feat: add first experiment sweep file for Tier 1 ablation

6 experiments: baseline, LoRA+ (ratio=16), dropout 0.05, dropout 0.1,
curriculum sampling, and all three combined. bf16 batch 16, 2000 steps,
seed 42. data_dir placeholder needs to be updated before running.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-06 13:15:06 +02:00
parent 3d9221c248
commit f1e2bbd55b
+56
View File
@@ -0,0 +1,56 @@
{
"name": "tier1_sweep",
"description": "Ablation of Tier 1 improvements: LoRA+, dropout, curriculum sampling. Baseline = uniform, no regularisation.",
"data_dir": "dataset/my_sound",
"output_root": "lora_sweeps/tier1_sweep",
"base": {
"steps": 2000,
"rank": 16,
"alpha": 0.0,
"lr": 1e-4,
"batch_size": 16,
"warmup_steps": 100,
"grad_accum": 1,
"save_every": 500,
"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": "baseline",
"description": "Standard LoRA — no Tier 1 changes. Reference point."
},
{
"id": "lora_plus_16",
"description": "LoRA+ only: lr_B = 16 * lr_A. Should converge faster in early steps.",
"lora_plus_ratio": 16.0
},
{
"id": "dropout_0.05",
"description": "LoRA dropout 0.05 only. Light regularisation for 10-clip dataset.",
"lora_dropout": 0.05
},
{
"id": "dropout_0.1",
"description": "LoRA dropout 0.1 only. Stronger regularisation — may prevent overfitting past step 2000.",
"lora_dropout": 0.1
},
{
"id": "curriculum",
"description": "Curriculum sampling only: logit_normal for steps 1-1200, then uniform. Should improve convergence vs pure uniform.",
"timestep_mode": "curriculum"
},
{
"id": "full_tier1",
"description": "All Tier 1 combined: LoRA+ + dropout 0.05 + curriculum.",
"lora_plus_ratio": 16.0,
"lora_dropout": 0.05,
"timestep_mode": "curriculum"
}
]
}