fix(train): 首次正式预训练（21850 步闭环到达 0%）排查后修正——FK/平滑改加在配对去噪估计上（原加在随机噪声一步采样上=回归条件均值，多峰塌成单峰，实测候选标准差 0.030/幅度 0.151）；时间嵌入最高角频率 1000→50、MF 分支 fp32、p_neq 前 5000 步为 0（实测 du/dt 均方根 6–12 vs v 1.1）；增广 40%/3°/12 步收回；新增 dagger 阶段（策略闭环状态请老师重规划 ×2 轮微调）；开训前老师轨迹回放自检；评估加开环误差与候选多样性，best/早停按到达率+开环误差

ml/configs/base.json

@@ -4,7 +4,7 @@
     "batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "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,
+    "p_neq": 0.25, "p_neq_warm": 5000, "fk_tmax": 0.3, "fk_caps": 96,
     "ckpt_min": 10, "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
   }
 }

ml/configs/small.json

@@ -4,7 +4,7 @@
     "batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "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,
+    "p_neq": 0.25, "p_neq_warm": 5000, "fk_tmax": 0.3, "fk_caps": 96,
     "ckpt_min": 10, "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
   }
 }

ml/configs/smoke.json

@@ -29,15 +29,36 @@
   "eval_every": 100,
   "eval_tasks": 16,
   "log_every": 10,
-  "patience_evals": 5
+  "patience_evals": 5,
+  "p_neq_warm": 100,
+  "fk_tmax": 0.3
  },
  "apg": {
-  "batch": 8, "lr": 0.0001, "steps": 10, "grad_clip": 1.0, "amp": "bf16",
-  "plans": 20, "plans_max": 30, "seg_plans": 5,
+  "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
+  "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。"
 }

ml/configs/wta.json

@@ -4,7 +4,7 @@
     "batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "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,
+    "p_neq": 0.25, "p_neq_warm": 5000, "fk_tmax": 0.3, "fk_caps": 96,
     "ckpt_min": 10, "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
   }
 }