# tinker.types.AdamParams

## _class_ [**tinker.types.AdamParams**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L12)( _[StrictBase](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/_models.py#L76)_)

**Fields:**

- [**learning\_rate**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L13) ( _float_) – Learning rate for the optimizer
- [**beta1**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L16) ( _float_) – Coefficient used for computing running averages of gradient
- [**beta2**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L19) ( _float_) – Coefficient used for computing running averages of gradient square
- [**eps**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L22) ( _float_) – Term added to the denominator to improve numerical stability
- [**weight\_decay**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L25) ( _float_) – Weight decay for the optimizer. Uses decoupled weight decay.
- [**grad\_clip\_norm**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/optim_step_request.py#L28) ( _float_) – Maximum global gradient norm. If the global gradient norm is greater than this value, it will be clipped to this value. 0.0 means no clipping.

## Referenced by

- [TrainingClient.optim\_step](https://tinker-docs.thinking-machines-ai/tinker/api-reference/trainingclient/#optim_step)