{ "model": { "d": 32, "heads": 4, "ff": 64, "enc": 1, "dec": 1 }, "train": { "batch": 64, "lr": 0.001, "warmup": 10, "steps": 300, "wd": 0.01, "betas": [ 0.9, 0.95 ], "amp": "bf16", "grad_clip": 1.0, "w_mf": 1.0, "w_fk": 0.5, "w_smooth": 0.05, "w_value": 0.1, "w_sub": 0.1, "p_neq": 0.25, "fk_caps": 96, "ckpt_min": 1, "eval_every": 100, "eval_tasks": 16, "log_every": 10, "patience_evals": 5 }, "_note": "冒烟专用(bash ml/smoke.sh):只验证流程能跑通,数值无意义" }