open-llm-leaderboard-old/details_yanolja__EEVE-Korean-Instruct-2.8B-v1.0
收藏数据集概述
数据集简介
该数据集是在评估模型yanolja/EEVE-Korean-Instruct-2.8B-v1.0在Open LLM Leaderboard上的运行过程中自动创建的。
数据集结构
- 数据集包含63个配置，每个配置对应一个评估任务。
- 数据集从1次运行中创建，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。
- 额外的配置"results"存储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_yanolja__EEVE-Korean-Instruct-2.8B-v1.0", "harness_winogrande_5", split="train")
最新结果
以下是最新结果从运行2024-02-24T12:23:11.293392：
python { "all": { "acc": 0.5359575580583875, "acc_stderr": 0.03412496053756963, "acc_norm": 0.5375250512818304, "acc_norm_stderr": 0.03483154089527838, "mc1": 0.3268053855569155, "mc1_stderr": 0.016419874731135032, "mc2": 0.483169553787504, "mc2_stderr": 0.01519249109360666 }, "harness|arc:challenge|25": { "acc": 0.5435153583617748, "acc_stderr": 0.014555949760496439, "acc_norm": 0.5827645051194539, "acc_norm_stderr": 0.014409825518403084 }, "harness|hellaswag|10": { "acc": 0.5435172276438957, "acc_stderr": 0.004970846697552311, "acc_norm": 0.7241585341565425, "acc_norm_stderr": 0.004460238879247421 }, "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": 0.4148148148148148, "acc_stderr": 0.042561937679014075, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5197368421052632, "acc_stderr": 0.040657710025626036, "acc_norm": 0.5197368421052632, "acc_norm_stderr": 0.040657710025626036 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5358490566037736, "acc_stderr": 0.030693675018458003, "acc_norm": 0.5358490566037736, "acc_norm_stderr": 0.030693675018458003 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5972222222222222, "acc_stderr": 0.04101405519842425, "acc_norm": 0.5972222222222222, "acc_norm_stderr": 0.04101405519842425 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5375722543352601, "acc_stderr": 0.0380168510452446, "acc_norm": 0.5375722543352601, "acc_norm_stderr": 0.0380168510452446 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.451063829787234, "acc_stderr": 0.03252909619613197, "acc_norm": 0.451063829787234, "acc_norm_stderr": 0.03252909619613197 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02530590624159063, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02530590624159063 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3492063492063492, "acc_stderr": 0.04263906892795132, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.04263906892795132 }, "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": 0.6806451612903226, "acc_stderr": 0.02652270967466777, "acc_norm": 0.6806451612903226, "acc_norm_stderr": 0.02652270967466777 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.03486731727419872, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3090909090909091, "acc_stderr": 0.036085410115739666, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6868686868686869, "acc_stderr": 0.033042050878136525, "acc_norm": 0.6868686868686869, "acc_norm_stderr": 0.033042050878136525 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7202072538860104, "acc_stderr": 0.03239637046735704, "acc_norm": 0.7202072538860104, "acc_norm_stderr": 0.03239637046735704 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.541025641025641, "acc_stderr": 0.025265525491284295, "acc_norm": 0.541025641025641, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.02773896963217609, "acc_norm": 0.29259
