At 124M, zero-shot LAMBADA, HellaSwag, and WikiText-2 results are mixed but directionally consistent overall with the validation-loss ordering: gated arms slightly improve LAMBADA, several modified arms tie at 0.325 on HellaSwag, and all modified arms reduce WikiText-2 perplexity.

At 124M, zero-shot LAMBADA, HellaSwag, and WikiText-2 results are mixed but directionally consistent overall with the validation-loss ordering: gated arms slightly improve LAMBADA, several modified arms tie at 0.325 on HellaSwag, and all modified arms reduce WikiText-2 perplexity. · CiteArk

Measurement results

0/30 assessed

0 supported0 disputed or conflicting30 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
arm: baseline · tier: 124M · zero_shot: true	0.182 fraction	—	Not assessed
arm: baseline · tier: 124M · zero_shot: true	0.006 fraction	—	Not assessed
arm: baseline · tier: 124M · zero_shot: true	0.323 fraction	—	Not assessed
arm: baseline · tier: 124M · zero_shot: true	0.002 fraction	—	Not assessed
arm: baseline · tier: 124M · zero_shot: true	58.1 perplexity	—	Not assessed
arm: baseline · tier: 124M · zero_shot: true	0.5 perplexity	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	0.179 fraction	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	0.004 fraction	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	0.325 fraction	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	0.003 fraction	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	57 perplexity	—	Not assessed
arm: sink logit · tier: 124M · zero_shot: true	0.5 perplexity	—	Not assessed

At 124M, zero-shot LAMBADA, HellaSwag, and WikiText-2 results are mixed but directionally consistent overall with the validation-loss ordering: gated arms slightly improve LAMBADA, several modified arms tie at 0.325 on HellaSwag, and all modified arms reduce WikiText-2 perplexity.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results