open-llm-leaderboard/details_nicholasKluge__Aira-Instruct-1B5
收藏数据集概述
数据集简介
该数据集是在评估模型 nicholasKluge/Aira-Instruct-1B5 在 Open LLM Leaderboard 上的自动创建的。数据集包含61个配置，每个配置对应一个评估任务。
数据集结构
数据集由2次运行结果组成，每个运行结果可以在每个配置中作为一个特定的分割找到，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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nicholasKluge__Aira-Instruct-1B5", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.26661052193576085, "acc_stderr": 0.03205800992365353, "acc_norm": 0.26841070974417724, "acc_norm_stderr": 0.03207045668897672, "mc1": 0.23011015911872704, "mc1_stderr": 0.014734557959807763, "mc2": 0.401147792785823, "mc2_stderr": 0.01487516040985077 }, "harness|arc:challenge|25": { "acc": 0.25, "acc_stderr": 0.012653835621466646, "acc_norm": 0.2883959044368601, "acc_norm_stderr": 0.013238394422428162 }, "harness|hellaswag|10": { "acc": 0.35829516032662817, "acc_stderr": 0.004785195049889159, "acc_norm": 0.4261103365863374, "acc_norm_stderr": 0.004934995402995939 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3169811320754717, "acc_stderr": 0.028637235639800942, "acc_norm": 0.3169811320754717, "acc_norm_stderr": 0.028637235639800942 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.037161774375660164, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.037161774375660164 }, "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": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.32947976878612717, "acc_stderr": 0.03583901754736411, "acc_norm": 0.32947976878612717, "acc_norm_stderr": 0.03583901754736411 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.040233822736177476, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.040233822736177476 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.18723404255319148, "acc_stderr": 0.02550158834188361, "acc_norm": 0.18723404255319148, "acc_norm_stderr": 0.02550158834188361 }, "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": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.022789673145776575, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.022789673145776575 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.04040610178208841, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04040610178208841 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25483870967741934, "acc_stderr": 0.024790118459332208, "acc_norm": 0.25483870967741934, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23636363636363636, "acc_stderr": 0.03317505930009179, "acc_norm": 0.23636363636363636, "acc_norm_stderr": 0.03317505930009179 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2676767676767677, "acc_stderr": 0.03154449888270286, "acc_norm": 0.2676767676767677, "acc_norm_stderr": 0.03154449888270286 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27461139896373055, "acc_stderr": 0.03221024508041153, "acc_norm": 0.27461139896373055, "acc_norm_stderr": 0.03221024508041153 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2358974358974359, "acc_stderr": 0.02152596540740872, "acc_norm": 0.2358974358974359, "acc_norm_stderr": 0.02152596540740872 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.026067159222275805, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.02
