Skip to content

Fix require_grad typo #1771

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

Closed
wants to merge 2 commits into from
Closed

Fix require_grad typo #1771

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
35aa0ec
Fix require_grad typo
kit1980 Jul 17, 2023
c2b42c9
Update position.py
kit1980 Jul 19, 2023
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
3 changes: 2 additions & 1 deletion torchbenchmark/models/BERT_pytorch/bert_pytorch/model/embedding/position.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,8 @@ def __init__(self, d_model, max_len=512):

# Compute the positional encodings once in log space.
pe = torch.zeros(max_len, d_model).float()
pe.require_grad = False
# Changed from upstream, see https://github.com/codertimo/BERT-pytorch/pull/104
pe.requires_grad = False
Copy link
Contributor

@xuzhao9 xuzhao9 Jul 19, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you please add https://github.com/codertimo/BERT-pytorch/pull/104 here so that we can track the upstream code change?

Copy link
Contributor Author

@kit1980 kit1980 Jul 19, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done


position = torch.arange(0, max_len).float().unsqueeze(1)
div_term = (torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model)).exp()
Expand Down