feat(trainer): add multi-round Verl GRPO data adaptation#191

RYY177 wants to merge 1 commit into

dev/v2OpenDCAI/Dataflow-LoopAI:dev/v2from

ryy/trainer0801-verl-multiroundOpenDCAI/Dataflow-LoopAI:ryy/trainer0801-verl-multiroundCopy head branch name to clipboard