File size: 1,377 Bytes
ee21b96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2022 The OFA-Sys Team. 
# All rights reserved.
# This source code is licensed under the Apache 2.0 license 
# found in the LICENSE file in the root directory.

import numpy as np


class LambdaWarmUpCosineScheduler:
    """
    note: use with a base_lr of 1.0
    """
    def __init__(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0):
        self.lr_warm_up_steps = warm_up_steps
        self.lr_start = lr_start
        self.lr_min = lr_min
        self.lr_max = lr_max
        self.lr_max_decay_steps = max_decay_steps
        self.last_lr = 0.
        self.verbosity_interval = verbosity_interval

    def schedule(self, n):
        if self.verbosity_interval > 0:
            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_lr}")
        if n < self.lr_warm_up_steps:
            lr = (self.lr_max - self.lr_start) / self.lr_warm_up_steps * n + self.lr_start
            self.last_lr = lr
            return lr
        else:
            t = (n - self.lr_warm_up_steps) / (self.lr_max_decay_steps - self.lr_warm_up_steps)
            t = min(t, 1.0)
            lr = self.lr_min + 0.5 * (self.lr_max - self.lr_min) * (
                    1 + np.cos(t * np.pi))
            self.last_lr = lr
            return lr

    def __call__(self, n):
        return self.schedule(n)