open-llm-leaderboard-old/details_arvindanand__Deepseek-Wizard-33B-slerp
收藏数据集概述
该数据集是在对模型 arvindanand/Deepseek-Wizard-33B-slerp 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
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 "results" 配置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_arvindanand__Deepseek-Wizard-33B-slerp", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-10T11:55:40.376566 运行的最新结果：
python { "all": { "acc": 0.3718561973371085, "acc_stderr": 0.03386409948633655, "acc_norm": 0.3767523316002052, "acc_norm_stderr": 0.03478643489608982, "mc1": 0.25091799265605874, "mc1_stderr": 0.015176985027707693, "mc2": 0.4481064242625741, "mc2_stderr": 0.016867993246611538 }, "harness|arc:challenge|25": { "acc": 0.2764505119453925, "acc_stderr": 0.013069662474252428, "acc_norm": 0.31399317406143346, "acc_norm_stderr": 0.013562691224726284 }, "harness|hellaswag|10": { "acc": 0.31398127862975506, "acc_stderr": 0.00463160353975196, "acc_norm": 0.3693487353116909, "acc_norm_stderr": 0.004816421208654089 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720385, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3881578947368421, "acc_stderr": 0.03965842097512744, "acc_norm": 0.3881578947368421, "acc_norm_stderr": 0.03965842097512744 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3622641509433962, "acc_stderr": 0.029582245128384296, "acc_norm": 0.3622641509433962, "acc_norm_stderr": 0.029582245128384296 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686935, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3352601156069364, "acc_stderr": 0.03599586301247078, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179326, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179326 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3659574468085106, "acc_stderr": 0.031489558297455304, "acc_norm": 0.3659574468085106, "acc_norm_stderr": 0.031489558297455304 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374767, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374767 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.38620689655172413, "acc_stderr": 0.04057324734419034, "acc_norm": 0.38620689655172413, "acc_norm_stderr": 0.04057324734419034 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36507936507936506, "acc_stderr": 0.024796060602699965, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.024796060602699965 }, "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": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4483870967741935, "acc_stderr": 0.028292056830112725, "acc_norm": 0.4483870967741935, "acc_norm_stderr": 0.028292056830112725 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.0316185633535861, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.0316185633535861 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4909090909090909, "acc_stderr": 0.0390369864774844, "acc_norm": 0.4909090909090909, "acc_norm_stderr": 0.0390369864774844 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3838383838383838, "acc_stderr": 0.03464881675016338, "acc_norm": 0.3838383838383838, "acc_norm_stderr": 0.03464881675016338 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35233160621761656, "acc_stderr": 0.03447478286414358, "acc_norm": 0.35233160621761656, "acc_norm_stderr": 0.03447478286414358 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30256410256410254, "acc_stderr": 0.023290888053772742, "acc_norm": 0.30256410256410254, "acc_norm_stderr": 0.023290888053772742 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114996, "acc
