open-llm-leaderboard-old/details_NLPinas__yi-bagel-2x34b-moe
收藏数据集概述
数据集简介
该数据集是在评估模型 NLPinas/yi-bagel-2x34b-moe 在 Open LLM Leaderboard 上的运行过程中自动创建的。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_NLPinas__yi-bagel-2x34b-moe", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-11T13:51:44.686657 运行的最新结果：
python { "all": { "acc": 0.7615183276503468, "acc_stderr": 0.02832471118128543, "acc_norm": 0.7668016554766149, "acc_norm_stderr": 0.028849292688075817, "mc1": 0.5642594859241126, "mc1_stderr": 0.01735834539886313, "mc2": 0.7142422056307771, "mc2_stderr": 0.014238871538897193 }, "harness|arc:challenge|25": { "acc": 0.6962457337883959, "acc_stderr": 0.013438909184778762, "acc_norm": 0.726962457337884, "acc_norm_stderr": 0.013019332762635748 }, "harness|hellaswag|10": { "acc": 0.6620195180242979, "acc_stderr": 0.0047205513235471265, "acc_norm": 0.8544114718183629, "acc_norm_stderr": 0.0035197241633108875 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7481481481481481, "acc_stderr": 0.03749850709174021, "acc_norm": 0.7481481481481481, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.027508689533549912, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.027508689533549912 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.025545239210256917, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.025545239210256917 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5784313725490197, "acc_stderr": 0.04913595201274503, "acc_norm": 0.5784313725490197, "acc_norm_stderr": 0.04913595201274503 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.027501752944412417, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.027501752944412417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5877192982456141, "acc_stderr": 0.04630653203366596, "acc_norm": 0.5877192982456141, "acc_norm_stderr": 0.04630653203366596 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.037245636197746304, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.037245636197746304 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.716931216931217, "acc_stderr": 0.023201392938194974, "acc_norm": 0.716931216931217, "acc_norm_stderr": 0.023201392938194974 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04360314860077459, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9032258064516129, "acc_stderr": 0.016818943416345197, "acc_norm": 0.9032258064516129, "acc_norm_stderr": 0.016818943416345197 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6403940886699507, "acc_stderr": 0.03376458246509567, "acc_norm": 0.6403940886699507, "acc_norm_stderr": 0.03376458246509567 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.8, "acc_stderr": 0.04020151261036846, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865394, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527033, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527033 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8179487179487179, "acc_stderr": 0.0195652367829309, "acc_norm": 0.8179487179487179, "acc_norm_stderr": 0.0195652367829309 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4703703703703704, "acc_stderr": 0.030431963547936584, "acc_norm": 0.4703703703703704,
