Shaer-adapters-grpo-vnext

This repo is the first patched rerun after Shaer-AI/Shaer-adapters-grpo was reclassified as reward hacked.

Place in the story

Project sequence:

1. Shaer-AI/Shaer-adapters clean SFT baseline
2. Shaer-AI/Shaer-adapters-grpo historically strong-looking but reward-hacked GRPO run
3. Shaer-AI/Shaer-adapters-grpo-vnext stricter anti-template and artifact-filtering GRPO rerun
4. Shaer-AI/Shaer-adapters-grpo-friend-v1 first judge-centered rerun
5. Shaer-AI/Shaer-adapters-grpo-friend-v1-easyfirst easier judge-centered rerun

What changed here

This run introduced the stricter reward patch that was designed to kill the old hacked behavior:

reward_total = meter * count_adherence * arabic_clean * repeat_penalty

with much stronger internals for:

• artifact-free Arabic filtering
• lexical plausibility
• near-duplicate detection
• opening diversity
• distinct-2 phrase diversity

Run snapshot

• starting adapter: Shaer-AI/Shaer-adapters
• train subset: dropped-trio curated subset, cap 3000 per surviving meter
• eval bank: full 13-meter eval, 104 rows

Best tracked checkpoint:

• step: 500
• eval total: 0.1937
• eval meter: 0.5652
• eval count adherence: 0.9099
• eval judge diagnostic: 0.3774
• eval repeat penalty: 0.5577
• eval arabic clean: 0.8750

What this run proved

This stage was important because it showed the patched anti-template reward was much better at rejecting the old hacked outputs.

But it still was not the final answer:

• tracked reward was much lower than the old hacked run
• generation quality was still not strong enough
• semantic quality still needed to be modeled more directly

Why we moved on

This repo motivated the next shift: bring in a focused Arabic semantic judge that scores whether the poem:

• has meaning
• is not garbage
• is relevant to the description

That next stage was published as Shaer-AI/Shaer-adapters-grpo-friend-v1.

Recommended use

Use this repo as the first serious post-hack reward patch, not as the final recommended GRPO model.