POST
/
api
/
v1
/
organizations
/
{organization_id}
/
jobs
{
  "dry_run": true,
  "estimated_usage": {
    "cost": 123,
    "tokens": 123
  },
  "job": {
    "base_model": "<string>",
    "completed_at": "2023-11-07T05:31:56Z",
    "dataset": {
      "answer_column": "<string>",
      "id": "<string>",
      "prompt_column": "<string>"
    },
    "hyperparameters": {
      "batch_size": 123,
      "best_checkpoints": true,
      "evaluation_epochs": 123,
      "learning_rate": 123,
      "lora": {
        "alpha": 123,
        "dropout": 123,
        "enabled": true,
        "r": 123,
        "trainable_modules": [
          "<string>"
        ]
      },
      "n_epochs": 123,
      "warmup_epochs": 123,
      "weight_decay": 123
    },
    "id": "<string>",
    "name": "<string>",
    "started_at": "2023-11-07T05:31:56Z",
    "status": "queued"
  }
}

Authorizations

Authorization
string
header
required

Bearer HTTP authentication. Allowed headers -- Authorization: Bearer <access_token>

Path Parameters

organization_id
string
required

Body

application/json
base_model_id
string
required

The ID of the base model.

dataset
object
required

The dataset to use for fine-tuning.

name
string
required

The name of the job.

dry_run
boolean
default:false

If true, the estimated usage of the job will be returned, but the job will not be created.

hyperparameters
object

The hyperparameters used to configure the job.

Response

Successful response.

dry_run
boolean
required

If true, the estimated usage of the job will be returned, but the job will not be created.

estimated_usage
object

The billable usage of the job.

job
object

The is an object representing a fine-tuning job.