Skip to main content
POST
/
v1
/
flow
/
fine-tune
Create fine-tuning job
curl --request POST \
  --url https://flow.seekr.com/v1/flow/fine-tune \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "training_config": {
    "training_files": [
      "<string>"
    ],
    "model": "<string>",
    "n_epochs": 123,
    "learning_rate": 123,
    "batch_size": 512,
    "n_checkpoints": 123,
    "experiment_name": "<string>",
    "max_length": 2500,
    "pre_train": false,
    "fine_tune_type": "STANDARD",
    "lora_config": {
      "r": 8,
      "alpha": 32,
      "dropout": 0.1,
      "bias": "none",
      "extras": {}
    },
    "reward_components": {
      "graders": [
        {
          "type": "format_check",
          "weight": 0.5
        }
      ],
      "format_reward_weight": 0.1
    },
    "beta": 123,
    "gradient_checkpointing": true
  },
  "infrastructure_config": {
    "n_accel": 123,
    "n_node": 1
  },
  "project_id": 123,
  "description": "<string>"
}
'
{}
Create a fine-tuning job by specifying a TrainingConfig and InfrastructureConfig. The TrainingConfig accepts an optional lora_config parameter for parameter-efficient training using low-rank adaptation. For guidance on configuring LoRA, see Low-rank adaptation. For the full fine-tuning workflow, see Create a fine-tuning job.

Authorizations

Authorization
string
header
required

Seekr API Key without 'Bearer' Prefix

Body

application/json
training_config
TrainingConfig · object
required
infrastructure_config
InfrastructureConfig · object
required
project_id
integer | null
description
string | null

Response

Successful Response

The response is of type object.

Last modified on June 18, 2026