From eb06651c63e4f65744611bc2e22eb5aba4ade5d4 Mon Sep 17 00:00:00 2001 From: job poller Date: Tue, 13 Oct 2026 10:25:54 +0200 Subject: [PATCH] runs: record 1 finished run(s) --- runs/aspect-ratio/034f3V1yKaIHGKT8RHonSV.json | 341 ++++++++++++++++++ 1 file changed, 341 insertions(+) create mode 100644 runs/aspect-ratio/034f3V1yKaIHGKT8RHonSV.json diff --git a/runs/aspect-ratio/034f3V1yKaIHGKT8RHonSV.json b/runs/aspect-ratio/034f3V1yKaIHGKT8RHonSV.json new file mode 100644 index 00000000..64f71f86 --- /dev/null +++ b/runs/aspect-ratio/034f3V1yKaIHGKT8RHonSV.json @@ -0,0 +1,341 @@ +{ + "base_sha": "a1844c99f008c25031d2b754634e752949e8b341", + "ended_at": "2026-10-13T08:25:27Z", + "energy": { + "gpu_ws": null, + "racks_ws": 35672101.0, + "samples": 196 + }, + "failed_stage": "findings-pages-prompt", + "format": 1, + "message": "run 034f3V1yKaIHGKT8RHonSV: a stage failed: stage findings-pages-prompt: command exited 1", + "models": { + "choices": [], + "planned": [ + "qwen3.8-27b-fast-2" + ], + "used": { + "qwen3.8-27b-fast-2": 2 + } + }, + "name": "aspect-ratio", + "outcome": "failed", + "reason": "command exited 1", + "result_tag": "result/aspect-ratio/034f3V1yKaIHGKT8RHonSV", + "review_verdict": "fail", + "round": 3, + "rounds": { + "failed_rounds_limit": 3, + "failed_rounds_used": 2, + "used": 3 + }, + "run_id": "034f3V1yKaIHGKT8RHonSV", + "run_step_exit": 1, + "run_steps": "tools:succeeded prepare:succeeded run:failed archive:aborted cleanup:aborted", + "spec_sha": "84dc43d87ee8d8b1a781a76854248fdb38ecc20c", + "stage_retries": 9, + "stages": [ + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "wpt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "test-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 47, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 3, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 5, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "fetch-specs", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "specification-text", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "types-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 28, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "types-candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "types-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 25, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "types-use", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 28, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "coverage-pages-prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 34, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "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-2:8:4:1800", + "name": "coverage-pages-keep", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 5, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "coverage-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 4, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "coverage-held-out-ground-truth", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "prompt-cases", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "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-2:8:4:1800", + "name": "prompt", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 1, + "duration_seconds": 148, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "candidates", + "status": "passed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 3, + "duration_seconds": 2, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "findings-pages-prompt", + "status": "failed", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 35, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "findings-pages-request", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 1, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "findings-pages-keep", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 6, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "findings-ground-truth", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "cases", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 1306, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "repair", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 0, + "kind": "script", + "models": "qwen3.8-27b-fast-2:8:4:1800", + "name": "store", + "status": "pending", + "tokens": 0, + "tool_calls": 0, + "turns": 0 + }, + { + "attempts": 2, + "duration_seconds": 5773, + "kind": "review", + "model": "qwen3.8-27b-fast-2", + "name": "review", + "status": "pending", + "tokens": 6333177, + "tool_calls": 160, + "turns": 96 + } + ], + "status": "failed", + "tokens": 6333177, + "tool_calls": 160, + "turns": 96, + "wall_clock_seconds": 7479.0 +} -- 2.54.0