open-llm-leaderboard-old/details_senseable__moe-x33
收藏数据集概述
该数据集是在评估模型senseable/moe-x33在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。
数据集结构
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"分片总是指向最新的结果。
结果配置
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_senseable__moe-x33", "harness_winogrande_5", split="train")
最新结果
这些是最新结果（来自2024-01-15T23:19:04.817000运行）的示例： python { "all": { "acc": 0.24904589888958967, "acc_stderr": 0.030588499686851015, "acc_norm": 0.24981435362475682, "acc_norm_stderr": 0.03140336687195182, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.5114318988938285, "mc2_stderr": 0.016424037479575066 }, "harness|arc:challenge|25": { "acc": 0.21160409556313994, "acc_stderr": 0.01193591635863285, "acc_norm": 0.2619453924914676, "acc_norm_stderr": 0.012849054826858117 }, "harness|hellaswag|10": { "acc": 0.25761800438159727, "acc_stderr": 0.004364287353415448, "acc_norm": 0.264389563831906, "acc_norm_stderr": 0.004401063265803209 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2222222222222222, "acc_stderr": 0.035914440841969694, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.035914440841969694 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2236842105263158, "acc_stderr": 0.03391160934343602, "acc_norm": 0.2236842105263158, "acc_norm_stderr": 0.03391160934343602 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2528301886792453, "acc_stderr": 0.026749899771241235, "acc_norm": 0.2528301886792453, "acc_norm_stderr": 0.026749899771241235 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2170212765957447, "acc_stderr": 0.02694748312149622, "acc_norm": 0.2170212765957447, "acc_norm_stderr": 0.02694748312149622 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "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": 0.1984126984126984, "acc_stderr": 0.02053948126188688, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.02053948126188688 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.040061680838488746, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.040061680838488746 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1870967741935484, "acc_stderr": 0.02218571009225226, "acc_norm": 0.1870967741935484, "acc_norm_stderr": 0.02218571009225226 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1724137931034483, "acc_stderr": 0.02657767218303658, "acc_norm": 0.1724137931034483, "acc_norm_stderr": 0.02657767218303658 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036843, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3484848484848485, "acc_stderr": 0.033948539651564025, "acc_norm": 0.3484848484848485, "acc_norm_stderr": 0.033948539651564025 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35233160621761656, "acc_stderr": 0.034474782864143586, "acc_norm": 0.35233160621761656, "acc_norm_stderr": 0.034474782864143586 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.32564102564102565, "acc_stderr": 0.02375966576741229, "acc_norm": 0.32564102564102565, "acc_norm_stderr": 0.02375966576741229 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857655075, "acc_norm": 0.2111111111111111, "acc_norm_stderr": 0.024882116857655075 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3319327731092437, "acc_stderr": 0.0305886
