FilterHN

Fine-Tuning LLMs: A Review of Technologies, Research, Best Practices, Challenges

99 points

by ignoramous

4 hours ago

| past

| 2 comments

| arxiv.org

| HN

▲

kcorbitt

3 hours ago

[-]

I saw this when it was making the rounds on X a few days ago. Fair warning: it seems like at least some sections are AI-generated, and there isn't much insight to be gained from reading the actual sections compared to eg. reading the relevant category pages on Huggingface.

▲

danielhanchen

24 minutes ago

[-]

I took a skim through it in the morning - I like the LoRA Learns Less and Forgets Less paper more https://openreview.net/forum?id=aloEru2qCG - it has much more signal in a few pages - also the original QLoRA paper from Dettmers https://arxiv.org/abs/2305.14314 has so many more important morsels.

But all in all, the review is a reasonable "manual" I guess. I would have liked maybe more instructive comprehensive practical examples, and maybe more mention of other OSS packages for finetuning :))

▲

worstspotgain

29 minutes ago

[-]

Glancing at the authors' names, it's possible that none of them are native English speakers. Any chance that the sections you're referring to were just AI-polished rather than AI-generated?

▲

daghamm

2 hours ago

[-]

I would not say that, as long as it is a good summary there is a value in having everything in the same document.

Obviously they should have stated that this is partially generated, but at least they are dog fooding it :)

▲

YetAnotherNick

2 hours ago

[-]

Not only the it seems to be AI generated, it seems these guys don't even know about best practices or even what works. e.g. It contains archaic comparison of optimizers and its pros and cons, but for LLMs no optimizer other than Adam and new ones like Lion works.

▲

abc-1

1 hour ago

[-]

Is there a paper on this? Why do no other optimizers give good results? Adam requires insane amounts of memory so alternatives would be welcome.

▲

anothername12

2 hours ago

[-]

Well, it sucks that we’re at the “best practices” phase already

▲

p1esk

1 hour ago

[-]

It sucks that we’re still at “best practices” phase. We’ve been in this phase for the last three decades [1], and I really hope we enter “good theory” phase soon.

[1] https://cseweb.ucsd.edu/classes/wi08/cse253/Handouts/lecun-9...

▲

kleiba

9 minutes ago

[-]

Why is that?