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 · A14 · planned

Runs 250 GSM8K test problems with five fixed examples on both models and computes the paired accuracy difference.

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/08_gsm8k_bridge.py
Working directory
experiments/E02-digit-policy
Configuration paths
None
Parameters
250 test problems stratified by answer digit length; five training problems as fixed examples; seed 20260703; greedy; at most 512 generated tokens; paired bootstrap of 1,000 resamples; GSM8K loaded without a revision from a cache holding only 740312add88f781978c0658806c59bc2815b9866
Environment
CPython 3.12.13 (uv 0.11.16); MLX 0.31.2 on Metal, bf16 weights, greedy decoding (temperature 0); 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

    Runs 250 GSM8K test problems with five fixed examples on both models and computes the paired accuracy difference.

    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.

    • gsm8k_bridge_spec.json · https://github.com/stw2/tokenizer-science-tax/blob/c43f19850803969bc1fefe537caf14e54cfd9a9f/experiments/E02-digit-policy/data/probes/gsm8k_bridge_spec.json · public · sha256 53d5a3eb7fab… · 9694 bytes · M78
    • gsm8k_bielik-pl-11b-v3.0-instruct.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/raw/gsm8k_bielik-pl-11b-v3.0-instruct.jsonl · public · sha256 2647c2b77864… · 124972 bytes · M79
    • gsm8k_bielik-11b-v3.0-instruct.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/raw/gsm8k_bielik-11b-v3.0-instruct.jsonl · public · sha256 c516a7389e78… · 110136 bytes · M80
    • gsm8k_bridge.json · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/gsm8k_bridge.json · public · sha256 06ad27521e97… · 437 bytes · M81
    • gsm8k_bridge.log · Archived private repository, experiments/E2/results/gsm8k_bridge.log at commit 707e7b3; not ported (a log with absolute paths); its facts are in this attempt's environment facts · unavailable · sha256 3762f3c72b81… · 1597 bytes · M82

    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.