AI Dynamics

Global AI News Aggregator

About

Why High-Rank LoRA Trains Worse Than Low-Rank and Full Finetuning

Anyone got any guesses as to why high-rank lora might train worse than either of low-rank low *and* full finetune? Must be something about the SGD training dynamics, right? https://
x.com/aicrumb/status
/aicrumb/status/1724911477725778148

→ View original post on X — @jeremyphoward