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>",
  "awsS3Config": {
    "credentialsSecret": "<string>",
    "iamRoleArn": "<string>"
  },
  "azureBlobStorageConfig": {
    "credentialsSecret": "<string>",
    "managedIdentityClientId": "<string>",
    "tenantId": "<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,
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "batchSizeSamples": 123,
  "optimizerWeightDecay": 123,
  "purpose": "PURPOSE_UNSPECIFIED"
}
'

{
  "dataset": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "completedTime": "2023-11-07T05:31:56Z",
  "awsS3Config": {
    "credentialsSecret": "<string>",
    "iamRoleArn": "<string>"
  },
  "azureBlobStorageConfig": {
    "credentialsSecret": "<string>",
    "managedIdentityClientId": "<string>",
    "tenantId": "<string>"
  },
  "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,
  "updateTime": "2023-11-07T05:31:56Z",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "jobProgress": {
    "percent": 123,
    "epoch": 123,
    "totalInputRequests": 123,
    "totalProcessedRequests": 123,
    "successfullyProcessedRequests": 123,
    "failedRequests": 123,
    "outputRows": 123,
    "inputTokens": 123,
    "outputTokens": 123,
    "cachedInputTokenCount": 123
  },
  "metricsFileSignedUrl": "<string>",
  "trainerLogsSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "batchSizeSamples": 123,
  "estimatedCost": {
    "currencyCode": "<string>",
    "units": "<string>",
    "nanos": 123
  },
  "optimizerWeightDecay": 123,
  "purpose": "PURPOSE_UNSPECIFIED"
}

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>",
  "awsS3Config": {
    "credentialsSecret": "<string>",
    "iamRoleArn": "<string>"
  },
  "azureBlobStorageConfig": {
    "credentialsSecret": "<string>",
    "managedIdentityClientId": "<string>",
    "tenantId": "<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,
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "metricsFileSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "batchSizeSamples": 123,
  "optimizerWeightDecay": 123,
  "purpose": "PURPOSE_UNSPECIFIED"
}
'

{
  "dataset": "<string>",
  "name": "<string>",
  "displayName": "<string>",
  "createTime": "2023-11-07T05:31:56Z",
  "completedTime": "2023-11-07T05:31:56Z",
  "awsS3Config": {
    "credentialsSecret": "<string>",
    "iamRoleArn": "<string>"
  },
  "azureBlobStorageConfig": {
    "credentialsSecret": "<string>",
    "managedIdentityClientId": "<string>",
    "tenantId": "<string>"
  },
  "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,
  "updateTime": "2023-11-07T05:31:56Z",
  "nodes": 123,
  "batchSize": 123,
  "mtpEnabled": true,
  "mtpNumDraftTokens": 123,
  "mtpFreezeBaseModel": true,
  "jobProgress": {
    "percent": 123,
    "epoch": 123,
    "totalInputRequests": 123,
    "totalProcessedRequests": 123,
    "successfullyProcessedRequests": 123,
    "failedRequests": 123,
    "outputRows": 123,
    "inputTokens": 123,
    "outputTokens": 123,
    "cachedInputTokenCount": 123
  },
  "metricsFileSignedUrl": "<string>",
  "trainerLogsSignedUrl": "<string>",
  "gradientAccumulationSteps": 123,
  "learningRateWarmupSteps": 123,
  "batchSizeSamples": 123,
  "estimatedCost": {
    "currencyCode": "<string>",
    "units": "<string>",
    "nanos": 123
  },
  "optimizerWeightDecay": 123,
  "purpose": "PURPOSE_UNSPECIFIED"
}

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

awsS3Config

object

The AWS configuration for S3 dataset access.

Show child attributes

azureBlobStorageConfig

object

The Azure configuration for Azure Blob Storage dataset access.

Show child attributes

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.

nodes

integer<int32>

Deprecated: multi-node scheduling is now handled by the cookbook orchestrator in V2 workflows. This field is ignored for V2 jobs and will be removed in a future release.

batchSize

integer<int32>

mtpEnabled

boolean

Deprecated: MTP is not supported in V2 training. These fields are retained for V1 Helm-based SFT backward compatibility only.

mtpNumDraftTokens

integer<int32>

Deprecated: see mtp_enabled.

mtpFreezeBaseModel

boolean

Deprecated: see mtp_enabled.

metricsFileSignedUrl

string

gradientAccumulationSteps

integer<int32>

learningRateWarmupSteps

integer<int32>

batchSizeSamples

integer<int32>

The number of samples per gradient batch.

optimizerWeightDecay

number<float>

Weight decay (L2 regularization) for optimizer.

purpose

enum<string>

default:PURPOSE_UNSPECIFIED

Scheduling purpose for this job.

Available options:

PURPOSE_UNSPECIFIED,

PURPOSE_PILOT

Response

200 - application/json

A successful response.

dataset

string

required

The name of the dataset used for training.

name

string

read-only

displayName

string

createTime

string<date-time>

read-only

completedTime

string<date-time>

read-only

awsS3Config

object

The AWS configuration for S3 dataset access.

Show child attributes

azureBlobStorageConfig

object

The Azure configuration for Azure Blob Storage dataset access.

Show child attributes

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

Show child attributes

createdBy

string

read-only

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.

updateTime

string<date-time>

read-only

The update time for the supervised fine-tuning job.

nodes

integer<int32>

Deprecated: multi-node scheduling is now handled by the cookbook orchestrator in V2 workflows. This field is ignored for V2 jobs and will be removed in a future release.

batchSize

integer<int32>

mtpEnabled

boolean

Deprecated: MTP is not supported in V2 training. These fields are retained for V1 Helm-based SFT backward compatibility only.

mtpNumDraftTokens

integer<int32>

Deprecated: see mtp_enabled.

mtpFreezeBaseModel

boolean

Deprecated: see mtp_enabled.

jobProgress

object

read-only

Job progress.

Show child attributes

metricsFileSignedUrl

string

trainerLogsSignedUrl

string

read-only

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

gradientAccumulationSteps

integer<int32>

learningRateWarmupSteps

integer<int32>

batchSizeSamples

integer<int32>

The number of samples per gradient batch.

estimatedCost

object

read-only

The estimated cost of the job.

Show child attributes

optimizerWeightDecay

number<float>

Weight decay (L2 regularization) for optimizer.

purpose

enum<string>

default:PURPOSE_UNSPECIFIED

Scheduling purpose for this job.

Available options:

PURPOSE_UNSPECIFIED,

PURPOSE_PILOT

Validate Dataset Upload

List Supervised Fine-tuning Jobs

⌘I

Documentation Index

Authorizations

Path Parameters

Query Parameters

Body

Response