Ask HN: Anyone Succesfully fine-tuning LLMs?
Has anyone of you successfully fine-tuned a LLM?
I have done several attempts for simple use cases and the result was always extremely poor generalization.
Any experience, guides, examples would be valuable. I have done my share of fine tuning on open source LLMs (e.g. Llama).
I'm surprised you have very poor generalization. I assume you're using standard techniques, like lora/qlora, which might leave room for issues with your data.
Can you share more details on what is the format of your data points? like, Q/A, free text,... I've tried it a few times without much success. I think it takes more data and discipline than most are prepared for. RAG is a lot easier to reason about and much cheaper to iterate.