File size: 1,329 Bytes
1e4d0ca | 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 | import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
# from utils import d_model
'''
optimizer = NoamOpt(d_model, 1, 4000, torch.optim.Adam(model.parameters(), lr=0, betas=(0.9, 0.98), eps=1e-9))
model_size: 256
factor: 1
warmup: 4000
optimizer: torch.optim.Adam(model.parameters(), lr=0, betas=(0.9, 0.98), eps=1e-9)
'''
class NoamOpt:
"Optim wrapper that implements rate."
def __init__(self, model_size, factor, warmup, optimizer):
self.optimizer = optimizer
self._step = 0
self.warmup = warmup
self.factor = factor
self.model_size = model_size
self._rate = 0
def step(self):
"Update parameters and rate"
self._step += 1
rate = self.rate()
# print("This is the rate:", rate)
for p in self.optimizer.param_groups:
p['lr'] = rate
self._rate = rate
self.optimizer.step()
def rate(self, step = None):
"Implement `lrate` above"
if step is None:
step = self._step
return self.factor * (self.model_size ** (-0.5) * min(step ** (-0.5), step * self.warmup ** (-1.5)))
def get_std_opt(model):
return NoamOpt(729, 2, 4000, torch.optim.Adam(model.parameters(), lr=0, betas=(0.9, 0.98), eps=1e-9)) |