# tinker_cookbook.hyperparam_utils

| Function                                                                                                                                                            | Description                                                                      |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |
| [`get_lora_lr_over_full_finetune_lr()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_lora_lr_over_full_finetune_lr/index.md) | Return the factor that you should scale the full fine-tuning learning rate by to |
| [`get_lora_param_count()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_lora_param_count/index.md)                           | Get the number of parameters in the LoRA adapter.                                |
| [`get_lr()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_lr/index.md)                                                       | Get a recommended learning rate for the given model.                             |
| [`get_full_finetune_param_count()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_full_finetune_param_count/index.md)         | Get the total parameter count for a model by reading safetensors headers.        |
| [`get_full_finetune_lr_multiplier()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_full_finetune_lr_multiplier/index.md)     | Get a model-specific LR multiplier for full fine-tuning, proportional to 1/sqrt( |
| [`get_lora_lr_multiplier()`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/hyperparam_utils/get_lora_lr_multiplier/index.md)                       | Get a model-specific multiplier for the LR, when training with LoRA.             |