Create SFT Training Job

Create a new SFT (Supervised Fine-Tuning) training job.

POST /v1/preview/sft-training-jobs

Create SFT Training Job

cURL

curl --request POST \
  --url https://api.example.com/v1/preview/sft-training-jobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "training_data_url": "<string>",
  "config": {
    "batch_size": 123,
    "learning_rate": 123
  },
  "experimental_config": {}
}
'

200

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

承認

Authorization · string · header · 必須

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

ボディ

application/json

Schema for creating a new SFT (Supervised Fine-Tuning) TrainingJob.

The client should upload the training data (trajectories.jsonl and metadata.json) to W&B Artifacts and provide the artifact URL.

model_id · string<uuid> · 必須

training_data_url · string · 必須

W&B artifact path for training data (e.g., 'wandb-artifact:///entity/project/artifact-name:version')

config · SFTTrainingConfig · object

Schema for SFT training config.

表示 子属性

experimental_config · Experimental Config · object

レスポンス

200

application/json

Successful Response

Schema for TrainingJob response.

id · string<uuid> · 必須