What does LoRA fine-tuning actually train?
"LoRA trains about 1% of the model" is the usual one-line explanation. It's true, but it hides the parts that decide whether a run fits on your machine and how long it takes: which layers get adapters, what the rank does to the count, what precision the frozen weights sit in, and how many optimizer…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-04 09:21 · DEV Community — Machine Learning
What does LoRA fine-tuning actually train?