Skip to content

add vapo#10951

Open
dddd-d wants to merge 31 commits intoPaddlePaddle:developfrom
dddd-d:merge
Open

add vapo#10951
dddd-d wants to merge 31 commits intoPaddlePaddle:developfrom
dddd-d:merge

Conversation

@dddd-d
Copy link
Copy Markdown
Contributor

@dddd-d dddd-d commented Aug 14, 2025

Before submitting

  • Lint code. If there are lint issues, please format the code first.
# Install and register `pre-commit` in the project folder
pip install pre-commit && pre-commit install

# Process previous code files separately
pre-commit run --file XXXX.py
  • Add test cases into tests folder. If there are codecov issues, please add tests cases first.

PR types

PR changes

Description

DesmonDay and others added 30 commits July 23, 2025 13:44
@DesmonDay
add ppo
0bda8a7
@dddd-d
Update run_rl.py
faaa350
@dddd-d
Update ppo_trainer.py
9f1b06c
@dddd-d
Update config_utils.py
f2664bc
@dddd-d
Update run_rl.py
b517f02
@dddd-d
Update gsm8k_processor.py
5d4c614
@dddd-d
Update run_rl.py
1a574bd
@dddd-d
Update score_model_utils.py
d48283a
@dddd-d
Update score_model_utils.py
d6d43a9
@dddd-d
Update run_rl.py
a4705c4
@dddd-d
Update ppo_trainer.py
01599d3
@dddd-d
Update ppo_trainer.py
89f25f3
@dddd-d
Update ppo_trainer.py
325d76c
@dddd-d
Update score_model_utils.py
c55a878
@DesmonDay
add vapo
15b277a
@dddd-d
Update gsm8k_processor.py
2614d18
@DesmonDay
add vapo_argument.yaml
abe2722
@DesmonDay
pre_commit
60486dc
@dddd-d
Update advantage.py
da24bff
@dddd-d
Update advantage.py
07a1dea
@DesmonDay
pre-commit check
dde6b5d
@Xing-lil @DesmonDay
[Auto Parallel] Fix sp in gpt modeling_auto (PaddlePaddle#10835)
99a7297 
* Update modeling_auto.py

* Update pretrain-gpt3_13b_dynamic_auto.json

* update

* fix gpt sp model

* Update loss base

* update loss base

* disable benchmark SP for now
@Liujie0926 @DesmonDay
fix CI bug (PaddlePaddle#10890)
8d68813
@RevL147 @DesmonDay
fix ordered_save func (PaddlePaddle#10896)
495fbe9 
Co-authored-by: luyuxiang <[email protected]>
@DesmonDay
fix global_mini_batch_size
9734c0e
@DesmonDay
fix ppo_argument.yaml
7136e10
@DesmonDay
fix ppo_argument.yaml
ce589fc
@DesmonDay
fix
fe61ae5
@DesmonDay
fix global_mini_batch_size
9dcabdf
@DesmonDay
merge ppo and vapo
52f620a
@paddle-bot
Copy link
Copy Markdown

paddle-bot bot commented Aug 14, 2025

Thanks for your contribution!

@CLAassistant
Copy link
Copy Markdown

CLAassistant commented Aug 14, 2025 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

@github-actions
Copy link
Copy Markdown

github-actions bot commented Dec 30, 2025

This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动，被标记为stale。

@github-actions github-actions bot added the stale label Dec 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@lugimzzz lugimzzz

Labels

contributor stale

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

7 participants

@dddd-d @CLAassistant @lugimzzz @DesmonDay @Xing-lil @Liujie0926 @RevL147