Ethanfel
0000878e76
- Dataset browser: audio/features now resolve through features/ subdir - tier1_sweep.json: update data_dir to BJ dataset path - tier1_thorough.json: 12-experiment overnight sweep across 4 groups (rank 16/32/64, alpha scaling, LoRA+/dropout/curriculum isolation, full Tier 1 stack at r16 and r64) — output to BJ/experiment/ Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
104 lines
3.2 KiB
JSON
104 lines
3.2 KiB
JSON
{
|
|
"name": "tier1_thorough",
|
|
"description": "Full overnight Tier 1 ablation on 49-clip BJ dataset. 4 groups: rank, alpha, regularisation, and best combinations. ~10-12h depending on GPU.",
|
|
"data_dir": "/media/unraid/davinci/Selva/BJ",
|
|
"output_root": "/media/unraid/davinci/Selva/BJ/experiment/tier1_thorough",
|
|
"base": {
|
|
"steps": 4000,
|
|
"rank": 16,
|
|
"alpha": 0.0,
|
|
"lr": 1e-4,
|
|
"batch_size": 16,
|
|
"warmup_steps": 100,
|
|
"grad_accum": 1,
|
|
"save_every": 1000,
|
|
"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_rank_16",
|
|
"group": "rank",
|
|
"description": "Rank 16 baseline — reference point for all groups."
|
|
},
|
|
{
|
|
"id": "g1_rank_32",
|
|
"group": "rank",
|
|
"description": "Rank 32 — midpoint. Does doubling rank improve quality without overfitting?",
|
|
"rank": 32
|
|
},
|
|
{
|
|
"id": "g1_rank_64",
|
|
"group": "rank",
|
|
"description": "Rank 64 — MMAudio LoRA guide default. Maximum expressiveness at 49 clips.",
|
|
"rank": 64
|
|
},
|
|
{
|
|
"id": "g2_alpha_half_r16",
|
|
"group": "alpha",
|
|
"description": "Alpha=8 with rank 16 (scale=0.5). Reduces intruder singular dimensions (arXiv:2410.21228).",
|
|
"alpha": 8.0
|
|
},
|
|
{
|
|
"id": "g2_alpha_half_r64",
|
|
"group": "alpha",
|
|
"description": "Alpha=32 with rank 64 (scale=0.5). Best-practice scaling for high-rank adapters.",
|
|
"rank": 64,
|
|
"alpha": 32.0
|
|
},
|
|
{
|
|
"id": "g3_lora_plus_4",
|
|
"group": "regularisation",
|
|
"description": "LoRA+ ratio=4 — conservative asymmetric LR. Lower bound for the technique.",
|
|
"lora_plus_ratio": 4.0
|
|
},
|
|
{
|
|
"id": "g3_lora_plus_16",
|
|
"group": "regularisation",
|
|
"description": "LoRA+ ratio=16 — standard from FLUX LoRA literature. Faster early convergence.",
|
|
"lora_plus_ratio": 16.0
|
|
},
|
|
{
|
|
"id": "g3_dropout_0.05",
|
|
"group": "regularisation",
|
|
"description": "LoRA dropout 0.05 only. Light sparsity regularisation (arXiv:2404.09610).",
|
|
"lora_dropout": 0.05
|
|
},
|
|
{
|
|
"id": "g3_dropout_0.1",
|
|
"group": "regularisation",
|
|
"description": "LoRA dropout 0.1 only. Stronger regularisation — may prevent overfitting past step 2000.",
|
|
"lora_dropout": 0.1
|
|
},
|
|
{
|
|
"id": "g3_curriculum",
|
|
"group": "regularisation",
|
|
"description": "Curriculum sampling only: logit_normal steps 1-2400, then uniform (arXiv:2603.12517).",
|
|
"timestep_mode": "curriculum"
|
|
},
|
|
{
|
|
"id": "g4_full_r16",
|
|
"group": "combined",
|
|
"description": "All Tier 1 at rank 16: LoRA+ 16 + dropout 0.05 + curriculum.",
|
|
"lora_plus_ratio": 16.0,
|
|
"lora_dropout": 0.05,
|
|
"timestep_mode": "curriculum"
|
|
},
|
|
{
|
|
"id": "g4_full_r64",
|
|
"group": "combined",
|
|
"description": "All Tier 1 at rank 64 + alpha=32. Best expressiveness + best regularisation.",
|
|
"rank": 64,
|
|
"alpha": 32.0,
|
|
"lora_plus_ratio": 16.0,
|
|
"lora_dropout": 0.05,
|
|
"timestep_mode": "curriculum"
|
|
}
|
|
]
|
|
}
|