Copyright | (c) 2013-2023 Brendan Hay |
---|---|
License | Mozilla Public License, v. 2.0. |
Maintainer | Brendan Hay |
Stability | auto-generated |
Portability | non-portable (GHC extensions) |
Safe Haskell | Safe-Inferred |
Language | Haskell2010 |
Returns information about a training job.
Some of the attributes below only appear if the training job
successfully starts. If the training job fails, TrainingJobStatus
is
Failed
and, depending on the FailureReason
, attributes like
TrainingStartTime
, TrainingTimeInSeconds
, TrainingEndTime
, and
BillableTimeInSeconds
may not be present in the response.
Synopsis
- data DescribeTrainingJob = DescribeTrainingJob' {}
- newDescribeTrainingJob :: Text -> DescribeTrainingJob
- describeTrainingJob_trainingJobName :: Lens' DescribeTrainingJob Text
- data DescribeTrainingJobResponse = DescribeTrainingJobResponse' {
- autoMLJobArn :: Maybe Text
- billableTimeInSeconds :: Maybe Natural
- checkpointConfig :: Maybe CheckpointConfig
- debugHookConfig :: Maybe DebugHookConfig
- debugRuleConfigurations :: Maybe [DebugRuleConfiguration]
- debugRuleEvaluationStatuses :: Maybe [DebugRuleEvaluationStatus]
- enableInterContainerTrafficEncryption :: Maybe Bool
- enableManagedSpotTraining :: Maybe Bool
- enableNetworkIsolation :: Maybe Bool
- environment :: Maybe (HashMap Text Text)
- experimentConfig :: Maybe ExperimentConfig
- failureReason :: Maybe Text
- finalMetricDataList :: Maybe [MetricData]
- hyperParameters :: Maybe (HashMap Text Text)
- inputDataConfig :: Maybe (NonEmpty Channel)
- labelingJobArn :: Maybe Text
- lastModifiedTime :: Maybe POSIX
- outputDataConfig :: Maybe OutputDataConfig
- profilerConfig :: Maybe ProfilerConfig
- profilerRuleConfigurations :: Maybe [ProfilerRuleConfiguration]
- profilerRuleEvaluationStatuses :: Maybe [ProfilerRuleEvaluationStatus]
- profilingStatus :: Maybe ProfilingStatus
- retryStrategy :: Maybe RetryStrategy
- roleArn :: Maybe Text
- secondaryStatusTransitions :: Maybe [SecondaryStatusTransition]
- tensorBoardOutputConfig :: Maybe TensorBoardOutputConfig
- trainingEndTime :: Maybe POSIX
- trainingStartTime :: Maybe POSIX
- trainingTimeInSeconds :: Maybe Natural
- tuningJobArn :: Maybe Text
- vpcConfig :: Maybe VpcConfig
- warmPoolStatus :: Maybe WarmPoolStatus
- httpStatus :: Int
- trainingJobName :: Text
- trainingJobArn :: Text
- modelArtifacts :: ModelArtifacts
- trainingJobStatus :: TrainingJobStatus
- secondaryStatus :: SecondaryStatus
- algorithmSpecification :: AlgorithmSpecification
- resourceConfig :: ResourceConfig
- stoppingCondition :: StoppingCondition
- creationTime :: POSIX
- newDescribeTrainingJobResponse :: Int -> Text -> Text -> ModelArtifacts -> TrainingJobStatus -> SecondaryStatus -> AlgorithmSpecification -> ResourceConfig -> StoppingCondition -> UTCTime -> DescribeTrainingJobResponse
- describeTrainingJobResponse_autoMLJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text)
- describeTrainingJobResponse_billableTimeInSeconds :: Lens' DescribeTrainingJobResponse (Maybe Natural)
- describeTrainingJobResponse_checkpointConfig :: Lens' DescribeTrainingJobResponse (Maybe CheckpointConfig)
- describeTrainingJobResponse_debugHookConfig :: Lens' DescribeTrainingJobResponse (Maybe DebugHookConfig)
- describeTrainingJobResponse_debugRuleConfigurations :: Lens' DescribeTrainingJobResponse (Maybe [DebugRuleConfiguration])
- describeTrainingJobResponse_debugRuleEvaluationStatuses :: Lens' DescribeTrainingJobResponse (Maybe [DebugRuleEvaluationStatus])
- describeTrainingJobResponse_enableInterContainerTrafficEncryption :: Lens' DescribeTrainingJobResponse (Maybe Bool)
- describeTrainingJobResponse_enableManagedSpotTraining :: Lens' DescribeTrainingJobResponse (Maybe Bool)
- describeTrainingJobResponse_enableNetworkIsolation :: Lens' DescribeTrainingJobResponse (Maybe Bool)
- describeTrainingJobResponse_environment :: Lens' DescribeTrainingJobResponse (Maybe (HashMap Text Text))
- describeTrainingJobResponse_experimentConfig :: Lens' DescribeTrainingJobResponse (Maybe ExperimentConfig)
- describeTrainingJobResponse_failureReason :: Lens' DescribeTrainingJobResponse (Maybe Text)
- describeTrainingJobResponse_finalMetricDataList :: Lens' DescribeTrainingJobResponse (Maybe [MetricData])
- describeTrainingJobResponse_hyperParameters :: Lens' DescribeTrainingJobResponse (Maybe (HashMap Text Text))
- describeTrainingJobResponse_inputDataConfig :: Lens' DescribeTrainingJobResponse (Maybe (NonEmpty Channel))
- describeTrainingJobResponse_labelingJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text)
- describeTrainingJobResponse_lastModifiedTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime)
- describeTrainingJobResponse_outputDataConfig :: Lens' DescribeTrainingJobResponse (Maybe OutputDataConfig)
- describeTrainingJobResponse_profilerConfig :: Lens' DescribeTrainingJobResponse (Maybe ProfilerConfig)
- describeTrainingJobResponse_profilerRuleConfigurations :: Lens' DescribeTrainingJobResponse (Maybe [ProfilerRuleConfiguration])
- describeTrainingJobResponse_profilerRuleEvaluationStatuses :: Lens' DescribeTrainingJobResponse (Maybe [ProfilerRuleEvaluationStatus])
- describeTrainingJobResponse_profilingStatus :: Lens' DescribeTrainingJobResponse (Maybe ProfilingStatus)
- describeTrainingJobResponse_retryStrategy :: Lens' DescribeTrainingJobResponse (Maybe RetryStrategy)
- describeTrainingJobResponse_roleArn :: Lens' DescribeTrainingJobResponse (Maybe Text)
- describeTrainingJobResponse_secondaryStatusTransitions :: Lens' DescribeTrainingJobResponse (Maybe [SecondaryStatusTransition])
- describeTrainingJobResponse_tensorBoardOutputConfig :: Lens' DescribeTrainingJobResponse (Maybe TensorBoardOutputConfig)
- describeTrainingJobResponse_trainingEndTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime)
- describeTrainingJobResponse_trainingStartTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime)
- describeTrainingJobResponse_trainingTimeInSeconds :: Lens' DescribeTrainingJobResponse (Maybe Natural)
- describeTrainingJobResponse_tuningJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text)
- describeTrainingJobResponse_vpcConfig :: Lens' DescribeTrainingJobResponse (Maybe VpcConfig)
- describeTrainingJobResponse_warmPoolStatus :: Lens' DescribeTrainingJobResponse (Maybe WarmPoolStatus)
- describeTrainingJobResponse_httpStatus :: Lens' DescribeTrainingJobResponse Int
- describeTrainingJobResponse_trainingJobName :: Lens' DescribeTrainingJobResponse Text
- describeTrainingJobResponse_trainingJobArn :: Lens' DescribeTrainingJobResponse Text
- describeTrainingJobResponse_modelArtifacts :: Lens' DescribeTrainingJobResponse ModelArtifacts
- describeTrainingJobResponse_trainingJobStatus :: Lens' DescribeTrainingJobResponse TrainingJobStatus
- describeTrainingJobResponse_secondaryStatus :: Lens' DescribeTrainingJobResponse SecondaryStatus
- describeTrainingJobResponse_algorithmSpecification :: Lens' DescribeTrainingJobResponse AlgorithmSpecification
- describeTrainingJobResponse_resourceConfig :: Lens' DescribeTrainingJobResponse ResourceConfig
- describeTrainingJobResponse_stoppingCondition :: Lens' DescribeTrainingJobResponse StoppingCondition
- describeTrainingJobResponse_creationTime :: Lens' DescribeTrainingJobResponse UTCTime
Creating a Request
data DescribeTrainingJob Source #
See: newDescribeTrainingJob
smart constructor.
DescribeTrainingJob' | |
|
Instances
newDescribeTrainingJob Source #
Create a value of DescribeTrainingJob
with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
DescribeTrainingJob
, describeTrainingJob_trainingJobName
- The name of the training job.
Request Lenses
describeTrainingJob_trainingJobName :: Lens' DescribeTrainingJob Text Source #
The name of the training job.
Destructuring the Response
data DescribeTrainingJobResponse Source #
See: newDescribeTrainingJobResponse
smart constructor.
DescribeTrainingJobResponse' | |
|
Instances
newDescribeTrainingJobResponse Source #
:: Int | |
-> Text | |
-> Text | |
-> ModelArtifacts | |
-> TrainingJobStatus | |
-> SecondaryStatus | |
-> AlgorithmSpecification | |
-> ResourceConfig | |
-> StoppingCondition | |
-> UTCTime | |
-> DescribeTrainingJobResponse |
Create a value of DescribeTrainingJobResponse
with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
DescribeTrainingJobResponse
, describeTrainingJobResponse_autoMLJobArn
- The Amazon Resource Name (ARN) of an AutoML job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_billableTimeInSeconds
- The billable time in seconds. Billable time refers to the absolute
wall-clock time.
Multiply BillableTimeInSeconds
by the number of instances
(InstanceCount
) in your training cluster to get the total compute time
SageMaker bills you if you run distributed training. The formula is as
follows: BillableTimeInSeconds * InstanceCount
.
You can calculate the savings from using managed spot training using the
formula (1 - BillableTimeInSeconds / TrainingTimeInSeconds) * 100
.
For example, if BillableTimeInSeconds
is 100 and
TrainingTimeInSeconds
is 500, the savings is 80%.
DescribeTrainingJobResponse
, describeTrainingJobResponse_checkpointConfig
- Undocumented member.
DescribeTrainingJobResponse
, describeTrainingJobResponse_debugHookConfig
- Undocumented member.
DescribeTrainingJobResponse
, describeTrainingJobResponse_debugRuleConfigurations
- Configuration information for Amazon SageMaker Debugger rules for
debugging output tensors.
DescribeTrainingJobResponse
, describeTrainingJobResponse_debugRuleEvaluationStatuses
- Evaluation status of Amazon SageMaker Debugger rules for debugging on a
training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_enableInterContainerTrafficEncryption
- 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 algorithms in
distributed training.
DescribeTrainingJobResponse
, describeTrainingJobResponse_enableManagedSpotTraining
- A Boolean indicating whether managed spot training is enabled (True
)
or not (False
).
DescribeTrainingJobResponse
, describeTrainingJobResponse_enableNetworkIsolation
- If you want to allow inbound or outbound network calls, except for calls
between peers within a training cluster for distributed training, choose
True
. If you enable network isolation for training jobs that are
configured to use a VPC, SageMaker downloads and uploads customer data
and model artifacts through the specified VPC, but the training
container does not have network access.
DescribeTrainingJobResponse
, describeTrainingJobResponse_environment
- The environment variables to set in the Docker container.
DescribeTrainingJobResponse
, describeTrainingJobResponse_experimentConfig
- Undocumented member.
DescribeTrainingJobResponse
, describeTrainingJobResponse_failureReason
- If the training job failed, the reason it failed.
DescribeTrainingJobResponse
, describeTrainingJobResponse_finalMetricDataList
- A collection of MetricData
objects that specify the names, values, and
dates and times that the training algorithm emitted to Amazon
CloudWatch.
DescribeTrainingJobResponse
, describeTrainingJobResponse_hyperParameters
- Algorithm-specific parameters.
DescribeTrainingJobResponse
, describeTrainingJobResponse_inputDataConfig
- An array of Channel
objects that describes each data input channel.
DescribeTrainingJobResponse
, describeTrainingJobResponse_labelingJobArn
- The Amazon Resource Name (ARN) of the SageMaker Ground Truth labeling
job that created the transform or training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_lastModifiedTime
- A timestamp that indicates when the status of the training job was last
modified.
DescribeTrainingJobResponse
, describeTrainingJobResponse_outputDataConfig
- The S3 path where model artifacts that you configured when creating the
job are stored. SageMaker creates subfolders for model artifacts.
$sel:profilerConfig:DescribeTrainingJobResponse'
, describeTrainingJobResponse_profilerConfig
- Undocumented member.
$sel:profilerRuleConfigurations:DescribeTrainingJobResponse'
, describeTrainingJobResponse_profilerRuleConfigurations
- Configuration information for Amazon SageMaker Debugger rules for
profiling system and framework metrics.
$sel:profilerRuleEvaluationStatuses:DescribeTrainingJobResponse'
, describeTrainingJobResponse_profilerRuleEvaluationStatuses
- Evaluation status of Amazon SageMaker Debugger rules for profiling on a
training job.
$sel:profilingStatus:DescribeTrainingJobResponse'
, describeTrainingJobResponse_profilingStatus
- Profiling status of a training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_retryStrategy
- The number of times to retry the job when the job fails due to an
InternalServerError
.
DescribeTrainingJobResponse
, describeTrainingJobResponse_roleArn
- The Amazon Web Services Identity and Access Management (IAM) role
configured for the training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_secondaryStatusTransitions
- A history of all of the secondary statuses that the training job has
transitioned through.
DescribeTrainingJobResponse
, describeTrainingJobResponse_tensorBoardOutputConfig
- Undocumented member.
DescribeTrainingJobResponse
, describeTrainingJobResponse_trainingEndTime
- Indicates the time when the training job ends on training instances. You
are billed for the time interval between the value of
TrainingStartTime
and this time. For successful jobs and stopped jobs,
this is the time after model artifacts are uploaded. For failed jobs,
this is the time when SageMaker detects a job failure.
DescribeTrainingJobResponse
, describeTrainingJobResponse_trainingStartTime
- Indicates the time when the training job starts on training instances.
You are billed for the time interval between this time and the value of
TrainingEndTime
. The start time in CloudWatch Logs might be later than
this time. The difference is due to the time it takes to download the
training data and to the size of the training container.
DescribeTrainingJobResponse
, describeTrainingJobResponse_trainingTimeInSeconds
- The training time in seconds.
DescribeTrainingJobResponse
, describeTrainingJobResponse_tuningJobArn
- The Amazon Resource Name (ARN) of the associated hyperparameter tuning
job if the training job was launched by a hyperparameter tuning job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_vpcConfig
- A VpcConfig object that specifies the VPC that this training job has
access to. For more information, see
Protect Training Jobs by Using an Amazon Virtual Private Cloud.
DescribeTrainingJobResponse
, describeTrainingJobResponse_warmPoolStatus
- The status of the warm pool associated with the training job.
$sel:httpStatus:DescribeTrainingJobResponse'
, describeTrainingJobResponse_httpStatus
- The response's http status code.
DescribeTrainingJob
, describeTrainingJobResponse_trainingJobName
- Name of the model training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_trainingJobArn
- The Amazon Resource Name (ARN) of the training job.
DescribeTrainingJobResponse
, describeTrainingJobResponse_modelArtifacts
- Information about the Amazon S3 location that is configured for storing
model artifacts.
DescribeTrainingJobResponse
, describeTrainingJobResponse_trainingJobStatus
- The status of the training job.
SageMaker provides the following training job statuses:
InProgress
- The training is in progress.Completed
- The training job has completed.Failed
- The training job has failed. To see the reason for the failure, see theFailureReason
field in the response to aDescribeTrainingJobResponse
call.Stopping
- The training job is stopping.Stopped
- The training job has stopped.
For more detailed information, see SecondaryStatus
.
DescribeTrainingJobResponse
, describeTrainingJobResponse_secondaryStatus
- Provides detailed information about the state of the training job. For
detailed information on the secondary status of the training job, see
StatusMessage
under SecondaryStatusTransition.
SageMaker provides primary statuses and secondary statuses that apply to each of them:
- InProgress
- -
Starting
- Starting the training job.Downloading
- An optional stage for algorithms that supportFile
training input mode. It indicates that data is being downloaded to the ML storage volumes.Training
- Training is in progress.Interrupted
- The job stopped because the managed spot training instances were interrupted.Uploading
- Training is complete and the model artifacts are being uploaded to the S3 location.
- Completed
- -
Completed
- The training job has completed. - Failed
- -
Failed
- The training job has failed. The reason for the failure is returned in theFailureReason
field ofDescribeTrainingJobResponse
. - Stopped
- -
MaxRuntimeExceeded
- The job stopped because it exceeded the maximum allowed runtime.MaxWaitTimeExceeded
- The job stopped because it exceeded the maximum allowed wait time.Stopped
- The training job has stopped.
- Stopping
- -
Stopping
- Stopping the training job.
Valid values for SecondaryStatus
are subject to change.
We no longer support the following secondary statuses:
LaunchingMLInstances
PreparingTraining
DownloadingTrainingImage
DescribeTrainingJobResponse
, describeTrainingJobResponse_algorithmSpecification
- Information about the algorithm used for training, and algorithm
metadata.
DescribeTrainingJobResponse
, describeTrainingJobResponse_resourceConfig
- Resources, including ML compute instances and ML storage volumes, that
are configured for model training.
DescribeTrainingJobResponse
, describeTrainingJobResponse_stoppingCondition
- 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, SageMaker ends the training job. Use this
API to cap model training costs.
To stop a job, 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.
DescribeTrainingJobResponse
, describeTrainingJobResponse_creationTime
- A timestamp that indicates when the training job was created.
Response Lenses
describeTrainingJobResponse_autoMLJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text) Source #
The Amazon Resource Name (ARN) of an AutoML job.
describeTrainingJobResponse_billableTimeInSeconds :: Lens' DescribeTrainingJobResponse (Maybe Natural) Source #
The billable time in seconds. Billable time refers to the absolute wall-clock time.
Multiply BillableTimeInSeconds
by the number of instances
(InstanceCount
) in your training cluster to get the total compute time
SageMaker bills you if you run distributed training. The formula is as
follows: BillableTimeInSeconds * InstanceCount
.
You can calculate the savings from using managed spot training using the
formula (1 - BillableTimeInSeconds / TrainingTimeInSeconds) * 100
.
For example, if BillableTimeInSeconds
is 100 and
TrainingTimeInSeconds
is 500, the savings is 80%.
describeTrainingJobResponse_checkpointConfig :: Lens' DescribeTrainingJobResponse (Maybe CheckpointConfig) Source #
Undocumented member.
describeTrainingJobResponse_debugHookConfig :: Lens' DescribeTrainingJobResponse (Maybe DebugHookConfig) Source #
Undocumented member.
describeTrainingJobResponse_debugRuleConfigurations :: Lens' DescribeTrainingJobResponse (Maybe [DebugRuleConfiguration]) Source #
Configuration information for Amazon SageMaker Debugger rules for debugging output tensors.
describeTrainingJobResponse_debugRuleEvaluationStatuses :: Lens' DescribeTrainingJobResponse (Maybe [DebugRuleEvaluationStatus]) Source #
Evaluation status of Amazon SageMaker Debugger rules for debugging on a training job.
describeTrainingJobResponse_enableInterContainerTrafficEncryption :: Lens' DescribeTrainingJobResponse (Maybe Bool) Source #
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 algorithms in
distributed training.
describeTrainingJobResponse_enableManagedSpotTraining :: Lens' DescribeTrainingJobResponse (Maybe Bool) Source #
A Boolean indicating whether managed spot training is enabled (True
)
or not (False
).
describeTrainingJobResponse_enableNetworkIsolation :: Lens' DescribeTrainingJobResponse (Maybe Bool) Source #
If you want to allow inbound or outbound network calls, except for calls
between peers within a training cluster for distributed training, choose
True
. If you enable network isolation for training jobs that are
configured to use a VPC, SageMaker downloads and uploads customer data
and model artifacts through the specified VPC, but the training
container does not have network access.
describeTrainingJobResponse_environment :: Lens' DescribeTrainingJobResponse (Maybe (HashMap Text Text)) Source #
The environment variables to set in the Docker container.
describeTrainingJobResponse_experimentConfig :: Lens' DescribeTrainingJobResponse (Maybe ExperimentConfig) Source #
Undocumented member.
describeTrainingJobResponse_failureReason :: Lens' DescribeTrainingJobResponse (Maybe Text) Source #
If the training job failed, the reason it failed.
describeTrainingJobResponse_finalMetricDataList :: Lens' DescribeTrainingJobResponse (Maybe [MetricData]) Source #
A collection of MetricData
objects that specify the names, values, and
dates and times that the training algorithm emitted to Amazon
CloudWatch.
describeTrainingJobResponse_hyperParameters :: Lens' DescribeTrainingJobResponse (Maybe (HashMap Text Text)) Source #
Algorithm-specific parameters.
describeTrainingJobResponse_inputDataConfig :: Lens' DescribeTrainingJobResponse (Maybe (NonEmpty Channel)) Source #
An array of Channel
objects that describes each data input channel.
describeTrainingJobResponse_labelingJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text) Source #
The Amazon Resource Name (ARN) of the SageMaker Ground Truth labeling job that created the transform or training job.
describeTrainingJobResponse_lastModifiedTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime) Source #
A timestamp that indicates when the status of the training job was last modified.
describeTrainingJobResponse_outputDataConfig :: Lens' DescribeTrainingJobResponse (Maybe OutputDataConfig) Source #
The S3 path where model artifacts that you configured when creating the job are stored. SageMaker creates subfolders for model artifacts.
describeTrainingJobResponse_profilerConfig :: Lens' DescribeTrainingJobResponse (Maybe ProfilerConfig) Source #
Undocumented member.
describeTrainingJobResponse_profilerRuleConfigurations :: Lens' DescribeTrainingJobResponse (Maybe [ProfilerRuleConfiguration]) Source #
Configuration information for Amazon SageMaker Debugger rules for profiling system and framework metrics.
describeTrainingJobResponse_profilerRuleEvaluationStatuses :: Lens' DescribeTrainingJobResponse (Maybe [ProfilerRuleEvaluationStatus]) Source #
Evaluation status of Amazon SageMaker Debugger rules for profiling on a training job.
describeTrainingJobResponse_profilingStatus :: Lens' DescribeTrainingJobResponse (Maybe ProfilingStatus) Source #
Profiling status of a training job.
describeTrainingJobResponse_retryStrategy :: Lens' DescribeTrainingJobResponse (Maybe RetryStrategy) Source #
The number of times to retry the job when the job fails due to an
InternalServerError
.
describeTrainingJobResponse_roleArn :: Lens' DescribeTrainingJobResponse (Maybe Text) Source #
The Amazon Web Services Identity and Access Management (IAM) role configured for the training job.
describeTrainingJobResponse_secondaryStatusTransitions :: Lens' DescribeTrainingJobResponse (Maybe [SecondaryStatusTransition]) Source #
A history of all of the secondary statuses that the training job has transitioned through.
describeTrainingJobResponse_tensorBoardOutputConfig :: Lens' DescribeTrainingJobResponse (Maybe TensorBoardOutputConfig) Source #
Undocumented member.
describeTrainingJobResponse_trainingEndTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime) Source #
Indicates the time when the training job ends on training instances. You
are billed for the time interval between the value of
TrainingStartTime
and this time. For successful jobs and stopped jobs,
this is the time after model artifacts are uploaded. For failed jobs,
this is the time when SageMaker detects a job failure.
describeTrainingJobResponse_trainingStartTime :: Lens' DescribeTrainingJobResponse (Maybe UTCTime) Source #
Indicates the time when the training job starts on training instances.
You are billed for the time interval between this time and the value of
TrainingEndTime
. The start time in CloudWatch Logs might be later than
this time. The difference is due to the time it takes to download the
training data and to the size of the training container.
describeTrainingJobResponse_trainingTimeInSeconds :: Lens' DescribeTrainingJobResponse (Maybe Natural) Source #
The training time in seconds.
describeTrainingJobResponse_tuningJobArn :: Lens' DescribeTrainingJobResponse (Maybe Text) Source #
The Amazon Resource Name (ARN) of the associated hyperparameter tuning job if the training job was launched by a hyperparameter tuning job.
describeTrainingJobResponse_vpcConfig :: Lens' DescribeTrainingJobResponse (Maybe VpcConfig) Source #
A VpcConfig object that specifies the VPC that this training job has access to. For more information, see Protect Training Jobs by Using an Amazon Virtual Private Cloud.
describeTrainingJobResponse_warmPoolStatus :: Lens' DescribeTrainingJobResponse (Maybe WarmPoolStatus) Source #
The status of the warm pool associated with the training job.
describeTrainingJobResponse_httpStatus :: Lens' DescribeTrainingJobResponse Int Source #
The response's http status code.
describeTrainingJobResponse_trainingJobName :: Lens' DescribeTrainingJobResponse Text Source #
Name of the model training job.
describeTrainingJobResponse_trainingJobArn :: Lens' DescribeTrainingJobResponse Text Source #
The Amazon Resource Name (ARN) of the training job.
describeTrainingJobResponse_modelArtifacts :: Lens' DescribeTrainingJobResponse ModelArtifacts Source #
Information about the Amazon S3 location that is configured for storing model artifacts.
describeTrainingJobResponse_trainingJobStatus :: Lens' DescribeTrainingJobResponse TrainingJobStatus Source #
The status of the training job.
SageMaker provides the following training job statuses:
InProgress
- The training is in progress.Completed
- The training job has completed.Failed
- The training job has failed. To see the reason for the failure, see theFailureReason
field in the response to aDescribeTrainingJobResponse
call.Stopping
- The training job is stopping.Stopped
- The training job has stopped.
For more detailed information, see SecondaryStatus
.
describeTrainingJobResponse_secondaryStatus :: Lens' DescribeTrainingJobResponse SecondaryStatus Source #
Provides detailed information about the state of the training job. For
detailed information on the secondary status of the training job, see
StatusMessage
under SecondaryStatusTransition.
SageMaker provides primary statuses and secondary statuses that apply to each of them:
- InProgress
- -
Starting
- Starting the training job.Downloading
- An optional stage for algorithms that supportFile
training input mode. It indicates that data is being downloaded to the ML storage volumes.Training
- Training is in progress.Interrupted
- The job stopped because the managed spot training instances were interrupted.Uploading
- Training is complete and the model artifacts are being uploaded to the S3 location.
- Completed
- -
Completed
- The training job has completed. - Failed
- -
Failed
- The training job has failed. The reason for the failure is returned in theFailureReason
field ofDescribeTrainingJobResponse
. - Stopped
- -
MaxRuntimeExceeded
- The job stopped because it exceeded the maximum allowed runtime.MaxWaitTimeExceeded
- The job stopped because it exceeded the maximum allowed wait time.Stopped
- The training job has stopped.
- Stopping
- -
Stopping
- Stopping the training job.
Valid values for SecondaryStatus
are subject to change.
We no longer support the following secondary statuses:
LaunchingMLInstances
PreparingTraining
DownloadingTrainingImage
describeTrainingJobResponse_algorithmSpecification :: Lens' DescribeTrainingJobResponse AlgorithmSpecification Source #
Information about the algorithm used for training, and algorithm metadata.
describeTrainingJobResponse_resourceConfig :: Lens' DescribeTrainingJobResponse ResourceConfig Source #
Resources, including ML compute instances and ML storage volumes, that are configured for model training.
describeTrainingJobResponse_stoppingCondition :: Lens' DescribeTrainingJobResponse StoppingCondition Source #
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, SageMaker ends the training job. Use this API to cap model training costs.
To stop a job, 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.
describeTrainingJobResponse_creationTime :: Lens' DescribeTrainingJobResponse UTCTime Source #
A timestamp that indicates when the training job was created.