open-llm-leaderboard-old/details_AIDC-ai-business__Marcoroni-70B
收藏数据集概述
数据集来源
该数据集是在评估模型AIDC-ai-business/Marcoroni-70B在Open LLM Leaderboard上的运行过程中自动创建的。
数据集结构
数据集包含61个配置，每个配置对应一个评估任务。数据集从4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。
额外配置
一个额外的配置"results"存储所有运行的聚合结果，用于计算并在Open LLM Leaderboard上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_AIDC-ai-business__Marcoroni-70B", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新的结果，来自2023-09-19T02:16:50.789886的运行：
python { "all": { "acc": 0.23992448312110085, "acc_stderr": 0.031078389352549952, "acc_norm": 0.24054395860756556, "acc_norm_stderr": 0.03108725267744147, "mc1": 1.0, "mc1_stderr": 0.0, "mc2": NaN, "mc2_stderr": NaN }, "harness|arc:challenge|25": { "acc": 0.24744027303754265, "acc_stderr": 0.012610352663292673, "acc_norm": 0.2790102389078498, "acc_norm_stderr": 0.013106784883601346 }, "harness|hellaswag|10": { "acc": 0.2621987651862179, "acc_stderr": 0.004389312748012152, "acc_norm": 0.2671778530173272, "acc_norm_stderr": 0.004415816696303084 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.0335567721631314, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.0335567721631314 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.033550453048829226, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.033550453048829226 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "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": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.18497109826589594, "acc_stderr": 0.029605623981771204, "acc_norm": 0.18497109826589594, "acc_norm_stderr": 0.029605623981771204 }, "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": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2723404255319149, "acc_stderr": 0.029101290698386705, "acc_norm": 0.2723404255319149, "acc_norm_stderr": 0.029101290698386705 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.25517241379310346, "acc_stderr": 0.03632984052707842, "acc_norm": 0.25517241379310346, "acc_norm_stderr": 0.03632984052707842 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24603174603174602, "acc_stderr": 0.022182037202948365, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.022182037202948365 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.04006168083848876, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.04006168083848876 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2, "acc_stderr": 0.022755204959542932, "acc_norm": 0.2, "acc_norm_stderr": 0.022755204959542932 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.22167487684729065, "acc_stderr": 0.029225575892489607, "acc_norm": 0.22167487684729065, "acc_norm_stderr": 0.029225575892489607 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2545454545454545, "acc_stderr": 0.0340150671524904, "acc_norm": 0.2545454545454545, "acc_norm_stderr": 0.0340150671524904 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.20707070707070707, "acc_stderr": 0.02886977846026705, "acc_norm": 0.20707070707070707, "acc_norm_stderr": 0.02886977846026705 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.2849740932642487, "acc_stderr": 0.03257714077709661, "acc_norm": 0.2849740932642487, "acc_norm_stderr": 0.03257714077709661 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.021444547301560486, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.021444547301560486 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.025497532639609542, "acc_norm": 0.22592592592592592, "acc_norm_stderr": 0.025497532639609542 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.19747899159663865, "acc_stderr": 0.025859164122051467, "acc_norm": 0.19747899159663865, "acc_norm_stderr": 0.0258591641
