LoRA finetuning Gemma2-2B on M3 Max — full run writeup

30k-sample instruction tune of Gemma2-2B. ~3 hours on M3 Max 64G.

mlx_lm.lora --train --model mlx-community/gemma-2-2b-4bit --data ./corpus.jsonl --batch-size 8 --iters 8000 --lora-layers 16