{
  "name": "r64_overnight",
  "description": "Focused rank-64 overnight sweep. All experiments use rank 64 as base — confirmed best from tier1_thorough early results. 8000 steps to reach convergence (none converged at 4000).",
  "data_dir": "/media/unraid/davinci/Selva/BJ/features",
  "output_root": "/media/unraid/davinci/Selva/BJ/experiment/r64_overnight",
  "base": {
    "steps": 8000,
    "rank": 64,
    "alpha": 0.0,
    "lr": 1e-4,
    "batch_size": 16,
    "warmup_steps": 200,
    "grad_accum": 1,
    "save_every": 2000,
    "seed": 42,
    "target": "attn.qkv",
    "timestep_mode": "uniform",
    "logit_normal_sigma": 1.0,
    "curriculum_switch": 0.6,
    "lora_dropout": 0.0,
    "lora_plus_ratio": 1.0
  },
  "experiments": [

    {
      "id": "g1_r64_baseline",
      "group": "rank",
      "description": "Rank 64 baseline — clean reference at 8000 steps."
    },
    {
      "id": "g1_r128_baseline",
      "group": "rank",
      "description": "Rank 128 — 102GB VRAM makes this free. Does doubling rank from 64 help further?",
      "rank": 128
    },

    {
      "id": "g2_r64_alpha_32",
      "group": "alpha",
      "description": "Rank 64 alpha=32 (scale=0.5). Reduces intruder singular dimensions (arXiv:2410.21228).",
      "alpha": 32.0
    },
    {
      "id": "g2_r64_alpha_16",
      "group": "alpha",
      "description": "Rank 64 alpha=16 (scale=0.25). More aggressive scale reduction — may over-constrain.",
      "alpha": 16.0
    },

    {
      "id": "g3_r64_lora_plus",
      "group": "regularisation",
      "description": "LoRA+ ratio=16. lr_B = 16 × lr_A. Faster convergence at constant step budget.",
      "lora_plus_ratio": 16.0
    },
    {
      "id": "g3_r64_dropout_0.05",
      "group": "regularisation",
      "description": "Dropout=0.05. Light sparsity regularisation on LoRA path.",
      "lora_dropout": 0.05
    },
    {
      "id": "g3_r64_dropout_0.1",
      "group": "regularisation",
      "description": "Dropout=0.1. Stronger regularisation — tests if 49 clips needs heavier constraint.",
      "lora_dropout": 0.1
    },
    {
      "id": "g3_r64_curriculum",
      "group": "regularisation",
      "description": "Curriculum sampling: logit_normal for steps 1-4800, then uniform (arXiv:2603.12517).",
      "timestep_mode": "curriculum"
    },

    {
      "id": "g4_r64_lr_low",
      "group": "lr",
      "description": "LR=3e-5. 3× lower — checks if 1e-4 is overshooting at rank 64.",
      "lr": 3e-5
    },
    {
      "id": "g4_r64_lr_high",
      "group": "lr",
      "description": "LR=3e-4. 3× higher — may converge faster but risk instability.",
      "lr": 3e-4
    },

    {
      "id": "g5_r64_target_full",
      "group": "target",
      "description": "Rank 64 targeting attn.qkv + linear1 (FFN projections). Doubles LoRA coverage.",
      "target": "attn.qkv linear1"
    },
    {
      "id": "g5_r128_target_full",
      "group": "target",
      "description": "Rank 128 + full target. Maximum possible coverage with available VRAM.",
      "rank": 128,
      "target": "attn.qkv linear1"
    },

    {
      "id": "g6_r64_full_tier1",
      "group": "combined",
      "description": "All Tier 1 at rank 64: LoRA+ 16 + dropout 0.05 + curriculum. Full stack at 8000 steps.",
      "lora_plus_ratio": 16.0,
      "lora_dropout": 0.05,
      "timestep_mode": "curriculum"
    },
    {
      "id": "g6_r64_alpha32_full",
      "group": "combined",
      "description": "Rank 64 alpha=32 + all Tier 1. Best alpha scaling + best regularisation stack.",
      "alpha": 32.0,
      "lora_plus_ratio": 16.0,
      "lora_dropout": 0.05,
      "timestep_mode": "curriculum"
    },
    {
      "id": "g6_r128_full_tier1",
      "group": "combined",
      "description": "Rank 128 + all Tier 1. Tests if more capacity + regularisation beats rank 64 full.",
      "rank": 128,
      "lora_plus_ratio": 16.0,
      "lora_dropout": 0.05,
      "timestep_mode": "curriculum"
    }

  ]
}