five

open-llm-leaderboard-old/details_bigscience__bloom

收藏
Hugging Face2023-08-29 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_bigscience__bloom
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型进行评估时自动创建的。数据集由61个配置组成,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,运行的时间戳作为分割的名称。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对模型进行评估时自动创建的。数据集由61个配置组成,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,运行的时间戳作为分割的名称。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型None进行评估运行期间自动创建的,用于Open LLM Leaderboard。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。此外,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。

最新结果

以下是2023-08-29T12:19:54.390376运行的最新结果:

python { "all": { "acc": 0.315597821758106, "acc_stderr": 0.0334554445358342, "acc_norm": 0.31957868125391004, "acc_norm_stderr": 0.03344403068302842, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299962, "mc2": 0.3975962282334165, "mc2_stderr": 0.013579754303009808 }, "harness|arc:challenge|25": { "acc": 0.4658703071672355, "acc_stderr": 0.014577311315231102, "acc_norm": 0.5042662116040956, "acc_norm_stderr": 0.014610858923956948 }, "harness|hellaswag|10": { "acc": 0.5676160127464649, "acc_stderr": 0.004943945069611452, "acc_norm": 0.7640908185620394, "acc_norm_stderr": 0.0042369801453443065 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720386, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3169811320754717, "acc_stderr": 0.028637235639800925, "acc_norm": 0.3169811320754717, "acc_norm_stderr": 0.028637235639800925 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686934, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686934 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24855491329479767, "acc_stderr": 0.03295304696818318, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617749, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617749 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3276595744680851, "acc_stderr": 0.030683020843231004, "acc_norm": 0.3276595744680851, "acc_norm_stderr": 0.030683020843231004 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481425, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481425 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.31724137931034485, "acc_stderr": 0.03878352372138623, "acc_norm": 0.31724137931034485, "acc_norm_stderr": 0.03878352372138623 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2804232804232804, "acc_stderr": 0.02313528797432563, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.02313528797432563 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.03852273364924315, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.03852273364924315 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2967741935483871, "acc_stderr": 0.02598850079241188, "acc_norm": 0.2967741935483871, "acc_norm_stderr": 0.02598850079241188 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358609, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358609 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3787878787878788, "acc_stderr": 0.03456088731993747, "acc_norm": 0.3787878787878788, "acc_norm_stderr": 0.03456088731993747 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.29533678756476683, "acc_stderr": 0.0329229663915514, "acc_norm": 0.29533678756476683, "acc_norm_stderr": 0.0329229663915514 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2230769230769231, "acc_stderr": 0.021107730127243998, "acc_norm": 0.2230769230769231, "acc_norm_stderr": 0.021107730127243998 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.24789915966386555, "acc_stderr": 0.028047967224176896, "acc_norm": 0.24789915966386555, "acc_norm_stderr": 0.

5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作