open-llm-leaderboard-old/details_abacusai__Liberated-Qwen1.5-72B
收藏数据集概述
数据集简介
该数据集是在评估模型abacusai/Liberated-Qwen1.5-72B在Open LLM Leaderboard上的自动创建的。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3次运行结果组成，每次运行的详细结果可以在每个配置中找到，以运行时间戳命名的特定分割形式存储。"train"分割始终指向最新的结果。
数据加载示例
以下是加载数据集详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_abacusai__Liberated-Qwen1.5-72B", "harness_winogrande_5", split="train")
最新结果
以下是最新结果的摘要： python { "all": { "acc": 0.7670290163222704, "acc_stderr": 0.02798437757890357, "acc_norm": 0.7701894146587901, "acc_norm_stderr": 0.02852511736756399, "mc1": 0.42717258261933905, "mc1_stderr": 0.01731683441096393, "mc2": 0.6056200701194389, "mc2_stderr": 0.014774813643771919 }, "harness|arc:challenge|25": { "acc": 0.6271331058020477, "acc_stderr": 0.01413117676013117, "acc_norm": 0.6569965870307167, "acc_norm_stderr": 0.013872423223718164 }, "harness|hellaswag|10": { "acc": 0.6560446126269668, "acc_stderr": 0.0047405557821421675, "acc_norm": 0.8458474407488548, "acc_norm_stderr": 0.003603569528678413 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7333333333333333, "acc_stderr": 0.038201699145179055, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.02750868953354992, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.02750868953354992 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.82, "acc_stderr": 0.038612291966536955, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8377358490566038, "acc_stderr": 0.02269148287203535, "acc_norm": 0.8377358490566038, "acc_norm_stderr": 0.02269148287203535 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9236111111111112, "acc_stderr": 0.022212203938345904, "acc_norm": 0.9236111111111112, "acc_norm_stderr": 0.022212203938345904 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.8034682080924855, "acc_stderr": 0.03029957466478814, "acc_norm": 0.8034682080924855, "acc_norm_stderr": 0.03029957466478814 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5196078431372549, "acc_stderr": 0.04971358884367406, "acc_norm": 0.5196078431372549, "acc_norm_stderr": 0.04971358884367406 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8, "acc_stderr": 0.026148818018424502, "acc_norm": 0.8, "acc_norm_stderr": 0.026148818018424502 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594963, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6931216931216931, "acc_stderr": 0.023752928712112122, "acc_norm": 0.6931216931216931, "acc_norm_stderr": 0.023752928712112122 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8838709677419355, "acc_stderr": 0.018225757949432306, "acc_norm": 0.8838709677419355, "acc_norm_stderr": 0.018225757949432306 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6403940886699507, "acc_stderr": 0.03376458246509566, "acc_norm": 0.6403940886699507, "acc_norm_stderr": 0.03376458246509566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.03942772444036625, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.026024657651656187, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.026024657651656187 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.018263105420199512, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.018263105420199512 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9896373056994818, "acc_stderr": 0.007308424386792194, "acc_norm": 0.9896373056994818, "acc_norm_stderr": 0.007308424386792194 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8025641025641026, "acc_stderr": 0.020182646968674847, "acc_norm": 0.8025641025641026, "acc_norm_stderr": 0.020182646968674847 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5, "acc_stderr": 0.030485538042484616, "acc_norm": 0.5, "acc_norm_stderr": 0.030485538042484616 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8319327731092437, "acc_stderr": 0.024289102115692275, "acc_norm": 0.8319327731092437, "acc_norm_stderr": 0.024289102115692275 },
