bench
ee4c7fce1c
reward v0.4: board_offline 不加分只免罚;board-backfill 支持 --rollout 用现成 HBM 补测
- export/reward.py: G3 unverified 且最后一次 07/08 为 board_offline → G2/G3 权重 0、G1 保持 1.0、免 TIMEOUT 罚分,
返回 unverifiable=board_offline;RECIPE v0.4。实测 r20260916-01 regnet.y.800mf −0.97 → +0.03
- export/to_agentrl.py: 记录 reward_unverifiable
- harness/pipeline.py: board_backfill_rollout:用 rollouts/kk/artifacts 的 HBM 补跑 07/08(lane=backfill)后 verify_rollout
- harness/cli.py: bench board-backfill --rollout JOB_ID[:KK]
- 单测 scripts/test_reward_board_offline.py、scripts/test_rollout_backfill.py;CONTRACT §9 / README 同步
2026-09-16 15:58:24 +08:00
..
2026-09-15 08:10:26 +08:00
2026-09-15 12:21:38 +08:00
2026-09-15 12:36:44 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 12:46:30 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 12:35:36 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 12:46:30 +08:00
2026-09-15 12:39:05 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 08:10:26 +08:00
2026-09-15 12:42:44 +08:00
2026-09-15 12:21:38 +08:00
2026-09-16 02:17:36 +08:00
2026-09-15 12:30:12 +08:00
2026-09-16 02:17:36 +08:00
2026-09-16 11:04:30 +08:00
2026-09-16 02:17:36 +08:00
2026-09-16 07:55:44 +08:00
2026-09-16 08:23:00 +08:00
2026-09-16 07:55:44 +08:00
2026-09-16 08:23:00 +08:00
2026-09-16 11:04:30 +08:00
2026-09-16 11:04:30 +08:00
2026-09-15 08:10:26 +08:00
2026-09-16 15:58:24 +08:00
2026-09-16 15:58:24 +08:00
2026-09-15 09:42:56 +08:00
2026-09-15 12:27:43 +08:00