Skip to main content
POST
/
v1
/
fine-tuning
Create a new fine-tuning job
curl --request POST \
  --url https://api.example.com/v1/fine-tuning \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "base_model_name": "<string>",
  "dataset_name": "<string>",
  "parameters": {
    "batch_size": 8,
    "num_epochs": 3,
    "shuffle": true,
    "lr": 0.0003,
    "seed": 42
  },
  "name": "<string>"
}
'
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "base_model_name": "<string>",
  "dataset_name": "<string>",
  "name": "<string>",
  "current_step": 123,
  "total_steps": 123,
  "current_epoch": 123,
  "total_epochs": 123,
  "num_tokens": 123
}

Documentation Index

Fetch the complete documentation index at: https://docs.luminolabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
x-api-key
string
header
required

Body

application/json
​
base_model_name
string
required
​
dataset_name
string
required
​
parameters
object
required
​
name
string
required

The name of the fine-tuning job

​
type
enum<string>
required

The type of fine-tuning job to run

Available options:
LORA,
QLORA

Response

Created

​
id
string<uuid>
​
created_at
string<date-time>
​
updated_at
string<date-time>
​
status
enum<string>
Available options:
NEW,
QUEUED,
RUNNING,
COMPLETED,
FAILED,
STOPPING,
STOPPED
​
base_model_name
string
​
dataset_name
string
​
name
string
​
type
enum<string>
Available options:
LORA,
QLORA
​
current_step
integer
​
total_steps
integer
​
current_epoch
integer
​
total_epochs
integer
​
num_tokens
integer

Number of tokens processed in the fine-tuning job