open-llm-leaderboard-old/details_Dans-DiscountModels__TinyMistral-v2-Test1

该数据集是在模型Dans-DiscountModels/TinyMistral-v2-Test1在Open LLM Leaderboard上的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。数据集是从一次运行中生成的，每次运行在每个配置中表示为特定的拆分，使用运行的时间戳命名。train拆分始终指向最新的结果。一个名为results的额外配置存储了运行的所有聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行中的详细信息的示例。

原始信息汇总

数据集概述

该数据集是在对模型 Dans-DiscountModels/TinyMistral-v2-Test1 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 "results" 配置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 2024-01-21T02:38:49.773813 运行的最新结果：

python { "all": { "acc": 0.2335310199962483, "acc_stderr": 0.02999531007525961, "acc_norm": 0.23385996059713224, "acc_norm_stderr": 0.03078636978062643, "mc1": 0.25091799265605874, "mc1_stderr": 0.015176985027707703, "mc2": 0.5030342289474727, "mc2_stderr": 0.015464982097707176 }, "harness|arc:challenge|25": { "acc": 0.18344709897610922, "acc_stderr": 0.011310170179554543, "acc_norm": 0.2150170648464164, "acc_norm_stderr": 0.01200571763413361 }, "harness|hellaswag|10": { "acc": 0.261700856403107, "acc_stderr": 0.004386622589119065, "acc_norm": 0.2678749253136825, "acc_norm_stderr": 0.00441946998393918 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.1925925925925926, "acc_stderr": 0.03406542058502653, "acc_norm": 0.1925925925925926, "acc_norm_stderr": 0.03406542058502653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17105263157894737, "acc_stderr": 0.030643607071677088, "acc_norm": 0.17105263157894737, "acc_norm_stderr": 0.030643607071677088 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.20754716981132076, "acc_stderr": 0.02495991802891127, "acc_norm": 0.20754716981132076, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2777777777777778, "acc_stderr": 0.037455547914624555, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.16, "acc_stderr": 0.03684529491774709, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.02880998985410297, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.02880998985410297 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.21428571428571427, "acc_stderr": 0.02113285918275444, "acc_norm": 0.21428571428571427, "acc_norm_stderr": 0.02113285918275444 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30158730158730157, "acc_stderr": 0.04104947269903394, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.04104947269903394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.18387096774193548, "acc_stderr": 0.022037217340267836, "acc_norm": 0.18387096774193548, "acc_norm_stderr": 0.022037217340267836 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.19704433497536947, "acc_stderr": 0.027986724666736205, "acc_norm": 0.19704433497536947, "acc_norm_stderr": 0.027986724666736205 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.18181818181818182, "acc_stderr": 0.027479603010538797, "acc_norm": 0.18181818181818182, "acc_norm_stderr": 0.027479603010538797 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860664, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860664 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2, "acc_stderr": 0.020280805062535722, "acc_norm": 0.2, "acc_norm_stderr": 0.020280805062535722 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21851851851851853, "acc_stderr": 0.02519575225182379, "acc_norm": 0.21851851851851853, "acc_norm_stderr": 0.02519575225182379 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.2226890756302