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

feat(monitor): 用时改为按阶段累计——"总用时"=各阶段之和、"本步用时"=该阶段累计，停止后再"继续训练"不再归零（训练跑 5 万步停一次，之前那段的时间会保留）；只有产物被归档、要从头重做的阶段才清零；本次改动前完成的老记录用 start/end 兜底；停止与流水线退出两处记账幂等（实测 180 s 不翻倍）

Browse Source
This commit is contained in:
cbb
2026-10-18 16:59:21 +08:00
parent 21ad209747
commit db0bbbc15d
3 changed files with 51 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ml/monitor.html
+6 -6
View File
@@ -633,8 +633,8 @@ function renderPipe(s) {
${cur ? `<div class="sublabel"><span>当前步骤 · ${SM[cur]?.n}</span><span>${pr.frac != null ? pct(pr.frac) : '无法计量，按用时估'}</span></div>
<div class="bar thin ${pr.frac == null ? 'ind' : ''}"><div class="fill" style="width:${pr.frac != null ? 100 * pr.frac : 30}%"></div></div>` : ''}
<div class="facts">
<div class="fact"><div class="k">总用时</div><div class="v">${hms((cur ? now : Math.max(...Object.values(P.stages).map(r => r.end || r.start))) - P.started)}</div></div>
<div class="fact"><div class="k">本步用时</div><div class="v">${cr ? hms(now - cr.start) : '—'}</div></div>
<div class="fact"><div class="k">总用时</div><div class="v">${hms(plan.reduce((a, k) => a + ((P.elapsed || {})[k] || 0), 0))}</div></div>
<div class="fact"><div class="k">本步用时</div><div class="v">${cur ? hms((P.elapsed || {})[cur] || 0) : '—'}</div></div>
<div class="fact"><div class="k">本步粗估 / 上限</div><div class="v">${cur ? hmsShort((SM[cur]?.w || 0) * 3600) + ' / ' + hmsShort((cr && cr.timeout_h || SM[cur]?.to || 0) * 3600) : '—'}</div></div>
<div class="fact"><div class="k">全流程剩余（粗估）</div><div class="v">${allDone ? '—' : '约 ' + hmsShort(remain * 3600)}</div></div>
</div>${btns}`;
@@ -730,10 +730,10 @@ function demoApi() {
}
let sc, runs, logs, pipe, jobS, con, genAt = 0;
// 示例流水线：stages 里的 [阶段, 开始距今小时, 用时小时]
const mkPipe = (done, cur, curStartH) => { const t = now(); const st = {}; let tt = t - curStartH * 3600;
for (let i = done.length - 1; i >= 0; i--) { const [k, dur] = done[i]; st[k] = { start: tt - dur * 3600, end: tt, rc: 0, info: {} }; tt -= dur * 3600; }
if (cur) st[cur] = { start: t - curStartH * 3600, end: null, rc: null, info: {} };
return { started: tt, plan: ['kin', 'r4', 'gate1', 'gen', 'prep', 'train', 'm5', 'apg', 'mine', 'export', 'bench', 'accept'], stages: st, current: cur }; };
const mkPipe = (done, cur, curStartH) => { const t = now(); const st = {}, el = {}; let tt = t - curStartH * 3600;
for (let i = done.length - 1; i >= 0; i--) { const [k, dur] = done[i]; st[k] = { start: tt - dur * 3600, end: tt, rc: 0, info: {} }; el[k] = dur * 3600; tt -= dur * 3600; }
if (cur) { st[cur] = { start: t - curStartH * 3600, end: null, rc: null, info: {} }; el[cur] = curStartH * 3600; }
return { started: tt, plan: ['kin', 'r4', 'gate1', 'gen', 'prep', 'train', 'm5', 'apg', 'mine', 'export', 'bench', 'accept'], stages: st, elapsed: el, current: cur }; };
const CON = {
train: '$ FROM=kin TO=accept bash ml/pipeline.sh all\n计划：kin r4 gate1 gen prep train m5 apg mine export bench accept\n== node ml/prep/export_kin.cjs\n== node ml/eval/dump_parity.cjs 2000\n== python -m ml.eval.check_parity\n{"PASS": true, "fk_mm": 0.0004, "gap_mm": 0.0011}\n== node ml/gen/consistency.cjs 300 4242\n{"consistentByGateRule": 0.86}\n一致性门禁结果 → CONSENSUS=1\n== bash ml/gen/run_parallel.sh 1786 28 1 --consensus 4\n样本数 1702000 ≥ 目标，完成\n== bash ml/prep/run_prep.sh 28\n== python -m ml.eval.check_r2 --samples ml/data/samples --out ml/data/r2.json\n{"pairs": 250, "label_std_mean": 0.071, "pass": true}\n== python -m ml.train --samples ml/data/samples --out ml/runs/bench_base --steps 2000 --no-eval\nstep 2000 loss 1.912 6150 samples/s\n== python -m ml.train --samples ml/data/samples --out ml/runs/base\n',
gen: '$ FROM=kin TO=accept bash ml/pipeline.sh all\n计划：kin r4 gate1 gen prep train m5 apg mine export bench accept\n== node ml/prep/export_kin.cjs\n== python -m ml.eval.check_parity\n{"PASS": true}\n== node ml/gen/consistency.cjs 300 4242\n{"consistentByGateRule": 0.86}\n一致性门禁结果 → CONSENSUS=1\n== bash ml/gen/run_parallel.sh 1786 28 1 --consensus 4\n',