{
  "name": "eval_sft_ref",
  "task": "evaluate",
  "note": "Q1 对照：SFT 参考权重（监督 2000 步）在 forced-obs 协议下的表现",
  "checkpoint": "checkpoints/l2_d64_maze_sft_ref.pt",
  "model_type": "gpt",
  "n_trials": 24,
  "seed": 7,
  "budget_scale": 2.0,
  "sizes": ["5x5", "6x6", "7x7"],
  "include_random": true
}