open-llm-leaderboard-old/details_DrNicefellow__Mistral-8-from-Mixtral-8x7B-v0.1
收藏数据集概述
数据集摘要
该数据集是在评估模型 DrNicefellow/Mistral-8-from-Mixtral-8x7B-v0.1 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 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_DrNicefellow__Mistral-8-from-Mixtral-8x7B-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自2024-04-15T19:49:47.219398 的摘要：
python { "all": { "acc": 0.25245829185158625, "acc_stderr": 0.030639623336771737, "acc_norm": 0.25365188950299444, "acc_norm_stderr": 0.03145980805499287, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456416, "mc2": 0.48121078410229307, "mc2_stderr": 0.016149169815746562 }, "harness|arc:challenge|25": { "acc": 0.22098976109215018, "acc_stderr": 0.012124929206818258, "acc_norm": 0.2901023890784983, "acc_norm_stderr": 0.01326157367752077 }, "harness|hellaswag|10": { "acc": 0.25761800438159727, "acc_stderr": 0.004364287353415458, "acc_norm": 0.2622983469428401, "acc_norm_stderr": 0.004389849907040309 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.25925925925925924, "acc_stderr": 0.03785714465066652, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.03785714465066652 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.20394736842105263, "acc_stderr": 0.0327900040631005, "acc_norm": 0.20394736842105263, "acc_norm_stderr": 0.0327900040631005 }, "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": 0.2490566037735849, "acc_stderr": 0.02661648298050171, "acc_norm": 0.2490566037735849, "acc_norm_stderr": 0.02661648298050171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.17341040462427745, "acc_stderr": 0.02886810787497064, "acc_norm": 0.17341040462427745, "acc_norm_stderr": 0.02886810787497064 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171453, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171453 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.2, "acc_stderr": 0.04020151261036843, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2765957446808511, "acc_stderr": 0.02924188386962883, "acc_norm": 0.2765957446808511, "acc_norm_stderr": 0.02924188386962883 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924811, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2275132275132275, "acc_stderr": 0.021591269407823778, "acc_norm": 0.2275132275132275, "acc_norm_stderr": 0.021591269407823778 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.03932537680392871, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392871 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.16, "acc_stderr": 0.03684529491774708, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3064516129032258, "acc_stderr": 0.026226485652553873, "acc_norm": 0.3064516129032258, "acc_norm_stderr": 0.026226485652553873 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2660098522167488, "acc_stderr": 0.031089826002937523, "acc_norm": 0.2660098522167488, "acc_norm_stderr": 0.031089826002937523 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.02937661648494563, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.02937661648494563 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35233160621761656, "acc_stderr": 0.03447478286414359, "acc_norm": 0.35233160621761656, "acc_norm_stderr": 0.03447478286414359 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23076923076923078, "acc_stderr": 0.021362027725222728, "acc_norm": 0.23076923076923078, "acc_norm_stderr": 0.021362027725222728 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.28888888888888886, "acc_stderr": 0.027634907
