open-llm-leaderboard-old/details_andrijdavid__tinyllama-dare
收藏数据集概述
数据集摘要
该数据集是在模型andrijdavid/tinyllama-dare在Open LLM Leaderboard上的评估运行期间自动创建的。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。
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。每个配置包含以下信息：
- 配置名称：如
harness_arc_challenge_25、harness_gsm8k_5等。 - 数据文件：每个配置包含多个数据文件，每个文件对应一个特定的分割，如
2024_01_19T19_20_12.926605和latest。
数据加载示例
以下是一个加载数据集的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_andrijdavid__tinyllama-dare", "harness_winogrande_5", split="train")
最新结果
以下是最新结果的部分内容： python { "all": { "acc": 0.260218948497339, "acc_stderr": 0.03089367507715055, "acc_norm": 0.26040524383105657, "acc_norm_stderr": 0.031653815968800486, "mc1": 0.2558139534883721, "mc1_stderr": 0.015274176219283361, "mc2": 0.3901127619389903, "mc2_stderr": 0.014174485975506508 }, "harness|arc:challenge|25": { "acc": 0.3643344709897611, "acc_stderr": 0.014063260279882412, "acc_norm": 0.3728668941979522, "acc_norm_stderr": 0.014131176760131163 }, "harness|hellaswag|10": { "acc": 0.4700258912567218, "acc_stderr": 0.004980807231136748, "acc_norm": 0.6277633937462657, "acc_norm_stderr": 0.004824130528590593 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.033556772163131424, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.033556772163131424 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123387, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123387 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2679245283018868, "acc_stderr": 0.027257260322494845, "acc_norm": 0.2679245283018868, "acc_norm_stderr": 0.027257260322494845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.034765901043041336, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.034765901043041336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "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": 0.20809248554913296, "acc_stderr": 0.030952890217749895, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749895 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237655, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.251063829787234, "acc_stderr": 0.028346963777162452, "acc_norm": 0.251063829787234, "acc_norm_stderr": 0.028346963777162452 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21052631578947367, "acc_stderr": 0.0383515395439942, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.0383515395439942 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113953, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113953 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276862, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276862 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25161290322580643, "acc_stderr": 0.02468597928623997, "acc_norm": 0.25161290322580643, "acc_norm_stderr": 0.02468597928623997 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03010833071801162, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03010833071801162 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24848484848484848, "acc_stderr": 0.03374402644139405, "acc_norm": 0.24848484848484848, "acc_norm_stderr": 0.03374402644139405 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.22727272727272727, "acc_stderr": 0.029857515673386407, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.029857515673386407 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21761658031088082, "acc_stderr": 0.029778663037752954, "acc_norm": 0.21761658031088082, "acc_norm_stderr": 0.029778663037752954 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2564102564102564, "acc_stderr": 0.022139081103971545, "acc_norm": 0.2564102564102564, "acc_norm_stderr": 0.022139081103971545 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.0262027665346
