open-llm-leaderboard-old/details_Qwen__Qwen1.5-72B-Chat
收藏数据集概述
数据集摘要
该数据集是在模型 Qwen/Qwen1.5-72B-Chat 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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 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。
加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Qwen__Qwen1.5-72B-Chat", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-03-08T06:44:33.909194 的运行： python { "all": { "acc": 0.7618755724472454, "acc_stderr": 0.02815008534788608, "acc_norm": 0.7744344937789645, "acc_norm_stderr": 0.028696138532381087, "mc1": 0.44430844553243576, "mc1_stderr": 0.017394586250743173, "mc2": 0.6389810525358077, "mc2_stderr": 0.015760859004207876 }, "harness|arc:challenge|25": { "acc": 0.6535836177474402, "acc_stderr": 0.013905011180063225, "acc_norm": 0.6851535836177475, "acc_norm_stderr": 0.013572657703084948 }, "harness|hellaswag|10": { "acc": 0.6837283409679347, "acc_stderr": 0.004640699483543309, "acc_norm": 0.8641704839673372, "acc_norm_stderr": 0.0034190724807353617 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7333333333333333, "acc_stderr": 0.038201699145179055, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.038201699145179055 }, "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": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.024079995130062225, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.024079995130062225 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.52, "acc_stderr": 0.05021167315686779, "acc_norm": 0.52, "acc_norm_stderr": 0.05021167315686779 }, "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": 0.5882352941176471, "acc_stderr": 0.048971049527263666, "acc_norm": 0.5882352941176471, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7957446808510639, "acc_stderr": 0.026355158413349417, "acc_norm": 0.7957446808510639, "acc_norm_stderr": 0.026355158413349417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594964, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594964 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.716931216931217, "acc_stderr": 0.023201392938194978, "acc_norm": 0.716931216931217, "acc_norm_stderr": 0.023201392938194978 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5873015873015873, "acc_stderr": 0.04403438954768177, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.04403438954768177 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.01706640371965726, "acc_norm": 0.9, "acc_norm_stderr": 0.01706640371965726 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6798029556650246, "acc_stderr": 0.032826493853041504, "acc_norm": 0.6798029556650246, "acc_norm_stderr": 0.032826493853041504 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865387, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865387 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9242424242424242, "acc_stderr": 0.018852670234993093, "acc_norm": 0.9242424242424242, "acc_norm_stderr": 0.018852670234993093 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084334, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084334 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8205128205128205, "acc_stderr": 0.019457390787681793, "acc_norm": 0.8205128205128205, "acc_norm_stderr": 0.019457390787681793 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5259259259259259, "acc_stderr": 0.03044452852881074, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.03044452852881074 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.865546218487395, "acc_stderr": 0.022159373072744442, "acc_norm": 0.865546218487395, "acc_norm_stderr": 0.02215937307274444
