Skip to content
Back to pull request #2057

Added error check to RLOO, PPOv2, OnlineDPO that ref_policy and policy have different identities #4992

Sign in to view logs

Added error check to RLOO, PPOv2, OnlineDPO that ref_policy and policy have different identities

Added error check to RLOO, PPOv2, OnlineDPO that ref_policy and policy have different identities #4992

Annotations

2 errors

The logs for this run have expired and are no longer available.