open-llm-leaderboard-old/details_Weyaxi__a
收藏数据集概述
数据集简介
该数据集是在对模型 Weyaxi/Einstein-v6.1-LLama3-8B-Instruct-Ties 进行评估时自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集从1次运行中创建，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_Weyaxi__Einstein-v6.1-LLama3-8B-Instruct-Ties", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-10T02:21:43.730137 运行的最新结果：
python { "all": { "acc": 0.5646393625024938, "acc_stderr": 0.0332095796161226, "acc_norm": 0.5738208212143998, "acc_norm_stderr": 0.03412746423842213, "mc1": 0.2974296205630355, "mc1_stderr": 0.016002651487361002, "mc2": 0.4454908751064698, "mc2_stderr": 0.014845534784458896 }, "harness|arc:challenge|25": { "acc": 0.5955631399317406, "acc_stderr": 0.014342036483436177, "acc_norm": 0.6348122866894198, "acc_norm_stderr": 0.014070265519268802 }, "harness|hellaswag|10": { "acc": 0.6676956781517626, "acc_stderr": 0.004700767741735561, "acc_norm": 0.8648675562636925, "acc_norm_stderr": 0.003411663071651109 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6118421052631579, "acc_stderr": 0.03965842097512744, "acc_norm": 0.6118421052631579, "acc_norm_stderr": 0.03965842097512744 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5660377358490566, "acc_stderr": 0.030503292013342592, "acc_norm": 0.5660377358490566, "acc_norm_stderr": 0.030503292013342592 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.03981240543717861, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.03981240543717861 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5491329479768786, "acc_stderr": 0.037940126746970296, "acc_norm": 0.5491329479768786, "acc_norm_stderr": 0.037940126746970296 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383888, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383888 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695238, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695238 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5106382978723404, "acc_stderr": 0.03267862331014063, "acc_norm": 0.5106382978723404, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.39473684210526316, "acc_stderr": 0.045981880578165414, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3783068783068783, "acc_stderr": 0.024976954053155243, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155243 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7129032258064516, "acc_stderr": 0.025736542745594525, "acc_norm": 0.7129032258064516, "acc_norm_stderr": 0.025736542745594525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.034139638059062345, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8238341968911918, "acc_stderr": 0.027493504244548057, "acc_norm": 0.8238341968911918, "acc_norm_stderr": 0.027493504244548057 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5102564102564102, "acc_stderr": 0.025345672221942374, "acc_norm": 0.5102564102564102, "acc_norm_stderr": 0.025345672221942374 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666,
