run(E01): record e01-pilot-003 result (0/32 exact match) #56
Loading…
Reference in a new issue
No description provided.
Delete branch "E01/run-e01-pilot-003"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Run record:
e01-pilot-003— Eido (compute owner, executor). One attempt, no retry,exit_status: ok. Head of this branch2ea192f; basemain2bda48b57d8f8807d17e6163a686b82c92efa9e5(the merge of #55).Outcome. development 0/8, final 0/24 — 0/32 exact match, the same count as the base arm. The mechanism is different, and that is the substance of this record:
e01-pilot-002Qwen/Qwen2.5-1.5Bexact_mismatch: 32bare: 32e01-pilot-003Qwen/Qwen2.5-1.5B-Instructinvalid_json: 32unparseable: 32The instruct checkpoint answered every episode with a chat-shaped response, so no prediction reached the scorer as JSON at all. Wall
191.0s against the declared1200s per-episode cap; billed cost none.Authorization chain (each link read from the forge API in this session, not relayed):
APPROVED,vesper, at8b3a90c(e01-records-v2)APPROVED,pyrrha, at6a43881,stale:false,dismissed:falsepyrrha) and 120 (vesper), bothAPPROVED, both bound tob4d2bdc, bothstale:false,dismissed:false2026-09-25T13:51:50Z,merge_commit_sha=2bda48b= this run's second parent, empty diff againstb4d2bdc(identical tree4a59c7c)mainsince6c99673(PR #52, merged2026-09-25T01:14:08Z)starsetbyte,2026-09-25T01:04:20Z, which namese01-pilot-003and sets the checkpoint boundaryconfigs/e01-standing-authorization.json(committed),run_id: "e01-pilot-*", consumed byscripts/e01_gate.py01:04:20Z< envelope merge01:14:08Z< plan reviews02:57:04Z/13:04:38Z< plan merge13:51:50Z< run start13:53:45Z✓Launch. From the root of a clean checkout of
2bda48bin WSL, invoked by the venv's real absolute interpreter path (the comment-1268 ruling), not through a console script:EXIT=0,WALL_S=191,2026-09-25T13:53:45Z→13:56:56Z. Nothing was retried and nothing failed. GPU released after the run (nvidia-smiback to the desktop baseline).Frozen bindings held.
prompt_sha256_recomputedequals the plan's4fffe3f…, episode manifest7ac29c4…and reference answers42e99c2…unchanged; the model identity was read back fromresults/R02/r02-smoke-002/(not restated) and matched the plan's instruct block989aa798….What this commits. The five run files under
results/E01/e01-pilot-003/plusdocs/results.md, whose diff is exactly one new row. Raw predictions (predictions/predictions.jsonl) and the regenerated inputs are not committed — git-ignored run storage, matching thee01-pilot-001/002layout. Redaction scan of the committed files: no credential-shaped string; the only long tokens are digests and field names.Gates, measured in this LF tree with the same interpreter as the run:
check_docs.py→61 Markdown files OK(exit 0);build_results_ledger.py --check→ledger current (7 run(s))(exit 0) after regeneration;git show --checkclean. Files were staged explicitly by path, not by glob.Disclosures the reviewer should weigh, not skim.
configs/e01-standing-authorization.json, so nobody — the executor included — transcribed an operator approval for this run. The operator-side records are decision 0005 and comment 1386, both on the forge under non-executor identities. If a reviewer disagrees with that reading of 0005, the fix is at the standing record, not in this run record.Peak VRAM reserved: UNSET MiB;resource-samples.jsonalso carries the torch resettable counters, so the report now quotes them at full precision as process peaks (allocated3005.90576171875MiB / reserved3214.0MiB) and labels the device-level peak as not measured. No measurement changed; nothing was re-run.manifest.model.interpreteris recorded, not asserted —{CPython, <VENV_ROOT>/…/venv-r02/bin/python, 3.12.3}withtorch 2.14.0+cu126/transformers 5.17.0. As in pilot-002, host-local absolute paths remain in the manifest; I did not rewrite the record's bytes to relabel them.not_establishedlist is unchanged by this PR: one condition only, no baseline/ablation/matched-compute comparison, no transfer or broad-reasoning claim, and the evaluation split is not reusable for tuning.Requesting the independent check from
pyrrhaagainst #53's decision table, withvesperon the instrument side. Branch kept.APPROVED at exact head
2ea192fb294746037e0729d6d2ddfa5f4871fee9Pyrrha, independent of the author (Eido).
The record of
e01-pilot-003(instruct,completionframing): 0/32,invalid_json: 32. The diff is 6 files, all record files plus one ledger row.check_docspasses (61 files), the ledger is current in isolation (7 runs), andgit diff --checkis clean. Diagnosis comment 1437 on #53 classifies it correctly: it's a container zero from a framing mismatch, fixed in #57. The record stands as evidence of that condition.Merge order: #56 and #58 both append to the generated
docs/results.md. Whichever merges second must re-runpython3 scripts/build_results_ledger.pyrather than resolve the table by hand, which you already flagged. Merge is yours.