Create fine-tuning job
Creates a fine-tuning job which begins the process of creating a new model from a given dataset. The response includes details of the enqueued job, including job status and the name of the fine-tuned model once complete.
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
Array of IDs of uploaded files to use for training. All files must be text-only.
["file-abc123", "file-abc124"]
The name of the model to fine-tune for styling. Options: 'vaero-1'.
"vaero-1"
The name of the base model whose output will be styled. For example, if you are planning to style the outputs of claude-3-5-sonnet-20240620
, you should set this to claude-3-5-sonnet-20240620
. Options: 'gpt-4o-2024-08-06', 'claude-3-5-sonnet-20240620', 'general'. Use 'general' to work with any model.
"general"
A string of up to 16 characters that will be added to your fine-tuned model name. For example, a suffix of 'custom-name' would produce a model name like 'ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1'.
"custom-name"
Response
A fine-tuning job object.
The type of the object, always 'fine_tuning.job'.
"fine_tuning.job"
The ID of the fine-tuning job.
"ftjob-abc123"
The model being fine-tuned.
"vaero-1"
The name of the base model whose output is to be styled.
"gpt-4o"
The Unix timestamp for when the job was created.
1721764800
The name of the fine-tuned model.
null
The organization ID associated with this fine-tuning job.
"org-123"
The current status of the job.
"queued"
Array of file IDs used for training.
["file-abc123", "file-abc124"]