Function adamw 

pub fn adamw(
    param: &mut [f32],
    grad: &[f32],
    m: &mut [f32],
    v: &mut [f32],
    lr: f32,
    beta1: f32,
    beta2: f32,
    eps: f32,
    weight_decay: f32,
    step: u32,
)

AdamW step (decoupled weight decay), in place. step is 1-based.