# tinker.types.DimuonParams

*Generated from tinker 0.30.4 at commit [`1e5777e`](https://github.com/thinking-machines-lab/tinker/tree/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d). Source links point at that snapshot.*

## *class* [**tinker.types.DimuonParams**](https://github.com/thinking-machines-lab/tinker/blob/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d/src/tinker/types/optimizer.py#L55)(*[OptimParamsBase](https://tinker-docs.thinkingmachines.ai/tinker/api-reference/types/optimparamsbase/index.md)*)

Hyperparameters for one Dimuon optimizer step.

**Fields:**

- [**type**](https://github.com/thinking-machines-lab/tinker/blob/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d/src/tinker/types/optimizer.py#L58) (*Literal['dimuon']*) – Optimizer family for this step.
- [**learning_rate**](https://github.com/thinking-machines-lab/tinker/blob/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d/src/tinker/types/optimizer.py#L61) (*float*) – Sets the step size for the optimizer.
- [**grad_clip_norm**](https://github.com/thinking-machines-lab/tinker/blob/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d/src/tinker/types/optimizer.py#L64) (*float*) – Maximum global gradient norm. Nonpositive values disable gradient clipping.
- [**beta1**](https://github.com/thinking-machines-lab/tinker/blob/1e5777ef1e0bb2bae6d9b8d63a6144eec405377d/src/tinker/types/optimizer.py#L67) (*float*) – EMA coefficient for the momentum. Should be between zero and one.