File size: 4,286 Bytes
e139fa3 |
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 |
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 = 0.0
self.verbosity_interval = verbosity_interval
def schedule(self, n, **kwargs):
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, **kwargs):
return self.schedule(n, **kwargs)
class LambdaWarmUpCosineScheduler2:
"""
supports repeated iterations, configurable via lists
note: use with a base_lr of 1.0.
"""
def __init__(
self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0
):
assert (
len(warm_up_steps)
== len(f_min)
== len(f_max)
== len(f_start)
== len(cycle_lengths)
)
self.lr_warm_up_steps = warm_up_steps
self.f_start = f_start
self.f_min = f_min
self.f_max = f_max
self.cycle_lengths = cycle_lengths
self.cum_cycles = np.cumsum([0] + list(self.cycle_lengths))
self.last_f = 0.0
self.verbosity_interval = verbosity_interval
def find_in_interval(self, n):
interval = 0
for cl in self.cum_cycles[1:]:
if n <= cl:
return interval
interval += 1
def schedule(self, n, **kwargs):
cycle = self.find_in_interval(n)
n = n - self.cum_cycles[cycle]
if self.verbosity_interval > 0:
if n % self.verbosity_interval == 0:
print(
f"current step: {n}, recent lr-multiplier: {self.last_f}, "
f"current cycle {cycle}"
)
if n < self.lr_warm_up_steps[cycle]:
f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[
cycle
] * n + self.f_start[cycle]
self.last_f = f
return f
else:
t = (n - self.lr_warm_up_steps[cycle]) / (
self.cycle_lengths[cycle] - self.lr_warm_up_steps[cycle]
)
t = min(t, 1.0)
f = self.f_min[cycle] + 0.5 * (self.f_max[cycle] - self.f_min[cycle]) * (
1 + np.cos(t * np.pi)
)
self.last_f = f
return f
def __call__(self, n, **kwargs):
return self.schedule(n, **kwargs)
class LambdaLinearScheduler(LambdaWarmUpCosineScheduler2):
def schedule(self, n, **kwargs):
cycle = self.find_in_interval(n)
n = n - self.cum_cycles[cycle]
if self.verbosity_interval > 0:
if n % self.verbosity_interval == 0:
print(
f"current step: {n}, recent lr-multiplier: {self.last_f}, "
f"current cycle {cycle}"
)
if n < self.lr_warm_up_steps[cycle]:
f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[
cycle
] * n + self.f_start[cycle]
self.last_f = f
return f
else:
f = self.f_min[cycle] + (self.f_max[cycle] - self.f_min[cycle]) * (
self.cycle_lengths[cycle] - n
) / (self.cycle_lengths[cycle])
self.last_f = f
return f
|