riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Same fix for addcmul_

Browse Source
This commit is contained in:
Julien Chaumond 2020-05-15 17:23:48 -04:00
parent ad02c961c6
commit 55bda52555
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/optimization.py
View File

@ -152,8 +152,8 @@ class AdamW(Optimizer):
# Decay the first and second moment running average coefficient
# In-place operations to update the averages at the same time
exp_avg.mul_(beta1).add_(grad, alpha=1.0 - beta1)
exp_avg_sq.mul_(beta2).addcmul_(1.0 - beta2, grad, grad)
exp_avg.mul_(beta1).add_(grad, 1.0 - beta1)
exp_avg_sq.mul_(beta2).addcmul_(grad, grad, 1.0 - beta2)
denom = exp_avg_sq.sqrt().add_(group["eps"])
step_size = group["lr"]
@ -173,6 +173,6 @@ class AdamW(Optimizer):
# of the weights to the loss with plain (non-momentum) SGD.
# Add weight decay at the end (fixed version)
if group["weight_decay"] > 0.0:
p.data.add_(p.data, alpha=-group["lr"] * group["weight_decay"])
p.data.add_(p.data, -group["lr"] * group["weight_decay"])
return loss