open-llm-leaderboard-old/details_eren23__ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2

该数据集是在模型eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2的评估运行期间自动创建的，用于Open LLM Leaderboard。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行可以在每个配置中找到，分割以运行的时间戳命名。train分割始终指向最新结果。此外，results配置存储了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。

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 eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2 进行评估运行期间自动创建的。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，每次运行的详细结果可以在每个配置的特定分片中找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。此外，一个名为 "results" 的额外配置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。

最新结果

以下是来自2024-03-01T23:34:01.291770运行的最新结果：

python { "all": { "acc": 0.653998983984977, "acc_stderr": 0.03205686303223958, "acc_norm": 0.6534966993814849, "acc_norm_stderr": 0.03272662727558437, "mc1": 0.627906976744186, "mc1_stderr": 0.01692109011881403, "mc2": 0.7746116985918058, "mc2_stderr": 0.013798217074345885 }, "harness|arc:challenge|25": { "acc": 0.7022184300341296, "acc_stderr": 0.01336308010724448, "acc_norm": 0.7312286689419796, "acc_norm_stderr": 0.012955065963710695 }, "harness|hellaswag|10": { "acc": 0.7151961760605458, "acc_stderr": 0.004503985839041969, "acc_norm": 0.8906592312288388, "acc_norm_stderr": 0.0031142850772280357 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119669, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119669 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.02825420034443866, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.02825420034443866 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.03614665424180826, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.03614665424180826 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107224, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107224 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108102, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.025379524910778394, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778394 }, "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": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.02328766512726855, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.02328766512726855 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5270935960591133, "acc_stderr": 0.03512819077876106, "acc_norm": 0.5270935960591133, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.032876667586034906, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.032876667586034906 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8080808080808081, "acc_stderr": 0.028057791672989017, "acc_norm": 0.8080808080808081, "acc_norm_stderr": 0.028057791672989017 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.022473253332768763, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.022473253332768763 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402538, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948485, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948485 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6890756302521008, "acc_stderr": 0.03006676158297793, "acc_norm": 0.6890756302521008, "acc_norm_stderr": 0.03006676158297793 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3973