mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-21 05:34:18 +08:00
7176c92687
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/71333 Updated - Adagrad - Adamax - Adam - AdamW - RAdam make multi_tensor functionals take `state_steps: List[Tensor]` instead of taking `states: List[Dict]` make `state_steps: List[int]s -> state_steps:List[Tensor]` where each is a Singleton tensor so step can be updated within the functional (NAdam and ASGD) were updated in separate diffs to fold their handling of state into the functionals Test Plan: Imported from OSS Reviewed By: anjali411 Differential Revision: D33767872 Pulled By: mikaylagawarecki fbshipit-source-id: 9baa7cafb6375eab839917df9287c65a437891f2 (cherry picked from commit 831c02b3d0f585f61165ead368213f94b97a99ee)
103 lines
3.9 KiB
Python
103 lines
3.9 KiB
Python
import torch
|
|
from . import _functional as F
|
|
from ..optimizer import Optimizer
|
|
|
|
class RAdam(Optimizer):
|
|
r"""Implements RAdam algorithm with multi tensor APIs.
|
|
|
|
It has been proposed in `On the variance of the adaptive learning rate and beyond`_.
|
|
|
|
Args:
|
|
params (iterable): iterable of parameters to optimize or dicts defining
|
|
parameter groups
|
|
lr (float, optional): learning rate (default: 2e-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 (L2 penalty) (default: 0)
|
|
|
|
.. _On the variance of the adaptive learning rate and beyond:
|
|
https://arxiv.org/pdf/1908.03265.pdf
|
|
"""
|
|
|
|
def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
|
|
weight_decay=0):
|
|
if not 0.0 <= lr:
|
|
raise ValueError("Invalid learning rate: {}".format(lr))
|
|
if not 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]))
|
|
if not 0.0 <= weight_decay:
|
|
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
|
|
defaults = dict(lr=lr, betas=betas, eps=eps, weight_decay=weight_decay, foreach=True)
|
|
super(RAdam, self).__init__(params, defaults)
|
|
|
|
def __setstate__(self, state):
|
|
super().__setstate__(state)
|
|
state_values = list(self.state.values())
|
|
step_is_tensor = (len(state_values) != 0) and torch.is_tensor(state_values[0]['step'])
|
|
if not step_is_tensor:
|
|
for s in state_values:
|
|
s['step'] = torch.tensor(float(s['step']))
|
|
|
|
@torch.no_grad()
|
|
def step(self, closure=None):
|
|
"""Performs a single optimization step.
|
|
|
|
Args:
|
|
closure (callable, optional): A closure that reevaluates the model
|
|
and returns the loss.
|
|
"""
|
|
loss = None
|
|
if closure is not None:
|
|
with torch.enable_grad():
|
|
loss = closure()
|
|
|
|
for group in self.param_groups:
|
|
params_with_grad = []
|
|
grads = []
|
|
exp_avg = []
|
|
exp_avg_sq = []
|
|
state_steps = []
|
|
beta1, beta2 = group['betas']
|
|
|
|
for p in group['params']:
|
|
if p.grad is not None:
|
|
if p.grad.is_sparse:
|
|
raise RuntimeError('RAdam does not support sparse gradients')
|
|
params_with_grad.append(p)
|
|
grads.append(p.grad)
|
|
|
|
for p in params_with_grad:
|
|
state = self.state[p]
|
|
|
|
# State initialization
|
|
if len(state) == 0:
|
|
state['step'] = torch.tensor(0.)
|
|
# Exponential moving average of gradient values
|
|
state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
|
|
# Exponential moving average of squared gradient values
|
|
state['exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)
|
|
|
|
exp_avg.append(state['exp_avg'])
|
|
exp_avg_sq.append(state['exp_avg_sq'])
|
|
|
|
state_steps.append(state['step'])
|
|
|
|
F.radam(params_with_grad,
|
|
grads,
|
|
exp_avg,
|
|
exp_avg_sq,
|
|
state_steps,
|
|
beta1=beta1,
|
|
beta2=beta2,
|
|
lr=group['lr'],
|
|
weight_decay=group['weight_decay'],
|
|
eps=group['eps'])
|
|
|
|
return loss
|