open-llm-leaderboard-old/details_amu__spin-phi2-2
收藏数据集概述
数据集简介
该数据集是在对模型 amu/spin-phi2-2 进行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 63 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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片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_amu__spin-phi2-2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-03T09:43:31.164221 运行的最新结果：
python { "all": { "acc": 0.5676543744455648, "acc_stderr": 0.033757658685339524, "acc_norm": 0.5697190789027621, "acc_norm_stderr": 0.03444152447795738, "mc1": 0.33659730722154224, "mc1_stderr": 0.016542412809494887, "mc2": 0.46398565870109565, "mc2_stderr": 0.015193614430666786 }, "harness|arc:challenge|25": { "acc": 0.5972696245733788, "acc_stderr": 0.014332236306790147, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068283 }, "harness|hellaswag|10": { "acc": 0.5680143397729536, "acc_stderr": 0.004943400892881052, "acc_norm": 0.7579167496514638, "acc_norm_stderr": 0.004274690143629144 }, "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": 0.45925925925925926, "acc_stderr": 0.04304979692464242, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5657894736842105, "acc_stderr": 0.04033565667848319, "acc_norm": 0.5657894736842105, "acc_norm_stderr": 0.04033565667848319 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5849056603773585, "acc_stderr": 0.03032594578928611, "acc_norm": 0.5849056603773585, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6458333333333334, "acc_stderr": 0.039994111357535424, "acc_norm": 0.6458333333333334, "acc_norm_stderr": 0.039994111357535424 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "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": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5895953757225434, "acc_stderr": 0.03750757044895537, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.047240073523838876, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.047240073523838876 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768077, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768077 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.502127659574468, "acc_stderr": 0.03268572658667493, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.03268572658667493 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.39473684210526316, "acc_stderr": 0.045981880578165414, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.041641887201693775, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.041641887201693775 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.025446365634406793, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406793 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6709677419354839, "acc_stderr": 0.02672949906834996, "acc_norm": 0.6709677419354839, "acc_norm_stderr": 0.02672949906834996 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6, "acc_stderr": 0.038254602783800246, "acc_norm": 0.6, "acc_norm_stderr": 0.038254602783800246 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7171717171717171, "acc_stderr": 0.03208779558786751, "acc_norm": 0.7171717171717171, "acc_norm_stderr": 0.03208779558786751 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.02977866303775295, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.02977866303775295 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5358974358974359, "acc_stderr": 0.025285585990017845, "acc_norm": 0.5358974358974359, "acc_norm_stderr": 0.025285585990017845 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.027840811495871923, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.027840811495871923 }, "harness|hendrycksTest
