open-llm-leaderboard-old/details_arvindanand__ValidateAI-33B-slerp
收藏数据集概述
该数据集是在对模型 arvindanand/ValidateAI-33B-slerp 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集是从 1 次运行中创建的，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_arvindanand__ValidateAI-33B-slerp", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-10T12:15:46.754568 运行的最新结果：
python { "all": { "acc": 0.39295856328198214, "acc_stderr": 0.03406418772246501, "acc_norm": 0.39843889983227476, "acc_norm_stderr": 0.03499234221764259, "mc1": 0.2582619339045288, "mc1_stderr": 0.015321821688476196, "mc2": 0.45660677334622446, "mc2_stderr": 0.01690873305006139 }, "harness|arc:challenge|25": { "acc": 0.2781569965870307, "acc_stderr": 0.013094469919538805, "acc_norm": 0.31143344709897613, "acc_norm_stderr": 0.013532472099850952 }, "harness|hellaswag|10": { "acc": 0.3147779326827325, "acc_stderr": 0.0046347821561286105, "acc_norm": 0.36825333598884685, "acc_norm_stderr": 0.00481344861540443 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.362962962962963, "acc_stderr": 0.04153948404742398, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4276315789473684, "acc_stderr": 0.04026097083296559, "acc_norm": 0.4276315789473684, "acc_norm_stderr": 0.04026097083296559 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3849056603773585, "acc_stderr": 0.02994649856769995, "acc_norm": 0.3849056603773585, "acc_norm_stderr": 0.02994649856769995 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686936, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686936 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "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": 0.3583815028901734, "acc_stderr": 0.036563436533531585, "acc_norm": 0.3583815028901734, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.04605661864718381, "acc_norm": 0.7, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3702127659574468, "acc_stderr": 0.03156564682236785, "acc_norm": 0.3702127659574468, "acc_norm_stderr": 0.03156564682236785 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.42758620689655175, "acc_stderr": 0.041227371113703316, "acc_norm": 0.42758620689655175, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.024180497164376893, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.024180497164376893 }, "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": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4096774193548387, "acc_stderr": 0.027976054915347364, "acc_norm": 0.4096774193548387, "acc_norm_stderr": 0.027976054915347364 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.031785297106427496, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.031785297106427496 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939098, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939098 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5515151515151515, "acc_stderr": 0.038835659779569286, "acc_norm": 0.5515151515151515, "acc_norm_stderr": 0.038835659779569286 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4090909090909091, "acc_stderr": 0.03502975799413007, "acc_norm": 0.4090909090909091, "acc_norm_stderr": 0.03502975799413007 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.37305699481865284, "acc_stderr": 0.03490205592048574, "acc_norm": 0.37305699481865284, "acc_norm_stderr": 0.03490205592048574 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.31025641025641026, "acc_stderr": 0.023454674889404288, "acc_norm": 0.31025641025641026, "acc_norm_stderr": 0.023454674889404288 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176095, "acc_norm": 0.292592592
