Execution attempt

Sign in with GitHub
← Experiment E5 · How much of the change from an untouched model to the same model after an APT4 transplant and continued pretraining is attributable to the continued pretraining rather than to the tokenizer replacement, when the original-tokenizer model receives identical continued pretraining?

Execution attempt · A43 · planned

Scores multiple-choice accuracy of the untouched base and arm A's five milestones.

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 @ b4c55e6e7d26917e239ccbe2f11886c4d4a733a2

Reference checked 2026-09-14 13:10 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
bash scripts/06_score_checkpoint.sh mcq armA t0_base=Qwen/Qwen2.5-1.5B ckpt_00100M=ckpts/armA/ckpt_00100M ckpt_00200M=ckpts/armA/ckpt_00200M ckpt_00300M=ckpts/armA/ckpt_00300M ckpt_00400M=ckpts/armA/ckpt_00400M ckpt_00500M=ckpts/armA/ckpt_00500M
Working directory
experiments/E05-control-arm
Configuration paths
None
Parameters
Summed log-probability of each answer letter after the question and 'Odpowiedź:'; first 300 items per set. The base and 100M rows also scored 250 GSM8K-PL items (accuracy 0), a set dropped from later rows.
Environment
3.12.13; PyTorch MPS, bf16; 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.

  • t0_base · checkpoint · M124 Qwen2.5-1.5B · checkpoint · Download
  • ckpt_00100M · checkpoint · M136 ckpt_00100M · raw output · Ask the reporter
  • ckpt_00200M · checkpoint · M137 ckpt_00200M · raw output · Ask the reporter
  • ckpt_00300M · checkpoint · M138 ckpt_00300M · raw output · Ask the reporter
  • ckpt_00400M · checkpoint · M139 ckpt_00400M · raw output · Ask the reporter
  • ckpt_00500M · checkpoint · M140 ckpt_00500M · raw output · Ask the reporter
  • items_llmzszl_stem.jsonl · evaluation data · M93 items_llmzszl_stem.jsonl · raw output · Ask the reporter
  • items_pes.jsonl · evaluation data · M94 items_pes.jsonl · raw output · Ask the reporter
  • items_gsm8k_pl.jsonl · evaluation data · M92 items_gsm8k_pl.jsonl · raw output · Download

Delivered events

  1. Registered

    #1

    Scores multiple-choice accuracy of the untouched base and arm A's five milestones.

    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.

    • probe_armA.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/9a57aa40f4e774136f51b6730c33266d59094a45/experiments/E05-control-arm/results/probe_armA.jsonl · public · sha256 ab11316a2dca… · 1566 bytes · M148
    • probe_armA.jsonl as originally written · Archived private repository, experiments/E5/results/probe_armA.jsonl at commit 5389273; the public copy replaces absolute model paths with paths relative to the experiment folder · unavailable · sha256 72e420099bbc… · 1826 bytes · M149

    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.