{
 "base_model": "Qwen/Qwen3.5-2B",
 "audit_solver": "Qwen/Qwen3.5-397B-A17B",
 "renderer": "qwen3_5_disable_thinking",
 "audit_renderer": "qwen3_5",
 "audit_decoding": {
  "temperature": 0,
  "max_tokens": 8192
 },
 "generation": {
  "temperature": 1.0,
  "max_tokens": 1024,
  "n_accept": 640,
  "filter_samples": 8,
  "keep_band": "1-6",
  "filter_max_tokens": 512,
  "chunk": 1024,
  "max_candidates": 12288
 },
 "arms": [
  "base",
  "rl_gsm8k",
  "rl_selfgen"
 ],
 "lora_rank": 32,
 "learning_rate": 4e-05,
 "adam": {
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 1e-08
 },
 "group_size": 8,
 "groups_per_batch": 16,
 "steps": 40,
 "seed": 0,
 "max_tokens": 512,
 "n_eval": 1319,
 "eval_decoding": {
  "temperature": 0,
  "max_tokens": 512
 },
 "training_executed": false,
 "stop_reason": "generation audit failed (25 label errors > 0)"
}