open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_r32_a256
收藏数据集概述
数据集来源
该数据集是在评估模型 BFauber/lora_llama2-13b_10e5_r32_a256 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_BFauber__lora_llama2-13b_10e5_r32_a256", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.5491118491191409, "acc_stderr": 0.03371068516054063, "acc_norm": 0.5553346595801392, "acc_norm_stderr": 0.034445348425841425, "mc1": 0.25458996328029376, "mc1_stderr": 0.015250117079156494, "mc2": 0.3674952163268229, "mc2_stderr": 0.013600341542779936 }, "harness|arc:challenge|25": { "acc": 0.5725255972696246, "acc_stderr": 0.014456862944650654, "acc_norm": 0.6015358361774744, "acc_norm_stderr": 0.01430694605273556 }, "harness|hellaswag|10": { "acc": 0.6164110734913364, "acc_stderr": 0.004852658876775389, "acc_norm": 0.8197570205138419, "acc_norm_stderr": 0.0038360412422598074 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5197368421052632, "acc_stderr": 0.04065771002562605, "acc_norm": 0.5197368421052632, "acc_norm_stderr": 0.04065771002562605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.04999999999999999, "acc_norm": 0.55, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5735849056603773, "acc_stderr": 0.03043779434298305, "acc_norm": 0.5735849056603773, "acc_norm_stderr": 0.03043779434298305 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5972222222222222, "acc_stderr": 0.04101405519842426, "acc_norm": 0.5972222222222222, "acc_norm_stderr": 0.04101405519842426 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "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": 0.5317919075144508, "acc_stderr": 0.038047497443647646, "acc_norm": 0.5317919075144508, "acc_norm_stderr": 0.038047497443647646 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.047240073523838876, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.047240073523838876 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.03246956919789958, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.03246956919789958 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.0416656757710158, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.0416656757710158 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr": 0.024552292209342668, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.024552292209342668 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6903225806451613, "acc_stderr": 0.026302774983517418, "acc_norm": 0.6903225806451613, "acc_norm_stderr": 0.026302774983517418 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4433497536945813, "acc_stderr": 0.03495334582162933, "acc_norm": 0.4433497536945813, "acc_norm_stderr": 0.03495334582162933 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.0368105086916155, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0368105086916155 }, "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": 0.8082901554404145, "acc_stderr": 0.02840895362624528, "acc_norm": 0.8082901554404145, "acc_norm_stderr": 0.02840895362624528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4948717948717949, "acc_stderr": 0.025349672906838653, "acc_norm": 0.4948717948717949, "acc_norm_stderr": 0.025349672906838653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.02773896963217609, "acc_norm": 0.2925925
