GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal

Add A/B comparison Job for trained-policy showdown

GRPO: expose --learning-rate, --temperature, --curriculum-schedule

Add HF Jobs entry-point for post-training evaluation

Add transformers-backend GRPO loader (no triton/Unsloth dep) + fix Jobs deps

Add HF Jobs entry-point script for GRPO training