Skip to content

fix: fix log step#1447

Merged
terrykong merged 1 commit intomainfrom
yukih/fix-log-step
Oct 30, 2025
Merged

fix: fix log step#1447
terrykong merged 1 commit intomainfrom
yukih/fix-log-step

Conversation

@yuki-97
Copy link
Copy Markdown
Contributor

@yuki-97 yuki-97 commented Oct 30, 2025

Previously we have one step mismatch when saving log in grpo and distillation, this PR will fix it.

Before this PR:

Logged data to logs/exp_014/train_data_step307.jsonl
Logged data to logs/exp_014/train_data_step308.jsonl

▶ Starting validation at step 310...
Saving checkpoint for step 310...

Logged data to logs/exp_014/train_data_step309.jsonl
Logged data to logs/exp_014/train_data_step310.jsonl
Logged data to logs/exp_014/train_data_step311.jsonl

After this PR:

Logged data to logs/exp_014/train_data_step308.jsonl
Logged data to logs/exp_014/train_data_step309.jsonl

▶ Starting validation at step 310...
Saving checkpoint for step 310...

Logged data to logs/exp_014/train_data_step310.jsonl
Logged data to logs/exp_014/train_data_step311.jsonl
Logged data to logs/exp_014/train_data_step312.jsonl

@yuki-97
fix log step
54634bc 
Signed-off-by: Yuki Huang <yukih@nvidia.com>
@yuki-97 yuki-97 requested a review from a team as a code owner October 30, 2025 04:05
@yuki-97 yuki-97 added the CI:L1 Run doctests, unit tests, and functional tests label Oct 30, 2025
@yuki-97 yuki-97 requested a review from terrykong October 30, 2025 04:05
@terrykong terrykong enabled auto-merge (squash) October 30, 2025 06:04
@terrykong terrykong merged commit bd2e645 into main Oct 30, 2025
55 of 58 checks passed
@terrykong terrykong deleted the yukih/fix-log-step branch October 30, 2025 13:54
terrykong pushed a commit that referenced this pull request Nov 2, 2025
@yuki-97 @terrykong
fix: fix log step (#1447)
e9fa861 
Signed-off-by: Yuki Huang <yukih@nvidia.com>
lbliii pushed a commit that referenced this pull request Nov 3, 2025
@yuki-97 @lbliii
fix: fix log step (#1447)
244b8c2 
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Lawrence Lane <llane@nvidia.com>
PrinsYin pushed a commit to PrinsYin/RL that referenced this pull request Nov 30, 2025
@yuki-97
fix: fix log step (NVIDIA-NeMo#1447)
6389ca1 
Signed-off-by: Yuki Huang <yukih@nvidia.com>
yuanhangsu1986 pushed a commit to yuanhangsu1986/RL-Nemontron-Edge-Omni that referenced this pull request Feb 21, 2026
@yuki-97 @yuanhangsu1986
fix: fix log step (NVIDIA-NeMo#1447)
bfe3eb3 
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: yuanhangs <yuanhangs@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@terrykong terrykong Awaiting requested review from terrykong

1 more reviewer

@parthchadha parthchadha parthchadha approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

CI:L1 Run doctests, unit tests, and functional tests

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@yuki-97 @parthchadha @terrykong