{
  "created_at": "2026-07-16 01:45:38",
  "name": "v45_v29_clean_r3_domainmix_lr55e7_ep045",
  "base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
  "dataset": "v45_clean_r3_domainmix",
  "dataset_manifest": {
    "name": "v45_clean_r3_domainmix",
    "path": "/home/ll/llm4rec/experiments/data/v45_clean_r3_domainmix.jsonl",
    "records": 9550,
    "bytes": 44408775,
    "sha256": "4c3dca009ec1070a50416a29ad6162f7c2251a7df59c7ab52408c2f9cecdd484",
    "requested_components": {
      "r3_balanced_ad_direct": 700,
      "r3_balanced_ad_think": 250,
      "r3_balanced_live_direct": 550,
      "r3_balanced_live_think": 700,
      "r3_balanced_goods_direct": 300,
      "r3_balanced_goods_think": 500,
      "r3_balanced_video_direct": 550,
      "r3_balanced_video_think": 550,
      "old_rec_live_direct": 300,
      "old_rec_live_think": 150,
      "old_rec_ad_direct": 300,
      "old_rec_ad_think": 150,
      "old_rec_goods_direct": 300,
      "old_rec_goods_think": 150,
      "old_rec_video_direct": 300,
      "old_rec_video_think": 150,
      "old_user_array_direct": 400,
      "old_user_logic_direct": 400,
      "old_user_logic_think": 150,
      "old_item_goods_direct": 300,
      "old_item_goods_think": 75,
      "old_item_live_direct": 300,
      "old_item_live_think": 75,
      "old_item_ad_direct": 300,
      "old_item_ad_think": 75,
      "old_item_video_direct": 300,
      "old_item_video_think": 75,
      "general_cn_direct": 500,
      "general_cn_think": 250,
      "general_other_direct": 300,
      "general_other_think": 150
    },
    "groups": {
      "old_rec_clean": 1800,
      "general_clean": 1200,
      "r3_clean": 4100,
      "old_item_clean": 1500,
      "old_user_clean": 950
    },
    "variants": {
      "old_rec_live_direct": 300,
      "strict_single_turn_cot": 400,
      "strict_video_cot": 550,
      "strict_single_turn_direct": 800,
      "strict_goods_cot": 500,
      "strict_live_cot": 700,
      "old_item_goods_direct": 300,
      "old_user_array_direct": 400,
      "old_user_logic_direct": 400,
      "old_rec_goods_direct": 300,
      "old_rec_ad_cot": 150,
      "strict_video_direct": 550,
      "old_item_video_direct": 300,
      "strict_goods_direct": 300,
      "old_user_logic_cot": 150,
      "old_item_ad_direct": 300,
      "old_rec_video_direct": 300,
      "old_item_live_direct": 300,
      "strict_ad_direct": 700,
      "strict_ad_cot": 250,
      "strict_live_direct": 550,
      "old_rec_live_cot": 150,
      "old_item_goods_cot": 75,
      "old_rec_ad_direct": 300,
      "old_rec_video_cot": 150,
      "old_item_live_cot": 75,
      "old_item_video_cot": 75,
      "old_rec_goods_cot": 150,
      "old_item_ad_cot": 75
    },
    "routes": {
      "no_think": 6100,
      "think": 3450
    },
    "domains": {
      "live": 2075,
      "video": 1925,
      "goods": 1625,
      "ad": 1775
    },
    "canonical_duplicates": 0,
    "output_chars_p50": 98,
    "output_chars_p90": 902,
    "seed": 202607252
  },
  "learning_rate": "5.5e-7",
  "epochs": 0.45,
  "stages": null,
  "note": "Strict balanced R3 with paper-motivated domain ratios: ad direct-heavy, product CoT-heavy, live moderately CoT-rich, and video balanced.",
  "cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
  "checkpoint_policy": "save_strategy=no; only the final model is retained.",
  "script": "/home/ll/llm4rec/experiments/run_experiments.py",
  "script_sha256": "78d5f1619c271f19b4204ff4fa210ff4bbbadd81cdc0221e5f40cee201fc9877",
  "data_builder": "/home/ll/llm4rec/experiments/source_data.py",
  "data_builder_sha256": "a689f0bf36e31f612c3800f971501655b403e38420f4aad9116a3110206a1d5c",
  "data_cleaner": "/home/ll/llm4rec/experiments/clean_data.py",
  "data_cleaner_sha256": "c1831a3d85c86c740ba80e095252574495b06d79d6341ed190ac2e3fe67133bf",
  "configs": [
    "/home/ll/llm4rec/experiments/configs/v45_v29_clean_r3_domainmix_lr55e7_ep045.yaml"
  ],
  "reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_experiments.py --single v45_v29_clean_r3_domainmix_lr55e7_ep045 --gpu <gpu>"
}