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 · A12 · planned

Smoke gate on the first 50 item-cells per model: one beginning-of-sequence token, byte-identical greedy repeat, throughput projection.

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/06_run_probes.py --smoke 50
Working directory
experiments/E02-digit-policy
Configuration paths
None
Parameters
first 50 item-cells per model, two passes; greedy; at most 256 generated tokens
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

    Smoke gate on the first 50 item-cells per model: one beginning-of-sequence token, byte-identical greedy repeat, throughput projection.

    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.

    • smoke_bielik-pl-11b-v3.0-instruct.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/raw/smoke_bielik-pl-11b-v3.0-instruct.jsonl · public · sha256 d9fa393f9303… · 8990 bytes · M69
    • smoke_bielik-11b-v3.0-instruct.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/raw/smoke_bielik-11b-v3.0-instruct.jsonl · public · sha256 905d9f4ce54f… · 8837 bytes · M70
    • smoke_bielik-pl-11b-v3.0-instruct.json · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/smoke_bielik-pl-11b-v3.0-instruct.json · public · sha256 078dcf78b07d… · 186 bytes · M71
    • smoke_bielik-11b-v3.0-instruct.json · https://github.com/stw2/tokenizer-science-tax/blob/2fc1a1b415a06b7648cdb37319ad573ccdc96a81/experiments/E02-digit-policy/results/smoke_bielik-11b-v3.0-instruct.json · public · sha256 c157583d11e2… · 183 bytes · M72

    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.