Skip to content

Allow negative learning rate #1277

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 19, 2024
Merged

Allow negative learning rate #1277

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions sdxl_train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,7 @@ def fn_recursive_set_mem_eff(module: torch.nn.Module):
# 学習を準備する：モデルを適切な状態にする
if args.gradient_checkpointing:
unet.enable_gradient_checkpointing()
train_unet = args.learning_rate > 0
train_unet = args.learning_rate != 0
train_text_encoder1 = False
train_text_encoder2 = False

Expand All @@ -284,8 +284,8 @@ def fn_recursive_set_mem_eff(module: torch.nn.Module):
text_encoder2.gradient_checkpointing_enable()
lr_te1 = args.learning_rate_te1 if args.learning_rate_te1 is not None else args.learning_rate # 0 means not train
lr_te2 = args.learning_rate_te2 if args.learning_rate_te2 is not None else args.learning_rate # 0 means not train
train_text_encoder1 = lr_te1 > 0
train_text_encoder2 = lr_te2 > 0
train_text_encoder1 = lr_te1 != 0
train_text_encoder2 = lr_te2 != 0

# caching one text encoder output is not supported
if not train_text_encoder1:
Expand Down
Loading