Capture fresh high-energy benchmark evidence in the restart handoff
Update the handoff and changelog with the newly finished capped FMA high_energy result so the next session starts from current evidence instead of stale partials. Constraint: Benchmark is still running overall and only partial strategies are complete Rejected: Wait for repeated_section_aware to finish before updating handoff | Risks another stale restart gap Confidence: high Scope-risk: narrow Directive: Replace the partial cap16 table with the final ranking once repeated_section_aware and report.json land Tested: Verified /tmp/ab_smoke_seg_cap16/high_energy/fma_reports_smoke/eval.json; verified docs now record high_energy = 12 / 1.0 / 1.0 Not-tested: Final cap16 multi-strategy report because repeated_section_aware is still in progress
Showing
2 changed files
with
4 additions
and
2 deletions
| ... | @@ -15,14 +15,16 @@ | ... | @@ -15,14 +15,16 @@ |
| 15 | - 写入当前已拿到的 partial result: | 15 | - 写入当前已拿到的 partial result: |
| 16 | - `hybrid`: `num_queries=12`, `top1=1.0`, `topk=1.0` | 16 | - `hybrid`: `num_queries=12`, `top1=1.0`, `topk=1.0` |
| 17 | - `beat_aware`: `num_queries=12`, `top1=0.9167`, `topk=1.0` | 17 | - `beat_aware`: `num_queries=12`, `top1=0.9167`, `topk=1.0` |
| 18 | - `high_energy`: `num_queries=12`, `top1=1.0`, `topk=1.0` | ||
| 18 | 19 | ||
| 19 | 验证结果: | 20 | 验证结果: |
| 20 | - 当前进程确认: | 21 | - 当前进程确认: |
| 21 | - `scripts/ab_smoke_segmentation.py ... --work-root /tmp/ab_smoke_seg_cap16` | 22 | - `scripts/ab_smoke_segmentation.py ... --work-root /tmp/ab_smoke_seg_cap16` |
| 22 | - `high_energy` 策略仍在进行中 | 23 | - `repeated_section_aware` 策略仍在进行中 |
| 23 | - 已落盘评测文件确认: | 24 | - 已落盘评测文件确认: |
| 24 | - `/tmp/ab_smoke_seg_cap16/hybrid/fma_reports_smoke/eval.json` | 25 | - `/tmp/ab_smoke_seg_cap16/hybrid/fma_reports_smoke/eval.json` |
| 25 | - `/tmp/ab_smoke_seg_cap16/beat_aware/fma_reports_smoke/eval.json` | 26 | - `/tmp/ab_smoke_seg_cap16/beat_aware/fma_reports_smoke/eval.json` |
| 27 | - `/tmp/ab_smoke_seg_cap16/high_energy/fma_reports_smoke/eval.json` | ||
| 26 | 28 | ||
| 27 | 结论: | 29 | 结论: |
| 28 | - 当前 session 即使立即中断,也已经具备可恢复的续跑交接材料 | 30 | - 当前 session 即使立即中断,也已经具备可恢复的续跑交接材料 | ... | ... |
| ... | @@ -337,7 +337,7 @@ cd /workspace/acr-engine | ... | @@ -337,7 +337,7 @@ cd /workspace/acr-engine |
| 337 | |---|---:|---:|---:|---| | 337 | |---|---:|---:|---:|---| |
| 338 | | `hybrid` | 12 | 1.0 | 1.0 | 已完成 | | 338 | | `hybrid` | 12 | 1.0 | 1.0 | 已完成 | |
| 339 | | `beat_aware` | 12 | 0.9167 | 1.0 | 已完成 | | 339 | | `beat_aware` | 12 | 0.9167 | 1.0 | 已完成 | |
| 340 | | `high_energy` | - | - | - | 进行中 | | 340 | | `high_energy` | 12 | 1.0 | 1.0 | 已完成 | |
| 341 | | `repeated_section_aware` | - | - | - | 未开始/未完成 | | 341 | | `repeated_section_aware` | - | - | - | 未开始/未完成 | |
| 342 | 342 | ||
| 343 | ### 重启后第一优先动作 | 343 | ### 重启后第一优先动作 | ... | ... |
-
Please register or sign in to post a comment