open-llm-leaderboard-old/details_TommyZQ__llama3

该数据集是在Open LLM Leaderboard上对模型TommyZQ/llama3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。数据集包含1次运行的结果，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果，这些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Python中的datasets库加载运行细节的示例。

原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 TommyZQ/llama3 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，每个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。
• 一个额外的配置 "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 2024-04-19T02:02:11.915036 运行的最新结果：

python { "all": { "acc": 0.25963732222468194, "acc_stderr": 0.03099098534859739, "acc_norm": 0.2610646605187679, "acc_norm_stderr": 0.03170559793701961, "mc1": 0.27050183598531213, "mc1_stderr": 0.015550778332842892, "mc2": 0.42790014826106193, "mc2_stderr": 0.014660921880640491 }, "harness|arc:challenge|25": { "acc": 0.3438566552901024, "acc_stderr": 0.01388064457015621, "acc_norm": 0.3771331058020478, "acc_norm_stderr": 0.014163366896192589 }, "harness|hellaswag|10": { "acc": 0.4386576379207329, "acc_stderr": 0.00495208708312889, "acc_norm": 0.5893248356901015, "acc_norm_stderr": 0.00490950953852518 }, "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": 0.17777777777777778, "acc_stderr": 0.03302789859901717, "acc_norm": 0.17777777777777778, "acc_norm_stderr": 0.03302789859901717 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19078947368421054, "acc_stderr": 0.03197565821032499, "acc_norm": 0.19078947368421054, "acc_norm_stderr": 0.03197565821032499 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27169811320754716, "acc_stderr": 0.02737770662467071, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.02737770662467071 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.032147373020294696, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.032147373020294696 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617748, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617748 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "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": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131183, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131183 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.03932537680392871, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392871 }, "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": 0.1870967741935484, "acc_stderr": 0.02218571009225225, "acc_norm": 0.1870967741935484, "acc_norm_stderr": 0.02218571009225225 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15763546798029557, "acc_stderr": 0.025639014131172408, "acc_norm": 0.15763546798029557, "acc_norm_stderr": 0.025639014131172408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24242424242424243, "acc_stderr": 0.03346409881055953, "acc_norm": 0.24242424242424243, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.02937661648494563, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.02937661648494563 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.25906735751295334, "acc_stderr": 0.03161877917935411, "acc_norm": 0.25906735751295334, "acc_norm_stderr": 0.03161877917935411 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.025348097468097866, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.025348097468097866 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.21848739495798