Execution attempt · A48 · planned
Scores multiple-choice accuracy of the transplant at time zero and arm B's five milestones.
Pinned source and configuration
https://github.com/stw2/tokenizer-science-tax @ b4c55e6e7d26917e239ccbe2f11886c4d4a733a2
Reference checked 2026-09-14 13:12 UTC. Later commits, branches or plan changes do not retarget this attempt.
- Command
- bash scripts/06_score_checkpoint.sh mcq armB t0_fvt=ckpts/fvt_t0 ckpt_00100M=ckpts/armB/ckpt_00100M ckpt_00200M=ckpts/armB/ckpt_00200M ckpt_00300M=ckpts/armB/ckpt_00300M ckpt_00400M=ckpts/armB/ckpt_00400M ckpt_00500M=ckpts/armB/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.
- 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_fvt · checkpoint · M132 qwen2.5-1.5b-apt4-fvt model directory · raw output · Ask the reporter
- ckpt_00100M · checkpoint · M141 ckpt_00100M · raw output · Ask the reporter
- ckpt_00200M · checkpoint · M142 ckpt_00200M · raw output · Ask the reporter
- ckpt_00300M · checkpoint · M143 ckpt_00300M · raw output · Ask the reporter
- ckpt_00400M · checkpoint · M144 ckpt_00400M · raw output · Ask the reporter
- ckpt_00500M · checkpoint · M145 ckpt_00500M · raw output · Ask the reporter
- data/apt4_reference/tokenizer.json · tokenizer · M125 APT4 tokenizer.json (Bielik-PL-11B-v3.0-Instruct) · tokenizer · 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
Delivered events
Registered
#1Scores multiple-choice accuracy of the transplant at time zero and arm B's five milestones.
Started
#2Started.
Succeeded
#3Completed with exit code 0.
Exit code 0.
- probe_armB.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/9a57aa40f4e774136f51b6730c33266d59094a45/experiments/E05-control-arm/results/probe_armB.jsonl · public · sha256 d05117f27d1c… · 1506 bytes · M170
- probe_armB.jsonl as originally written · Archived private repository, experiments/E5/results/probe_armB.jsonl at commit 5389273; the public copy replaces absolute model paths with paths relative to the experiment folder · unavailable · sha256 9c00bfe53082… · 1818 bytes · M171
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.