open-llm-leaderboard-old/details_blueapple8259__TinyStories-Alpaca

该数据集是在评估模型blueapple8259/TinyStories-Alpaca时自动创建的，评估过程在Open LLM Leaderboard上进行。数据集由64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。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

数据集摘要

该数据集是在对模型 blueapple8259/TinyStories-Alpaca 进行评估运行期间自动创建的。数据集包含 64 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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。

数据集结构

数据集包含以下配置：

• harness_arc_challenge_25
• harness_drop_3
• harness_gsm8k_5
• harness_hellaswag_10
• harness_hendrycksTest_5

每个配置包含多个分片，包括特定时间戳的分片和最新的分片。

最新结果

以下是 2023-11-13T12:08:32.889015 运行的最新结果：

python { "all": { "acc": 0.2343052459270292, "acc_stderr": 0.030014283954142254, "acc_norm": 0.2339194036543238, "acc_norm_stderr": 0.030804772038430715, "mc1": 0.23745410036719705, "mc1_stderr": 0.014896277441041834, "mc2": 0.46675301460809676, "mc2_stderr": 0.016264340534335325, "em": 0.0012583892617449664, "em_stderr": 0.00036305608931191567, "f1": 0.008077810402684559, "f1_stderr": 0.000561047245736677 }, "harness|arc:challenge|25": { "acc": 0.20392491467576793, "acc_stderr": 0.011774262478702259, "acc_norm": 0.23976109215017063, "acc_norm_stderr": 0.012476304127453961 }, "harness|hellaswag|10": { "acc": 0.25781716789484166, "acc_stderr": 0.004365388351563101, "acc_norm": 0.24915355506871142, "acc_norm_stderr": 0.004316389476434519 }, "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": 0.2962962962962963, "acc_stderr": 0.03944624162501116, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.03944624162501116 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22264150943396227, "acc_stderr": 0.0256042334708991, "acc_norm": 0.22264150943396227, "acc_norm_stderr": 0.0256042334708991 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.034370793441061344, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.034370793441061344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.0285048564705142, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.0285048564705142 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2698412698412698, "acc_stderr": 0.02286083830923207, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.02286083830923207 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523812, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523812 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.19032258064516128, "acc_stderr": 0.022331707611823085, "acc_norm": 0.19032258064516128, "acc_norm_stderr": 0.022331707611823085 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.270935960591133, "acc_stderr": 0.03127090713297698, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.03127090713297698 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.15656565656565657, "acc_stderr": 0.025890520358141454, "acc_norm": 0.15656565656565657, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.15544041450777202, "acc_stderr": 0.026148483469153314, "acc_norm": 0.15544041450777202, "acc_norm_stderr": 0.026148483469153314 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2076923076923077, "acc_stderr": 0.020567539567246794, "acc_norm": 0.2076923076923077, "acc_norm_stderr": 0.020567539567246794 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22962962962962963, "