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

27 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
3f2ca8bfd5 aria2c multi-connection dataset downloads (CDN edge roulette fix) 
The mirror's CDN assigns 6KB/s or 4.8MB/s to the SAME file depending
on which edge a connection lands on -- a single-connection download
is one dice roll that can stall for the whole file. aria2c (-x8 -s8)
splits the file so each segment rolls independently, and
--lowest-speed-limit=50K re-opens stalled segments. Falls back to the
urllib path when aria2c is absent. Live test: the mrcr file that sat
at 2.1MB/190MB for 6 minutes came down in 43s (4.4MB/s).

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-17 08:03:34 +00:00
sora
3cc0158236 hf_raw: fall back to cached blobs when the mirror listing degrades 
The tree API intermittently returns truncated listings (9 parquets
listed as [.gitattributes, README.md] at night); previously that failed
the bench even though 5 of the files were already in the shared blob
store. Empty selection now uses matching cached blobs with a notice;
only a truly cold cache still raises.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-17 06:37:55 +00:00
sora
63ffd1b613 Fix NameError _fmt (module-level helper restored); aime/hmmt max_tokens 32768->8192 (non-stream path, gateway honors nothink) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-11 07:20:02 +00:00
sora
dd7e1933ff HF endpoint auto-fallback: when huggingface.co is unreachable, probe mirrors (hf-mirror.com) and switch automatically with a one-line notice; error only if all fail 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-10 10:57:16 +00:00
sora
c728db5f35 HF hub downloads: reachability probe fails fast with the mirror fix hint (was minutes of silent retries looking like a hang); status lines around hub downloads (start + records + elapsed) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-10 10:51:09 +00:00
sora
afe2fb8d28 Progress coverage for minute-scale work: overall bench bar (which benchmark of N, covers loading/scoring), byte-level download bars for dataset fetches (ModelScope/HF raw, tty-only), one shared reporter across benchmarks (caller-owned lifecycle) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-10 10:47:21 +00:00
sora
27cf8b3c7e Usability round: progress plugin, CLI provider flags, top-level run(), vendored BFCL checker 
- progress/: Rich per-sample terminal progress plugin (Run Plan panel,
  in-flight/rate/ETA bar); shared console + log-through-live to avoid
  interleaved writes, rollback() pairs begin_sample on the retry path,
  begin moved inside the semaphore (in-flight = actually generating),
  graceful degradation when rich is absent
- cli.py: --provider/--api-url/--model composition (openai-chat |
  openai-pool), --disable-thinking/--perf/--textools as first-class
  flags, per-bench phase lines and done/failed result lines
- __init__: top-level run()/arun() entries (event-loop safe for notebooks)
- third_party/bfcl: vendored official BFCL ast_checker + type mappings
  (Apache-2.0, provenance in __init__.py); imports rerouted locally,
  underscore_to_dot parameterized; verified bit-identical with the
  bfcl-eval package on 100 real rows -- removes the heavy extra
  (pinned numpy + cloud SDK wall) from the install path
- runner: progress/status hooks through generate+evaluate, checkpoint
  key scheme fix (empty-store falsy bug), tiered retry backoff,
  multi-segment pool {range} expansion fix, adapter-instance passthrough
- pyproject: tree_sitter family joins core deps; [bfcl] extra retired
- README: rewritten (zh) -- install/quickstart/flags reference/bench
  table/reliability/extension/architecture/validation

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-10 05:46:45 +00:00
sora
46bef7d3dd dp4-flash 28-bench alignment: renderer plugin layer, exec_workers, gen_profiles, AIMD pool, BCB/LCB/bfcl/gfc judge fixes 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-09-08 05:55:04 +00:00
sora
bee997423a GPQA 0.15->0.55: (1) per-bench prompt_style cot_letter (es GPQA CoT template, matches its 'Think step by step' contract), (2) mcq_letter extractor case-insensitive answer-tail (ANSWER: vs answer), (3) deterministic choice shuffle 2026-08-28 18:01:16 +00:00
sora
60b2bfc0dc GPQA deterministic per-question choice shuffle (es-adapter parity: sha256(question) seed, position-bias protection) — was fixed-A; lb2 subset grouping aligned to es (length field, 60 samples) 2026-08-28 16:24:11 +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
7ce04b8ac6 cmmlu few_shot_num 5->0 (es code default is 0-shot despite docstring claiming 5); 28-bench parity check all green 2026-08-27 06:43:09 +00:00
sora
e11cae038b Parity pre-flight check (truncation/few-shot/judge/no-think endpoints vs es run.py); bbh few_shot_num=3 fixed (was 0, es/paper default 3-shot CoT) 2026-08-27 06:37:57 +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
7114564301 Multi-endpoint model pool (openai-pool/{lo..hi} round-robin with failover), nothink/textools spec flags (chat_template_kwargs enable_thinking=false; text-protocol tool calls for backends without --enable-auto-tool-choice), global cross-bench queue in ladder runs 2026-08-26 06:26:52 +00:00
sora
78459c974e tau2 via OFFICIAL engine: self-running env plugin (run_task hook + needs_adapter generic dispatch, no name hardcoding), deep generate() patch, official ToolCall shape, data plugin keeps verbatim Task json, official reward scoring; checkpoint plugin (per-sample resume) + summary csv with time/categories 2026-08-25 11:06:08 +00:00
sora
89e721414f Simplify install: light deps (datasets/pyarrow/sympy/pylatexenc/numpy/scipy) are DEFAULT; single [bfcl] extra for the heavy official checker 2026-08-25 02:51:55 +00:00
sora
99c9df5412 Unify on-demand install hints to extras names ([all]/[bfcl]); native bfcl fallback carries upgrade hint 2026-08-25 02:49:09 +00:00
sora
a8d3400ed5 Paper-faithful eval: P1 logprob scoring (completions_echo + chat_first_token fallback, sglang top_logprobs parser), few_shot_num dataset defaults (mmlu5/cmmlu5/mmlu_pro5/gsm8k4/math4/drop3), official BBH 3-shot CoT vendored, strict_letter default prompt (evalscope parity), official simpleqa grader prompt 2026-08-25 02:21:59 +00:00
sora
3d16ab9103 Add SWE-bench single-turn harness (patch apply + FAIL_TO_PASS in official sweb image, sh entries in docker sandbox), bigcodebench official all-libs image, docker default for humaneval/LCB, input truncation (max_input_chars) + context assembly (passage/context), API retry with backoff, judge thread-safe bridge, parquet blob integrity check, summary.csv in out-dir, sandbox prefetch CLI 2026-08-24 08:43:49 +00:00
sora
4a15f80897 Add evaluation layer + visualization: extract/score/aggregate plugins, 28 recipes, official-aligned scorers (PRM800K math, DROP Hungarian EM/F1, SimpleQA A/B/C judge), report artifacts, console renderers, CLI eval/viz, regression tests 2026-08-24 06:09:38 +00:00
sora
414a89216c Unify cache root override: loader.get/set_cache_root as single source, fixes --cache-dir not relocating .raw blobs 2026-08-24 03:37:15 +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