Create Supervised Fine-tuning Job

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/supervisedFineTuningJobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "dataset": "<string>",
  "displayName": "<string>",
  "outputModel": "<string>",
  "baseModel": "<string>",
  "warmStartFrom": "<string>",
  "jinjaTemplate": "<string>",
  "earlyStop": true,
  "epochs": 123,
  "learningRate": 123,
  "maxContextLength": 123,
  "loraRank": 123,
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>"
  },
  "evaluationDataset": "<string>",
  "isTurbo": true,
  "evalAutoCarveout": true,
  "region": "REGION_UNSPECIFIED",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "hiddenStatesGenConfig": {
    "deployedModel": "<string>",
    "maxWorkers": 123,
    "maxTokens": 123,
    "inputOffset": 123,
    "inputLimit": 123,
    "regenerateAssistant": true,
    "outputActivations": true,
    "apiKey": "<string>"
  },
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123
}
'

{
  "dataset": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "completedTime": "2023-11-07T05:31:56Z",
  "state": "JOB_STATE_UNSPECIFIED",
  "status": {
    "code": "OK",
    "message": "<string>"
  },
  "createdBy": "<string>",
  "outputModel": "<string>",
  "baseModel": "<string>",
  "warmStartFrom": "<string>",
  "jinjaTemplate": "<string>",
  "earlyStop": true,
  "epochs": 123,
  "learningRate": 123,
  "maxContextLength": 123,
  "loraRank": 123,
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>",
    "url": "<string>"
  },
  "evaluationDataset": "<string>",
  "isTurbo": true,
  "evalAutoCarveout": true,
  "region": "REGION_UNSPECIFIED",
  "updateTime": "2023-11-07T05:31:56Z",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "hiddenStatesGenConfig": {
    "deployedModel": "<string>",
    "maxWorkers": 123,
    "maxTokens": 123,
    "inputOffset": 123,
    "inputLimit": 123,
    "regenerateAssistant": true,
    "outputActivations": true,
    "apiKey": "<string>"
  },
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "estimatedCost": {
    "currencyCode": "<string>",
    "units": "<string>",
    "nanos": 123
  }
}

POST

accounts

{account_id}

supervisedFineTuningJobs

Create Supervised Fine-tuning Job

curl --request POST \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/supervisedFineTuningJobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "dataset": "<string>",
  "displayName": "<string>",
  "outputModel": "<string>",
  "baseModel": "<string>",
  "warmStartFrom": "<string>",
  "jinjaTemplate": "<string>",
  "earlyStop": true,
  "epochs": 123,
  "learningRate": 123,
  "maxContextLength": 123,
  "loraRank": 123,
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>"
  },
  "evaluationDataset": "<string>",
  "isTurbo": true,
  "evalAutoCarveout": true,
  "region": "REGION_UNSPECIFIED",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "hiddenStatesGenConfig": {
    "deployedModel": "<string>",
    "maxWorkers": 123,
    "maxTokens": 123,
    "inputOffset": 123,
    "inputLimit": 123,
    "regenerateAssistant": true,
    "outputActivations": true,
    "apiKey": "<string>"
  },
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123
}
'

{
  "dataset": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "completedTime": "2023-11-07T05:31:56Z",
  "state": "JOB_STATE_UNSPECIFIED",
  "status": {
    "code": "OK",
    "message": "<string>"
  },
  "createdBy": "<string>",
  "outputModel": "<string>",
  "baseModel": "<string>",
  "warmStartFrom": "<string>",
  "jinjaTemplate": "<string>",
  "earlyStop": true,
  "epochs": 123,
  "learningRate": 123,
  "maxContextLength": 123,
  "loraRank": 123,
  "wandbConfig": {
    "enabled": true,
    "apiKey": "<string>",
    "project": "<string>",
    "entity": "<string>",
    "runId": "<string>",
    "url": "<string>"
  },
  "evaluationDataset": "<string>",
  "isTurbo": true,
  "evalAutoCarveout": true,
  "region": "REGION_UNSPECIFIED",
  "updateTime": "2023-11-07T05:31:56Z",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "hiddenStatesGenConfig": {
    "deployedModel": "<string>",
    "maxWorkers": 123,
    "maxTokens": 123,
    "inputOffset": 123,
    "inputLimit": 123,
    "regenerateAssistant": true,
    "outputActivations": true,
    "apiKey": "<string>"
  },
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "estimatedCost": {
    "currencyCode": "<string>",
    "units": "<string>",
    "nanos": 123
  }
}

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

Query Parameters

supervisedFineTuningJobId

string

ID of the supervised 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.

displayName

string

outputModel

string

The model ID to be assigned to the resulting fine-tuned model. If not specified, the job ID will be used.

baseModel

string

The name of the base model to be fine-tuned Only one of 'base_model' or 'warm_start_from' should be specified.

warmStartFrom

string

The PEFT addon model in Fireworks format to be fine-tuned from Only one of 'base_model' or 'warm_start_from' should be specified.

jinjaTemplate

string

earlyStop

boolean

Whether to stop training early if the validation loss does not improve.

epochs

integer<int32>

The number of epochs to train for.

learningRate

number<float>

The learning rate used for training.

maxContextLength

integer<int32>

The maximum context length to use with the model.

loraRank

integer<int32>

The rank of the LoRA layers.

wandbConfig

object

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

Show child attributes

evaluationDataset

string

The name of a separate dataset to use for evaluation.

isTurbo

boolean

Whether to run the fine-tuning job in turbo mode.

evalAutoCarveout

boolean

Whether to auto-carve the dataset for eval.

region

enum<string>

default:REGION_UNSPECIFIED

The region where the fine-tuning job is located.

Available options:

REGION_UNSPECIFIED,

US_IOWA_1,

US_VIRGINIA_1,

US_VIRGINIA_2,

US_ILLINOIS_1,

AP_TOKYO_1,

EU_LONDON_1,

US_ARIZONA_1,

US_TEXAS_1,

US_ILLINOIS_2,

EU_FRANKFURT_1,

US_TEXAS_2,

EU_PARIS_1,

EU_HELSINKI_1,

US_NEVADA_1,

EU_ICELAND_1,

EU_ICELAND_2,

US_WASHINGTON_1,

US_WASHINGTON_2,

EU_ICELAND_DEV_1,

US_WASHINGTON_3,

US_ARIZONA_2,

AP_TOKYO_2,

US_CALIFORNIA_1,

US_MISSOURI_1,

US_UTAH_1,

US_TEXAS_3,

US_ARIZONA_3,

US_GEORGIA_1,

US_GEORGIA_2,

US_WASHINGTON_4,

US_GEORGIA_3,

NA_BRITISHCOLUMBIA_1,

US_GEORGIA_4

nodes

integer<int32>

The number of nodes to use for the fine-tuning job.

batchSize

integer<int32>

mtpEnabled

boolean

mtpNumDraftTokens

integer<int32>

mtpFreezeBaseModel

boolean

hiddenStatesGenConfig

Config for generating dataset with hidden states for SFTJ or eagle training. Next ID: 10 · object

Config for generating dataset with hidden states for training.

Show child attributes

metricsFileSignedUrl

string

gradientAccumulationSteps

integer<int32>

learningRateWarmupSteps

integer<int32>

Response

200 - application/json

A successful response.

dataset

string

required

The name of the dataset used for training.

name

string

displayName

string

createTime

string<date-time>

completedTime

string<date-time>

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.

outputModel

string

The model ID to be assigned to the resulting fine-tuned model. If not specified, the job ID will be used.

baseModel

string

The name of the base model to be fine-tuned Only one of 'base_model' or 'warm_start_from' should be specified.

warmStartFrom

string

The PEFT addon model in Fireworks format to be fine-tuned from Only one of 'base_model' or 'warm_start_from' should be specified.

jinjaTemplate

string

earlyStop

boolean

Whether to stop training early if the validation loss does not improve.

epochs

integer<int32>

The number of epochs to train for.

learningRate

number<float>

The learning rate used for training.

maxContextLength

integer<int32>

The maximum context length to use with the model.

loraRank

integer<int32>

The rank of the LoRA layers.

wandbConfig

object

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

Show child attributes

evaluationDataset

string

The name of a separate dataset to use for evaluation.

isTurbo

boolean

Whether to run the fine-tuning job in turbo mode.

evalAutoCarveout

boolean

Whether to auto-carve the dataset for eval.

region

enum<string>

default:REGION_UNSPECIFIED

The region where the fine-tuning job is located.

Available options:

REGION_UNSPECIFIED,

US_IOWA_1,

US_VIRGINIA_1,

US_VIRGINIA_2,

US_ILLINOIS_1,

AP_TOKYO_1,

EU_LONDON_1,

US_ARIZONA_1,

US_TEXAS_1,

US_ILLINOIS_2,

EU_FRANKFURT_1,

US_TEXAS_2,

EU_PARIS_1,

EU_HELSINKI_1,

US_NEVADA_1,

EU_ICELAND_1,

EU_ICELAND_2,

US_WASHINGTON_1,

US_WASHINGTON_2,

EU_ICELAND_DEV_1,

US_WASHINGTON_3,

US_ARIZONA_2,

AP_TOKYO_2,

US_CALIFORNIA_1,

US_MISSOURI_1,

US_UTAH_1,

US_TEXAS_3,

US_ARIZONA_3,

US_GEORGIA_1,

US_GEORGIA_2,

US_WASHINGTON_4,

US_GEORGIA_3,

NA_BRITISHCOLUMBIA_1,

US_GEORGIA_4

updateTime

string<date-time>

The update time for the supervised fine-tuning job.

nodes

integer<int32>

The number of nodes to use for the fine-tuning job.

batchSize

integer<int32>

mtpEnabled

boolean

mtpNumDraftTokens

integer<int32>

mtpFreezeBaseModel

boolean

hiddenStatesGenConfig

Config for generating dataset with hidden states for SFTJ or eagle training. Next ID: 10 · object

Config for generating dataset with hidden states for training.

Show child attributes

metricsFileSignedUrl

string

gradientAccumulationSteps

integer<int32>

learningRateWarmupSteps

integer<int32>

estimatedCost

object

The estimated cost of the job.

Show child attributes

Validate Dataset Upload

List Supervised Fine-tuning Jobs

⌘I

API Reference

Inference

Deployments

Fine-tuning

Evals

Multimedia

Admin

Build SDK (Deprecated)

Create Supervised Fine-tuning Job

Authorizations

Path Parameters

Query Parameters

Body

Response