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 '
{
"dataset": "<string>",
"evaluator": "<string>",
"displayName": "<string>",
"evaluationDataset": "<string>",
"evalAutoCarveout": true,
"trainingConfig": {
"outputModel": "<string>",
"baseModel": "<string>",
"warmStartFrom": "<string>",
"jinjaTemplate": "<string>",
"learningRate": 123,
"maxContextLength": 123,
"loraRank": 123,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": true
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": [
"<string>"
]
},
"wandbConfig": {
"enabled": true,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": {
"lambda": 123
}
},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}
'import requests
url = "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs"
payload = {
"dataset": "<string>",
"evaluator": "<string>",
"displayName": "<string>",
"evaluationDataset": "<string>",
"evalAutoCarveout": True,
"trainingConfig": {
"outputModel": "<string>",
"baseModel": "<string>",
"warmStartFrom": "<string>",
"jinjaTemplate": "<string>",
"learningRate": 123,
"maxContextLength": 123,
"loraRank": 123,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": True
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": ["<string>"]
},
"wandbConfig": {
"enabled": True,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": { "lambda": 123 }
},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
dataset: '<string>',
evaluator: '<string>',
displayName: '<string>',
evaluationDataset: '<string>',
evalAutoCarveout: true,
trainingConfig: {
outputModel: '<string>',
baseModel: '<string>',
warmStartFrom: '<string>',
jinjaTemplate: '<string>',
learningRate: 123,
maxContextLength: 123,
loraRank: 123,
epochs: 123,
batchSize: 123,
gradientAccumulationSteps: 123,
learningRateWarmupSteps: 123,
batchSizeSamples: 123,
optimizerWeightDecay: 123,
trainerShardingScheme: {
tensorParallelism: 123,
pipelineParallelism: 123,
contextParallelism: 123,
expertParallelism: 123,
sequenceParallelism: true
},
loraAlpha: 123,
loraDropout: 123,
loraTargetModules: ['<string>']
},
wandbConfig: {
enabled: true,
apiKey: '<string>',
project: '<string>',
entity: '<string>',
runId: '<string>'
},
awsS3Config: {credentialsSecret: '<string>', iamRoleArn: '<string>'},
azureBlobStorageConfig: {
credentialsSecret: '<string>',
managedIdentityClientId: '<string>',
tenantId: '<string>'
},
inferenceParameters: {
maxOutputTokens: 123,
temperature: 123,
topP: 123,
responseCandidatesCount: 123,
extraBody: '<string>',
topK: 123
},
chunkSize: 123,
maxInferenceReplicaCount: 123,
nodeCount: 123,
lossConfig: {
method: 'METHOD_UNSPECIFIED',
klBeta: 123,
dpo: {beta: 123, refCacheConcurrency: 123, refCacheBatchSize: 123},
orpo: {lambda: 123}
},
maxConcurrentRollouts: 123,
maxConcurrentEvaluations: 123,
purpose: 'PURPOSE_UNSPECIFIED'
})
};
fetch('https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'dataset' => '<string>',
'evaluator' => '<string>',
'displayName' => '<string>',
'evaluationDataset' => '<string>',
'evalAutoCarveout' => true,
'trainingConfig' => [
'outputModel' => '<string>',
'baseModel' => '<string>',
'warmStartFrom' => '<string>',
'jinjaTemplate' => '<string>',
'learningRate' => 123,
'maxContextLength' => 123,
'loraRank' => 123,
'epochs' => 123,
'batchSize' => 123,
'gradientAccumulationSteps' => 123,
'learningRateWarmupSteps' => 123,
'batchSizeSamples' => 123,
'optimizerWeightDecay' => 123,
'trainerShardingScheme' => [
'tensorParallelism' => 123,
'pipelineParallelism' => 123,
'contextParallelism' => 123,
'expertParallelism' => 123,
'sequenceParallelism' => true
],
'loraAlpha' => 123,
'loraDropout' => 123,
'loraTargetModules' => [
'<string>'
]
],
'wandbConfig' => [
'enabled' => true,
'apiKey' => '<string>',
'project' => '<string>',
'entity' => '<string>',
'runId' => '<string>'
],
'awsS3Config' => [
'credentialsSecret' => '<string>',
'iamRoleArn' => '<string>'
],
'azureBlobStorageConfig' => [
'credentialsSecret' => '<string>',
'managedIdentityClientId' => '<string>',
'tenantId' => '<string>'
],
'inferenceParameters' => [
'maxOutputTokens' => 123,
'temperature' => 123,
'topP' => 123,
'responseCandidatesCount' => 123,
'extraBody' => '<string>',
'topK' => 123
],
'chunkSize' => 123,
'maxInferenceReplicaCount' => 123,
'nodeCount' => 123,
'lossConfig' => [
'method' => 'METHOD_UNSPECIFIED',
'klBeta' => 123,
'dpo' => [
'beta' => 123,
'refCacheConcurrency' => 123,
'refCacheBatchSize' => 123
],
'orpo' => [
'lambda' => 123
]
],
'maxConcurrentRollouts' => 123,
'maxConcurrentEvaluations' => 123,
'purpose' => 'PURPOSE_UNSPECIFIED'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs"
payload := strings.NewReader("{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}"
response = http.request(request)
puts response.read_body{
"dataset": "<string>",
"evaluator": "<string>",
"name": "<string>",
"displayName": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"completedTime": "2023-11-07T05:31:56Z",
"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,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": true
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": [
"<string>"
]
},
"wandbConfig": {
"enabled": true,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>",
"url": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"outputStats": "<string>",
"jobProgress": {
"percent": 123,
"epoch": 123,
"totalInputRequests": 123,
"totalProcessedRequests": 123,
"successfullyProcessedRequests": 123,
"failedRequests": 123,
"outputRows": 123,
"inputTokens": 123,
"outputTokens": 123,
"cachedInputTokenCount": 123
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"outputMetrics": "<string>",
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": {
"lambda": 123
}
},
"trainerLogsSignedUrl": "<string>",
"acceleratorSeconds": {},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}Reinforcement Fine-tuning Jobs
Create Reinforcement Fine-tuning Job
POST
/
v1
/
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 '
{
"dataset": "<string>",
"evaluator": "<string>",
"displayName": "<string>",
"evaluationDataset": "<string>",
"evalAutoCarveout": true,
"trainingConfig": {
"outputModel": "<string>",
"baseModel": "<string>",
"warmStartFrom": "<string>",
"jinjaTemplate": "<string>",
"learningRate": 123,
"maxContextLength": 123,
"loraRank": 123,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": true
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": [
"<string>"
]
},
"wandbConfig": {
"enabled": true,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": {
"lambda": 123
}
},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}
'import requests
url = "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs"
payload = {
"dataset": "<string>",
"evaluator": "<string>",
"displayName": "<string>",
"evaluationDataset": "<string>",
"evalAutoCarveout": True,
"trainingConfig": {
"outputModel": "<string>",
"baseModel": "<string>",
"warmStartFrom": "<string>",
"jinjaTemplate": "<string>",
"learningRate": 123,
"maxContextLength": 123,
"loraRank": 123,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": True
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": ["<string>"]
},
"wandbConfig": {
"enabled": True,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": { "lambda": 123 }
},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
dataset: '<string>',
evaluator: '<string>',
displayName: '<string>',
evaluationDataset: '<string>',
evalAutoCarveout: true,
trainingConfig: {
outputModel: '<string>',
baseModel: '<string>',
warmStartFrom: '<string>',
jinjaTemplate: '<string>',
learningRate: 123,
maxContextLength: 123,
loraRank: 123,
epochs: 123,
batchSize: 123,
gradientAccumulationSteps: 123,
learningRateWarmupSteps: 123,
batchSizeSamples: 123,
optimizerWeightDecay: 123,
trainerShardingScheme: {
tensorParallelism: 123,
pipelineParallelism: 123,
contextParallelism: 123,
expertParallelism: 123,
sequenceParallelism: true
},
loraAlpha: 123,
loraDropout: 123,
loraTargetModules: ['<string>']
},
wandbConfig: {
enabled: true,
apiKey: '<string>',
project: '<string>',
entity: '<string>',
runId: '<string>'
},
awsS3Config: {credentialsSecret: '<string>', iamRoleArn: '<string>'},
azureBlobStorageConfig: {
credentialsSecret: '<string>',
managedIdentityClientId: '<string>',
tenantId: '<string>'
},
inferenceParameters: {
maxOutputTokens: 123,
temperature: 123,
topP: 123,
responseCandidatesCount: 123,
extraBody: '<string>',
topK: 123
},
chunkSize: 123,
maxInferenceReplicaCount: 123,
nodeCount: 123,
lossConfig: {
method: 'METHOD_UNSPECIFIED',
klBeta: 123,
dpo: {beta: 123, refCacheConcurrency: 123, refCacheBatchSize: 123},
orpo: {lambda: 123}
},
maxConcurrentRollouts: 123,
maxConcurrentEvaluations: 123,
purpose: 'PURPOSE_UNSPECIFIED'
})
};
fetch('https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'dataset' => '<string>',
'evaluator' => '<string>',
'displayName' => '<string>',
'evaluationDataset' => '<string>',
'evalAutoCarveout' => true,
'trainingConfig' => [
'outputModel' => '<string>',
'baseModel' => '<string>',
'warmStartFrom' => '<string>',
'jinjaTemplate' => '<string>',
'learningRate' => 123,
'maxContextLength' => 123,
'loraRank' => 123,
'epochs' => 123,
'batchSize' => 123,
'gradientAccumulationSteps' => 123,
'learningRateWarmupSteps' => 123,
'batchSizeSamples' => 123,
'optimizerWeightDecay' => 123,
'trainerShardingScheme' => [
'tensorParallelism' => 123,
'pipelineParallelism' => 123,
'contextParallelism' => 123,
'expertParallelism' => 123,
'sequenceParallelism' => true
],
'loraAlpha' => 123,
'loraDropout' => 123,
'loraTargetModules' => [
'<string>'
]
],
'wandbConfig' => [
'enabled' => true,
'apiKey' => '<string>',
'project' => '<string>',
'entity' => '<string>',
'runId' => '<string>'
],
'awsS3Config' => [
'credentialsSecret' => '<string>',
'iamRoleArn' => '<string>'
],
'azureBlobStorageConfig' => [
'credentialsSecret' => '<string>',
'managedIdentityClientId' => '<string>',
'tenantId' => '<string>'
],
'inferenceParameters' => [
'maxOutputTokens' => 123,
'temperature' => 123,
'topP' => 123,
'responseCandidatesCount' => 123,
'extraBody' => '<string>',
'topK' => 123
],
'chunkSize' => 123,
'maxInferenceReplicaCount' => 123,
'nodeCount' => 123,
'lossConfig' => [
'method' => 'METHOD_UNSPECIFIED',
'klBeta' => 123,
'dpo' => [
'beta' => 123,
'refCacheConcurrency' => 123,
'refCacheBatchSize' => 123
],
'orpo' => [
'lambda' => 123
]
],
'maxConcurrentRollouts' => 123,
'maxConcurrentEvaluations' => 123,
'purpose' => 'PURPOSE_UNSPECIFIED'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs"
payload := strings.NewReader("{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.fireworks.ai/v1/accounts/{account_id}/reinforcementFineTuningJobs")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"dataset\": \"<string>\",\n \"evaluator\": \"<string>\",\n \"displayName\": \"<string>\",\n \"evaluationDataset\": \"<string>\",\n \"evalAutoCarveout\": true,\n \"trainingConfig\": {\n \"outputModel\": \"<string>\",\n \"baseModel\": \"<string>\",\n \"warmStartFrom\": \"<string>\",\n \"jinjaTemplate\": \"<string>\",\n \"learningRate\": 123,\n \"maxContextLength\": 123,\n \"loraRank\": 123,\n \"epochs\": 123,\n \"batchSize\": 123,\n \"gradientAccumulationSteps\": 123,\n \"learningRateWarmupSteps\": 123,\n \"batchSizeSamples\": 123,\n \"optimizerWeightDecay\": 123,\n \"trainerShardingScheme\": {\n \"tensorParallelism\": 123,\n \"pipelineParallelism\": 123,\n \"contextParallelism\": 123,\n \"expertParallelism\": 123,\n \"sequenceParallelism\": true\n },\n \"loraAlpha\": 123,\n \"loraDropout\": 123,\n \"loraTargetModules\": [\n \"<string>\"\n ]\n },\n \"wandbConfig\": {\n \"enabled\": true,\n \"apiKey\": \"<string>\",\n \"project\": \"<string>\",\n \"entity\": \"<string>\",\n \"runId\": \"<string>\"\n },\n \"awsS3Config\": {\n \"credentialsSecret\": \"<string>\",\n \"iamRoleArn\": \"<string>\"\n },\n \"azureBlobStorageConfig\": {\n \"credentialsSecret\": \"<string>\",\n \"managedIdentityClientId\": \"<string>\",\n \"tenantId\": \"<string>\"\n },\n \"inferenceParameters\": {\n \"maxOutputTokens\": 123,\n \"temperature\": 123,\n \"topP\": 123,\n \"responseCandidatesCount\": 123,\n \"extraBody\": \"<string>\",\n \"topK\": 123\n },\n \"chunkSize\": 123,\n \"maxInferenceReplicaCount\": 123,\n \"nodeCount\": 123,\n \"lossConfig\": {\n \"method\": \"METHOD_UNSPECIFIED\",\n \"klBeta\": 123,\n \"dpo\": {\n \"beta\": 123,\n \"refCacheConcurrency\": 123,\n \"refCacheBatchSize\": 123\n },\n \"orpo\": {\n \"lambda\": 123\n }\n },\n \"maxConcurrentRollouts\": 123,\n \"maxConcurrentEvaluations\": 123,\n \"purpose\": \"PURPOSE_UNSPECIFIED\"\n}"
response = http.request(request)
puts response.read_body{
"dataset": "<string>",
"evaluator": "<string>",
"name": "<string>",
"displayName": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"completedTime": "2023-11-07T05:31:56Z",
"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,
"epochs": 123,
"batchSize": 123,
"gradientAccumulationSteps": 123,
"learningRateWarmupSteps": 123,
"batchSizeSamples": 123,
"optimizerWeightDecay": 123,
"trainerShardingScheme": {
"tensorParallelism": 123,
"pipelineParallelism": 123,
"contextParallelism": 123,
"expertParallelism": 123,
"sequenceParallelism": true
},
"loraAlpha": 123,
"loraDropout": 123,
"loraTargetModules": [
"<string>"
]
},
"wandbConfig": {
"enabled": true,
"apiKey": "<string>",
"project": "<string>",
"entity": "<string>",
"runId": "<string>",
"url": "<string>"
},
"awsS3Config": {
"credentialsSecret": "<string>",
"iamRoleArn": "<string>"
},
"azureBlobStorageConfig": {
"credentialsSecret": "<string>",
"managedIdentityClientId": "<string>",
"tenantId": "<string>"
},
"outputStats": "<string>",
"jobProgress": {
"percent": 123,
"epoch": 123,
"totalInputRequests": 123,
"totalProcessedRequests": 123,
"successfullyProcessedRequests": 123,
"failedRequests": 123,
"outputRows": 123,
"inputTokens": 123,
"outputTokens": 123,
"cachedInputTokenCount": 123
},
"inferenceParameters": {
"maxOutputTokens": 123,
"temperature": 123,
"topP": 123,
"responseCandidatesCount": 123,
"extraBody": "<string>",
"topK": 123
},
"chunkSize": 123,
"outputMetrics": "<string>",
"maxInferenceReplicaCount": 123,
"nodeCount": 123,
"lossConfig": {
"method": "METHOD_UNSPECIFIED",
"klBeta": 123,
"dpo": {
"beta": 123,
"refCacheConcurrency": 123,
"refCacheBatchSize": 123
},
"orpo": {
"lambda": 123
}
},
"trainerLogsSignedUrl": "<string>",
"acceleratorSeconds": {},
"maxConcurrentRollouts": 123,
"maxConcurrentEvaluations": 123,
"purpose": "PURPOSE_UNSPECIFIED"
}Authorizations
Bearer authentication using your Fireworks API key. Format: Bearer <API_KEY>
Path Parameters
The Account Id
Query Parameters
ID of the reinforcement fine-tuning job, a random UUID will be generated if not specified.
Body
application/json
The name of the dataset used for training.
The evaluator resource name to use for RLOR fine-tuning job.
The name of a separate dataset to use for evaluation.
Whether to auto-carve the dataset for eval.
trainingConfig
BaseTrainingConfig contains common configuration fields shared across
different training job types. · object
Common training configurations.
Show child attributes
Show child attributes
The Weights & Biases team/user account for logging training progress.
Show child attributes
Show child attributes
The AWS configuration for S3 dataset access.
Show child attributes
Show child attributes
The Azure configuration for Blob Storage dataset access.
Show child attributes
Show child attributes
RFT inference parameters.
Show child attributes
Show child attributes
Data chunking for rollout, default size 200, enabled when dataset > 300. Valid range is 1-10,000.
The number of nodes to use for the fine-tuning job. If not specified, the default is 1.
Reinforcement learning loss method + hyperparameters for the underlying trainers.
Show child attributes
Show child attributes
Maximum number of concurrent rollouts during the RFT job.
Maximum number of concurrent evaluations during the RFT job.
Scheduling purpose for this job.
Available options:
PURPOSE_UNSPECIFIED, PURPOSE_PILOT Response
200 - application/json
A successful response.
The name of the dataset used for training.
The evaluator resource name to use for RLOR fine-tuning job.
The completed time for the reinforcement fine-tuning job.
The name of a separate dataset to use for evaluation.
Whether to auto-carve the dataset for eval.
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
Show child attributes
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.
Show child attributes
Show child attributes
The Weights & Biases team/user account for logging training progress.
Show child attributes
Show child attributes
The AWS configuration for S3 dataset access.
Show child attributes
Show child attributes
The Azure configuration for Blob Storage dataset access.
Show child attributes
Show child attributes
The output dataset's aggregated stats for the evaluation job.
Job progress.
Show child attributes
Show child attributes
RFT inference parameters.
Show child attributes
Show child attributes
Data chunking for rollout, default size 200, enabled when dataset > 300. Valid range is 1-10,000.
The number of nodes to use for the fine-tuning job. If not specified, the default is 1.
Reinforcement learning loss method + hyperparameters for the underlying trainers.
Show child attributes
Show child attributes
The signed URL for the trainer logs file (stdout/stderr). Only populated if the account has trainer log reading enabled.
Accelerator seconds used by the job, keyed by accelerator type (e.g., "NVIDIA_H100_80GB"). Updated when job completes or is cancelled.
Show child attributes
Show child attributes
Maximum number of concurrent rollouts during the RFT job.
Maximum number of concurrent evaluations during the RFT job.
Scheduling purpose for this job.
Available options:
PURPOSE_UNSPECIFIED, PURPOSE_PILOT Was this page helpful?
⌘I