open-llm-leaderboard-old/details_Weyaxi__Qwen-72B-Llama

该数据集是在评估模型Weyaxi/Qwen-72B-Llama时自动创建的，评估过程在Open LLM Leaderboard上进行。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命名。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

该数据集是在对模型 Weyaxi/Qwen-72B-Llama 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 2024-02-02T06:36:25.719099 运行的最新结果：

python { "all": { "acc": 0.7316507461013225, "acc_stderr": 0.02876333054548078, "acc_norm": 0.7367632357692079, "acc_norm_stderr": 0.029299960559549205, "mc1": 0.40514075887392903, "mc1_stderr": 0.01718561172775337, "mc2": 0.5759942995358094, "mc2_stderr": 0.015126059763108792 }, "harness|arc:challenge|25": { "acc": 0.6168941979522184, "acc_stderr": 0.014206472661672877, "acc_norm": 0.6484641638225256, "acc_norm_stderr": 0.013952413699600931 }, "harness|hellaswag|10": { "acc": 0.6480780720971918, "acc_stderr": 0.004765937515197188, "acc_norm": 0.8327026488747261, "acc_norm_stderr": 0.00372478338925333 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6962962962962963, "acc_stderr": 0.039725528847851355, "acc_norm": 0.6962962962962963, "acc_norm_stderr": 0.039725528847851355 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.02407999513006224, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.02407999513006224 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9027777777777778, "acc_stderr": 0.02477451625044018, "acc_norm": 0.9027777777777778, "acc_norm_stderr": 0.02477451625044018 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7745664739884393, "acc_stderr": 0.03186209851641143, "acc_norm": 0.7745664739884393, "acc_norm_stderr": 0.03186209851641143 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.036845294917747094, "acc_norm": 0.84, "acc_norm_stderr": 0.036845294917747094 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8170212765957446, "acc_stderr": 0.025276041000449966, "acc_norm": 0.8170212765957446, "acc_norm_stderr": 0.025276041000449966 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5614035087719298, "acc_stderr": 0.04668000738510455, "acc_norm": 0.5614035087719298, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6851851851851852, "acc_stderr": 0.023919984164047732, "acc_norm": 0.6851851851851852, "acc_norm_stderr": 0.023919984164047732 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.864516129032258, "acc_stderr": 0.019469334586486933, "acc_norm": 0.864516129032258, "acc_norm_stderr": 0.019469334586486933 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6945812807881774, "acc_stderr": 0.03240661565868408, "acc_norm": 0.6945812807881774, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9141414141414141, "acc_stderr": 0.01996022556317289, "acc_norm": 0.9141414141414141, "acc_norm_stderr": 0.01996022556317289 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084317, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084317 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7948717948717948, "acc_stderr": 0.02047323317355199, "acc_norm": 0.7948717948717948, "acc_norm_stderr": 0.02047323317355199 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.030296771286067323, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.030296771286067323 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8025210084033614, "acc_stderr": 0.025859164122051453, "acc_norm": 0.8025210084033614,