Skip to content

fix: remove extra bracket in std calc and specify tensor device #21

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

Open
study8677 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: remove extra bracket in std calc and specify tensor device #21

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
48cda85
fix: remove extra bracket in std calc and specify tensor device
study8677 Dec 7, 2025
5ac5511
refactor: apply PR feedback for N=1 logic and torch.stack optimization
study8677 Dec 7, 2025
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
9 changes: 5 additions & 4 deletions agentevolver/module/trainer/ae_ray_trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,11 +197,12 @@ def compute_grpo_outcome_advantage(
id2score[index[i]].append(scores[i])
for idx in id2score:
if len(id2score[idx]) == 1:
id2mean[idx] = torch.tensor(0.0)
id2std[idx] = torch.tensor(1.0)
id2mean[idx] = id2score[idx][0]
id2std[idx] = torch.tensor(1.0, device=scores.device)
elif len(id2score[idx]) > 1:
id2mean[idx] = torch.mean(torch.tensor(id2score[idx]))
id2std[idx] = torch.std(torch.tensor([id2score[idx]]))
group_scores = torch.stack(id2score[idx])
id2mean[idx] = group_scores.mean()
id2std[idx] = group_scores.std()
else:
raise ValueError(f"no score in prompt index: {idx}")
for i in range(bsz):
Expand Down