{
  "format": "simpletuner-minimaxmusic-rvq-three-model-comparison-v1",
  "models": [
    {
      "acoustic_top1": 0.07169886997767858,
      "acoustic_top5": 0.20938229251217533,
      "ce_loss": 4.696246407248757,
      "checkpoint": "checkpoint-17500",
      "label": "v1, 41M",
      "loss": 5.337855945933949,
      "model_id": "SimpleTuner/open-rvq-encoder-minimax-music3-41m-v1",
      "semantic_top1": 0.41028941761363635,
      "semantic_top5": 0.7838023792613636,
      "step": 17500,
      "teacher_kl_loss": 2.5664437033913354
    },
    {
      "acoustic_top1": 0.0762291301094137,
      "acoustic_top5": 0.21976204453963666,
      "ce_loss": 4.6332796129877165,
      "checkpoint": "checkpoint-17500",
      "label": "v2, 155M",
      "loss": 5.264569409320809,
      "model_id": "SimpleTuner/open-rvq-encoder-minimax-music3-155m-v2",
      "semantic_top1": 0.42864884393063585,
      "semantic_top5": 0.8017380554552023,
      "step": 17500,
      "teacher_kl_loss": 2.525154951679913
    },
    {
      "acoustic_top1": 0.07652936662946429,
      "acoustic_top5": 0.22019304547991073,
      "ce_loss": 4.629444122314453,
      "checkpoint": "checkpoint-17500",
      "label": "v3, 155M + MERT",
      "loss": 5.260235873135653,
      "model_id": "SimpleTuner/open-rvq-encoder-minimax-music3-155m-v3",
      "semantic_top1": 0.4303006258877841,
      "semantic_top5": 0.8048234419389204,
      "step": 17500,
      "teacher_kl_loss": 2.523169430819425
    }
  ],
  "protocol": {
    "dataset": "bghira/minimax-music3-rvq-reverse-distillation",
    "matched_step": 17500,
    "records": 130,
    "require_exact_alignment": true,
    "split": "holdout",
    "windows": 2768
  }
}