File size: 7,440 Bytes
4e40454 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 |
import math
import torch
from torch import Tensor
from torch.optim.optimizer import Optimizer
from typing import List, Optional
class SophiaG(Optimizer):
def __init__(self, params, lr=1e-4, betas=(0.965, 0.99), rho = 0.04,
weight_decay=1e-1, *, maximize: bool = False,
capturable: bool = False):
if not 0.0 <= lr:
raise ValueError("Invalid learning rate: {}".format(lr))
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 <= rho:
raise ValueError("Invalid rho parameter at index 1: {}".format(rho))
if not 0.0 <= weight_decay:
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
defaults = dict(lr=lr, betas=betas, rho=rho,
weight_decay=weight_decay,
maximize=maximize, capturable=capturable)
super(SophiaG, self).__init__(params, defaults)
def __setstate__(self, state):
super().__setstate__(state)
for group in self.param_groups:
group.setdefault('maximize', False)
group.setdefault('capturable', False)
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 update_hessian(self):
for group in self.param_groups:
beta1, beta2 = group['betas']
for p in group['params']:
if p.grad is None:
continue
state = self.state[p]
if len(state) == 0:
state['step'] = torch.zeros((1,), dtype=torch.float, device=p.device) \
if self.defaults['capturable'] else torch.tensor(0.)
state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
state['hessian'] = torch.zeros_like(p, memory_format=torch.preserve_format)
if 'hessian' not in state.keys():
state['hessian'] = torch.zeros_like(p, memory_format=torch.preserve_format)
state['hessian'].mul_(beta2).addcmul_(p.grad, p.grad, value=1 - beta2)
@torch.no_grad()
def step(self, closure=None, bs=5120):
loss = None
if closure is not None:
with torch.enable_grad():
loss = closure()
for group in self.param_groups:
params_with_grad = []
grads = []
exp_avgs = []
state_steps = []
hessian = []
beta1, beta2 = group['betas']
for p in group['params']:
if p.grad is None:
continue
params_with_grad.append(p)
if p.grad.is_sparse:
raise RuntimeError('Hero does not support sparse gradients')
grads.append(p.grad)
state = self.state[p]
# State initialization
if len(state) == 0:
state['step'] = torch.zeros((1,), dtype=torch.float, device=p.device) \
if self.defaults['capturable'] else torch.tensor(0.)
state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
state['hessian'] = torch.zeros_like(p, memory_format=torch.preserve_format)
if 'hessian' not in state.keys():
state['hessian'] = torch.zeros_like(p, memory_format=torch.preserve_format)
exp_avgs.append(state['exp_avg'])
state_steps.append(state['step'])
hessian.append(state['hessian'])
if self.defaults['capturable']:
bs = torch.ones((1,), dtype=torch.float, device=p.device) * bs
sophiag(params_with_grad,
grads,
exp_avgs,
hessian,
state_steps,
bs=bs,
beta1=beta1,
beta2=beta2,
rho=group['rho'],
lr=group['lr'],
weight_decay=group['weight_decay'],
maximize=group['maximize'],
capturable=group['capturable'])
return loss
def sophiag(params: List[Tensor],
grads: List[Tensor],
exp_avgs: List[Tensor],
hessian: List[Tensor],
state_steps: List[Tensor],
capturable: bool = False,
*,
bs: int,
beta1: float,
beta2: float,
rho: float,
lr: float,
weight_decay: float,
maximize: bool):
if not all(isinstance(t, torch.Tensor) for t in state_steps):
raise RuntimeError("API has changed, `state_steps` argument must contain a list of singleton tensors")
func = _single_tensor_sophiag
func(params,
grads,
exp_avgs,
hessian,
state_steps,
bs=bs,
beta1=beta1,
beta2=beta2,
rho=rho,
lr=lr,
weight_decay=weight_decay,
maximize=maximize,
capturable=capturable)
def _single_tensor_sophiag(params: List[Tensor],
grads: List[Tensor],
exp_avgs: List[Tensor],
hessian: List[Tensor],
state_steps: List[Tensor],
*,
bs: int,
beta1: float,
beta2: float,
rho: float,
lr: float,
weight_decay: float,
maximize: bool,
capturable: bool):
for i, param in enumerate(params):
grad = grads[i] if not maximize else -grads[i]
exp_avg = exp_avgs[i]
hess = hessian[i]
step_t = state_steps[i]
if capturable:
assert param.is_cuda and step_t.is_cuda and bs.is_cuda
if torch.is_complex(param):
grad = torch.view_as_real(grad)
exp_avg = torch.view_as_real(exp_avg)
hess = torch.view_as_real(hess)
param = torch.view_as_real(param)
# update step
step_t += 1
# Perform stepweight decay
param.mul_(1 - lr * weight_decay)
# Decay the first and second moment running average coefficient
exp_avg.mul_(beta1).add_(grad, alpha=1 - beta1)
if capturable:
step = step_t
step_size = lr
step_size_neg = step_size.neg()
ratio = (exp_avg.abs() / (rho * bs * hess + 1e-15)).clamp(None,1)
param.addcmul_(exp_avg.sign(), ratio, value=step_size_neg)
else:
step = step_t.item()
step_size_neg = - lr
ratio = (exp_avg.abs() / (rho * bs * hess + 1e-15)).clamp(None,1)
param.addcmul_(exp_avg.sign(), ratio, value=step_size_neg) |