open-llm-leaderboard-old/details_kaitchup__Mayonnaise-4in1-02
收藏Hugging Face2024-01-27 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_kaitchup__Mayonnaise-4in1-02
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型kaitchup/Mayonnaise-4in1-02的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。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。
该数据集是在模型kaitchup/Mayonnaise-4in1-02的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。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
数据集信息
- 数据集名称: Evaluation run of kaitchup/Mayonnaise-4in1-02
- 数据集来源: 自动创建于模型 kaitchup/Mayonnaise-4in1-02 在 Open LLM Leaderboard 的评估运行中。
- 数据集组成: 包含63个配置,每个配置对应一个评估任务。
- 数据集创建: 从1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。"train" 分割始终指向最新的结果。
- 额外配置: "results" 配置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_kaitchup__Mayonnaise-4in1-02", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-01-27T14:39:43.226327
- 结果示例: python { "all": { "acc": 0.6551916779138574, "acc_stderr": 0.03200844050733691, "acc_norm": 0.6543582791974909, "acc_norm_stderr": 0.03267980180170166, "mc1": 0.5667074663402693, "mc1_stderr": 0.017347024450107475, "mc2": 0.6904124035444142, "mc2_stderr": 0.015168084933661277 }, "harness|arc:challenge|25": { "acc": 0.7056313993174061, "acc_stderr": 0.01331852846053942, "acc_norm": 0.7337883959044369, "acc_norm_stderr": 0.012915774781523193 }, "harness|hellaswag|10": { "acc": 0.7186815375423222, "acc_stderr": 0.0044872356579556735, "acc_norm": 0.8850826528579964, "acc_norm_stderr": 0.00318270383035113 }, ... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_27T14_39_43.226327
- 路径: **/details_harness|arc:challenge|25_2024-01-27T14-39-43.226327.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-27T14-39-43.226327.parquet
- 分割: 2024_01_27T14_39_43.226327
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_27T14_39_43.226327
- 路径: **/details_harness|gsm8k|5_2024-01-27T14-39-43.226327.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-27T14-39-43.226327.parquet
- 分割: 2024_01_27T14_39_43.226327
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_27T14_39_43.226327
- 路径: **/details_harness|hellaswag|10_2024-01-27T14-39-43.226327.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-27T14-39-43.226327.parquet
- 分割: 2024_01_27T14_39_43.226327
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_27T14_39_43.226327
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-27T14-39-43.226327.parquet ...
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-27T14-39-43.226327.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-27T14-39-43.226327.parquet ...
- 路径:
- 分割: 2024_01_27T14_39_43.226327
- 数据文件:



