Been working w/ the Assistants API & have done about 4 fine-tunes on gpt-4o-2024-08-06. Their documentation states that this is a fine-tunable model, as well (the support bot said it wasn’t but the docs, plus my use counters that).
All of my previous FT models were available pretty instantly after completion of the FT job, and continue to be available (and being used) today. However my most recent three FT models (as new as 24, 6 & 5 hrs ago as of this post) are unavailable for use in the API or the assistants playground (they are available for use for chat completions, though).
I only did the 3 most recent, because I wanted to see if it was something I was doing causing that issue, but I don’t believe it is. I tried:
- Starting from scratch, fine-tuning plain-ol gpt-4o-2024-08-06 with the entire data set from the 4 prev FT’s
- Fine tuning a previous FT model (the first ‘version’ - which was trained on gpt-4o-2024-08-06 as well)
- Limiting the data set being trained on to 10 basic examples
I can confirm that the fine-tune jobs finished successfully, that it’s using a compatible model (seemingly), refresh/logout doesn’t help, model is listed as available in the dashboard.
The issue seems to be exactly related to this incident from a couple days ago, which is marked resolved but definitely doesn’t seem to be. I do also notice the ‘Usage policy evaluations completed, model is now enabled for sampling’ messages from the recent FT job
