Add option to recompute old policy logprobs on the trainer.#1487
Open
copybara-service[bot] wants to merge 1 commit intomainfrom
Open
Add option to recompute old policy logprobs on the trainer.#1487copybara-service[bot] wants to merge 1 commit intomainfrom
copybara-service[bot] wants to merge 1 commit intomainfrom
Commits
Commits on May 5, 2026
- authored andcommitted
