open-llm-leaderboard-old/details_rishiraj__cutie
收藏数据集概述
该数据集是在评估模型rishiraj/cutie在Open LLM Leaderboard上的运行过程中自动创建的。数据集包含63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。
加载数据
可以通过以下代码加载特定运行的详细信息：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_rishiraj__cutie", "harness_winogrande_5", split="train")
最新结果
以下是最新结果（来自2023-12-16T15:05:22.803589运行）的摘要：
python { "all": { "acc": 0.2422854544334347, "acc_stderr": 0.030350774274944006, "acc_norm": 0.24263810423714618, "acc_norm_stderr": 0.03115733731927302, "mc1": 0.23255813953488372, "mc1_stderr": 0.014789157531080508, "mc2": 0.48417001401061344, "mc2_stderr": 0.016564877497923215 }, "harness|arc:challenge|25": { "acc": 0.22098976109215018, "acc_stderr": 0.012124929206818258, "acc_norm": 0.2696245733788396, "acc_norm_stderr": 0.01296804068686916 }, "harness|hellaswag|10": { "acc": 0.2561242780322645, "acc_stderr": 0.004355992090030987, "acc_norm": 0.27016530571599284, "acc_norm_stderr": 0.00443137554991136 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03591444084196969, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03591444084196969 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.14473684210526316, "acc_stderr": 0.0286319518459304, "acc_norm": 0.14473684210526316, "acc_norm_stderr": 0.0286319518459304 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2490566037735849, "acc_stderr": 0.02661648298050171, "acc_norm": 0.2490566037735849, "acc_norm_stderr": 0.02661648298050171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.03716177437566015, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.03716177437566015 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680814, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179325, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179325 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2297872340425532, "acc_stderr": 0.027501752944412428, "acc_norm": 0.2297872340425532, "acc_norm_stderr": 0.027501752944412428 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489361, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489361 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2275132275132275, "acc_stderr": 0.021591269407823795, "acc_norm": 0.2275132275132275, "acc_norm_stderr": 0.021591269407823795 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333338, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333338 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23548387096774193, "acc_stderr": 0.02413763242933772, "acc_norm": 0.23548387096774193, "acc_norm_stderr": 0.02413763242933772 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.19704433497536947, "acc_stderr": 0.027986724666736212, "acc_norm": 0.19704433497536947, "acc_norm_stderr": 0.027986724666736212 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.0347769116216366, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2222222222222222, "acc_stderr": 0.02962022787479049, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02962022787479049 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.20207253886010362, "acc_stderr": 0.02897908979429673, "acc_norm": 0.20207253886010362, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.19230769230769232, "acc_stderr": 0.019982347208637292, "acc_norm": 0.19230769230769232, "acc_norm_stderr": 0.019982347208637292 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945277, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945277 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.193277310924369
