model_customization_jobs

Creates, updates, deletes, gets or lists a model_customization_jobs resource.

Overview

Name	model_customization_jobs
Type	Resource
Id	aws.bedrock.model_customization_jobs

Fields

The following fields are returned by SELECT queries:

get_model_customization_job

Name	Datatype	Description
base_model_arn	string	Amazon Resource Name (ARN) of the base model. (pattern: <code>arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}::foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}</code>)
client_request_token	string	The token that you specified in the CreateCustomizationJob request. (pattern: <code>[a-zA-Z0-9]([-a-zA-Z0-9]{0,254}[a-zA-Z0-9])?</code>)
creation_time	string (date-time)	Time that the resource was created.
customization_config	object	A model customization configuration
customization_type	string	The type of model customization. (FINE_TUNING, CONTINUED_PRE_TRAINING, DISTILLATION, REINFORCEMENT_FINE_TUNING, IMPORTED)
end_time	string (date-time)	Time that the resource transitioned to terminal state.
failure_message	string	Information about why the job failed.
hyper_parameters	object	The hyperparameter values for the job. For details on the format for different models, see Custom model hyperparameters.
job_arn	string	The Amazon Resource Name (ARN) of the customization job. (pattern: <code>arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-customization-job/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}/[a-z0-9]{12}</code>)
job_name	string	The name of the customization job. (pattern: <code>[a-zA-Z0-9](-[a-zA-Z0-9+-.])</code>)
last_modified_time	string (date-time)	Time that the resource was last modified.
output_data_config	object	S3 Location of the output data.
output_model_arn	string	The Amazon Resource Name (ARN) of the output model. (pattern: <code>arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:[a-z0-9-]{1,20}:[0-9]{12}:custom-model/(imported|[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2})/[a-z0-9]{12}</code>)
output_model_kms_key_arn	string	The custom model is encrypted at rest using this key. (pattern: <code>arn:aws(-[^:]+)?:kms:[a-zA-Z0-9-]*:[0-9]{12}:key/[a-zA-Z0-9-]{36}</code>)
output_model_name	string	The name of the output model. (pattern: <code>([0-9a-zA-Z][_-]?){1,63}</code>)
role_arn	string	The Amazon Resource Name (ARN) of the IAM role. (pattern: <code>arn:aws(-[^:]+)?:iam::([0-9]{12})?:role/.+</code>)
status	string	The status of the job. A successful job transitions from in-progress to completed when the output model is ready to use. If the job failed, the failure message contains information about why the job failed. (InProgress, Completed, Failed, Stopping, Stopped)
status_details	object	For a Distillation job, the details about the statuses of the sub-tasks of the customization job.
training_data_config	object	S3 Location of the training data.
training_metrics	object	Contains training metrics from the job creation.
validation_data_config	object	Array of up to 10 validators.
validation_metrics	array	The loss metric for each validator that you provided in the createjob request.
vpc_config	object	The configuration of a virtual private cloud (VPC). For more information, see Protect your data using Amazon Virtual Private Cloud and Amazon Web Services PrivateLink.

list_model_customization_jobs

Name	Datatype	Description
base_model_arn	string	Amazon Resource Name (ARN) of the base model. (pattern: <code>arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/((imported)|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}))(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}))</code>)
creation_time	string (date-time)	Creation time of the custom model.
custom_model_arn	string	Amazon Resource Name (ARN) of the custom model. (pattern: <code>arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:[a-z0-9-]{1,20}:[0-9]{12}:custom-model/(imported|[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2})/[a-z0-9]{12}</code>)
custom_model_name	string	Name of the custom model. (pattern: <code>([0-9a-zA-Z][_-]?){1,63}</code>)
customization_type	string	Specifies whether to carry out continued pre-training of a model or whether to fine-tune it. For more information, see Custom models. (FINE_TUNING, CONTINUED_PRE_TRAINING, DISTILLATION, REINFORCEMENT_FINE_TUNING, IMPORTED)
end_time	string (date-time)	Time that the customization job ended.
job_arn	string	Amazon Resource Name (ARN) of the customization job. (pattern: <code>arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-customization-job/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}/[a-z0-9]{12}</code>)
job_name	string	Name of the customization job. (pattern: <code>[a-zA-Z0-9](-[a-zA-Z0-9+-.])</code>)
last_modified_time	string (date-time)	Time that the customization job was last modified.
status	string	Status of the customization job. (InProgress, Completed, Failed, Stopping, Stopped)
status_details	object	Details about the status of the data processing sub-task of the job.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_model_customization_job	select	job_identifier, region		Retrieves the properties associated with a model-customization job, including the status of the job. For more information, see Custom models in the Amazon Bedrock User Guide.
list_model_customization_jobs	select	region	creationTimeAfter, creationTimeBefore, statusEquals, nameContains, maxResults, nextToken, sortBy, sortOrder	Returns a list of model customization jobs that you have submitted. You can filter the jobs to return based on one or more criteria. For more information, see Custom models in the Amazon Bedrock User Guide.
create_model_customization_job	insert	region, jobName, customModelName, roleArn, baseModelIdentifier, trainingDataConfig, outputDataConfig		Creates a fine-tuning job to customize a base model. You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. Amazon Bedrock returns validation loss metrics and output generations after the job completes. For information on the format of training and validation data, see Prepare the datasets. Model-customization jobs are asynchronous and the completion time depends on the base model and the training/validation data size. To monitor a job, use the GetModelCustomizationJob operation to retrieve the job status. For more information, see Custom models in the Amazon Bedrock User Guide.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
job_identifier	string	Identifier for the customization job.
region	string	AWS region (default: us-east-1)
creationTimeAfter	string (date-time)	Return customization jobs created after the specified time.
creationTimeBefore	string (date-time)	Return customization jobs created before the specified time.
maxResults	integer	The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
nameContains	string	Return customization jobs only if the job name contains these characters.
nextToken	string	If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
sortBy	string	The field to sort by in the returned list of jobs.
sortOrder	string	The sort order of the results.
statusEquals	string	Return customization jobs with the specified status.

SELECT examples

get_model_customization_job

Retrieves the properties associated with a model-customization job, including the status of the job. For more information, see Custom models in the Amazon Bedrock User Guide.

SELECT
base_model_arn,
client_request_token,
creation_time,
customization_config,
customization_type,
end_time,
failure_message,
hyper_parameters,
job_arn,
job_name,
last_modified_time,
output_data_config,
output_model_arn,
output_model_kms_key_arn,
output_model_name,
role_arn,
status,
status_details,
training_data_config,
training_metrics,
validation_data_config,
validation_metrics,
vpc_config
FROM aws.bedrock.model_customization_jobs
WHERE job_identifier = '{{ job_identifier }}' -- required
AND region = '{{ region }}' -- required
;

list_model_customization_jobs

Returns a list of model customization jobs that you have submitted. You can filter the jobs to return based on one or more criteria. For more information, see Custom models in the Amazon Bedrock User Guide.

SELECT
base_model_arn,
creation_time,
custom_model_arn,
custom_model_name,
customization_type,
end_time,
job_arn,
job_name,
last_modified_time,
status,
status_details
FROM aws.bedrock.model_customization_jobs
WHERE region = '{{ region }}' -- required
AND creationTimeAfter = '{{ creationTimeAfter }}'
AND creationTimeBefore = '{{ creationTimeBefore }}'
AND statusEquals = '{{ statusEquals }}'
AND nameContains = '{{ nameContains }}'
AND maxResults = '{{ maxResults }}'
AND nextToken = '{{ nextToken }}'
AND sortBy = '{{ sortBy }}'
AND sortOrder = '{{ sortOrder }}'
;

INSERT examples

create_model_customization_job

Creates a fine-tuning job to customize a base model. You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. Amazon Bedrock returns validation loss metrics and output generations after the job completes. For information on the format of training and validation data, see Prepare the datasets. Model-customization jobs are asynchronous and the completion time depends on the base model and the training/validation data size. To monitor a job, use the GetModelCustomizationJob operation to retrieve the job status. For more information, see Custom models in the Amazon Bedrock User Guide.

INSERT INTO aws.bedrock.model_customization_jobs (
jobName,
customModelName,
roleArn,
clientRequestToken,
baseModelIdentifier,
customizationType,
customModelKmsKeyId,
jobTags,
customModelTags,
trainingDataConfig,
validationDataConfig,
outputDataConfig,
hyperParameters,
vpcConfig,
customizationConfig,
region
)
SELECT 
'{{ jobName }}' /* required */,
'{{ customModelName }}' /* required */,
'{{ roleArn }}' /* required */,
'{{ clientRequestToken }}',
'{{ baseModelIdentifier }}' /* required */,
'{{ customizationType }}',
'{{ customModelKmsKeyId }}',
'{{ jobTags }}',
'{{ customModelTags }}',
'{{ trainingDataConfig }}' /* required */,
'{{ validationDataConfig }}',
'{{ outputDataConfig }}' /* required */,
'{{ hyperParameters }}',
'{{ vpcConfig }}',
'{{ customizationConfig }}',
'{{ region }}'
RETURNING
job_arn
;

Manifest

# Description fields are for documentation purposes
- name: model_customization_jobs
props:
  - name: region
    value: "{{ region }}"
    description: Required parameter for the model_customization_jobs resource.
  - name: jobName
    value: "{{ jobName }}"
  - name: customModelName
    value: "{{ customModelName }}"
  - name: roleArn
    value: "{{ roleArn }}"
  - name: clientRequestToken
    value: "{{ clientRequestToken }}"
  - name: baseModelIdentifier
    value: "{{ baseModelIdentifier }}"
  - name: customizationType
    value: "{{ customizationType }}"
    valid_values: ['FINE_TUNING', 'CONTINUED_PRE_TRAINING', 'DISTILLATION', 'REINFORCEMENT_FINE_TUNING', 'IMPORTED']
  - name: customModelKmsKeyId
    value: "{{ customModelKmsKeyId }}"
  - name: jobTags
    value:
      - key: "{{ key }}"
        value: "{{ value }}"
  - name: customModelTags
    value:
      - key: "{{ key }}"
        value: "{{ value }}"
  - name: trainingDataConfig
    description: |
      S3 Location of the training data.
    value:
      s3Uri: "{{ s3Uri }}"
      invocationLogsConfig:
        usePromptResponse: {{ usePromptResponse }}
        invocationLogSource:
          s3Uri: "{{ s3Uri }}"
        requestMetadataFilters:
          equals: "{{ equals }}"
          notEquals: "{{ notEquals }}"
          andAll:
            - equals: "{{ equals }}"
              notEquals: "{{ notEquals }}"
          orAll:
            - equals: "{{ equals }}"
              notEquals: "{{ notEquals }}"
  - name: validationDataConfig
    description: |
      Array of up to 10 validators.
    value:
      validators:
        - s3Uri: "{{ s3Uri }}"
  - name: outputDataConfig
    description: |
      S3 Location of the output data.
    value:
      s3Uri: "{{ s3Uri }}"
  - name: hyperParameters
    value: "{{ hyperParameters }}"
  - name: vpcConfig
    description: |
      The configuration of a virtual private cloud (VPC). For more information, see Protect your data using Amazon Virtual Private Cloud and Amazon Web Services PrivateLink.
    value:
      subnetIds:
        - "{{ subnetIds }}"
      securityGroupIds:
        - "{{ securityGroupIds }}"
  - name: customizationConfig
    description: |
      A model customization configuration
    value:
      distillationConfig:
        teacherModelConfig:
          teacherModelIdentifier: "{{ teacherModelIdentifier }}"
          maxResponseLengthForInference: {{ maxResponseLengthForInference }}
      rftConfig:
        graderConfig:
          lambdaGrader:
            lambdaArn: "{{ lambdaArn }}"
        hyperParameters:
          epochCount: {{ epochCount }}
          batchSize: {{ batchSize }}
          learningRate: {{ learningRate }}
          maxPromptLength: {{ maxPromptLength }}
          trainingSamplePerPrompt: {{ trainingSamplePerPrompt }}
          inferenceMaxTokens: {{ inferenceMaxTokens }}
          reasoningEffort: "{{ reasoningEffort }}"
          evalInterval: {{ evalInterval }}