#Is fine-tuning gpt-3.5-turbo-0613 being deprecated?
mild ferry
wintry juncoBOT
Hi @mild ferry. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Yes, the base model gpt-3.5-turbo-0613 is being deprecated and will be shut down on September 13, 2024. However, fine-tuned models created from this base model will not be affected by this deprecation. This means that even after the shutdown of the base model, you will still be able to use your fine-tuned model. However, you will no longer be able to create new fine-tuned versions with this base model after the shutdown date.
Please note that the original /v1/fine-tunes API along with legacy models (including those fine-tuned with the /v1/fine-tunes API) will be shut down on January 04, 2024. This means that models fine-tuned using the /v1/fine-tunes API will no longer be accessible and you would have to fine-tune new models with the updated endpoint and associated base models.
For future fine-tuning, OpenAI recommends using the gpt-4o-mini-2024-07-18 model, which is expected to be the right model for most users in terms of performance, cost, and ease of use.
You can find more details in the deprecation documentation (https://platform.openai.com/docs/deprecations/2023-11-06-chat-model-updates) and the fine-tuning guide (https://platform.openai.com/docs/guides/fine-tuning).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
mild ferry
@wintry junco However, you will no longer be able to create new fine-tuned versions with this base model after the shutdown date. - Really?
wintry juncoBOT
Let me check the knowledge base for you. One moment! :books:
Yes, that's correct. After the shutdown date of the base model gpt-3.5-turbo-0613, you will not be able to create new fine-tuned versions with this base model. However, if you have already fine-tuned a model using gpt-3.5-turbo-0613, you can continue to use that fine-tuned model even after the base model has been deprecated.
Furthermore, if you want to continue training a new model from one you’ve already fine-tuned, you can specify the fine-tuned model as your model instead of the base model name when creating a fine-tuning job. This will start a new fine-tuning job using the fine-tuned model as the starting point.