open-llm-leaderboard-old/details_u-chom__preded-title-amazongoogle-abtbuy
收藏数据集概述
该数据集是在模型 u-chom/preded-title-amazongoogle-abtbuy 的评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 61 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。
- 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 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_u-chom__preded-title-amazongoogle-abtbuy", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-10-08T23:27:01.372351 运行的最新结果：
python { "all": { "acc": 0.38488561065128146, "acc_stderr": 0.03460083230388379, "acc_norm": 0.38889827098513907, "acc_norm_stderr": 0.034587970268505575, "mc1": 0.2692778457772338, "mc1_stderr": 0.015528566637087281, "mc2": 0.4164930056701617, "mc2_stderr": 0.013916947335276144 }, "harness|arc:challenge|25": { "acc": 0.4667235494880546, "acc_stderr": 0.014578995859605808, "acc_norm": 0.5093856655290102, "acc_norm_stderr": 0.014608816322065 }, "harness|hellaswag|10": { "acc": 0.5873332005576578, "acc_stderr": 0.00491307684443376, "acc_norm": 0.7814180442143, "acc_norm_stderr": 0.004124396294659584 }, "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": 0.4222222222222222, "acc_stderr": 0.042667634040995814, "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.042667634040995814 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.34868421052631576, "acc_stderr": 0.038781398887976104, "acc_norm": 0.34868421052631576, "acc_norm_stderr": 0.038781398887976104 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3584905660377358, "acc_stderr": 0.02951470358398177, "acc_norm": 0.3584905660377358, "acc_norm_stderr": 0.02951470358398177 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04076663253918567, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.0356760379963917, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.0356760379963917 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617747, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617747 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3829787234042553, "acc_stderr": 0.03177821250236922, "acc_norm": 0.3829787234042553, "acc_norm_stderr": 0.03177821250236922 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481425, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481425 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3586206896551724, "acc_stderr": 0.03996629574876719, "acc_norm": 0.3586206896551724, "acc_norm_stderr": 0.03996629574876719 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.21164021164021163, "acc_stderr": 0.021037331505262883, "acc_norm": 0.21164021164021163, "acc_norm_stderr": 0.021037331505262883 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.35161290322580646, "acc_stderr": 0.027162537826948458, "acc_norm": 0.35161290322580646, "acc_norm_stderr": 0.027162537826948458 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2413793103448276, "acc_stderr": 0.030108330718011625, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.030108330718011625 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4484848484848485, "acc_stderr": 0.038835659779569286, "acc_norm": 0.4484848484848485, "acc_norm_stderr": 0.038835659779569286 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.40404040404040403, "acc_stderr": 0.03496130972056127, "acc_norm": 0.40404040404040403, "acc_norm_stderr": 0.03496130972056127 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5492227979274611, "acc_stderr": 0.03590910952235524, "acc_norm": 0.5492227979274611, "acc_norm_stderr": 0.03590910952235524 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.32564102564102565, "acc_stderr": 0.02375966576741229, "acc_norm": 0.32564102564102565, "acc_norm_stderr": 0.02375966576741229 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21851851851851853, "acc_stderr": 0.02519575225182379, "acc
