open-llm-leaderboard-old/details_Riiid__sheep-duck-llama-2
收藏数据集概述
数据集简介
该数据集是在评估模型Riiid/sheep-duck-llama-2在Open LLM Leaderboard上的运行过程中自动创建的。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。
额外配置
一个额外的配置"results"存储了所有运行的聚合结果，用于计算和显示在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_Riiid__sheep-duck-llama-2", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是2023-09-19T02:41:38.567550运行的最新结果： python { "all": { "acc": 0.7074787526637408, "acc_stderr": 0.030842770794867788, "acc_norm": 0.7112713043078007, "acc_norm_stderr": 0.03081173438001915, "mc1": 0.4663402692778458, "mc1_stderr": 0.017463793867168103, "mc2": 0.6379733867215786, "mc2_stderr": 0.014804542452694204 }, "harness|arc:challenge|25": { "acc": 0.6851535836177475, "acc_stderr": 0.013572657703084948, "acc_norm": 0.7226962457337884, "acc_norm_stderr": 0.013082095839059376 }, "harness|hellaswag|10": { "acc": 0.6915952997410875, "acc_stderr": 0.0046089078729577085, "acc_norm": 0.8778131846245768, "acc_norm_stderr": 0.003268321260913631 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8026315789473685, "acc_stderr": 0.03238981601699397, "acc_norm": 0.8026315789473685, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.04408440022768081, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7471698113207547, "acc_stderr": 0.02674989977124121, "acc_norm": 0.7471698113207547, "acc_norm_stderr": 0.02674989977124121 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.03216600808802267, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.03216600808802267 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6851063829787234, "acc_stderr": 0.03036358219723817, "acc_norm": 0.6851063829787234, "acc_norm_stderr": 0.03036358219723817 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6413793103448275, "acc_stderr": 0.03996629574876719, "acc_norm": 0.6413793103448275, "acc_norm_stderr": 0.03996629574876719 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4708994708994709, "acc_stderr": 0.02570765861415495, "acc_norm": 0.4708994708994709, "acc_norm_stderr": 0.02570765861415495 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8225806451612904, "acc_stderr": 0.021732540689329286, "acc_norm": 0.8225806451612904, "acc_norm_stderr": 0.021732540689329286 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5665024630541872, "acc_stderr": 0.034867317274198714, "acc_norm": 0.5665024630541872, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781678, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781678 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.022390787638216763, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.022390787638216763 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240528, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7102564102564103, "acc_stderr": 0.023000628243687968, "acc_norm": 0.7102564102564103, "acc_norm_stderr": 0.023000628243687968 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.0284934650910286, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.0284934650910
