diff --git a/runs/padding/034krb3UXNjU9uMFYHf6UZ.json b/runs/padding/034krb3UXNjU9uMFYHf6UZ.json new file mode 100644 index 00000000..e97370c7 --- /dev/null +++ b/runs/padding/034krb3UXNjU9uMFYHf6UZ.json @@ -0,0 +1,352 @@ +{ + "base_sha": "1f134e40dcb02e25ca1acaed2d0786453d8c2f73", + "ended_at": "2026-10-23T11:38:11Z", + "energy": { + "gpu_ws": 293222.0, + "racks_ws": 3109549.0, + "samples": 16 + }, + "failed_stage": "repair", + "format": 1, + "message": "run 034krb3UXNjU9uMFYHf6UZ: its failed rounds are used up: stage repair: no gain: round 2 of repair passes 160 train cases, no more than the 160 an earlier round's passed; 2 of 3 failed rounds used (why it gained nothing: logs/padding/034krb3UXNjU9uMFYHf6UZ-no-gain.json in the jobs state directory); resend with jobs/scripts/submit.sh padding once a fix or a spec change is in", + "models": { + "choices": [], + "planned": [ + "qwen3.8-27b-fast-2" + ], + "used": {} + }, + "name": "padding", + "outcome": "no-gain", + "reason": "no gain: round 2 of repair passes 160 train cases, no more than the 160 an earlier round's passed; 2 of 3 failed rounds used", + "result_tag": "result/padding/034krb3UXNjU9uMFYHf6UZ", + "round": 2, + "rounds": { + "failed_rounds_limit": 3, + "failed_rounds_used": 2, + "used": 2 + }, + "run_id": "034krb3UXNjU9uMFYHf6UZ", + "run_step_exit": 11, + "run_steps": "tools:succeeded prepare:succeeded run:failed archive:aborted cleanup:aborted", + "spec_sha": "bd221cb8568be38903a5cbb5438eb630a80f60b7", + "stage_retries": 1, + "stages": [ + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "wpt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "test-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "fetch-specs", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "specification-text", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 44, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 168, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 28, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-use", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 9, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 56, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-request", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 3, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 3, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "prompt-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "held-out-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 221, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-request", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 34, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "repair", + "status": "failed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "kind": "script", + "name": "store", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "kind": "review", + "name": "review", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "kind": "script", + "name": "admit", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "kind": "script", + "name": "feature-map", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + } + ], + "status": "needs-person", + "tokens": 0, + "tool_calls": 0, + "turns": 0, + "wall_clock_seconds": 590.0 +} diff --git a/runs/stretch/034kqtz1SMbeveHhu5jMlN.json b/runs/stretch/034kqtz1SMbeveHhu5jMlN.json new file mode 100644 index 00000000..5855c52b --- /dev/null +++ b/runs/stretch/034kqtz1SMbeveHhu5jMlN.json @@ -0,0 +1,380 @@ +{ + "base_sha": "15111596cc707b5260d2c54a1e08fe682b19bd0e", + "candidate": { + "known_failures": [ + "abspos-1.html", + "bfc-next-to-float-1.html", + "c0_qwen3_8_27b_fast_2-15.html", + "c1_qwen3_8_27b_fast_2-1.html", + "c1_qwen3_8_27b_fast_2-4.html", + "c1_qwen3_8_27b_fast_2-5.html", + "c1_qwen3_8_27b_fast_2-6.html", + "c2_qwen3_8_27b_fast_2-10.html", + "c2_qwen3_8_27b_fast_2-3.html", + "c3_qwen3_8_27b_fast_2-7.html", + "flexbox-stretch-minimum-001.html", + "positioned-non-replaced-1.html" + ], + "misses": "partial", + "train_passed": 43, + "train_run": 55 + }, + "ended_at": "2026-10-23T11:37:31Z", + "energy": { + "gpu_ws": 1513907.0, + "racks_ws": 16067818.0, + "samples": 87 + }, + "format": 1, + "message": "landed stretch at 919a177e, tag spec/stretch/c4fcd5cde7290758f22b55f535670c2a7bd0d784; owed: lane copies not removed (see bench/lane-sweep.sh); partial, train 43 of 55, 12 known failures; review failed, landed on the score bar, 0 known failures from the review", + "models": { + "choices": [], + "planned": [ + "qwen3.8-27b-fast-2" + ], + "used": { + "qwen3.8-27b-fast-2": 1 + } + }, + "name": "stretch", + "outcome": "landed", + "result_tag": "result/stretch/034kqtz1SMbeveHhu5jMlN", + "review_advisory": true, + "review_verdict": "pass", + "review_verdict_was": "fail", + "round": 1, + "rounds": { + "failed_rounds_limit": 3, + "failed_rounds_used": 0, + "used": 1 + }, + "run_id": "034kqtz1SMbeveHhu5jMlN", + "run_step_exit": 0, + "run_steps": "tools:succeeded prepare:succeeded run:succeeded archive:succeeded cleanup:succeeded", + "spec_sha": "3b6c8e372ff559e3ec0702ea4dcb664b746a3a73", + "stage_retries": 0, + "stages": [ + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "wpt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "test-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 11, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "fetch-specs", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "specification-text", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 43, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 17, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 26, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "types-use", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 10, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 38, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-request", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-pages-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 4, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 3, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "coverage-held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "prompt-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "held-out-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 195, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-request", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-pages-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 2, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "findings-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 577, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "repair", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:16:8:1800", + "name": "store", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 2377, + "kind": "review", + "model": "qwen3.8-27b-fast-2", + "name": "review", + "status": "passed", + "tokens": 2720434, + "tool_calls": 62, + "turns": 51 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "name": "admit", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 0, + "duration_seconds": 0, + "kind": "script", + "name": "feature-map", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + } + ], + "status": "passed", + "tokens": 2720434, + "tool_calls": 62, + "turns": 51, + "wall_clock_seconds": 3324.0 +}