Sign in
gateway.openapi_Gateway

Create Reinforcement Fine-tuning Step

post/v1/accounts/{account_id}/rlorTrainerJobs

Path parameters

account_idstring required

The Account Id

Query parameters

rlorTrainerJobIdstring

ID of the RLOR trainer job, a random UUID will be generated if not specified.

Request body

namestring
displayNamestring
createTimestring date-time
completedTimestring date-time
datasetstring

The name of the dataset used for training.

evaluationDatasetstring

The name of a separate dataset to use for evaluation.

evalAutoCarveoutboolean

Whether to auto-carve the dataset for eval.

state'JOB_STATE_UNSPECIFIED' | 'JOB_STATE_CREATING' | 'JOB_STATE_RUNNING' | 'JOB_STATE_COMPLETED' | 'JOB_STATE_FAILED' | 'JOB_STATE_CANCELLED' | 'JOB_STATE_DELETING' | 'JOB_STATE_WRITING_RESULTS' | 'JOB_STATE_VALIDATING' | 'JOB_STATE_DELETING_CLEANING_UP' | 'JOB_STATE_PENDING' | 'JOB_STATE_EXPIRED' | 'JOB_STATE_RE_QUEUEING' | 'JOB_STATE_CREATING_INPUT_DATASET' | 'JOB_STATE_IDLE' | 'JOB_STATE_CANCELLING' | 'JOB_STATE_EARLY_STOPPED' | 'JOB_STATE_PAUSED'

JobState represents the state an asynchronous job can be in.

  • JOB_STATE_PAUSED: Job is paused, typically due to account suspension or manual intervention.
createdBystring

The email address of the user who initiated this fine-tuning job.

rewardWeightsstring[]

A list of reward metrics to use for training in format of "<reward_name>=<weight>".

keepAliveboolean
rolloutDeploymentNamestring

Rollout deployment name associated with this RLOR trainer job. This is optional. If not set, trainer will not trigger weight sync to rollout engine.

nodeCountinteger

The number of nodes to use for the fine-tuning job. If not specified, the default is 1.

acceleratorSecondsobject

Accelerator seconds used by the job, keyed by accelerator type (e.g., "NVIDIA_H100_80GB"). Updated periodically.

serviceModeboolean

Service-mode RLOR trainers currently support full-parameter tuning only. When enabled, trainingConfig.loraRank must be 0 (loraRank>0 is rejected).

directRouteHandlestring
hotLoadDeploymentIdstring

The deployment ID used for hot loading. When set, checkpoints are saved to this deployment's hot load bucket, enabling weight swaps on inference. Only valid for service-mode or keep-alive jobs.

usePurposestring

Use dedicated resources for the job. The only supported value currently is "pilot". Defaults to empty.

forwardOnlyboolean

When true, run the trainer in forward-only mode (no backward/optimizer). Used for reference models in GRPO that only need forward passes.

Response

A successful response.

namestring
displayNamestring
createTimestring date-time
completedTimestring date-time
datasetstring

The name of the dataset used for training.

evaluationDatasetstring

The name of a separate dataset to use for evaluation.

evalAutoCarveoutboolean

Whether to auto-carve the dataset for eval.

state'JOB_STATE_UNSPECIFIED' | 'JOB_STATE_CREATING' | 'JOB_STATE_RUNNING' | 'JOB_STATE_COMPLETED' | 'JOB_STATE_FAILED' | 'JOB_STATE_CANCELLED' | 'JOB_STATE_DELETING' | 'JOB_STATE_WRITING_RESULTS' | 'JOB_STATE_VALIDATING' | 'JOB_STATE_DELETING_CLEANING_UP' | 'JOB_STATE_PENDING' | 'JOB_STATE_EXPIRED' | 'JOB_STATE_RE_QUEUEING' | 'JOB_STATE_CREATING_INPUT_DATASET' | 'JOB_STATE_IDLE' | 'JOB_STATE_CANCELLING' | 'JOB_STATE_EARLY_STOPPED' | 'JOB_STATE_PAUSED'

JobState represents the state an asynchronous job can be in.

  • JOB_STATE_PAUSED: Job is paused, typically due to account suspension or manual intervention.
createdBystring

The email address of the user who initiated this fine-tuning job.

rewardWeightsstring[]

A list of reward metrics to use for training in format of "<reward_name>=<weight>".

keepAliveboolean
rolloutDeploymentNamestring

Rollout deployment name associated with this RLOR trainer job. This is optional. If not set, trainer will not trigger weight sync to rollout engine.

nodeCountinteger

The number of nodes to use for the fine-tuning job. If not specified, the default is 1.

acceleratorSecondsobject

Accelerator seconds used by the job, keyed by accelerator type (e.g., "NVIDIA_H100_80GB"). Updated periodically.

serviceModeboolean

Service-mode RLOR trainers currently support full-parameter tuning only. When enabled, trainingConfig.loraRank must be 0 (loraRank>0 is rejected).

directRouteHandlestring
hotLoadDeploymentIdstring

The deployment ID used for hot loading. When set, checkpoints are saved to this deployment's hot load bucket, enabling weight swaps on inference. Only valid for service-mode or keep-alive jobs.

usePurposestring

Use dedicated resources for the job. The only supported value currently is "pilot". Defaults to empty.

forwardOnlyboolean

When true, run the trainer in forward-only mode (no backward/optimizer). Used for reference models in GRPO that only need forward passes.

Changes

Changed in 11 of the 27 revisions of this API.11948

  • 407f0a0fd7674See the full diff
    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

  • 79bf507c9d101See the full diff
    • ○

      added the optional property to the response with the status

      response-optional-property-added

  • a1b77ea182882See the full diff
    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    This revision also has 4 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 3c3ed322dd5211See the full diff
    • ●

      added the new US_NEWYORK_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ○

      added the new US_NEWYORK_1 enum value to the request property /

      request-property-enum-value-added

  • 80bec85988ad414See the full diff
    • ●

      added the new DPO enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new GSPO_TOKEN enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new ORPO enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_OHIO_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new optional request property /

      new-optional-request-property

    • ○

      added the new DPO enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new GSPO_TOKEN enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new ORPO enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_OHIO_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property / to the response with the status

      response-optional-property-added

  • 9823da16483715See the full diff
    • ●

      added the new EU_ICELAND_3 enum value to the / response property for the response status

      response-property-enum-value-added

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new optional request property /

      new-optional-request-property

    • ○

      added the new EU_ICELAND_3 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property / to the response with the status

      response-optional-property-added

    This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 4e1bdf0cae561113See the full diff
    • ●

      added the new EU_HELSINKI_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new EU_ICELAND_DEV_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new EU_LONDON_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new EU_PARIS_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_ARIZONA_2 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_ARIZONA_3 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_GEORGIA_4 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_MISSOURI_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_NEVADA_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_TEXAS_3 enum value to the / response property for the response status

      response-property-enum-value-added

    • ●

      added the new US_VIRGINIA_2 enum value to the / response property for the response status

      response-property-enum-value-added

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new EU_HELSINKI_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new EU_ICELAND_DEV_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new EU_LONDON_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new EU_PARIS_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_ARIZONA_2 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_ARIZONA_3 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_GEORGIA_4 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_MISSOURI_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_NEVADA_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_TEXAS_3 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the new US_VIRGINIA_2 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

  • f76a6182f2d513See the full diff
    • ●

      added the new NA_BRITISHCOLUMBIA_1 enum value to the / response property for the response status

      response-property-enum-value-added

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new NA_BRITISHCOLUMBIA_1 enum value to the request property /

      request-property-enum-value-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

  • 3cece9a35f2613See the full diff
    • ▲

      removed the enum value US_TEXAS_3 of the request property /

      request-property-enum-value-removed

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      removed the US_TEXAS_3 enum value from the / response property for the response status

      response-property-enum-value-removed

  • 4506ec9d12ff11See the full diff
    • ●

      added the new JOB_STATE_PAUSED enum value to the response property for the response status

      response-property-enum-value-added

    • ○

      added the new JOB_STATE_PAUSED enum value to the request property

      request-property-enum-value-added