{ "name": "ti_sweep_1", "description": "First TI sweep: token count, learning rate, and warm init. All generator weights frozen throughout. Baseline = n_tokens=4, lr=1e-3, random init. Primary goal: find a working (n_tokens, lr) pair before optimising further.", "data_dir": "/media/unraid/davinci/Selva/BJ/features", "output_root": "/media/unraid/davinci/Selva/BJ/experiment/ti_sweep_1", "base": { "steps": 3000, "batch_size": 16, "warmup_steps": 100, "save_every": 1000, "seed": 42, "init_text": "", "lr": 1e-3, "n_tokens": 4 }, "experiments": [ { "id": "n4_baseline", "group": "token_count", "description": "4 tokens, lr=1e-3, random init. Primary reference point — all other experiments are measured against this." }, { "id": "n8", "group": "token_count", "description": "8 tokens, lr=1e-3, random init. Double the capacity — does it capture more style or just overfit faster?", "n_tokens": 8 }, { "id": "n16", "group": "token_count", "description": "16 tokens, lr=1e-3, random init. Maximum expressiveness — worth the extra convergence difficulty?", "n_tokens": 16 }, { "id": "lr_5e4", "group": "learning_rate", "description": "n_tokens=4, lr=5e-4. Half the default LR — smoother convergence, possibly better generalisation.", "lr": 5e-4 }, { "id": "lr_2e3", "group": "learning_rate", "description": "n_tokens=4, lr=2e-3. Double the default LR — faster early convergence, risk of oscillation.", "lr": 2e-3 }, { "id": "n4_warm", "group": "warm_init", "description": "4 tokens warm-started from 'mechanical impact sound design'. CLIP embedding initialises tokens in a semantically relevant region of the space — may converge faster and to a better style representation.", "init_text": "mechanical impact sound design" }, { "id": "n8_warm", "group": "warm_init", "description": "8 tokens warm-started from 'mechanical impact sound design'. Combines the warm-init advantage with more expressive capacity.", "n_tokens": 8, "init_text": "mechanical impact sound design" } ] }