open-llm-leaderboard-old/details_bit-dny__MindLLM
收藏数据集概述
数据集来源
该数据集是在对模型 bit-dny/MindLLM 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集结构
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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bit-dny__MindLLM", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-27T12:33:52.223530 运行的最新结果：
python { "all": { "acc": 0.2547315459012399, "acc_stderr": 0.030757121924893716, "acc_norm": 0.2559855532831359, "acc_norm_stderr": 0.03153175700940631, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015025, "mc2": 0.43479871223663846, "mc2_stderr": 0.015180815930542027 }, "harness|arc:challenge|25": { "acc": 0.19539249146757678, "acc_stderr": 0.011586907189952911, "acc_norm": 0.22440273037542663, "acc_norm_stderr": 0.012191404938603838 }, "harness|hellaswag|10": { "acc": 0.30392352121091415, "acc_stderr": 0.004590100050198833, "acc_norm": 0.34106751643098987, "acc_norm_stderr": 0.004730991357194287 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614866, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.20394736842105263, "acc_stderr": 0.0327900040631005, "acc_norm": 0.20394736842105263, "acc_norm_stderr": 0.0327900040631005 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27169811320754716, "acc_stderr": 0.027377706624670713, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2916666666666667, "acc_stderr": 0.03800968060554858, "acc_norm": 0.2916666666666667, "acc_norm_stderr": 0.03800968060554858 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.03214737302029471, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.03214737302029471 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.17647058823529413, "acc_stderr": 0.0379328118530781, "acc_norm": 0.17647058823529413, "acc_norm_stderr": 0.0379328118530781 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2851063829787234, "acc_stderr": 0.02951319662553935, "acc_norm": 0.2851063829787234, "acc_norm_stderr": 0.02951319662553935 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.022717467897708617, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.022717467897708617 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287394, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23870967741935484, "acc_stderr": 0.024251071262208837, "acc_norm": 0.23870967741935484, "acc_norm_stderr": 0.024251071262208837 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2828282828282828, "acc_stderr": 0.03208779558786752, "acc_norm": 0.2828282828282828, "acc_norm_stderr": 0.03208779558786752 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35233160621761656, "acc_stderr": 0.034474782864143586, "acc_norm": 0.35233160621761656, "acc_norm_stderr": 0.034474782864143586 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2846153846153846, "acc_stderr": 0.0228783227997063, "acc_norm": 0.2846153846153846, "acc_norm_stderr": 0.0228783227997063 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145668, "acc_norm": 0.2703703703703
