Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-3.5 Turbo fine-tuning and API updates

openai.com

Post reply on HN
Print view View original

31–40 of 244 posts

Re: GPT-3.5 Turbo fine-tuning and API updates

#31

Post by minimaxir »

danielbln wrote: post #27
BoorishBears wrote: post #25

Earlier quoted context omitted.

Fine tuning is not a replacement for retrieval augmentation. If you wanted to do that you'd be better off fine-tuning BERT to retrieve data more effectively (identify key points, smarter summarization, cross-encoder relevancy, etc)

Could you elaborate? It may not be a replacement, but I can think of a few use cases where RAG could be avoided entirely by having the model be fine tuned on the right dataset.

There is a risk of (greater) hallucination if there aren't explicit sample inputs provided by RAG.

Re: GPT-3.5 Turbo fine-tuning and API updates

#33

Post by swyx »

lamroger wrote: post #7
minimaxir wrote: post #4

Generating from a finetuned GPT 3.5 Turbo is 8x the cost of generating from the base model, so you really have to be in the “reduce prompt size by 90%” bucket they mention to get cost effectiveness out of it.

i didn't catch that but getting consistency is probably worth it in most cases. depends on your budget

but consistency isn't guaranteed. like, at all

Re: GPT-3.5 Turbo fine-tuning and API updates

#34

Post by swyx »

icelancer wrote: post #20
chenxi9649 wrote: post #17

Are there any benchmarks/results showcasing the performance increase with fine tuning? Like showcasing a list of prompt and answers between a fine-tuned LLM and a non fine-tuned one. Could be with LLAMA 2 as well. Even if it's quite specialized like in Medical/Legal, it would be great to see the expected value one can derive from fine-tuning.

There is such a limited amount of this and most of what you can find is blogspam. Lots of people asked the OpenAI GPT rep on Twitter for exactly this; hoping we see it as GPT-4 becomes tunable.

link for those who also wanted to look it up https://twitter.com/OfficialLoganK/status/169406294917713961...

Re: GPT-3.5 Turbo fine-tuning and API updates

#35

Post by alooPotato »

minimaxir wrote: post #4

Generating from a finetuned GPT 3.5 Turbo is 8x the cost of generating from the base model, so you really have to be in the “reduce prompt size by 90%” bucket they mention to get cost effectiveness out of it.

I think you have to compare it to your alternative which is prob gpt4 in which case its much cheaper?

Re: GPT-3.5 Turbo fine-tuning and API updates

#37

Post by siva7 »

TheCaptain4815 wrote: post #9

Quite exciting, this is the first time their "Chat" model is available for finetuning. Has anyone successfully bypassed the current Ai detectors using fine-tuned models? I know it's possible, I'm just trying to conceptualize how the dataset would be organized...

ai detectors are scam products. it's not possible to detect with reliable certainty if text is human or chatgpt generated

Re: GPT-3.5 Turbo fine-tuning and API updates

#38

Post by netruk44 »

todd3834 wrote: post #19

> It is very important to us that the deployment of fine-tuning is safe. To preserve the default model's safety features through the fine-tuning process, fine-tuning training data is passed through our Moderation API and a GPT-4 powered moderation system to detect unsafe training data that conflict with our safety standards. I wish there was some documentation on what kinds of things are determined unsafe. There are…

You can see the list of things the moderation endpoint scans for in the OpenAI documentation: https://platform.openai.com/docs/guides/moderation/overview

I'm unsure of what the "GPT-4 powered moderation system" entails, though.

Conjecture: My unsubstantiated guess would be them prompting GPT-4 with something like "Is the following excerpt considered to be harmful or unsafe: {training data}" and then limiting the output to just a few words like "Yes", "No" and "It's unclear".

Re: GPT-3.5 Turbo fine-tuning and API updates

#39

Post by icelancer »

swyx wrote: post #34
icelancer wrote: post #20

Earlier quoted context omitted.

There is such a limited amount of this and most of what you can find is blogspam. Lots of people asked the OpenAI GPT rep on Twitter for exactly this; hoping we see it as GPT-4 becomes tunable.

link for those who also wanted to look it up https://twitter.com/OfficialLoganK/status/169406294917713961...

That's a different link than the one I was thinking of, but I came here to post it all the same!

Definitely encourage everyone to post in support of increased documentation and specific examples on why you'd use it.

Re: GPT-3.5 Turbo fine-tuning and API updates

#40

Post by minimaxir »

alooPotato wrote: post #35
minimaxir wrote: post #4

Generating from a finetuned GPT 3.5 Turbo is 8x the cost of generating from the base model, so you really have to be in the “reduce prompt size by 90%” bucket they mention to get cost effectiveness out of it.

I think you have to compare it to your alternative which is prob gpt4 in which case its much cheaper?

Correct, GPT-4 is 20-30x the cost compared to GPT-3.5-turbo, but that's more in another class entirely. IMO a finetuned-GPT-3.5-turbo won't beat base GPT-4 for the use cases where you really really need GPT-4, but that remains to be seen.

The real alternative to a finetuned GPT-3.5-turbo is still the base model with a very very complicated system prompt.

Post reply on HN