open-llm-leaderboard-old/details_inswave__AISquare-Instruct-llama2-koen-13b-v0.9.24
收藏数据集概述
数据集简介
该数据集是在评估模型 inswave/AISquare-Instruct-llama2-koen-13b-v0.9.24 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_inswave__AISquare-Instruct-llama2-koen-13b-v0.9.24", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-01-22T04:44:53.381027 的摘要：
python { "all": { "acc": 0.5189240030169358, "acc_stderr": 0.03417423514779615, "acc_norm": 0.5233187157188728, "acc_norm_stderr": 0.03491752755385364, "mc1": 0.3574051407588739, "mc1_stderr": 0.016776599676729405, "mc2": 0.530042963383804, "mc2_stderr": 0.014928626205495087 }, "harness|arc:challenge|25": { "acc": 0.5307167235494881, "acc_stderr": 0.014583792546304038, "acc_norm": 0.5563139931740614, "acc_norm_stderr": 0.014518421825670452 }, "harness|hellaswag|10": { "acc": 0.6161123282214698, "acc_stderr": 0.004853371646239246, "acc_norm": 0.813483369846644, "acc_norm_stderr": 0.0038872693686016107 }, "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": 0.4888888888888889, "acc_stderr": 0.04318275491977976, "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5328947368421053, "acc_stderr": 0.040601270352363966, "acc_norm": 0.5328947368421053, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5584905660377358, "acc_stderr": 0.030561590426731833, "acc_norm": 0.5584905660377358, "acc_norm_stderr": 0.030561590426731833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5347222222222222, "acc_stderr": 0.04171115858181618, "acc_norm": 0.5347222222222222, "acc_norm_stderr": 0.04171115858181618 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "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": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5028901734104047, "acc_stderr": 0.038124005659748335, "acc_norm": 0.5028901734104047, "acc_norm_stderr": 0.038124005659748335 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006717, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006717 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3659574468085106, "acc_stderr": 0.0314895582974553, "acc_norm": 0.3659574468085106, "acc_norm_stderr": 0.0314895582974553 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.32275132275132273, "acc_stderr": 0.024078943243597016, "acc_norm": 0.32275132275132273, "acc_norm_stderr": 0.024078943243597016 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.040406101782088394, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.040406101782088394 }, "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": 0.5741935483870968, "acc_stderr": 0.028129112709165904, "acc_norm": 0.5741935483870968, "acc_norm_stderr": 0.028129112709165904 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4187192118226601, "acc_stderr": 0.034711928605184676, "acc_norm": 0.4187192118226601, "acc_norm_stderr": 0.034711928605184676 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6606060606060606, "acc_stderr": 0.03697442205031595, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.03697442205031595 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6515151515151515, "acc_stderr": 0.033948539651564025, "acc_norm": 0.6515151515151515, "acc_norm_stderr": 0.033948539651564025 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.029778663037752954, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.029778663037752954 }, "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": 0.3, "acc_stderr": 0.027940457136228402, "acc_norm": 0.3, "acc_norm_stderr": 0.0279
