Class AdamW

ML/src/python/neuralforge/optim/optimizers.py:5–67

import math

class AdamW(Optimizer):
    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0.01, amsgrad=False):
        if lr < 0.0:
            raise ValueError(f"Invalid learning rate: {lr}")
        if eps < 0.0:
            raise ValueError(f"Invalid epsilon value: {eps}")
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError(f"Invalid beta parameter at index 0: {betas[0]}")
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError(f"Invalid beta parameter at index 1: {betas[1]}")
        
        defaults = dict(lr=lr, betas=betas, eps=eps, weight_decay=weight_decay, amsgrad=amsgrad)
        super().__init__(params, defaults)
    
    def step(self, closure=None):
        loss = None
        if closure is not None:
            loss = closure()
        
        for group in self.param_groups:
            for p in group['params']:
                if p.grad is None:
                    continue
                
                grad = p.grad.data
                if grad.is_sparse:
                    raise RuntimeError('AdamW does not support sparse gradients')
                
                amsgrad = group['amsgrad']
                state = self.state[p]
                
                if len(state) == 0:
                    state['step'] = 0
                    state['exp_avg'] = torch.zeros_like(p.data)
                    state['exp_avg_sq'] = torch.zeros_like(p.data)
                    if amsgrad:
                        state['max_exp_avg_sq'] = torch.zeros_like(p.data)
                
                exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
                if amsgrad:
                    max_exp_avg_sq = state['max_exp_avg_sq']
                beta1, beta2 = group['betas']
                
                state['step'] += 1
                
                p.data.mul_(1 - group['lr'] * group['weight_decay'])
                
                exp_avg.mul_(beta1).add_(grad, alpha=1 - beta1)
                exp_avg_sq.mul_(beta2).addcmul_(grad, grad, value=1 - beta2)
                
                if amsgrad:
                    torch.max(max_exp_avg_sq, exp_avg_sq, out=max_exp_avg_sq)
                    denom = max_exp_avg_sq.sqrt().add_(group['eps'])
                else:
                    denom = exp_avg_sq.sqrt().add_(group['eps'])
                
                bias_correction1 = 1 - beta1 ** state['step']
                bias_correction2 = 1 - beta2 ** state['step']