Skip to main content
GET
Get Reinforcement Fine-tuning Job

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

reinforcement_fine_tuning_job_id
string
required

The Reinforcement Fine-tuning Job Id

Query Parameters

readMask
string

The fields to be returned in the response. If empty or "*", all fields will be returned.

Response

200 - application/json

A successful response.

dataset
string
required

The name of the dataset used for training.

evaluator
string
required

The evaluator resource name to use for RLOR fine-tuning job.

name
string
read-only
displayName
string
createTime
string<date-time>
read-only
completedTime
string<date-time>
read-only

The completed time for the reinforcement fine-tuning job.

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
read-only

JobState represents the state an asynchronous job can be in.

  • JOB_STATE_PAUSED: Job is paused, typically due to account suspension or manual intervention.
  • JOB_STATE_DELETED: Job has been deleted.
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,
JOB_STATE_DELETED
status
Mimics [https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto] · object
read-only
createdBy
string
read-only

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

trainingConfig
BaseTrainingConfig contains common configuration fields shared across different training job types. · object

Common training configurations.

wandbConfig
object

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

awsS3Config
object

The AWS configuration for S3 dataset access.

azureBlobStorageConfig
object

The Azure configuration for Blob Storage dataset access.

outputStats
string
read-only

The output dataset's aggregated stats for the evaluation job.

jobProgress
object
read-only

Job progress.

inferenceParameters
RFT inference parameters · object

RFT inference parameters.

chunkSize
integer<int32>

Data chunking for rollout, default size 200, enabled when dataset > 300. Valid range is 1-10,000.

outputMetrics
string
read-only
maxInferenceReplicaCount
integer<int32>
nodeCount
integer<int32>

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

lossConfig
object

Reinforcement learning loss method + hyperparameters for the underlying trainers.

trainerLogsSignedUrl
string
read-only

The signed URL for the trainer logs file (stdout/stderr). Only populated if the account has trainer log reading enabled.

acceleratorSeconds
object
read-only

Accelerator seconds used by the job, keyed by accelerator type (e.g., "NVIDIA_H100_80GB"). Updated when job completes or is cancelled.

maxConcurrentRollouts
integer<int32>

Maximum number of concurrent rollouts during the RFT job.

maxConcurrentEvaluations
integer<int32>

Maximum number of concurrent evaluations during the RFT job.

purpose
enum<string>
default:PURPOSE_UNSPECIFIED

Scheduling purpose for this job.

Available options:
PURPOSE_UNSPECIFIED,
PURPOSE_PILOT