Execution attempt

Sign in with GitHub
← Experiment E2 · Does APT4's tokenization of digits and number separators differ from the Mistral-derived tokenizer's, and does the difference account for the lower GSM8K score of Bielik-PL-11B-v3.0-Instruct and for accuracy differences between English and Polish number formats?

Execution attempt · A7 · planned

Downloads both 11B Instruct models at their revisions, hashes every file and checks tokenizer.json against E1's frozen copies.

Succeeded · Registered by @stw2 via agent. Reported and received times are kept apart; no computation or result is verified.

Pinned source and configuration

https://github.com/stw2/tokenizer-science-tax @ c43f19850803969bc1fefe537caf14e54cfd9a9f

Reference checked 2026-09-14 13:08 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/01_fetch_models.py
Working directory
experiments/E02-digit-policy
Configuration paths
None
Parameters
revisions a74fa8560324b6b1502d01bf6440e2b0affcfa4f and 735bfee1125fe8b497ac2769de94822a11f77167, resolved from main at run time; file patterns *.safetensors *.json *.model *.txt *.jinja; tokenizer.json must equal E1's copies 536b4dffbed89b3741d008a06c4308a42b3e3e969b92c7e3c6fd0ca1f40d04b1 and c3574b108114217bdfc00cb1de99bd84a71b218a360dc30671669c1e50c53604
Environment
CPython 3.12.13 (uv 0.11.16); CPU and network; Apple silicon, 128 GB unified memory
Output directory
Not recorded

Inputs

Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.

Delivered events

  1. Registered

    #1

    Downloads both 11B Instruct models at their revisions, hashes every file and checks tokenizer.json against E1's frozen copies.

    reported · received · @stw2 via agent · posted to the Thread

  2. Started

    #2

    Started.

    reported · received · @stw2 via agent · attempt only

  3. Succeeded

    #3

    Completed with exit code 0.

    Exit code 0.

    • bielik-pl-11b-v3.0-instruct hf snapshot · Not redistributed: ask the Room owner, or rebuild with scripts/01_fetch_models.py at the pinned revisions · restricted · sha256 cde0309abdfa… · 22339295372 bytes · M49
    • bielik-11b-v3.0-instruct hf snapshot · Not redistributed: ask the Room owner, or rebuild with scripts/01_fetch_models.py at the pinned revisions · restricted · sha256 929e0f7698cd… · 22341741569 bytes · M50
    • fetch_models.log · Archived private repository, experiments/E2/results/fetch_models.log at commit 707e7b3; not ported (a log with absolute paths); its facts are in this attempt's environment facts · unavailable · sha256 c10d126dce6e… · 1878 bytes · M51
    • models_manifest.json first version · Rewritten by scripts/02_convert_mlx.py in the same run; this version was not kept · unavailable

    reported · received · @stw2 via agent · posted to the Thread

Report an event

The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.

This attempt has a delivered outcome. A new execution is a new attempt.