{
  "adapter_weights_sha256": "cdf3f3b5a77fc78fa418932bcfb2245687923202678e058879e8c2d52dc45cf8",
  "base_model": "Hyukkyu/Qwen3-8B-Base-RAQUEL-TOFU-M-orig-LoRA-v1",
  "base_revision": "4f55767275e481122f80a29a53fc0bacf07b859a",
  "data": {
    "forget_rows": 3600,
    "max_length": 512,
    "pairing": "all forget and all retain source QA; the smaller side cycled in a seeded order, paired 1:1",
    "qa_serialization": "paper_v1",
    "repository": "Hyukkyu/RAQUEL2-ICLR",
    "retain_rows": 3600,
    "revision": "ac82756570fcce84441fb413ab523de8da679efd"
  },
  "early_stopping": {
    "config": {
      "cached_decode_agreement": 1.0,
      "continue_after_stop": true,
      "every_steps": 4,
      "max_new_tokens": 64,
      "rule": "max retain ROUGE-L s.t. forget ROUGE-L <= M_ret (margin 0; user 2026-09-24)",
      "seed": 0,
      "subset_size": 100,
      "target_forget_rouge": 0.3903,
      "target_source": "early_stop/tofu_qwen3_M_ret.json"
    },
    "released_adapter": "step 352",
    "rule": "max retain ROUGE-L s.t. forget ROUGE-L <= M_ret (user 2026-09-24)",
    "selected_forget_rougeL_recall": 0.0017251051893408134,
    "selected_retain_rougeL_recall": 0.9983076923076923,
    "selected_step": 352
  },
  "export_merge_algorithm": "fp32_sum_then_cast_once",
  "export_precision": "bfloat16",
  "learning_rate_note": "10x the full-parameter protocol's learning rates (LoRA convention), fixed before any LoRA result",
  "lora": {
    "adapter_dtype": "float32",
    "alpha": 128.0,
    "base_dtype": "bfloat16",
    "dropout": 0.05,
    "initialisation": "peft default (B=0: start == M_orig)",
    "rank": 64,
    "targets": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ]
  },
  "merged_weights_sha256": "39452776724d67b76e5562bf90d61f8f564883460341f42fcf96e21b94a0a2f5",
  "method": {
    "idk_target": "I don't know.",
    "method": "ga",
    "preference_beta": 0.1,
    "retain_weight": 4.0
  },
  "optimizer": {
    "global_batch_size": 32,
    "learning_rate": 0.0001,
    "scheduler": "constant",
    "seed": 0,
    "weight_decay": 0.0
  },
  "parameter_counts": {
    "total": 8365323264,
    "trainable": 174587904
  },
  "schedule": {
    "epochs": 5,
    "total_steps": 565
  },
  "training_complete": true
}