open-llm-leaderboard-old/details_OpenBuddy__openbuddy-falcon-40b-v16.1-4k
收藏数据集概述
数据集简介
该数据集是在对模型 OpenBuddy/openbuddy-falcon-40b-v16.1-4k 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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，每个运行可以在每个配置中作为一个特定的分割找到，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 一个额外的配置 "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_OpenBuddy__openbuddy-falcon-40b-v16.1-4k", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-05T01:55:41.370923 运行的最新结果：
python { "all": { "acc": 0.5625701552873708, "acc_stderr": 0.033637694579668774, "acc_norm": 0.5659961003783944, "acc_norm_stderr": 0.034333508282820065, "mc1": 0.35862913096695226, "mc1_stderr": 0.016789289499502022, "mc2": 0.5057283082668802, "mc2_stderr": 0.015027075356912903 }, "harness|arc:challenge|25": { "acc": 0.5750853242320819, "acc_stderr": 0.014445698968520769, "acc_norm": 0.60580204778157, "acc_norm_stderr": 0.014280522667467327 }, "harness|hellaswag|10": { "acc": 0.6463851822346146, "acc_stderr": 0.004771143074426131, "acc_norm": 0.8385779725154352, "acc_norm_stderr": 0.0036716784499612135 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.046482319871173156, "acc_norm": 0.31, "acc_norm_stderr": 0.046482319871173156 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5407407407407407, "acc_stderr": 0.04304979692464242, "acc_norm": 0.5407407407407407, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5394736842105263, "acc_stderr": 0.04056242252249034, "acc_norm": 0.5394736842105263, "acc_norm_stderr": 0.04056242252249034 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6037735849056604, "acc_stderr": 0.030102793781791197, "acc_norm": 0.6037735849056604, "acc_norm_stderr": 0.030102793781791197 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960718, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960718 }, "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": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4797687861271676, "acc_stderr": 0.03809342081273958, "acc_norm": 0.4797687861271676, "acc_norm_stderr": 0.03809342081273958 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.03257901482099835, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.044629175353369376, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.044629175353369376 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.041546596717075474, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr": 0.024552292209342665, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.024552292209342665 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6516129032258065, "acc_stderr": 0.027104826328100944, "acc_norm": 0.6516129032258065, "acc_norm_stderr": 0.027104826328100944 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.034454876862647144, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.034454876862647144 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.03374402644139403, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139403 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7171717171717171, "acc_stderr": 0.03208779558786751, "acc_norm": 0.7171717171717171, "acc_norm_stderr": 0.03208779558786751 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7668393782383419, "acc_stderr": 0.03051611137147601, "acc_norm": 0.7668393782383419, "acc_norm_stderr": 0.03051611137147601 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5358974358974359, "acc_stderr": 0.025285585990017848, "acc_norm": 0.5358974358974359, "acc_norm_stderr": 0.025285585990017848 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.0270803
