open-llm-leaderboard-old/details_starmpcc__Asclepius-Llama2-13B
收藏数据集概述
数据集简介
该数据集是在评估模型starmpcc/Asclepius-Llama2-13B在Open LLM Leaderboard上的自动创建的。数据集包含64个配置，每个配置对应一个评估任务。
数据集结构
数据集由1次运行创建，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"分割始终指向最新的结果。
结果配置
一个额外的配置"results"存储所有运行的聚合结果，用于计算和显示在Open LLM Leaderboard上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_starmpcc__Asclepius-Llama2-13B_public", "harness_winogrande_5", split="train")
最新结果
以下是2023-11-19T12:18:05.781996的最新结果：
python { "all": { "acc": 0.5201519972088248, "acc_stderr": 0.034051581317112195, "acc_norm": 0.5290222877161421, "acc_norm_stderr": 0.03495991688232667, "mc1": 0.2827417380660955, "mc1_stderr": 0.01576477083677731, "mc2": 0.4075956796231733, "mc2_stderr": 0.015612342660639225, "em": 0.022546140939597316, "em_stderr": 0.0015202810875087338, "f1": 0.12420616610738253, "f1_stderr": 0.002172993439883863 }, "harness|arc:challenge|25": { "acc": 0.5324232081911263, "acc_stderr": 0.014580637569995421, "acc_norm": 0.5588737201365188, "acc_norm_stderr": 0.014509747749064664 }, "harness|hellaswag|10": { "acc": 0.6115315674168492, "acc_stderr": 0.004864058877626275, "acc_norm": 0.7965544712208723, "acc_norm_stderr": 0.004017383866405767 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04292596718256981, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04292596718256981 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5197368421052632, "acc_stderr": 0.04065771002562605, "acc_norm": 0.5197368421052632, "acc_norm_stderr": 0.04065771002562605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5962264150943396, "acc_stderr": 0.03019761160019795, "acc_norm": 0.5962264150943396, "acc_norm_stderr": 0.03019761160019795 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5763888888888888, "acc_stderr": 0.0413212501972337, "acc_norm": 0.5763888888888888, "acc_norm_stderr": 0.0413212501972337 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "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": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5260115606936416, "acc_stderr": 0.038073017265045125, "acc_norm": 0.5260115606936416, "acc_norm_stderr": 0.038073017265045125 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993179, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.04336432707993179 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4297872340425532, "acc_stderr": 0.03236214467715564, "acc_norm": 0.4297872340425532, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3439153439153439, "acc_stderr": 0.024464426625596433, "acc_norm": 0.3439153439153439, "acc_norm_stderr": 0.024464426625596433 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.04793724854411018, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411018 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6096774193548387, "acc_stderr": 0.027751256636969583, "acc_norm": 0.6096774193548387, "acc_norm_stderr": 0.027751256636969583 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.03445487686264715, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.03445487686264715 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6545454545454545, "acc_stderr": 0.03713158067481913, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.03713158067481913 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6868686868686869, "acc_stderr": 0.033042050878136525, "acc_norm": 0.6868686868686869, "acc_norm_stderr": 0.033042050878136525 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7668393782383419, "acc_stderr": 0.03051611137147601, "acc_norm": 0.7668393782383419, "acc_norm_stderr": 0.03051611137147601 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5307692307692308, "acc_stderr": 0.025302958890850154, "acc_norm": 0.5307692307692308, "acc_norm_stderr": 0.0253029588908501
