open-llm-leaderboard-old/details_frankenmerger__gemoy-4b-instruct

该数据集是在模型 frankenmerger/gemoy-4b-instruct 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，每个配置对应一个被评估的任务。它包含 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，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。README 还提供了一个如何使用 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

数据集组成

• 该数据集包含63个配置，每个配置对应一个评估任务。
• 数据集是从1次运行中创建的，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"分割总是指向最新的结果。
• 一个额外的配置"results"存储所有运行的聚合结果，用于计算和显示在Open LLM Leaderboard上的聚合指标。

最新结果

• 以下是2024-03-10T10:59:13.672299运行的最新结果：

python { "all": { "acc": 0.3635342339637508, "acc_stderr": 0.03346560799526674, "acc_norm": 0.36857377594697643, "acc_norm_stderr": 0.03436928129673128, "mc1": 0.2729498164014688, "mc1_stderr": 0.015594753632006518, "mc2": 0.46641168216975853, "mc2_stderr": 0.016269583261373614 }, "harness|arc:challenge|25": { "acc": 0.3728668941979522, "acc_stderr": 0.014131176760131167, "acc_norm": 0.4069965870307167, "acc_norm_stderr": 0.01435639941800913 }, "harness|hellaswag|10": { "acc": 0.44981079466241786, "acc_stderr": 0.004964579685712441, "acc_norm": 0.5802628958374826, "acc_norm_stderr": 0.004925072159723828 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.362962962962963, "acc_stderr": 0.041539484047424, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.041539484047424 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.32894736842105265, "acc_stderr": 0.038234289699266046, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.038234289699266046 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.05021167315686781, "acc_norm": 0.52, "acc_norm_stderr": 0.05021167315686781 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4075471698113208, "acc_stderr": 0.030242233800854494, "acc_norm": 0.4075471698113208, "acc_norm_stderr": 0.030242233800854494 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3333333333333333, "acc_stderr": 0.039420826399272135, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.039420826399272135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2832369942196532, "acc_stderr": 0.034355680560478746, "acc_norm": 0.2832369942196532, "acc_norm_stderr": 0.034355680560478746 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617747, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617747 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.34893617021276596, "acc_stderr": 0.031158522131357783, "acc_norm": 0.34893617021276596, "acc_norm_stderr": 0.031158522131357783 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489362, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489362 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4413793103448276, "acc_stderr": 0.04137931034482757, "acc_norm": 0.4413793103448276, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2830687830687831, "acc_stderr": 0.023201392938194974, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194974 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.25396825396825395, "acc_stderr": 0.03893259610604674, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.03893259610604674 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.35161290322580646, "acc_stderr": 0.027162537826948458, "acc_norm": 0.35161290322580646, "acc_norm_stderr": 0.027162537826948458 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.22660098522167488, "acc_stderr": 0.029454863835292992, "acc_norm": 0.22660098522167488, "acc_norm_stderr": 0.029454863835292992 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.40606060606060607, "acc_stderr": 0.03834816355401181, "acc_norm": 0.40606060606060607, "acc_norm_stderr": 0.03834816355401181 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4797979797979798, "acc_stderr": 0.035594435655639196, "acc_norm": 0.4797979797979798, "acc_norm_stderr": 0.035594435655639196 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.47150259067357514, "acc_stderr": 0.036025735712884414, "acc_norm": 0.47150259067357514, "acc_norm_stderr": 0.036025735712884414 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3487179487179487, "acc_stderr": 0.024162780284017717, "acc_norm": 0.3487179487179487, "acc_norm_stderr": 0.024162780284017717 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21481481481481482, "acc_stderr": 0.025040443877000683, "acc_norm": 0.21481481481481482, "acc_norm_stderr": 0.025040443877000683 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.31932773109243695, "acc_stderr": 0.030283995525884396, "acc_norm": 0.31932773109243695, "acc_norm_stderr": 0.0302839955