open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-40b
收藏数据集概述
数据集简介
该数据集是在对模型 AI-Sweden-Models/gpt-sw3-40b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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：数据集来自1次运行。每个运行结果作为一个特定的分割（split）存储，分割名称使用运行的时间戳。
- 分割（split）：每个配置包含多个分割，其中“train”分割指向最新的结果。
- 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_AI-Sweden-Models__gpt-sw3-40b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-04T15:00:33.518629 运行的最新结果：
python { "all": { "acc": 0.354049089015047, "acc_stderr": 0.033417526940887884, "acc_norm": 0.35741274788934346, "acc_norm_stderr": 0.03422297037663694, "mc1": 0.22276621787025705, "mc1_stderr": 0.014566506961396728, "mc2": 0.3752465265593006, "mc2_stderr": 0.013533322814931005 }, "harness|arc:challenge|25": { "acc": 0.40102389078498296, "acc_stderr": 0.01432225579071987, "acc_norm": 0.4300341296928328, "acc_norm_stderr": 0.014467631559137993 }, "harness|hellaswag|10": { "acc": 0.535749850627365, "acc_stderr": 0.004977010670436551, "acc_norm": 0.7236606253734316, "acc_norm_stderr": 0.004462727543055892 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "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": 0.2631578947368421, "acc_stderr": 0.03583496176361063, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.03583496176361063 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3471698113207547, "acc_stderr": 0.029300101705549655, "acc_norm": 0.3471698113207547, "acc_norm_stderr": 0.029300101705549655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3541666666666667, "acc_stderr": 0.039994111357535424, "acc_norm": 0.3541666666666667, "acc_norm_stderr": 0.039994111357535424 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.0498887651569859, "acc_norm": 0.44, "acc_norm_stderr": 0.0498887651569859 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.28901734104046245, "acc_stderr": 0.034564257450869995, "acc_norm": 0.28901734104046245, "acc_norm_stderr": 0.034564257450869995 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.1568627450980392, "acc_stderr": 0.03618664819936245, "acc_norm": 0.1568627450980392, "acc_norm_stderr": 0.03618664819936245 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.31063829787234043, "acc_stderr": 0.03025123757921317, "acc_norm": 0.31063829787234043, "acc_norm_stderr": 0.03025123757921317 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21929824561403508, "acc_stderr": 0.038924311065187546, "acc_norm": 0.21929824561403508, "acc_norm_stderr": 0.038924311065187546 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3724137931034483, "acc_stderr": 0.04028731532947559, "acc_norm": 0.3724137931034483, "acc_norm_stderr": 0.04028731532947559 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.022644212615525214, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.022644212615525214 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574924, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574924 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.36129032258064514, "acc_stderr": 0.02732754844795754, "acc_norm": 0.36129032258064514, "acc_norm_stderr": 0.02732754844795754 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.0307127300709826, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.0307127300709826 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.503030303030303, "acc_stderr": 0.03904272341431857, "acc_norm": 0.503030303030303, "acc_norm_stderr": 0.03904272341431857 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3434343434343434, "acc_stderr": 0.03383201223244442, "acc_norm": 0.3434343434343434, "acc_norm_stderr": 0.03383201223244442 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.41450777202072536, "acc_stderr": 0.035553003195576735, "acc_norm": 0.41450777202072536, "acc_norm_stderr": 0.035553003195576735 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.28717948717948716, "acc_stderr": 0.02293992541853062, "acc_norm": 0.28717948717948716, "acc_norm_stderr": 0.02293992541853062 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2518518518518518, "acc_stderr": 0.02646611753895992, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.0
