open-llm-leaderboard-old/details_TencentARC__LLaMA-Pro-8B
收藏数据集概述
数据集简介
该数据集是在评估模型TencentARC/LLaMA-Pro-8B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2次运行结果组成，每个运行结果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_TencentARC__LLaMA-Pro-8B", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-05T15:06:36.564331运行的最新结果：
python { "all": { "acc": 0.4764197375438744, "acc_stderr": 0.034552955932007474, "acc_norm": 0.48115021504516975, "acc_norm_stderr": 0.035323141272306104, "mc1": 0.24112607099143207, "mc1_stderr": 0.014974827279752329, "mc2": 0.38859489598867014, "mc2_stderr": 0.013678861072074354 }, "harness|arc:challenge|25": { "acc": 0.49146757679180886, "acc_stderr": 0.01460926316563219, "acc_norm": 0.537542662116041, "acc_norm_stderr": 0.014570144495075578 }, "harness|hellaswag|10": { "acc": 0.578868751244772, "acc_stderr": 0.004927314729433552, "acc_norm": 0.7791276638119896, "acc_norm_stderr": 0.0041398679751162995 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04063302731486671, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04063302731486671 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.49433962264150944, "acc_stderr": 0.030770900763851302, "acc_norm": 0.49433962264150944, "acc_norm_stderr": 0.030770900763851302 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4583333333333333, "acc_stderr": 0.04166666666666665, "acc_norm": 0.4583333333333333, "acc_norm_stderr": 0.04166666666666665 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.42196531791907516, "acc_stderr": 0.0376574669386515, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237655, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.63, "acc_stderr": 0.04852365870939098, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939098 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.03227834510146268, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489364, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489364 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3201058201058201, "acc_stderr": 0.0240268463928735, "acc_norm": 0.3201058201058201, "acc_norm_stderr": 0.0240268463928735 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.03852273364924316, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.03852273364924316 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5516129032258065, "acc_stderr": 0.028292056830112728, "acc_norm": 0.5516129032258065, "acc_norm_stderr": 0.028292056830112728 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.03413963805906235, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.03413963805906235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5878787878787879, "acc_stderr": 0.03843566993588717, "acc_norm": 0.5878787878787879, "acc_norm_stderr": 0.03843566993588717 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5151515151515151, "acc_stderr": 0.0356071651653106, "acc_norm": 0.5151515151515151, "acc_norm_stderr": 0.0356071651653106 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6839378238341969, "acc_stderr": 0.033553973696861736, "acc_norm": 0.6839378238341969, "acc_norm_stderr": 0.033553973696861736 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.45897435897435895, "acc_stderr": 0.025265525491284295, "acc_norm": 0.45897435897435895, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945284, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.0274200
