open-llm-leaderboard-old/details_davidkim205__Rhea-72b-v0.2
收藏数据集概述
数据集简介
该数据集是在评估模型 davidkim205/Rhea-72b-v0.2 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 1 次运行创建，每个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_davidkim205__Rhea-72b-v0.2", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.7806390565791278, "acc_stderr": 0.027711233842223508, "acc_norm": 0.7818850286033018, "acc_norm_stderr": 0.02826655133417084, "mc1": 0.6487148102815178, "mc1_stderr": 0.0167113581635444, "mc2": 0.7450059289802828, "mc2_stderr": 0.014438907380750043 }, "harness|arc:challenge|25": { "acc": 0.7568259385665529, "acc_stderr": 0.012536554144587087, "acc_norm": 0.7755972696245734, "acc_norm_stderr": 0.01219140493860383 }, "harness|hellaswag|10": { "acc": 0.7667795259908384, "acc_stderr": 0.00422017156927332, "acc_norm": 0.9083847839075881, "acc_norm_stderr": 0.0028789243105734504 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.725925925925926, "acc_stderr": 0.038532548365520045, "acc_norm": 0.725925925925926, "acc_norm_stderr": 0.038532548365520045 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.040201512610368445, "acc_norm": 0.8, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8452830188679246, "acc_stderr": 0.022257075558791282, "acc_norm": 0.8452830188679246, "acc_norm_stderr": 0.022257075558791282 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9375, "acc_stderr": 0.02024219611347799, "acc_norm": 0.9375, "acc_norm_stderr": 0.02024219611347799 }, "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": 0.65, "acc_stderr": 0.04793724854411019, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7745664739884393, "acc_stderr": 0.031862098516411454, "acc_norm": 0.7745664739884393, "acc_norm_stderr": 0.031862098516411454 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.049665709039785295, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.049665709039785295 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.85, "acc_stderr": 0.03588702812826371, "acc_norm": 0.85, "acc_norm_stderr": 0.03588702812826371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8212765957446808, "acc_stderr": 0.02504537327205098, "acc_norm": 0.8212765957446808, "acc_norm_stderr": 0.02504537327205098 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.045981880578165414, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7862068965517242, "acc_stderr": 0.034165204477475494, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.034165204477475494 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7222222222222222, "acc_stderr": 0.02306818884826113, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.02306818884826113 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5317460317460317, "acc_stderr": 0.04463112720677172, "acc_norm": 0.5317460317460317, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8806451612903226, "acc_stderr": 0.018443411325315413, "acc_norm": 0.8806451612903226, "acc_norm_stderr": 0.018443411325315413 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6748768472906403, "acc_stderr": 0.032957975663112704, "acc_norm": 0.6748768472906403, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.82, "acc_stderr": 0.038612291966536934, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781675, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781675 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9343434343434344, "acc_stderr": 0.01764652667723332, "acc_norm": 0.9343434343434344, "acc_norm_stderr": 0.01764652667723332 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084315, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084315 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.019880165406588768, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.019880165406588768 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4925925925925926, "acc_stderr": 0.030482192395191506, "acc_norm": 0.4925925925925926, "acc_norm_stderr": 0.030482192395191506 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.861
