open-llm-leaderboard-old/details_tokyotech-llm__Swallow-70b-instruct-hf

该数据集是在模型tokyotech-llm/Swallow-70b-instruct-hf在Open LLM Leaderboard上的评估运行期间自动创建的。它由63个配置组成，每个配置对应一个被评估的任务。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的额外配置存储了运行的所有聚合结果，这些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 tokyotech-llm/Swallow-70b-instruct-hf 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。
• "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 2023-12-30T17:31:51.560670 运行的最新结果：

python { "all": { "acc": 0.668542166197933, "acc_stderr": 0.031317102785635216, "acc_norm": 0.6737570900410808, "acc_norm_stderr": 0.03193599243400287, "mc1": 0.33047735618115054, "mc1_stderr": 0.016466769613698296, "mc2": 0.4799587332250507, "mc2_stderr": 0.014270049627097015 }, "harness|arc:challenge|25": { "acc": 0.6151877133105802, "acc_stderr": 0.014218371065251104, "acc_norm": 0.6621160409556314, "acc_norm_stderr": 0.013822047922283509 }, "harness|hellaswag|10": { "acc": 0.6474805815574587, "acc_stderr": 0.004767782256040988, "acc_norm": 0.8514240191196972, "acc_norm_stderr": 0.0035494312479073657 }, "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": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.743421052631579, "acc_stderr": 0.0355418036802569, "acc_norm": 0.743421052631579, "acc_norm_stderr": 0.0355418036802569 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7916666666666666, "acc_stderr": 0.033961162058453336, "acc_norm": 0.7916666666666666, "acc_norm_stderr": 0.033961162058453336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663434, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663434 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.045126085985421296, "acc_norm": 0.72, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6297872340425532, "acc_stderr": 0.03156564682236785, "acc_norm": 0.6297872340425532, "acc_norm_stderr": 0.03156564682236785 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.046570472605949625, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.046570472605949625 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6, "acc_stderr": 0.040824829046386284, "acc_norm": 0.6, "acc_norm_stderr": 0.040824829046386284 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.02548718714785938, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.02548718714785938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04444444444444449, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7903225806451613, "acc_stderr": 0.023157879349083522, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.023157879349083522 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.04292346959909281, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.029311188674983127, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.029311188674983127 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8484848484848485, "acc_stderr": 0.025545650426603617, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.025545650426603617 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.020986854593289708, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.020986854593289708 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6897435897435897, "acc_stderr": 0.02345467488940429, "acc_norm": 0.6897435897435897, "acc_norm_stderr": 0.02345467488940429 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37777777777777777, "acc_stderr": 0.02956070739246572, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.02956070739246572 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7352941176470589, "acc_stderr": 0.028