Resume Rlor Trainer Job

POST /v1/accounts/{account_id}/rlorTrainerJobs/{rlor_trainer_job_id}:resume

Resume Rlor Trainer Job

cURL

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/rlorTrainerJobs/{rlor_trainer_job_id}:resume \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{}'

200

{
  "name": "<string>",
  "displayName": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "completedTime": "2023-11-07T05:31:56Z",
  "dataset": "<string>",
  "evaluationDataset": "<string>",
  "evalAutoCarveout": true,
  "state": "JOB_STATE_UNSPECIFIED",
  "status": {
    "code": "OK",
    "message": "<string>"
  },
  "createdBy": "<string>",
  "trainingConfig": {
    "outputModel": "<string>",
    "baseModel": "<string>",
    "warmStartFrom": "<string>",
    "jinjaTemplate": "<string>",
    "learningRate": 123,
    "maxContextLength": 123,
    "loraRank": 123,
    "region": "REGION_UNSPECIFIED",
    "epochs": 123,
    "batchSize": 123,
    "gradientAccumulationSteps": 123,
    "learningRateWarmupSteps": 123,
    "batchSizeSamples": 123,
    "optimizerWeightDecay": 123
  },
  "rewardWeights": [
    "<string>"
  ],
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>",
    "url": "<string>"
  },
  "awsS3Config": {
    "credentialsSecret": "<string>",
    "iamRoleArn": "<string>"
  },
  "keepAlive": true,
  "rolloutDeploymentName": "<string>",
  "lossConfig": {
    "method": "METHOD_UNSPECIFIED",
    "klBeta": 123
  },
  "nodeCount": 123,
  "acceleratorSeconds": {},
  "serviceMode": true,
  "directRouteHandle": "<string>",
  "hotLoadDeploymentId": "<string>"
}

Authorizations

Authorization · string · header · required

Bearer authentication using your Fireworks API key. Format: Bearer <API_KEY>

Path Parameters

account_id · string · required

The Account Id

rlor_trainer_job_id · string · required

The Rlor Trainer Job Id

Body

application/json

The body is of type object.

Response

200 - application/json

A successful response.

name · string

displayName · string

createTime · string<date-time>

completedTime · string<date-time>

dataset · string

The name of the dataset used for training.

evaluationDataset · string

The name of a separate dataset to use for evaluation.

evalAutoCarveout · boolean

Whether to auto-carve the dataset for eval.

state · enum<string> · default: JOB_STATE_UNSPECIFIED

JobState represents the state an asynchronous job can be in.

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

Available options: 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

status · Mimics [https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto] · object

Show child attributes

createdBy · string

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

trainingConfig · BaseTrainingConfig contains common configuration fields shared across different training job types. Next ID: 22 · object

Common training configurations.

Show child attributes

rewardWeights · string[]

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

wandbConfig · object

The Weights & Biases team/user account for logging training progress.

Show child attributes

awsS3Config · object

The AWS configuration for S3 dataset access.

Show child attributes

keepAlive · boolean

rolloutDeploymentName · string

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

lossConfig · object

Reinforcement learning loss method + hyperparameters for the underlying trainer.

Show child attributes

nodeCount · integer<int32>

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

acceleratorSeconds · object

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

Show child attributes

serviceMode · boolean

directRouteHandle · string

hotLoadDeploymentId · string

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.