Source code for pywick.optimizers.adamw

# Source:

import math
import torch
from torch.optim.optimizer import Optimizer

[docs]class AdamW(Optimizer): r"""Implements AdamW algorithm. The original Adam algorithm was proposed in `Adam: A Method for Stochastic Optimization`_. The AdamW variant was proposed in `Decoupled Weight Decay Regularization`_. Arguments: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, optional): learning rate (default: 1e-3) betas (Tuple[float, float], optional): coefficients used for computing running averages of gradient and its square (default: (0.9, 0.999)) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8) weight_decay (float, optional): weight decay coefficient (default: 1e-2) amsgrad (boolean, optional): whether to use the AMSGrad variant of this algorithm from the paper `On the Convergence of Adam and Beyond`_ (default: False) .. _Adam\: A Method for Stochastic Optimization: .. _Decoupled Weight Decay Regularization: .. _On the Convergence of Adam and Beyond: """ def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=1e-2, amsgrad=False): if 0.0 > lr: raise ValueError("Invalid learning rate: {}".format(lr)) if 0.0 > eps: raise ValueError("Invalid epsilon value: {}".format(eps)) if not 0.0 <= betas[0] < 1.0: raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0])) if not 0.0 <= betas[1] < 1.0: raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1])) defaults = dict(lr=lr, betas=betas, eps=eps, weight_decay=weight_decay, amsgrad=amsgrad) super(AdamW, self).__init__(params, defaults) def __setstate__(self, state): super(AdamW, self).__setstate__(state) for group in self.param_groups: group.setdefault('amsgrad', False)
[docs] def step(self, closure=None): """Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model and returns the loss. """ 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 # Perform stepweight decay - group['lr'] * group['weight_decay']) # Perform optimization step grad = if grad.is_sparse: raise RuntimeError('Adam does not support sparse gradients, please consider SparseAdam instead') amsgrad = group['amsgrad'] state = self.state[p] # State initialization if len(state) == 0: state['step'] = 0 # Exponential moving average of gradient values state['exp_avg'] = torch.zeros_like( # Exponential moving average of squared gradient values state['exp_avg_sq'] = torch.zeros_like( if amsgrad: # Maintains max of all exp. moving avg. of sq. grad. values state['max_exp_avg_sq'] = torch.zeros_like( 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 # Decay the first and second moment running average coefficient exp_avg.mul_(beta1).add_(1 - beta1, grad) exp_avg_sq.mul_(beta2).addcmul_(1 - beta2, grad, grad) if amsgrad: # Maintains the maximum of all 2nd moment running avg. till now torch.max(max_exp_avg_sq, exp_avg_sq, out=max_exp_avg_sq) # Use the max. for normalizing running avg. of gradient 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'] step_size = group['lr'] * math.sqrt(bias_correction2) / bias_correction1, exp_avg, denom) return loss