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

测量结果

已评估 0/30 项

获得支持 0有争议或冲突 0尚未评估 30

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
arm: baseline · tier: 124M · zero_shot: true	0.182 fraction	—	尚未评估
arm: baseline · tier: 124M · zero_shot: true	0.006 fraction	—	尚未评估
arm: baseline · tier: 124M · zero_shot: true	0.323 fraction	—	尚未评估
arm: baseline · tier: 124M · zero_shot: true	0.002 fraction	—	尚未评估
arm: baseline · tier: 124M · zero_shot: true	58.1 perplexity	—	尚未评估
arm: baseline · tier: 124M · zero_shot: true	0.5 perplexity	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	0.179 fraction	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	0.004 fraction	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	0.325 fraction	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	0.003 fraction	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	57 perplexity	—	尚未评估
arm: sink logit · tier: 124M · zero_shot: true	0.5 perplexity	—	尚未评估

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.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果