# tinker_cookbook.hyperparam_utils.get_lora_lr_over_full_finetune_lr

### [**tinker_cookbook.hyperparam_utils.get_lora_lr_over_full_finetune_lr**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/hyperparam_utils.py#L66)(*model_name*, *lora_alpha*)

Return the factor that you should scale the full fine-tuning learning rate by to get the equivalent LoRA learning rate. Previously we had a more complicated formula, but the factor of 10 was more accurate empirically. See Lora Without Regret (https://thinkingmachines.ai/blog/lora/) for more details.

**Parameters:**

- [**model_name**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/hyperparam_utils.py#L66) (*str*) – HuggingFace model identifier (currently unused but kept for API consistency).
- [**lora_alpha**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/hyperparam_utils.py#L66) (*int*) – LoRA alpha scaling parameter (currently unused; multiplier is fixed at 10).

**Returns:** *float*