open-llm-leaderboard-old/details_LeroyDyer__Mixtral_AI_CyberTron
收藏数据集概述
数据集摘要
该数据集是在评估模型LeroyDyer/Mixtral_AI_CyberTron在Open LLM Leaderboard上的运行过程中自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。
数据集结构
- 配置数量：63个配置
- 数据来源：1次运行结果
- 数据分割：每个配置包含特定运行的分割，分割名称使用运行的时间戳。"train"分割始终指向最新结果。
- 额外配置："results"配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_LeroyDyer__Mixtral_AI_CyberTron", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-15T15:25:26.631470运行的最新结果：
python { "all": { "acc": 0.6207341899016878, "acc_stderr": 0.03268647985396864, "acc_norm": 0.6244114490529663, "acc_norm_stderr": 0.03334075921277243, "mc1": 0.4222766217870257, "mc1_stderr": 0.017290733254248174, "mc2": 0.6122385287224691, "mc2_stderr": 0.01514349395606483 }, "harness|arc:challenge|25": { "acc": 0.5887372013651877, "acc_stderr": 0.014379441068522084, "acc_norm": 0.6203071672354948, "acc_norm_stderr": 0.014182119866974872 }, "harness|hellaswag|10": { "acc": 0.6326428998207528, "acc_stderr": 0.004810996652324729, "acc_norm": 0.8222465644293966, "acc_norm_stderr": 0.003815237269961105 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720386, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6776315789473685, "acc_stderr": 0.03803510248351585, "acc_norm": 0.6776315789473685, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.02854479331905533, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.02854479331905533 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7152777777777778, "acc_stderr": 0.03773809990686934, "acc_norm": 0.7152777777777778, "acc_norm_stderr": 0.03773809990686934 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6127167630057804, "acc_stderr": 0.037143259063020656, "acc_norm": 0.6127167630057804, "acc_norm_stderr": 0.037143259063020656 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.04655010411319616, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.04655010411319616 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.046854730419077895, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.02522545028406788, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.02522545028406788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7516129032258064, "acc_stderr": 0.024580028921481003, "acc_norm": 0.7516129032258064, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4827586206896552, "acc_stderr": 0.035158955511656986, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.04793724854411019, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.03256866661681102, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7777777777777778, "acc_stderr": 0.02962022787479048, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.02962022787479048 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6307692307692307, "acc_stderr": 0.024468615241478926, "acc_norm": 0.6307692307692307, "acc_norm_stderr": 0.024468615241478926 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524575, "acc_norm": 0.329629629
