open-llm-leaderboard-old/details_acrastt__Vicuna-3B
收藏数据集概述
数据集简介
该数据集是在对模型 acrastt/Vicuna-3B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集包含 61 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_acrastt__Vicuna-3B", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-17T13:42:02.549031 运行 的最新结果：
python { "all": { "acc": 0.2811009875581447, "acc_stderr": 0.03252062846238445, "acc_norm": 0.2849236147706273, "acc_norm_stderr": 0.03251779934164602, "mc1": 0.24479804161566707, "mc1_stderr": 0.01505186948671501, "mc2": 0.38343994316155305, "mc2_stderr": 0.013903929837677163 }, "harness|arc:challenge|25": { "acc": 0.3651877133105802, "acc_stderr": 0.014070265519268804, "acc_norm": 0.4129692832764505, "acc_norm_stderr": 0.014388344935398326 }, "harness|hellaswag|10": { "acc": 0.5407289384584744, "acc_stderr": 0.004973199296339957, "acc_norm": 0.7184823740290779, "acc_norm_stderr": 0.004488201756642574 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909281, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.23703703703703705, "acc_stderr": 0.03673731683969506, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.26973684210526316, "acc_stderr": 0.03611780560284898, "acc_norm": 0.26973684210526316, "acc_norm_stderr": 0.03611780560284898 }, "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": 0.2641509433962264, "acc_stderr": 0.027134291628741713, "acc_norm": 0.2641509433962264, "acc_norm_stderr": 0.027134291628741713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.03942772444036623, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2138728323699422, "acc_stderr": 0.03126511206173044, "acc_norm": 0.2138728323699422, "acc_norm_stderr": 0.03126511206173044 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.33617021276595743, "acc_stderr": 0.030881618520676942, "acc_norm": 0.33617021276595743, "acc_norm_stderr": 0.030881618520676942 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21929824561403508, "acc_stderr": 0.03892431106518755, "acc_norm": 0.21929824561403508, "acc_norm_stderr": 0.03892431106518755 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2620689655172414, "acc_stderr": 0.036646663372252565, "acc_norm": 0.2620689655172414, "acc_norm_stderr": 0.036646663372252565 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.0230681888482611, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.0230681888482611 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.0361960452412425, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.0361960452412425 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.22903225806451613, "acc_stderr": 0.023904914311782648, "acc_norm": 0.22903225806451613, "acc_norm_stderr": 0.023904914311782648 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694436, "acc_norm": 0.2512315270935961, "acc_norm_stderr": 0.030516530732694436 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.29, "acc_stderr": 0.04560480215720685, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720685 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.30303030303030304, "acc_stderr": 0.035886248000917075, "acc_norm": 0.30303030303030304, "acc_norm_stderr": 0.035886248000917075 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365904, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365904 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24352331606217617, "acc_stderr": 0.03097543638684543, "acc_norm": 0.24352331606217617, "acc_norm_stderr": 0.03097543638684543 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.258974358974359, "acc_stderr": 0.02221110681006166, "acc_norm": 0.258974358974359, "acc_norm_stderr": 0.02221110681006166 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.026335739404055803, "acc_norm": 0.24814814814814815, "acc_norm_stderr": 0.0263357394040
