Create Reinforcement Fine-tuning Job

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "displayName": "<string>",
  "dataset": "<string>",
  "evaluationDataset": "<string>",
  "evalAutoCarveout": true,
  "trainingConfig": {
    "outputModel": "<string>",
    "baseModel": "<string>",
    "warmStartFrom": "<string>",
    "jinjaTemplate": "<string>",
    "learningRate": 123,
    "maxContextLength": 123,
    "loraRank": 123,
    "acceleratorCount": 123,
    "region": "REGION_UNSPECIFIED",
    "epochs": 123,
    "batchSize": 123,
    "gradientAccumulationSteps": 123,
    "learningRateWarmupSteps": 123
  },
  "evaluator": "<string>",
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>"
  },
  "outputStats": "<string>",
  "inferenceParameters": {
    "maxTokens": 123,
    "temperature": 123,
    "topP": 123,
    "n": 123,
    "extraBody": "<string>",
    "topK": 123
  },
  "outputMetrics": "<string>",
  "mcpServer": "<string>"
}'

{
  "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,
    "acceleratorCount": 123,
    "region": "REGION_UNSPECIFIED",
    "epochs": 123,
    "batchSize": 123,
    "gradientAccumulationSteps": 123,
    "learningRateWarmupSteps": 123
  },
  "evaluator": "<string>",
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>",
    "url": "<string>"
  },
  "outputStats": "<string>",
  "inferenceParameters": {
    "maxTokens": 123,
    "temperature": 123,
    "topP": 123,
    "n": 123,
    "extraBody": "<string>",
    "topK": 123
  },
  "outputMetrics": "<string>",
  "mcpServer": "<string>"
}

POST

accounts

{account_id}

reinforcementFineTuningJobs

Create Reinforcement Fine-tuning Job

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "displayName": "<string>",
  "dataset": "<string>",
  "evaluationDataset": "<string>",
  "evalAutoCarveout": true,
  "trainingConfig": {
    "outputModel": "<string>",
    "baseModel": "<string>",
    "warmStartFrom": "<string>",
    "jinjaTemplate": "<string>",
    "learningRate": 123,
    "maxContextLength": 123,
    "loraRank": 123,
    "acceleratorCount": 123,
    "region": "REGION_UNSPECIFIED",
    "epochs": 123,
    "batchSize": 123,
    "gradientAccumulationSteps": 123,
    "learningRateWarmupSteps": 123
  },
  "evaluator": "<string>",
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>"
  },
  "outputStats": "<string>",
  "inferenceParameters": {
    "maxTokens": 123,
    "temperature": 123,
    "topP": 123,
    "n": 123,
    "extraBody": "<string>",
    "topK": 123
  },
  "outputMetrics": "<string>",
  "mcpServer": "<string>"
}'

{
  "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,
    "acceleratorCount": 123,
    "region": "REGION_UNSPECIFIED",
    "epochs": 123,
    "batchSize": 123,
    "gradientAccumulationSteps": 123,
    "learningRateWarmupSteps": 123
  },
  "evaluator": "<string>",
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>",
    "url": "<string>"
  },
  "outputStats": "<string>",
  "inferenceParameters": {
    "maxTokens": 123,
    "temperature": 123,
    "topP": 123,
    "n": 123,
    "extraBody": "<string>",
    "topK": 123
  },
  "outputMetrics": "<string>",
  "mcpServer": "<string>"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

account_id

string

required

The Account Id

Query Parameters

reinforcementFineTuningJobId

string

ID of the reinforcement fine-tuning job, a random UUID will be generated if not specified.

Body

application/json

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.

displayName

string

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.

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

status

object

Show child attributes

trainingConfig

object

Common training configurations.

Show child attributes

wandbConfig

object

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

Show child attributes

outputStats

string

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

inferenceParameters

object

BIJ parameters.

Show child attributes

outputMetrics

string

mcpServer

string

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

displayName

string

createTime

string<date-time>

completedTime

string<date-time>

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

JobState represents the state an asynchronous job can be in.

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

status

object

Show child attributes

createdBy

string

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

trainingConfig

object

Common training configurations.

Show child attributes

wandbConfig

object

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

Show child attributes

outputStats

string

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

inferenceParameters

object

BIJ parameters.

Show child attributes

outputMetrics

string

mcpServer

string

Get Reinforcement Fine-tuning Job

Delete Reinforcement Fine-tuning Job

⌘I

API Reference

Build SDK

Create Reinforcement Fine-tuning Job

Authorizations

Path Parameters

Query Parameters

Body

Response