{
  "record": "qwen3.5-2b-grpo",
  "arm": "lora",
  "receipt_arm": "ctrl",
  "seed": 0,
  "step": 150,
  "base_model": "Qwen/Qwen3.5-2B",
  "base_revision": "15852e8c16360a2fea060d615a32b45270f8a8fc",
  "recipe": "GRPO, correctness-gated length penalty alpha 0.2, 150 steps from the shared warm-up (paper Section 4)",
  "lora_rank": 16,
  "lora_alpha": 32,
  "lora_targets": [
    "in_proj_qkv",
    "in_proj_a",
    "in_proj_b",
    "out_proj"
  ],
  "gate": null,
  "n_tensors": 144,
  "n_params": 4727808,
  "source_sha256": "de2794c085f5096fea53374ba1cea31075071bb6de3f227bb3350b3035970447"
}