{ "config": { "steps": 3000, "batch": 16, "lr": 0.001, "seed": 0, "objective": "epsilon (stock schedule)", "cond": "nl77", "optimizer": "torch.optim.Adam wd=0" }, "frozen": { "val": 0.1247876692286809 }, "relay_all16": { "n_params": 3227568, "train": { "steps": 3000, "final_loss_ma50": 0.10553, "s_per_step": 1.816, "peak_mem_gb": 11.17 }, "val": 0.12169808566522988, "val_toggled_off": 0.1247876692286809, "gates": { "gate_mean": 0.07003, "gate_min": 0.03646, "gate_max": 0.09857 }, "round_trip": { "cond": 0.7809, "shuffled": 0.5637, "cond_minus_shuffled": 0.2172 } }, "lora_r32": { "n_params": 3182592, "train": { "steps": 3000, "final_loss_ma50": 0.10699, "s_per_step": 1.635, "peak_mem_gb": 10.08 }, "val": 0.12267412961273294, "round_trip": { "cond": 0.736, "shuffled": 0.5764, "cond_minus_shuffled": 0.1596 } }, "verdict": { "relay_beats_frozen": true, "relay_vs_lora": "relay", "param_ratio": 1.014, "note": "core epred substrate; prereg relay >= lora; 1-seed CANDIDATE" } }