feat: NeMo RL: don't do on-policy fixes during validation

[bxyu-nvidia]

Use cases, pain points, and background
Why should we do this? Why is this needed or wanted?

Description:
What should we do?

Design:
What files should be touched? What logic should be written?

Out of scope:
What are some items that this issue could be mistaken to cover that this issue should explicitly NOT cover?

Acceptance Criteria:

• Individual items that need to be finished in order for this issue to be considered completed