open-llm-leaderboard-old/details_01-ai__Yi-1.5-34B
收藏数据集概述
数据集简介
该数据集是在评估模型01-ai/Yi-1.5-34B在Open LLM Leaderboard上的运行过程中自动创建的。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_01-ai__Yi-1.5-34B", "harness_winogrande_5", split="train")
最新结果
以下是2024-05-16T00:23:07.920103运行的最新结果：
python { "all": { "acc": 0.775704314920382, "acc_stderr": 0.028030256643903333, "acc_norm": 0.7792625977038656, "acc_norm_stderr": 0.028572819290919916, "mc1": 0.3684210526315789, "mc1_stderr": 0.016886551261046042, "mc2": 0.5384452997155903, "mc2_stderr": 0.015010112043916876 }, "harness|arc:challenge|25": { "acc": 0.621160409556314, "acc_stderr": 0.014175915490000326, "acc_norm": 0.6578498293515358, "acc_norm_stderr": 0.013864152159177278 }, "harness|hellaswag|10": { "acc": 0.666301533559052, "acc_stderr": 0.004705697745222149, "acc_norm": 0.8610834495120494, "acc_norm_stderr": 0.003451525868724679 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7555555555555555, "acc_stderr": 0.03712537833614866, "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474928, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474928 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8301886792452831, "acc_stderr": 0.023108393799841316, "acc_norm": 0.8301886792452831, "acc_norm_stderr": 0.023108393799841316 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.875, "acc_stderr": 0.02765610492929436, "acc_norm": 0.875, "acc_norm_stderr": 0.02765610492929436 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7514450867052023, "acc_stderr": 0.03295304696818317, "acc_norm": 0.7514450867052023, "acc_norm_stderr": 0.03295304696818317 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.86, "acc_stderr": 0.03487350880197771, "acc_norm": 0.86, "acc_norm_stderr": 0.03487350880197771 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8382978723404255, "acc_stderr": 0.024068505289695345, "acc_norm": 0.8382978723404255, "acc_norm_stderr": 0.024068505289695345 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6491228070175439, "acc_stderr": 0.044895393502706986, "acc_norm": 0.6491228070175439, "acc_norm_stderr": 0.044895393502706986 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7862068965517242, "acc_stderr": 0.03416520447747548, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.03416520447747548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7195767195767195, "acc_stderr": 0.023135287974325625, "acc_norm": 0.7195767195767195, "acc_norm_stderr": 0.023135287974325625 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6746031746031746, "acc_stderr": 0.041905964388711366, "acc_norm": 0.6746031746031746, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8774193548387097, "acc_stderr": 0.018656720991789406, "acc_norm": 0.8774193548387097, "acc_norm_stderr": 0.018656720991789406 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6945812807881774, "acc_stderr": 0.032406615658684086, "acc_norm": 0.6945812807881774, "acc_norm_stderr": 0.032406615658684086 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.026024657651656187, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.026024657651656187 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9343434343434344, "acc_stderr": 0.01764652667723333, "acc_norm": 0.9343434343434344, "acc_norm_stderr": 0.01764652667723333 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9481865284974094, "acc_stderr": 0.01599622932024412, "acc_norm": 0.9481865284974094, "acc_norm_stderr": 0.01599622932024412 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8307692307692308, "acc_stderr": 0.019011004523651048, "acc_norm": 0.8307692307692308, "acc_norm_stderr": 0.019011004523651048 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5111111111111111, "acc_stderr": 0.030478009819615817, "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.030478009819615817 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8865546218487395, "acc_stderr": 0.020600225750204
