open-llm-leaderboard-old/details_liuchanghf__phi2_gsm8k_lora

该数据集是在Open LLM Leaderboard上对模型liuchanghf/phi2_gsm8k_lora进行评估时自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集从1次运行中创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 liuchanghf/phi2_gsm8k_lora 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 数据集包含 63 个配置，每个配置对应一个评估任务。
• 数据集从 1 次运行中创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
• "train" 分割始终指向最新的结果。
• 额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是 2024-04-23T04:21:09.653323 运行的最新结果：

python { "all": { "acc": 0.5697065607682864, "acc_stderr": 0.03397581694661876, "acc_norm": 0.5703767860937092, "acc_norm_stderr": 0.034678726853616546, "mc1": 0.2741738066095471, "mc1_stderr": 0.015616518497219373, "mc2": 0.3886038487775018, "mc2_stderr": 0.014713287515628878 }, "harness|arc:challenge|25": { "acc": 0.5656996587030717, "acc_stderr": 0.014484703048857359, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.01437035863247244 }, "harness|hellaswag|10": { "acc": 0.5632344154550887, "acc_stderr": 0.00494971636889049, "acc_norm": 0.7428799044015136, "acc_norm_stderr": 0.004361529679492747 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.0404633688397825, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.0404633688397825 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5886792452830188, "acc_stderr": 0.030285009259009794, "acc_norm": 0.5886792452830188, "acc_norm_stderr": 0.030285009259009794 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960717, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960717 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201943, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201943 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4978723404255319, "acc_stderr": 0.03268572658667492, "acc_norm": 0.4978723404255319, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.025379524910778387, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778387 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6838709677419355, "acc_stderr": 0.026450874489042764, "acc_norm": 0.6838709677419355, "acc_norm_stderr": 0.026450874489042764 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6121212121212121, "acc_stderr": 0.03804913653971013, "acc_norm": 0.6121212121212121, "acc_norm_stderr": 0.03804913653971013 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124498, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124498 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7772020725388601, "acc_stderr": 0.03003114797764154, "acc_norm": 0.7772020725388601, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5974358974358974, "acc_stderr": 0.02486499515976776, "acc_norm": 0.5974358974358974, "acc_norm_stderr": 0.02486499515976776 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524582, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524582 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.630252100