python scripts/lora.py --model mlx-community/Mistral-7B-Instruct-v0.2-4bit 
                       --train 
                       --iters 100 
                       --steps-per-eval 10 
                       --val-batches -1 
                       --learning-rate 1e-5 
                       --lora-layers 16 
                       --test

# --train = runs LoRA training
# --iters = number of training steps
# --steps-per-eval = number steps to do before computing val loss
# --val-batches = number val dataset examples to use in val loss (-1 = all)
# --learning-rate (same as default)
# --lora-layers (same as default)
# --test = computes test loss at the end of training