ByteDance-Seed / ByteDance-Seed/Seed-Coder
Batch Size for RL training
Open
- Dominant language
- No language data
- Stars
- 759
- Forks
- 59
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for this great work!
In the report, it's mentioned that a batch size of 128 is used. Is this including the rollout number or not?
Also, how many mini-batches are used during training?
Thanks
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.