Robot_Arm/ml/configs/smoke.json

{
 "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
 },
 "apg": {
  "batch": 8, "lr": 0.0001, "steps": 10, "grad_clip": 1.0, "amp": "bf16",
  "plans": 20, "plans_max": 30, "seg_plans": 5,
  "margin_train_mm": 3.0,
  "w_tgt": 1.0, "w_rot": 0.3, "w_col": 2.0, "w_smooth": 0.02, "w_len": 0.001, "w_bc": 0.5,
  "cat_weights": {"A": 0.4, "B": 1.0, "C": 1.6, "D": 0.6, "Dr": 0.6},
  "ckpt_min": 10, "eval_every": 1000, "eval_tasks": 4
 },
 "_note": "冒烟与自检专用（bash ml/pipeline.sh selftest / smoke）：只验证流程能跑通，数值无意义。apg 段必须有：selftest.sh 第 6 项原先不带 --config，走的是正式 apg.json 的 batch=128，本机实测第一次反向就 OOM；改成正式值 48 也要约 13 GiB，自检不必吃这么多。"
}