open-llm-leaderboard-old/details_ALBADDAWI__DeepCode-7B-Aurora-v13
收藏数据集概述
数据集简介
该数据集是在评估模型 ALBADDAWI/DeepCode-7B-Aurora-v13 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从2次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：一个额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示在 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_ALBADDAWI__DeepCode-7B-Aurora-v13", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-15T12:22:06.560807 运行 的最新结果：
python { "all": { "acc": 0.5602939981344383, "acc_stderr": 0.03441897837176519, "acc_norm": 0.5705247302143901, "acc_norm_stderr": 0.03524623166939266, "mc1": 0.2937576499388005, "mc1_stderr": 0.015945068581236614, "mc2": 0.4036948798131458, "mc2_stderr": 0.015288577859532484 }, "harness|arc:challenge|25": { "acc": 0.5255972696245734, "acc_stderr": 0.014592230885298964, "acc_norm": 0.5546075085324232, "acc_norm_stderr": 0.014523987638344086 }, "harness|hellaswag|10": { "acc": 0.5488946425014938, "acc_stderr": 0.0049658660983181715, "acc_norm": 0.724457279426409, "acc_norm_stderr": 0.004458742356237882 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411022, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411022 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4, "acc_stderr": 0.04232073695151589, "acc_norm": 0.4, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.631578947368421, "acc_stderr": 0.03925523381052932, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5433962264150943, "acc_stderr": 0.030656748696739428, "acc_norm": 0.5433962264150943, "acc_norm_stderr": 0.030656748696739428 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5694444444444444, "acc_stderr": 0.04140685639111502, "acc_norm": 0.5694444444444444, "acc_norm_stderr": 0.04140685639111502 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5433526011560693, "acc_stderr": 0.03798106566014498, "acc_norm": 0.5433526011560693, "acc_norm_stderr": 0.03798106566014498 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6553191489361702, "acc_stderr": 0.031068985963122145, "acc_norm": 0.6553191489361702, "acc_norm_stderr": 0.031068985963122145 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.0402873153294756, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.0402873153294756 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.582010582010582, "acc_stderr": 0.02540255550326091, "acc_norm": 0.582010582010582, "acc_norm_stderr": 0.02540255550326091 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5396825396825397, "acc_stderr": 0.04458029125470973, "acc_norm": 0.5396825396825397, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6387096774193548, "acc_stderr": 0.02732754844795754, "acc_norm": 0.6387096774193548, "acc_norm_stderr": 0.02732754844795754 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5320197044334976, "acc_stderr": 0.03510766597959217, "acc_norm": 0.5320197044334976, "acc_norm_stderr": 0.03510766597959217 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6909090909090909, "acc_stderr": 0.036085410115739666, "acc_norm": 0.6909090909090909, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178815, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6787564766839378, "acc_stderr": 0.033699508685490674, "acc_norm": 0.6787564766839378, "acc_norm_stderr": 0.033699508685490674 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5692307692307692, "acc_stderr": 0.025106820660539753, "acc_norm": 0.5692307692307692, "acc_norm_stderr": 0.025106820660539753 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4222222222222222, "acc_stderr": 0.030114442019668092, "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.03011
