SageMaker / Client / create_auto_ml_job_v2

create_auto_ml_job_v2#

SageMaker.Client.create_auto_ml_job_v2(**kwargs)#

Creates an Autopilot job also referred to as Autopilot experiment or AutoML job V2.

An AutoML job in SageMaker AI is a fully automated process that allows you to build machine learning models with minimal effort and machine learning expertise. When initiating an AutoML job, you provide your data and optionally specify parameters tailored to your use case. SageMaker AI then automates the entire model development lifecycle, including data preprocessing, model training, tuning, and evaluation. AutoML jobs are designed to simplify and accelerate the model building process by automating various tasks and exploring different combinations of machine learning algorithms, data preprocessing techniques, and hyperparameter values. The output of an AutoML job comprises one or more trained models ready for deployment and inference. Additionally, SageMaker AI AutoML jobs generate a candidate model leaderboard, allowing you to select the best-performing model for deployment.

For more information about AutoML jobs, see https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-automate-model-development.html in the SageMaker AI developer guide.

AutoML jobs V2 support various problem types such as regression, binary, and multiclass classification with tabular data, text and image classification, time-series forecasting, and fine-tuning of large language models (LLMs) for text generation.

Note

CreateAutoMLJobV2 and DescribeAutoMLJobV2 are new versions of CreateAutoMLJob and DescribeAutoMLJob which offer backward compatibility.

CreateAutoMLJobV2 can manage tabular problem types identical to those of its previous version CreateAutoMLJob, as well as time-series forecasting, non-tabular problem types such as image or text classification, and text generation (LLMs fine-tuning).

Find guidelines about how to migrate a CreateAutoMLJob to CreateAutoMLJobV2 in Migrate a CreateAutoMLJob to CreateAutoMLJobV2.

For the list of available problem types supported by CreateAutoMLJobV2, see AutoMLProblemTypeConfig.

You can find the best-performing model after you run an AutoML job V2 by calling DescribeAutoMLJobV2.

See also: AWS API Documentation

Request Syntax

response = client.create_auto_ml_job_v2(
    AutoMLJobName='string',
    AutoMLJobInputDataConfig=[
        {
            'ChannelType': 'training'|'validation',
            'ContentType': 'string',
            'CompressionType': 'None'|'Gzip',
            'DataSource': {
                'S3DataSource': {
                    'S3DataType': 'ManifestFile'|'S3Prefix'|'AugmentedManifestFile',
                    'S3Uri': 'string'
                }
            }
        },
    ],
    OutputDataConfig={
        'KmsKeyId': 'string',
        'S3OutputPath': 'string'
    },
    AutoMLProblemTypeConfig={
        'ImageClassificationJobConfig': {
            'CompletionCriteria': {
                'MaxCandidates': 123,
                'MaxRuntimePerTrainingJobInSeconds': 123,
                'MaxAutoMLJobRuntimeInSeconds': 123
            }
        },
        'TextClassificationJobConfig': {
            'CompletionCriteria': {
                'MaxCandidates': 123,
                'MaxRuntimePerTrainingJobInSeconds': 123,
                'MaxAutoMLJobRuntimeInSeconds': 123
            },
            'ContentColumn': 'string',
            'TargetLabelColumn': 'string'
        },
        'TimeSeriesForecastingJobConfig': {
            'FeatureSpecificationS3Uri': 'string',
            'CompletionCriteria': {
                'MaxCandidates': 123,
                'MaxRuntimePerTrainingJobInSeconds': 123,
                'MaxAutoMLJobRuntimeInSeconds': 123
            },
            'ForecastFrequency': 'string',
            'ForecastHorizon': 123,
            'ForecastQuantiles': [
                'string',
            ],
            'Transformations': {
                'Filling': {
                    'string': {
                        'string': 'string'
                    }
                },
                'Aggregation': {
                    'string': 'sum'|'avg'|'first'|'min'|'max'
                }
            },
            'TimeSeriesConfig': {
                'TargetAttributeName': 'string',
                'TimestampAttributeName': 'string',
                'ItemIdentifierAttributeName': 'string',
                'GroupingAttributeNames': [
                    'string',
                ]
            },
            'HolidayConfig': [
                {
                    'CountryCode': 'string'
                },
            ],
            'CandidateGenerationConfig': {
                'AlgorithmsConfig': [
                    {
                        'AutoMLAlgorithms': [
                            'xgboost'|'linear-learner'|'mlp'|'lightgbm'|'catboost'|'randomforest'|'extra-trees'|'nn-torch'|'fastai'|'cnn-qr'|'deepar'|'prophet'|'npts'|'arima'|'ets',
                        ]
                    },
                ]
            }
        },
        'TabularJobConfig': {
            'CandidateGenerationConfig': {
                'AlgorithmsConfig': [
                    {
                        'AutoMLAlgorithms': [
                            'xgboost'|'linear-learner'|'mlp'|'lightgbm'|'catboost'|'randomforest'|'extra-trees'|'nn-torch'|'fastai'|'cnn-qr'|'deepar'|'prophet'|'npts'|'arima'|'ets',
                        ]
                    },
                ]
            },
            'CompletionCriteria': {
                'MaxCandidates': 123,
                'MaxRuntimePerTrainingJobInSeconds': 123,
                'MaxAutoMLJobRuntimeInSeconds': 123
            },
            'FeatureSpecificationS3Uri': 'string',
            'Mode': 'AUTO'|'ENSEMBLING'|'HYPERPARAMETER_TUNING',
            'GenerateCandidateDefinitionsOnly': True|False,
            'ProblemType': 'BinaryClassification'|'MulticlassClassification'|'Regression',
            'TargetAttributeName': 'string',
            'SampleWeightAttributeName': 'string'
        },
        'TextGenerationJobConfig': {
            'CompletionCriteria': {
                'MaxCandidates': 123,
                'MaxRuntimePerTrainingJobInSeconds': 123,
                'MaxAutoMLJobRuntimeInSeconds': 123
            },
            'BaseModelName': 'string',
            'TextGenerationHyperParameters': {
                'string': 'string'
            },
            'ModelAccessConfig': {
                'AcceptEula': True|False
            }
        }
    },
    RoleArn='string',
    Tags=[
        {
            'Key': 'string',
            'Value': 'string'
        },
    ],
    SecurityConfig={
        'VolumeKmsKeyId': 'string',
        'EnableInterContainerTrafficEncryption': True|False,
        'VpcConfig': {
            'SecurityGroupIds': [
                'string',
            ],
            'Subnets': [
                'string',
            ]
        }
    },
    AutoMLJobObjective={
        'MetricName': 'Accuracy'|'MSE'|'F1'|'F1macro'|'AUC'|'RMSE'|'BalancedAccuracy'|'R2'|'Recall'|'RecallMacro'|'Precision'|'PrecisionMacro'|'MAE'|'MAPE'|'MASE'|'WAPE'|'AverageWeightedQuantileLoss'
    },
    ModelDeployConfig={
        'AutoGenerateEndpointName': True|False,
        'EndpointName': 'string'
    },
    DataSplitConfig={
        'ValidationFraction': ...
    },
    AutoMLComputeConfig={
        'EmrServerlessComputeConfig': {
            'ExecutionRoleARN': 'string'
        }
    }
)
Parameters:

  • AutoMLJobName (string) –

    [REQUIRED]

    Identifies an Autopilot job. The name must be unique to your account and is case insensitive.

  • AutoMLJobInputDataConfig (list) –

    [REQUIRED]

    An array of channel objects describing the input data and their location. Each channel is a named input source. Similar to the InputDataConfig attribute in the CreateAutoMLJob input parameters. The supported formats depend on the problem type:

    • For tabular problem types: S3Prefix, ManifestFile.

    • For image classification: S3Prefix, ManifestFile, AugmentedManifestFile.

    • For text classification: S3Prefix.

    • For time-series forecasting: S3Prefix.

    • For text generation (LLMs fine-tuning): S3Prefix.

    • (dict) –

      A channel is a named input source that training algorithms can consume. This channel is used for AutoML jobs V2 (jobs created by calling CreateAutoMLJobV2).

      • ChannelType (string) –

        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

        Note

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

      • ContentType (string) –

        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.

      • CompressionType (string) –

        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.

      • DataSource (dict) –

        The data source for an AutoML channel (Required).

        • S3DataSource (dict) – [REQUIRED]

          The Amazon S3 location of the input data.

          • S3DataType (string) – [REQUIRED]

            The data type.

            • If you choose S3Prefix, S3Uri identifies a key name prefix. SageMaker AI 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 AI 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.

          • S3Uri (string) – [REQUIRED]

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

  • OutputDataConfig (dict) –

    [REQUIRED]

    Provides information about encryption and the Amazon S3 output path needed to store artifacts from an AutoML job.

    • KmsKeyId (string) –

      The Key Management Service encryption key ID.

    • S3OutputPath (string) – [REQUIRED]

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

  • AutoMLProblemTypeConfig (dict) –

    [REQUIRED]

    Defines the configuration settings of one of the supported problem types.

    Note

    This is a Tagged Union structure. Only one of the following top level keys can be set: ImageClassificationJobConfig, TextClassificationJobConfig, TimeSeriesForecastingJobConfig, TabularJobConfig, TextGenerationJobConfig.

    • ImageClassificationJobConfig (dict) –

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

      • CompletionCriteria (dict) –

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

        • MaxCandidates (integer) –

          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.

        • MaxRuntimePerTrainingJobInSeconds (integer) –

          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).

        • MaxAutoMLJobRuntimeInSeconds (integer) –

          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.

    • TextClassificationJobConfig (dict) –

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

      • CompletionCriteria (dict) –

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

        • MaxCandidates (integer) –

          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.

        • MaxRuntimePerTrainingJobInSeconds (integer) –

          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).

        • MaxAutoMLJobRuntimeInSeconds (integer) –

          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.

      • ContentColumn (string) – [REQUIRED]

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

      • TargetLabelColumn (string) – [REQUIRED]

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

    • TimeSeriesForecastingJobConfig (dict) –

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

      • FeatureSpecificationS3Uri (string) –

        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.

        Note

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

      • CompletionCriteria (dict) –

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

        • MaxCandidates (integer) –

          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.

        • MaxRuntimePerTrainingJobInSeconds (integer) –

          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).

        • MaxAutoMLJobRuntimeInSeconds (integer) –

          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.

      • ForecastFrequency (string) – [REQUIRED]

        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

      • ForecastHorizon (integer) – [REQUIRED]

        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.

      • ForecastQuantiles (list) –

        The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

        • (string) –

      • Transformations (dict) –

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

        • Filling (dict) –

          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".

          • (string) –

            • (dict) –

              • (string) –

                • (string) –

        • Aggregation (dict) –

          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.

          Note

          Aggregation is only supported for the target column.

          • (string) –

            • (string) –

      • TimeSeriesConfig (dict) – [REQUIRED]

        The collection of components that defines the time-series.

        • TargetAttributeName (string) – [REQUIRED]

          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.

        • TimestampAttributeName (string) – [REQUIRED]

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

        • ItemIdentifierAttributeName (string) – [REQUIRED]

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

        • GroupingAttributeNames (list) –

          A set of columns names that can be grouped with the item identifier column to create a composite key for which a target value is predicted.

          • (string) –

      • HolidayConfig (list) –

        The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

        • (dict) –

          Stores the holiday featurization attributes applicable to each item of time-series datasets during the training of a forecasting model. This allows the model to identify patterns associated with specific holidays.

          • CountryCode (string) –

            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.

      • CandidateGenerationConfig (dict) –

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

        • AlgorithmsConfig (list) –

          Your Autopilot job trains a default set of algorithms on your dataset. For tabular and time-series data, you can customize the algorithm list by selecting a subset of algorithms for your problem type.

          AlgorithmsConfig stores the customized selection of algorithms to train on your data.

          • For the tabular problem type TabularJobConfig, the list of available algorithms to choose from depends on the training mode set in AutoMLJobConfig.Mode.

            • AlgorithmsConfig should not be set when the training mode AutoMLJobConfig.Mode is set to AUTO.

            • When AlgorithmsConfig is provided, one AutoMLAlgorithms attribute must be set and one only. If the list of algorithms provided as values for AutoMLAlgorithms is empty, CandidateGenerationConfig uses the full set of algorithms for the given training mode.

            • When AlgorithmsConfig is not provided, CandidateGenerationConfig uses the full set of algorithms for the given training mode.

          For the list of all algorithms per training mode, see AlgorithmConfig.

          For more information on each algorithm, see the Algorithm support section in the Autopilot developer guide.

          • For the time-series forecasting problem type TimeSeriesForecastingJobConfig, choose your algorithms from the list provided in AlgorithmConfig. For more information on each algorithm, see the Algorithms support for time-series forecasting section in the Autopilot developer guide.

            • When AlgorithmsConfig is provided, one AutoMLAlgorithms attribute must be set and one only. If the list of algorithms provided as values for AutoMLAlgorithms is empty, CandidateGenerationConfig uses the full set of algorithms for time-series forecasting.

            • When AlgorithmsConfig is not provided, CandidateGenerationConfig uses the full set of algorithms for time-series forecasting.

          • (dict) –

            The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

            • AutoMLAlgorithms (list) – [REQUIRED]

              The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

              • For the tabular problem type TabularJobConfig:

              Note

              Selected algorithms must belong to the list corresponding to the training mode set in AutoMLJobConfig.Mode ( ENSEMBLING or HYPERPARAMETER_TUNING). Choose a minimum of 1 algorithm.

              • In ENSEMBLING mode:

                • ”catboost”

                • ”extra-trees”

                • ”fastai”

                • ”lightgbm”

                • ”linear-learner”

                • ”nn-torch”

                • ”randomforest”

                • ”xgboost”

              • In HYPERPARAMETER_TUNING mode:

                • ”linear-learner”

                • ”mlp”

                • ”xgboost”

              • For the time-series forecasting problem type TimeSeriesForecastingJobConfig:

                • Choose your algorithms from this list.

                  • ”cnn-qr”

                  • ”deepar”

                  • ”prophet”

                  • ”arima”

                  • ”npts”

                  • ”ets”

              • (string) –

    • TabularJobConfig (dict) –

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

      • CandidateGenerationConfig (dict) –

        The configuration information of how model candidates are generated.

        • AlgorithmsConfig (list) –

          Your Autopilot job trains a default set of algorithms on your dataset. For tabular and time-series data, you can customize the algorithm list by selecting a subset of algorithms for your problem type.

          AlgorithmsConfig stores the customized selection of algorithms to train on your data.

          • For the tabular problem type TabularJobConfig, the list of available algorithms to choose from depends on the training mode set in AutoMLJobConfig.Mode.

            • AlgorithmsConfig should not be set when the training mode AutoMLJobConfig.Mode is set to AUTO.

            • When AlgorithmsConfig is provided, one AutoMLAlgorithms attribute must be set and one only. If the list of algorithms provided as values for AutoMLAlgorithms is empty, CandidateGenerationConfig uses the full set of algorithms for the given training mode.

            • When AlgorithmsConfig is not provided, CandidateGenerationConfig uses the full set of algorithms for the given training mode.

          For the list of all algorithms per training mode, see AlgorithmConfig.

          For more information on each algorithm, see the Algorithm support section in the Autopilot developer guide.

          • For the time-series forecasting problem type TimeSeriesForecastingJobConfig, choose your algorithms from the list provided in AlgorithmConfig. For more information on each algorithm, see the Algorithms support for time-series forecasting section in the Autopilot developer guide.

            • When AlgorithmsConfig is provided, one AutoMLAlgorithms attribute must be set and one only. If the list of algorithms provided as values for AutoMLAlgorithms is empty, CandidateGenerationConfig uses the full set of algorithms for time-series forecasting.

            • When AlgorithmsConfig is not provided, CandidateGenerationConfig uses the full set of algorithms for time-series forecasting.

          • (dict) –

            The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

            • AutoMLAlgorithms (list) – [REQUIRED]

              The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

              • For the tabular problem type TabularJobConfig:

              Note

              Selected algorithms must belong to the list corresponding to the training mode set in AutoMLJobConfig.Mode ( ENSEMBLING or HYPERPARAMETER_TUNING). Choose a minimum of 1 algorithm.

              • In ENSEMBLING mode:

                • ”catboost”

                • ”extra-trees”

                • ”fastai”

                • ”lightgbm”

                • ”linear-learner”

                • ”nn-torch”

                • ”randomforest”

                • ”xgboost”

              • In HYPERPARAMETER_TUNING mode:

                • ”linear-learner”

                • ”mlp”

                • ”xgboost”

              • For the time-series forecasting problem type TimeSeriesForecastingJobConfig:

                • Choose your algorithms from this list.

                  • ”cnn-qr”

                  • ”deepar”

                  • ”prophet”

                  • ”arima”

                  • ”npts”

                  • ”ets”

              • (string) –

      • CompletionCriteria (dict) –

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

        • MaxCandidates (integer) –

          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.

        • MaxRuntimePerTrainingJobInSeconds (integer) –

          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).

        • MaxAutoMLJobRuntimeInSeconds (integer) –

          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.

      • FeatureSpecificationS3Uri (string) –

        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" ... } }

        Note

        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.

      • Mode (string) –

        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.

      • GenerateCandidateDefinitionsOnly (boolean) –

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

      • ProblemType (string) –

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

        Note

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

      • TargetAttributeName (string) – [REQUIRED]

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

      • SampleWeightAttributeName (string) –

        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.

    • TextGenerationJobConfig (dict) –

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

      Note

      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.

      • CompletionCriteria (dict) –

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

        • MaxCandidates (integer) –

          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.

        • MaxRuntimePerTrainingJobInSeconds (integer) –

          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).

        • MaxAutoMLJobRuntimeInSeconds (integer) –

          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.

      • BaseModelName (string) –

        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.

      • TextGenerationHyperParameters (dict) –

        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" }

        • (string) –

          • (string) –

      • ModelAccessConfig (dict) –

        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.

        • AcceptEula (boolean) – [REQUIRED]

          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.

  • RoleArn (string) –

    [REQUIRED]

    The ARN of the role that is used to access the data.

  • Tags (list) –

    An array of key-value pairs. You can use tags to categorize your Amazon Web Services resources in different ways, such as by purpose, owner, or environment. For more information, see Tagging Amazon Web ServicesResources. Tag keys must be unique per resource.

    • (dict) –

      A tag object that consists of a key and an optional value, used to manage metadata for SageMaker Amazon Web Services resources.

      You can add tags to notebook instances, training jobs, hyperparameter tuning jobs, batch transform jobs, models, labeling jobs, work teams, endpoint configurations, and endpoints. For more information on adding tags to SageMaker resources, see AddTags.

      For more information on adding metadata to your Amazon Web Services resources with tagging, see Tagging Amazon Web Services resources. For advice on best practices for managing Amazon Web Services resources with tagging, see Tagging Best Practices: Implement an Effective Amazon Web Services Resource Tagging Strategy.

      • Key (string) – [REQUIRED]

        The tag key. Tag keys must be unique per resource.

      • Value (string) – [REQUIRED]

        The tag value.

  • SecurityConfig (dict) –

    The security configuration for traffic encryption or Amazon VPC settings.

    • VolumeKmsKeyId (string) –

      The key used to encrypt stored data.

    • EnableInterContainerTrafficEncryption (boolean) –

      Whether to use traffic encryption between the container layers.

    • VpcConfig (dict) –

      The VPC configuration.

      • SecurityGroupIds (list) – [REQUIRED]

        The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.

        • (string) –

      • Subnets (list) – [REQUIRED]

        The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.

        • (string) –

  • AutoMLJobObjective (dict) –

    Specifies a metric to minimize or maximize as the objective of a job. If not specified, the default objective metric depends on the problem type. For the list of default values per problem type, see AutoMLJobObjective.

    Note

    • For tabular problem types: You must either provide both the AutoMLJobObjective and indicate the type of supervised learning problem in AutoMLProblemTypeConfig ( TabularJobConfig.ProblemType), or none at all.

    • 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.

    • MetricName (string) – [REQUIRED]

      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.

  • ModelDeployConfig (dict) –

    Specifies how to generate the endpoint name for an automatic one-click Autopilot model deployment.

    • AutoGenerateEndpointName (boolean) –

      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.

      Note

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

    • EndpointName (string) –

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

      Note

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

  • DataSplitConfig (dict) –

    This structure specifies how to split the data into train and validation datasets.

    The validation and training datasets must contain the same headers. For jobs created by calling CreateAutoMLJob, the validation dataset must be less than 2 GB in size.

    Note

    This attribute must not be set for the time-series forecasting problem type, as Autopilot automatically splits the input dataset into training and validation sets.

    • ValidationFraction (float) –

      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.

  • AutoMLComputeConfig (dict) –

    Specifies the compute configuration for the AutoML job V2.

    • EmrServerlessComputeConfig (dict) –

      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.

Return type:

dict

Returns:

Response Syntax

{
    'AutoMLJobArn': 'string'
}

Response Structure

  • (dict) –

    • AutoMLJobArn (string) –

      The unique ARN assigned to the AutoMLJob when it is created.

Exceptions

  • SageMaker.Client.exceptions.ResourceInUse

  • SageMaker.Client.exceptions.ResourceLimitExceeded