidate_metrics" STRUCT(
            "metric_name" VARCHAR,
            "value" DOUBLE,
            "set" VARCHAR,
            "standard_metric_name" VARCHAR
        )[]
    ),
    "inference_container_definitions" MAP(VARCHAR, STRUCT(
            "image" VARCHAR,
            "model_data_url" VARCHAR,
            "environment" MAP(VARCHAR, VARCHAR)
        )[])
)
Show child fields
best_candidate.candidate_name

The name of the candidate.

best_candidate.candidate_properties

The properties of an AutoML candidate job.

Show child fields
best_candidate.candidate_properties.candidate_artifact_locations

The Amazon S3 prefix to the artifacts generated for an AutoML candidate.

Show child fields
best_candidate.candidate_properties.candidate_artifact_locations.backtest_results

The Amazon S3 prefix to the accuracy metrics and the inference results observed over the testing window. Available only for the time-series forecasting problem type.

best_candidate.candidate_properties.candidate_artifact_locations.explainability

The Amazon S3 prefix to the explainability artifacts generated for the AutoML candidate.

best_candidate.candidate_properties.candidate_artifact_locations.model_insights

The Amazon S3 prefix to the model insight artifacts generated for the AutoML candidate.

best_candidate.candidate_properties.candidate_metrics[]
Show child fields
best_candidate.candidate_properties.candidate_metrics[].metric_name

The name of the metric.

best_candidate.candidate_properties.candidate_metrics[].set

The dataset split from which the AutoML job produced the metric.

best_candidate.candidate_properties.candidate_metrics[].standard_metric_name

The name of the standard metric.

For definitions of the standard metrics, see Autopilot candidate metrics .

best_candidate.candidate_properties.candidate_metrics[].value

The value of the metric.

best_candidate.candidate_status

The candidate's status.

best_candidate.candidate_steps[]
Show child fields
best_candidate.candidate_steps[].candidate_step_arn

The ARN for the candidate's step.

best_candidate.candidate_steps[].candidate_step_name

The name for the candidate's step.

best_candidate.candidate_steps[].candidate_step_type

Whether the candidate is at the transform, training, or processing step.

best_candidate.creation_time

The creation time.

best_candidate.end_time

The end time.

best_candidate.failure_reason

The failure reason.

best_candidate.final_auto_ml_job_objective_metric

The best candidate result from an AutoML training job.

Show child fields
best_candidate.final_auto_ml_job_objective_metric.metric_name

The name of the metric with the best result. For a description of the possible objective metrics, see AutoMLJobObjective$MetricName.

best_candidate.final_auto_ml_job_objective_metric.standard_metric_name

The name of the standard metric. For a description of the standard metrics, see Autopilot candidate metrics.

best_candidate.final_auto_ml_job_objective_metric.type

The type of metric with the best result.

best_candidate.final_auto_ml_job_objective_metric.value

The value of the metric with the best result.

best_candidate.inference_container_definitions

The mapping of all supported processing unit (CPU, GPU, etc...) to inference container definitions for the candidate. This field is populated for the AutoML jobs V2 (for example, for jobs created by calling CreateAutoMLJobV2) related to image or text classification problem types only.

best_candidate.inference_containers[]
Show child fields
best_candidate.inference_containers[].environment

The environment variables to set in the container. For more information, see ContainerDefinition.

best_candidate.inference_containers[].image

The Amazon Elastic Container Registry (Amazon ECR) path of the container. For more information, see ContainerDefinition.

best_candidate.inference_containers[].model_data_url

The location of the model artifacts. For more information, see ContainerDefinition.

best_candidate.last_modified_time

The last modified time.

best_candidate.objective_status

The objective's status.

creation_time

Returns the creation time of the AutoML job V2.

TIMESTAMP_S
data_split_config

Returns the configuration settings of how the data are split into train and validation datasets.

STRUCT(
    "validation_fraction" DOUBLE
)
Show child fields
data_split_config.validation_fraction

The validation fraction (optional) is a float that specifies the portion of the training dataset to be used for validation. The default value is 0.2, and values must be greater than 0 and less than 1. We recommend setting this value to be less than 0.5.

end_time

Returns the end time of the AutoML job V2.

TIMESTAMP_S
failure_reason

Returns the reason for the failure of the AutoML job V2, when applicable.

VARCHAR
last_modified_time

Returns the job's last modified time.

TIMESTAMP_S
model_deploy_config

Indicates whether the model was deployed automatically to an endpoint and the name of that endpoint if deployed automatically.

STRUCT(
    "auto_generate_endpoint_name" BOOLEAN,
    "endpoint_name" VARCHAR
)
Show child fields
model_deploy_config.auto_generate_endpoint_name

Set to True to automatically generate an endpoint name for a one-click Autopilot model deployment; set to False otherwise. The default value is False.

If you set AutoGenerateEndpointName to True, do not specify the EndpointName; otherwise a 400 error is thrown.

model_deploy_config.endpoint_name

Specifies the endpoint name to use for a one-click Autopilot model deployment if the endpoint name is not generated automatically.

Specify the EndpointName if and only if you set AutoGenerateEndpointName to False; otherwise a 400 error is thrown.

model_deploy_result

Provides information about endpoint for the model deployment.

STRUCT(
    "endpoint_name" VARCHAR
)
Show child fields
model_deploy_result.endpoint_name

The name of the endpoint to which the model has been deployed.

If model deployment fails, this field is omitted from the response.

output_data_config

Returns the job's output data config.

STRUCT(
    "kms_key_id" VARCHAR,
    "s3_output_path" VARCHAR
)
Show child fields
output_data_config.kms_key_id

The Key Management Service encryption key ID.

output_data_config.s3_output_path

The Amazon S3 output path. Must be 512 characters or less.

partial_failure_reasons

Returns a list of reasons for partial failures within an AutoML job V2.

STRUCT(
    "partial_failure_message" VARCHAR
)[]
Show child fields
partial_failure_reasons[]
Show child fields
partial_failure_reasons[].partial_failure_message

The message containing the reason for a partial failure of an AutoML job.

resolved_attributes

Returns the resolved attributes used by the AutoML job V2.

STRUCT(
    "auto_ml_job_objective" STRUCT(
        "metric_name" VARCHAR
    ),
    "completion_criteria" STRUCT(
        "max_candidates" BIGINT,
        "max_runtime_per_training_job_in_seconds" BIGINT,
        "max_auto_ml_job_runtime_in_seconds" BIGINT
    ),
    "auto_ml_problem_type_resolved_attributes" STRUCT(
        "tabular_resolved_attributes" STRUCT(
            "problem_type" VARCHAR
        ),
        "text_generation_resolved_attributes" STRUCT(
            "base_model_name" VARCHAR
        )
    )
)
Show child fields
resolved_attributes.auto_ml_job_objective

Specifies a metric to minimize or maximize as the objective of an AutoML job.

Show child fields
resolved_attributes.auto_ml_job_objective.metric_name

The name of the objective metric used to measure the predictive quality of a machine learning system. During training, the model's parameters are updated iteratively to optimize its performance based on the feedback provided by the objective metric when evaluating the model on the validation dataset.

The list of available metrics supported by Autopilot and the default metric applied when you do not specify a metric name explicitly depend on the problem type.

  • For tabular problem types:

    • List of available metrics:

      • Regression: MAE, MSE, R2, RMSE

      • Binary classification: Accuracy, AUC, BalancedAccuracy, F1, Precision, Recall

      • Multiclass classification: Accuracy, BalancedAccuracy, F1macro, PrecisionMacro, RecallMacro

      For a description of each metric, see Autopilot metrics for classification and regression.

    • Default objective metrics:

      • Regression: MSE.

      • Binary classification: F1.

      • Multiclass classification: Accuracy.

  • For image or text classification problem types:

  • For time-series forecasting problem types:

  • For text generation problem types (LLMs fine-tuning): Fine-tuning language models in Autopilot does not require setting the AutoMLJobObjective field. Autopilot fine-tunes LLMs without requiring multiple candidates to be trained and evaluated. Instead, using your dataset, Autopilot directly fine-tunes your target model to enhance a default objective metric, the cross-entropy loss. After fine-tuning a language model, you can evaluate the quality of its generated text using different metrics. For a list of the available metrics, see Metrics for fine-tuning LLMs in Autopilot.

resolved_attributes.auto_ml_problem_type_resolved_attributes

Defines the resolved attributes specific to a problem type.

Show child fields
resolved_attributes.auto_ml_problem_type_resolved_attributes.tabular_resolved_attributes

The resolved attributes for the tabular problem type.

Show child fields
resolved_attributes.auto_ml_problem_type_resolved_attributes.tabular_resolved_attributes.problem_type

The type of supervised learning problem available for the model candidates of the AutoML job V2 (Binary Classification, Multiclass Classification, Regression). For more information, see SageMaker Autopilot problem types.

resolved_attributes.auto_ml_problem_type_resolved_attributes.text_generation_resolved_attributes

The resolved attributes for the text generation problem type.

Show child fields
resolved_attributes.auto_ml_problem_type_resolved_attributes.text_generation_resolved_attributes.base_model_name

The name of the base model to fine-tune.

resolved_attributes.completion_criteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.

Show child fields
resolved_attributes.completion_criteria.max_auto_ml_job_runtime_in_seconds

The maximum runtime, in seconds, an AutoML job has to complete.

If an AutoML job exceeds the maximum runtime, the job is stopped automatically and its processing is ended gracefully. The AutoML job identifies the best model whose training was completed and marks it as the best-performing model. Any unfinished steps of the job, such as automatic one-click Autopilot model deployment, are not completed.

resolved_attributes.completion_criteria.max_candidates

The maximum number of times a training job is allowed to run.

For text and image classification, time-series forecasting, as well as text generation (LLMs fine-tuning) problem types, the supported value is 1. For tabular problem types, the maximum value is 750.

resolved_attributes.completion_criteria.max_runtime_per_training_job_in_seconds

The maximum time, in seconds, that each training job executed inside hyperparameter tuning is allowed to run as part of a hyperparameter tuning job. For more information, see the StoppingCondition used by the CreateHyperParameterTuningJob action.

For job V2s (jobs created by calling CreateAutoMLJobV2), this field controls the runtime of the job candidate.

For TextGenerationJobConfig problem types, the maximum time defaults to 72 hours (259200 seconds).

role_arn

The ARN of the IAM role that has read permission to the input data location and write permission to the output data location in Amazon S3.

VARCHAR
security_config

Returns the security configuration for traffic encryption or Amazon VPC settings.

STRUCT(
    "volume_kms_key_id" VARCHAR,
    "enable_inter_container_traffic_encryption" BOOLEAN,
    "vpc_config" STRUCT(
        "security_group_ids" VARCHAR[],
        "subnets" VARCHAR[]
    )
)
Show child fields
security_config.enable_inter_container_traffic_encryption

Whether to use traffic encryption between the container layers.

security_config.volume_kms_key_id

The key used to encrypt stored data.

security_config.vpc_config

The VPC configuration.

Show child fields
security_config.vpc_config.security_group_ids[]
security_config.vpc_config.subnets[]