open-llm-leaderboard-old/details_Undi95__Mixtral-8x7B-MoE-RP-Story
收藏数据集概述
数据集摘要
该数据集是在评估模型 Undi95/Mixtral-8x7B-MoE-RP-Story 在 Open LLM Leaderboard 上的自动创建的。
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_Undi95__Mixtral-8x7B-MoE-RP-Story", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T21:32:27.266201 运行的最新结果：
python { "all": { "acc": 0.43068446823982826, "acc_stderr": 0.03444996506735285, "acc_norm": 0.43640169503643583, "acc_norm_stderr": 0.03524813638857257, "mc1": 0.26438188494492043, "mc1_stderr": 0.015438211119522514, "mc2": 0.41531240642156975, "mc2_stderr": 0.01492327563743382 }, "harness|arc:challenge|25": { "acc": 0.46501706484641636, "acc_stderr": 0.014575583922019665, "acc_norm": 0.515358361774744, "acc_norm_stderr": 0.014604496129394904 }, "harness|hellaswag|10": { "acc": 0.5017924716191994, "acc_stderr": 0.004989749347461088, "acc_norm": 0.6999601672973511, "acc_norm_stderr": 0.004573383672159088 }, "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": 0.43703703703703706, "acc_stderr": 0.04284958639753399, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.04284958639753399 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4934210526315789, "acc_stderr": 0.040685900502249704, "acc_norm": 0.4934210526315789, "acc_norm_stderr": 0.040685900502249704 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.41509433962264153, "acc_stderr": 0.030325945789286105, "acc_norm": 0.41509433962264153, "acc_norm_stderr": 0.030325945789286105 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4513888888888889, "acc_stderr": 0.041614023984032786, "acc_norm": 0.4513888888888889, "acc_norm_stderr": 0.041614023984032786 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3988439306358382, "acc_stderr": 0.037336266553835096, "acc_norm": 0.3988439306358382, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3574468085106383, "acc_stderr": 0.03132941789476425, "acc_norm": 0.3574468085106383, "acc_norm_stderr": 0.03132941789476425 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.044895393502707, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.044895393502707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.43448275862068964, "acc_stderr": 0.04130740879555497, "acc_norm": 0.43448275862068964, "acc_norm_stderr": 0.04130740879555497 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.023068188848261114, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.023068188848261114 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523812, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523812 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.41935483870967744, "acc_stderr": 0.028071588901091838, "acc_norm": 0.41935483870967744, "acc_norm_stderr": 0.028071588901091838 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2660098522167488, "acc_stderr": 0.03108982600293753, "acc_norm": 0.2660098522167488, "acc_norm_stderr": 0.03108982600293753 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.36363636363636365, "acc_stderr": 0.03756335775187896, "acc_norm": 0.36363636363636365, "acc_norm_stderr": 0.03756335775187896 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5151515151515151, "acc_stderr": 0.03560716516531061, "acc_norm": 0.5151515151515151, "acc_norm_stderr": 0.03560716516531061 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6424870466321243, "acc_stderr": 0.034588160421810114, "acc_norm": 0.6424870466321243, "acc_norm_stderr": 0.034588160421810114 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.44358974358974357, "acc_stderr": 0.025189149894764205, "acc_norm": 0.44358974358974357, "acc_norm_stderr": 0.025189149894764205 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.0271959348
