Skip to content

[RL] Fix shape mismatch on tail batch in GRPO training#4252

Open
susanbao wants to merge 4 commits into
mainfrom
sanbao/gpt
Open

[RL] Fix shape mismatch on tail batch in GRPO training#4252
susanbao wants to merge 4 commits into
mainfrom
sanbao/gpt

fix mock configs in train_rl_test.py for drop_remainder=True

7a0c1c7
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Jun 25, 2026 in 12s

✅ All contributors are covered under a CLA with Google

See https://cla.developers.google.com/ for more info about Google's Contributor License Agreement (CLA).

ℹ️ Googlers: Go here to view more details and manage scans for this pull request.

Details

The following contributors were found for this pull request:

✅ 7a0c1c7 Author: @susanbao <sus******ju​@gmail.com>, <sa***o​@google.com>

(Only the first commit for a unique contributor is listed.)

View more details on Google CLA