RL阶段冻结相关问题 #47

Open

opened

感谢作者开源相关代码，注意到sft阶段有提供freeze的功能，由于计算资源限制的原因，想要在rl阶段也只训练sft解冻的层，这样是否会降低rl阶段的训练效果？

to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests