arm3 / README.md
rulins's picture
Upload README.md with huggingface_hub
edac065 verified
|
Raw History Blame Contribute Delete
443 Bytes
---
license: apache-2.0
base_model: allenai/Olmo-3-1025-7B
tags: [grpo, rlvr, reasoning-registers, lora]
---
# arm3 — free register + truncation penalty
GRPO (TRL) LoRA adapters (r=64, alpha=128) on `allenai/Olmo-3-1025-7B`, RL-Zero prompt.
One cell of the 2x2 factorial {register forced} x {truncation penalty}. Folders `step100/ ... step300/`.
Paired eval rollouts: `ReasoningRegisters/arm3-eval-rollouts` (splits `step{k}_{benchmark}`).