* use warmup_ratio as a better default than warmup steps since it's data dependent * replace remainder of warmup_steps
openllama-3b
Basic full tune
accelerate launch scripts/finetune.py examples/openllama-3b/config.yml
LoRA
accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml
QLoRA
accelerate launch scripts/finetune.py examples/openllama-3b/qlora.yml