Commit 3243aebb 3243aebb4979ad388eaca2333174461ea004be60 by cnb.bofCdSsphPA

Preserve proof that cap64 advanced into evaluation before results landed

Constraint: The cap64 run is still active, so this checkpoint can only record stage completion evidence rather than final benchmark conclusions
Rejected: Wait for eval.json or report.json before committing | Would lose the verified handoff that indexing finished and evaluate.py is now running
Confidence: high
Scope-risk: narrow
Directive: Keep stage checkpoints explicit—training complete, index complete, evaluation running, report complete—until cap64 fully settles
Tested: Verified reference_progress.json shows 64 refs, 657 windows, and complete status; verified active process is evaluate.py on /tmp/ab_smoke_seg_cap64_top2/high_energy/fma/manifests; verified high_energy eval.json and report.json are still absent
Not-tested: Final cap64 high_energy metrics, hybrid branch execution, and post-cap64 strategy guidance
1 parent efd63cd9
## 2026-06-02 cap64 索引完成并进入评测 checkpoint
完成项:
- 已确认 cap64 的 `high_energy` reference index 构建完成。
- 已确认流程从 `build-index` 推进到 `evaluate.py`
验证证据:
- `reference_progress.json`
- `status=complete`
- `refs_done=64`
- `windows_done=657`
- `embedding_shape=[657, 192]`
- `elapsed_sec=108.986`
- 进程树显示:
- `evaluate.py --data /tmp/ab_smoke_seg_cap64_top2/high_energy/fma/manifests ... --seed 42 --max-queries 32`
- 截至本 checkpoint:
- `report.json` 仍未生成
## 2026-06-02 cap64 训练完成证据 checkpoint
完成项:
......
......@@ -66,3 +66,5 @@ cd /workspace/acr-engine
- 已补齐 `seed=999` 最终结果,并完成 cap48 三 seed aggregate 归纳。
- 已记录 cap64 benchmark 已启动,并确认进入 `high_energy` 训练阶段。
- 已补充 cap64 新鲜证据:`high_energy` 索引完成(`64 refs / 657 windows / 192-d`)并进入 `evaluate.py`
......
......@@ -60,5 +60,5 @@ test -f /tmp/ab_smoke_seg_cap48_top2_seed999/report.json && cat /tmp/ab_smoke_se
## 下一轮已启动
- 新 benchmark:`/tmp/ab_smoke_seg_cap64_top2`
- 当前阶段:`high_energy` 训练已完成,现处于 build-index
- 当前阶段:`high_energy` 索引已完成,现处于 evaluate
- 下一 session 应优先检查 `report.json` 是否生成
......
......@@ -675,6 +675,6 @@ seed123 最终结论:
- 已启动:`/tmp/ab_smoke_seg_cap64_top2`
- 配置:`subset_size=64`, `max_test_queries=32`, `seed=42`
- 当前最新证据:
- 已从运行会话确认 `high_energy``Epoch 1/1` 完整跑完(`32/32`
- 当前处于 `run_demo.py build-index`,尚未产出最终 `report.json`
- `high_energy` reference index 已完成:`64 refs / 657 windows / 192-d`
- 当前已进入 `evaluate.py`,尚未产出最终 `report.json`
......