File size: 2,584 Bytes
8e0b903
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""PyTorch implementation of the Lion optimizer."""
import torch
from torch.optim.optimizer import Optimizer


class Lion(Optimizer):
    r"""Implements Lion algorithm."""

    def __init__(self, params, lr=1e-4, betas=(0.9, 0.99), weight_decay=0.0):
        """Initialize the hyperparameters.

        Args:

          params (iterable): iterable of parameters to optimize or dicts defining

            parameter groups

          lr (float, optional): learning rate (default: 1e-4)

          betas (Tuple[float, float], optional): coefficients used for computing

            running averages of gradient and its square (default: (0.9, 0.99))

          weight_decay (float, optional): weight decay coefficient (default: 0)

        """

        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]))
        defaults = dict(lr=lr, betas=betas, weight_decay=weight_decay)
        super().__init__(params, defaults)

    @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.

        Returns:

          the loss.

        """
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            for p in group['params']:
                if p.grad is None:
                    continue

                # Perform stepweight decay
                p.data.mul_(1 - group['lr'] * group['weight_decay'])

                grad = p.grad
                state = self.state[p]
                # State initialization
                if len(state) == 0:
                    # Exponential moving average of gradient values
                    state['exp_avg'] = torch.zeros_like(p)

                exp_avg = state['exp_avg']
                beta1, beta2 = group['betas']

                # Weight update
                update = exp_avg * beta1 + grad * (1 - beta1)
                p.add_(torch.sign(update), alpha=-group['lr'])
                # Decay the momentum running average coefficient
                exp_avg.mul_(beta2).add_(grad, alpha=1 - beta2)

        return loss