cbb/Robot_Arm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ml: 按运行手册审查修订——头分目录不互相覆盖（ml/runs/<CFG>、selected_ckpt/CKPT）；统一 $PYTHON（Windows Git Bash 可跑）；gen 按实测样本/任务自动补量；R10 改终态判据（≥5k 样本/s≈60k 步≤3.5h）；m5 纯策略/仿真安全层双口径；无老师题定长 6 s 口径；APG 展开随批时长、端点+中点铰链、余量 3 mm（投影同步）；挖错池只用本轮；门禁加 R7；bench 加 R8 对抗集与刹停率、--nc-n/--route-n/--r8-n；新增 check_r2 与 acceptance；export 默认 fp32；出题分块防 OOM；val 为空保护

Browse Source
This commit is contained in:
Hark
2026-10-18 06:40:24 +08:00
committed by cbb
parent 8800a68cad
commit f8cdabb781
18 changed files with 493 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ml/mining/loop.sh
+9 -7
View File
@@ -1,29 +1,31 @@
#!/usr/bin/env bash
# 后训练主循环（方案 §7）：APG 首轮 → 挖错 3–6 轮（每轮：挖错 → [E2 老师补路径] → APG 微调 → 门禁/回滚）
# bash ml/mining/loop.sh [轮数=6] [每轮 APG 步数=1000] [每轮出题数=50000]
# 2026-10-18：APG 采样池只用本轮错题（此前累积所有历史轮，后期分布偏向老错题）；老错题的保持由门禁"上轮修好仍对"负责。
# 统一 $PYTHON；门禁加 R7（左右比例 / 行程）。
set -e
cd "$(dirname "$0")/../.."
PY=${PYTHON:-python}
ROUNDS=${1:-6}; STEPS=${2:-1000}; N=${3:-50000}
mkdir -p ml/runs/mine
[ -f ml/runs/gate_tasks.jsonl ] || python -m ml.mining.mine_round --make-gate 2000 --seed 777 --out ml/runs
[ -f ml/runs/gate_tasks.jsonl ] || $PY -m ml.mining.mine_round --make-gate 2000 --seed 777 --out ml/runs
[ -f ml/runs/current.pt ] || cp ml/runs/apg/best.pt ml/runs/current.pt
SAMPLES="ml/data/samples"; FIXED=""; small=0
for ((r=1; r<=ROUNDS; r++)); do
D=ml/runs/mine/r$r; mkdir -p $D
python -m ml.mining.mine_round --ckpt ml/runs/current.pt --seed $((1000+r)) --n $N --out $D
$PY -m ml.mining.mine_round --ckpt ml/runs/current.pt --seed $((1000+r)) --n $N --out $D
# E2（局部极小）请老师补少量路径（唯一保留的后训练老师用途）
if [ -s $D/e2_tasks.jsonl ]; then
node ml/gen/gen_dataset.cjs --tasks $D/e2_tasks.jsonl --seed $((5000+r)) --out ml/data/e2/shard_e2_r$r.jsonl
node ml/prep/build_dataset.cjs ml/data/e2/shard_e2_r$r.jsonl ml/data/samples_e2
SAMPLES="ml/data/samples ml/data/samples_e2"
fi
POOLS=$(ls ml/runs/mine/r*/pool.jsonl)
python -m ml.apg.apg_finetune --init ml/runs/current.pt --samples $SAMPLES --pool $POOLS --out ml/runs/apg_r$r --steps $STEPS
python -m ml.mining.gate --old ml/runs/current.pt --new ml/runs/apg_r$r/best.pt --tasks ml/runs/gate_tasks.jsonl --out $D/gate.json $FIXED
$PY -m ml.apg.apg_finetune --init ml/runs/current.pt --samples $SAMPLES --pool $D/pool.jsonl --out ml/runs/apg_r$r --steps $STEPS
$PY -m ml.mining.gate --old ml/runs/current.pt --new ml/runs/apg_r$r/best.pt --tasks ml/runs/gate_tasks.jsonl --out $D/gate.json $FIXED
FIXED="--fixed $D/gate_fixed.jsonl"
gain=$(python -c "import json;print(json.load(open('$D/gate.json'))['gain_pp'])")
gain=$($PY -c "import json;print(json.load(open('$D/gate.json'))['gain_pp'])")
echo "round $r gain ${gain} pp"
if python -c "import sys;sys.exit(0 if $gain < 0.5 else 1)"; then small=$((small+1)); else small=0; fi
if $PY -c "import sys;sys.exit(0 if $gain < 0.5 else 1)"; then small=$((small+1)); else small=0; fi
if [ $small -ge 2 ]; then echo "连续 2 轮提升 < 0.5 pp，停止"; break; fi
done
echo "最终模型：ml/runs/current.pt"