Meta-Eval/EvalHarness
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
217 Commits 1 Branch 0 Tags
Commit Graph

7 Commits

Author SHA1 Message Date
sora
565ba11790 swe datasets: carry version/patch/hints/created_at in metadata 
Official make_test_spec indexes MAP_REPO_VERSION_TO_SPECS[repo][version]
-- a None version KeyError'd the official scorer (first agentic run
scored 0 with 'KeyError: None' hidden in details). The base converter
never copied these fields; both variants now carry them, verified with
a live make_test_spec call (spec + 2KB eval script + correct image key).

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-18 08:11:18 +00:00
sora
f662006517 swe_bench_verified_agentic: multi-turn SWE agent (mini-swe-agent protocol) 
Ports es's swe_bench_agentic_adapter into our plugin architecture:
- env swe_agentic: per-sample LONG-RUNNING container (official sweb
  image, /testbed, bash -lc like the testbed startup files expect),
  single bash tool via function calling, sentinel-submission protocol
  (COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT + patch), git-diff fallback;
  observations capped at 30k chars
- dataset swe_bench_verified_agentic: same princeton source/converter,
  separate bench name so both variants coexist
- recipe: recovered patch + OFFICIAL test_patch applied in-container,
  FAIL_TO_PASS + capped PASS_TO_PASS via conda testbed pytest, 1800s
- config: max_turns 250, env swe_agentic

Single-turn swe_bench_verified is untouched.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-18 02:29:35 +00:00
sora
587274d8b6 sandbox pull: SWE-bench per-instance pre-pull with resume (es port) 
- naming corrected to the Docker Hub truth es verified 500/500:
  swebench/sweb.eval.x86_64.{instance_id.lower(), __->_1776_}:latest
  (my repo-base rewrite was wrong; per-instance images ARE published)
- 'evalharness sandbox pull swe_bench_verified': concurrent pulls,
  resume state in <cache-dir>/swe_pull_state.json, --dry-run N,
  --retry-failed; self-contained (own dataset registry, no evalscope
  import)
- save/load intentionally omitted per user call (pull-only for now)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-17 09:36:20 +00:00
sora
081249d47c swe: repo-base image naming (correct indentation this time) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-17 08:33:45 +00:00
sora
da989ea665 Align with local evalscope run.py (full read-through): (1) shuffle+seed42 sample selection identical to es _shuffle_in_place -- same exact sample subset both frameworks; (2) official MATH_PROMPT_TEMPLATE CoT boxed suffix on 7 math benches via DatasetSpec.prompt_suffix; (3) per-bench gen_config (temp/max_tokens from dpv4 yaml) on DatasetSpec, default-merged into gen_kwargs 2026-08-27 11:25:17 +00:00
sora
0e1e31ba10 swe_bench_verified end-to-end verified (oracle patch -> official sweb image -> resolved); image naming mapped to local swebench/ set; ladder2 complete 28/28 2026-08-26 06:40:55 +00:00
sora
f8cd15fea1 EvalHarness data layer: 28 dataset plugins, lazy materialize cache (raw/ + samples.jsonl + meta.json), ModelScope native loader, CLI list/fetch/unload/stats/show 2026-08-24 03:35:11 +00:00