class Aws::SageMaker::Types::CreateTrainingJobRequest

@note When making an API call, you may pass CreateTrainingJobRequest

data as a hash:

    {
      training_job_name: "TrainingJobName", # required
      hyper_parameters: {
        "HyperParameterKey" => "HyperParameterValue",
      },
      algorithm_specification: { # required
        training_image: "AlgorithmImage",
        algorithm_name: "ArnOrName",
        training_input_mode: "Pipe", # required, accepts Pipe, File
        metric_definitions: [
          {
            name: "MetricName", # required
            regex: "MetricRegex", # required
          },
        ],
        enable_sage_maker_metrics_time_series: false,
      },
      role_arn: "RoleArn", # required
      input_data_config: [
        {
          channel_name: "ChannelName", # required
          data_source: { # required
            s3_data_source: {
              s3_data_type: "ManifestFile", # required, accepts ManifestFile, S3Prefix, AugmentedManifestFile
              s3_uri: "S3Uri", # required
              s3_data_distribution_type: "FullyReplicated", # accepts FullyReplicated, ShardedByS3Key
              attribute_names: ["AttributeName"],
            },
            file_system_data_source: {
              file_system_id: "FileSystemId", # required
              file_system_access_mode: "rw", # required, accepts rw, ro
              file_system_type: "EFS", # required, accepts EFS, FSxLustre
              directory_path: "DirectoryPath", # required
            },
          },
          content_type: "ContentType",
          compression_type: "None", # accepts None, Gzip
          record_wrapper_type: "None", # accepts None, RecordIO
          input_mode: "Pipe", # accepts Pipe, File
          shuffle_config: {
            seed: 1, # required
          },
        },
      ],
      output_data_config: { # required
        kms_key_id: "KmsKeyId",
        s3_output_path: "S3Uri", # required
      },
      resource_config: { # required
        instance_type: "ml.m4.xlarge", # required, accepts ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge, ml.p4d.24xlarge, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.c5n.xlarge, ml.c5n.2xlarge, ml.c5n.4xlarge, ml.c5n.9xlarge, ml.c5n.18xlarge
        instance_count: 1, # required
        volume_size_in_gb: 1, # required
        volume_kms_key_id: "KmsKeyId",
      },
      vpc_config: {
        security_group_ids: ["SecurityGroupId"], # required
        subnets: ["SubnetId"], # required
      },
      stopping_condition: { # required
        max_runtime_in_seconds: 1,
        max_wait_time_in_seconds: 1,
      },
      tags: [
        {
          key: "TagKey", # required
          value: "TagValue", # required
        },
      ],
      enable_network_isolation: false,
      enable_inter_container_traffic_encryption: false,
      enable_managed_spot_training: false,
      checkpoint_config: {
        s3_uri: "S3Uri", # required
        local_path: "DirectoryPath",
      },
      debug_hook_config: {
        local_path: "DirectoryPath",
        s3_output_path: "S3Uri", # required
        hook_parameters: {
          "ConfigKey" => "ConfigValue",
        },
        collection_configurations: [
          {
            collection_name: "CollectionName",
            collection_parameters: {
              "ConfigKey" => "ConfigValue",
            },
          },
        ],
      },
      debug_rule_configurations: [
        {
          rule_configuration_name: "RuleConfigurationName", # required
          local_path: "DirectoryPath",
          s3_output_path: "S3Uri",
          rule_evaluator_image: "AlgorithmImage", # required
          instance_type: "ml.t3.medium", # accepts ml.t3.medium, ml.t3.large, ml.t3.xlarge, ml.t3.2xlarge, ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.r5.large, ml.r5.xlarge, ml.r5.2xlarge, ml.r5.4xlarge, ml.r5.8xlarge, ml.r5.12xlarge, ml.r5.16xlarge, ml.r5.24xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge
          volume_size_in_gb: 1,
          rule_parameters: {
            "ConfigKey" => "ConfigValue",
          },
        },
      ],
      tensor_board_output_config: {
        local_path: "DirectoryPath",
        s3_output_path: "S3Uri", # required
      },
      experiment_config: {
        experiment_name: "ExperimentEntityName",
        trial_name: "ExperimentEntityName",
        trial_component_display_name: "ExperimentEntityName",
      },
      profiler_config: {
        s3_output_path: "S3Uri", # required
        profiling_interval_in_milliseconds: 1,
        profiling_parameters: {
          "ConfigKey" => "ConfigValue",
        },
      },
      profiler_rule_configurations: [
        {
          rule_configuration_name: "RuleConfigurationName", # required
          local_path: "DirectoryPath",
          s3_output_path: "S3Uri",
          rule_evaluator_image: "AlgorithmImage", # required
          instance_type: "ml.t3.medium", # accepts ml.t3.medium, ml.t3.large, ml.t3.xlarge, ml.t3.2xlarge, ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.r5.large, ml.r5.xlarge, ml.r5.2xlarge, ml.r5.4xlarge, ml.r5.8xlarge, ml.r5.12xlarge, ml.r5.16xlarge, ml.r5.24xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge
          volume_size_in_gb: 1,
          rule_parameters: {
            "ConfigKey" => "ConfigValue",
          },
        },
      ],
      environment: {
        "TrainingEnvironmentKey" => "TrainingEnvironmentValue",
      },
      retry_strategy: {
        maximum_retry_attempts: 1, # required
      },
    }

@!attribute [rw] training_job_name

The name of the training job. The name must be unique within an
Amazon Web Services Region in an Amazon Web Services account.
@return [String]

@!attribute [rw] hyper_parameters

Algorithm-specific parameters that influence the quality of the
model. You set hyperparameters before you start the learning
process. For a list of hyperparameters for each training algorithm
provided by Amazon SageMaker, see [Algorithms][1].

You can specify a maximum of 100 hyperparameters. Each
hyperparameter is a key-value pair. Each key and value is limited to
256 characters, as specified by the `Length Constraint`.

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html
@return [Hash<String,String>]

@!attribute [rw] algorithm_specification

The registry path of the Docker image that contains the training
algorithm and algorithm-specific metadata, including the input mode.
For more information about algorithms provided by Amazon SageMaker,
see [Algorithms][1]. For information about providing your own
algorithms, see [Using Your Own Algorithms with Amazon
SageMaker][2].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html
[2]: https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms.html
@return [Types::AlgorithmSpecification]

@!attribute [rw] role_arn

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

During model training, Amazon SageMaker needs your permission to
read input data from an S3 bucket, download a Docker image that
contains training code, write model artifacts to an S3 bucket, write
logs to Amazon CloudWatch Logs, and publish metrics to Amazon
CloudWatch. You grant permissions for all of these tasks to an IAM
role. For more information, see [Amazon SageMaker Roles][1].

<note markdown="1"> To be able to pass this role to Amazon SageMaker, the caller of this
API must have the `iam:PassRole` permission.

 </note>

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-roles.html
@return [String]

@!attribute [rw] input_data_config

An array of `Channel` objects. Each channel is a named input source.
`InputDataConfig` describes the input data and its location.

Algorithms can accept input data from one or more channels. For
example, an algorithm might have two channels of input data,
`training_data` and `validation_data`. The configuration for each
channel provides the S3, EFS, or FSx location where the input data
is stored. It also provides information about the stored data: the
MIME type, compression method, and whether the data is wrapped in
RecordIO format.

Depending on the input mode that the algorithm supports, Amazon
SageMaker either copies input data files from an S3 bucket to a
local directory in the Docker container, or makes it available as
input streams. For example, if you specify an EFS location, input
data files will be made available as input streams. They do not need
to be downloaded.
@return [Array<Types::Channel>]

@!attribute [rw] output_data_config

Specifies the path to the S3 location where you want to store model
artifacts. Amazon SageMaker creates subfolders for the artifacts.
@return [Types::OutputDataConfig]

@!attribute [rw] resource_config

The resources, including the ML compute instances and ML storage
volumes, to use for model training.

ML storage volumes store model artifacts and incremental states.
Training algorithms might also use ML storage volumes for scratch
space. If you want Amazon SageMaker to use the ML storage volume to
store the training data, choose `File` as the `TrainingInputMode` in
the algorithm specification. For distributed training algorithms,
specify an instance count greater than 1.
@return [Types::ResourceConfig]

@!attribute [rw] vpc_config

A VpcConfig object that specifies the VPC that you want your
training job to connect to. Control access to and from your training
container by configuring the VPC. For more information, see [Protect
Training Jobs by Using an Amazon Virtual Private Cloud][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/train-vpc.html
@return [Types::VpcConfig]

@!attribute [rw] stopping_condition

Specifies a limit to how long a model training job can run. It also
specifies how long a managed Spot training job has to complete. When
the job reaches the time limit, Amazon SageMaker ends the training
job. Use this API to cap model training costs.

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

@!attribute [rw] tags

An array of key-value pairs. You can use tags to categorize your
Amazon Web Services resources in different ways, for example, by
purpose, owner, or environment. For more information, see [Tagging
Amazon Web Services Resources][1].

[1]: https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html
@return [Array<Types::Tag>]

@!attribute [rw] enable_network_isolation

Isolates the training container. No inbound or outbound network
calls can be made, except for calls between peers within a training
cluster for distributed training. If you enable network isolation
for training jobs that are configured to use a VPC, Amazon SageMaker
downloads and uploads customer data and model artifacts through the
specified VPC, but the training container does not have network
access.
@return [Boolean]

@!attribute [rw] enable_inter_container_traffic_encryption

To encrypt all communications between ML compute instances in
distributed training, choose `True`. Encryption provides greater
security for distributed training, but training might take longer.
How long it takes depends on the amount of communication between
compute instances, especially if you use a deep learning algorithm
in distributed training. For more information, see [Protect
Communications Between ML Compute Instances in a Distributed
Training Job][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/train-encrypt.html
@return [Boolean]

@!attribute [rw] enable_managed_spot_training

To train models using managed spot training, choose `True`. Managed
spot training provides a fully managed and scalable infrastructure
for training machine learning models. this option is useful when
training jobs can be interrupted and when there is flexibility when
the training job is run.

The complete and intermediate results of jobs are stored in an
Amazon S3 bucket, and can be used as a starting point to train
models incrementally. Amazon SageMaker provides metrics and logs in
CloudWatch. They can be used to see when managed spot training jobs
are running, interrupted, resumed, or completed.
@return [Boolean]

@!attribute [rw] checkpoint_config

Contains information about the output location for managed spot
training checkpoint data.
@return [Types::CheckpointConfig]

@!attribute [rw] debug_hook_config

Configuration information for the Debugger hook parameters, metric
and tensor collections, and storage paths. To learn more about how
to configure the `DebugHookConfig` parameter, see [Use the SageMaker
and Debugger Configuration API Operations to Create, Update, and
Debug Your Training Job][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/debugger-createtrainingjob-api.html
@return [Types::DebugHookConfig]

@!attribute [rw] debug_rule_configurations

Configuration information for Debugger rules for debugging output
tensors.
@return [Array<Types::DebugRuleConfiguration>]

@!attribute [rw] tensor_board_output_config

Configuration of storage locations for the Debugger TensorBoard
output data.
@return [Types::TensorBoardOutputConfig]

@!attribute [rw] experiment_config

Associates a SageMaker job as a trial component with an experiment
and trial. Specified when you call the following APIs:

* CreateProcessingJob

* CreateTrainingJob

* CreateTransformJob
@return [Types::ExperimentConfig]

@!attribute [rw] profiler_config

Configuration information for Debugger system monitoring, framework
profiling, and storage paths.
@return [Types::ProfilerConfig]

@!attribute [rw] profiler_rule_configurations

Configuration information for Debugger rules for profiling system
and framework metrics.
@return [Array<Types::ProfilerRuleConfiguration>]

@!attribute [rw] environment

The environment variables to set in the Docker container.
@return [Hash<String,String>]

@!attribute [rw] retry_strategy

The number of times to retry the job when the job fails due to an
`InternalServerError`.
@return [Types::RetryStrategy]

@see docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CreateTrainingJobRequest AWS API Documentation

Constants

SENSITIVE