From 420c18c57400aa7015d0101931b97df16e6e66c4 Mon Sep 17 00:00:00 2001 From: sora <2075279110@qq.com> Date: Thu, 17 Sep 2026 02:53:56 +0000 Subject: [PATCH] Retarget the bar to 0/N the moment scoring starts The scoring phase only reset the bar on the first judged sample; until then the stale GENERATION state (100%, +N new) stayed on screen -- through multi-minute image-pull preflights it read as 'already done' while nothing was scored yet. Co-Authored-By: Claude --- evalharness/model/runner.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/evalharness/model/runner.py b/evalharness/model/runner.py index 450a49b..7084237 100644 --- a/evalharness/model/runner.py +++ b/evalharness/model/runner.py @@ -829,6 +829,13 @@ async def run_eval( if status_callback: status_callback('Scoring predictions against the benchmark recipe') + # retarget the bar to scoring IMMEDIATELY (0/N): waiting for the first + # on_scored left the stale GENERATION counters (100%, +N new) on screen + # through minute-long preflights (image pulls) -- reading as 'done' + if progress_reporter is not None and _records is None: + _ss0 = getattr(progress_reporter, 'set_scoring', None) + if _ss0 is not None: + _ss0(0, len(samples)) _meta = {'gen_input_tokens': usage.input_tokens, 'gen_output_tokens': usage.output_tokens, 'gen_total_tokens': usage.total_tokens,