In the official documentation , gpt-4-0613 is listed as a model available for fine-tuning. However, it is not an option in the dashboard as a base model for fine-tuning, and when I run it through code, it returns the following error:
BadRequestError: Error code: 400 - {'error': {'message': 'Model gpt-4-0613 is not available for fine-tuning or does not exist.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_available'}}
Fine-tuning works fine when I use gpt-4o and gpt-4o-mini models, so I know this issue is specific to GPT-4. Is the article outdated and OpenAI no longer supports fine-tuning for GPT-4? Or am I missing something? Any help is appreciated.
On November 6th, 2023, we announced the release of an updated GPT-3.5-Turbo model (which now comes by default with 16k context) along with deprecation of gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613. As of June 17, 2024, only existing users of these models will be able to continue using them.
As an existing user still able to use the model, it appears the fine-tuning has been shut off as part of the deprecation path of “shutdown: 2024-09-13” for everyone else, having just tried to run a fine-tuning.
gpt-4-0613 is also listed casually, despite the number of developers approved and able to use that model approaching zero.