open-llm-leaderboard-old/details_LeroyDyer__Mixtral_AI_Cyber_5.0
收藏数据集概述
数据集来源
该数据集是在评估模型 LeroyDyer/Mixtral_AI_Cyber_5.0 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
数据集包含 63 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" 存储了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_Cyber_5.0", "harness_winogrande_5", split="train")
最新结果
这些是最新结果（来自 2024-04-05T06:42:38.392993 运行）的摘要：
python { "all": { "acc": 0.6319018824466575, "acc_stderr": 0.03243701667042675, "acc_norm": 0.6339164216412606, "acc_norm_stderr": 0.03309308870008847, "mc1": 0.40636474908200737, "mc1_stderr": 0.017193835812093893, "mc2": 0.5786475510628558, "mc2_stderr": 0.015303043316159103 }, "harness|arc:challenge|25": { "acc": 0.6143344709897611, "acc_stderr": 0.014224250973257182, "acc_norm": 0.6484641638225256, "acc_norm_stderr": 0.013952413699600935 }, "harness|hellaswag|10": { "acc": 0.6544513045210117, "acc_stderr": 0.004745749538752324, "acc_norm": 0.8445528779127663, "acc_norm_stderr": 0.0036158989282692785 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "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": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145634, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145634 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6069364161849711, "acc_stderr": 0.03724249595817731, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.03724249595817731 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "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": 0.5446808510638298, "acc_stderr": 0.032555253593403555, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.032555253593403555 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366595, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366595 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43386243386243384, "acc_stderr": 0.02552503438247489, "acc_norm": 0.43386243386243384, "acc_norm_stderr": 0.02552503438247489 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.0442626668137991, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.0442626668137991 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7387096774193549, "acc_stderr": 0.024993053397764805, "acc_norm": 0.7387096774193549, "acc_norm_stderr": 0.024993053397764805 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586815, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8652849740932642, "acc_stderr": 0.024639789097709443, "acc_norm": 0.8652849740932642, "acc_norm_stderr": 0.024639789097709443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6538461538461539, "acc_stderr": 0.024121125416941197, "acc_norm": 0.6538461538461539, "acc_norm_stderr": 0.024121125416941197 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524565, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524565 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6680672268907563,
