open-llm-leaderboard-old/details_Aryanne__sheared-silicon10p
收藏Hugging Face2024-01-24 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Aryanne__sheared-silicon10p
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Aryanne/sheared-silicon10p进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集包含一次运行的结果,每次运行都作为每个配置中的一个特定分割存储。train分割始终指向最新结果。此外,还有一个results配置存储了所有运行的聚合结果,用于计算和展示在Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
该数据集是在Open LLM Leaderboard上对模型Aryanne/sheared-silicon10p进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集包含一次运行的结果,每次运行都作为每个配置中的一个特定分割存储。train分割始终指向最新结果。此外,还有一个results配置存储了所有运行的聚合结果,用于计算和展示在Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集信息
- 名称: Evaluation run of Aryanne/sheared-silicon10p
- 来源: 自动创建于模型 Aryanne/sheared-silicon10p 在 Open LLM Leaderboard 的评估运行中。
- 组成: 包含63个配置,每个配置对应一个评估任务。
- 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_Aryanne__sheared-silicon10p", "harness_winogrande_5", split="train")
最新结果
- 来源: 最新结果来自2024-01-24T01:36:29.411153
- 详细结果: python { "all": { "acc": 0.2599470421169613, "acc_stderr": 0.030910228069377786, "acc_norm": 0.26177545641423533, "acc_norm_stderr": 0.03173012245284717, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608774, "mc2": 0.44852499686717784, "mc2_stderr": 0.015613508500309613 }, "harness|arc:challenge|25": { "acc": 0.32764505119453924, "acc_stderr": 0.013715847940719342, "acc_norm": 0.36177474402730375, "acc_norm_stderr": 0.014041957945038073 }, "harness|hellaswag|10": { "acc": 0.3850826528579964, "acc_stderr": 0.004856203374715455, "acc_norm": 0.5111531567416849, "acc_norm_stderr": 0.004988539870174639 }, ... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_24T01_36_29.411153
- 路径: **/details_harness|arc:challenge|25_2024-01-24T01-36-29.411153.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-24T01-36-29.411153.parquet
- 分割: 2024_01_24T01_36_29.411153
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_24T01_36_29.411153
- 路径: **/details_harness|gsm8k|5_2024-01-24T01-36-29.411153.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-24T01-36-29.411153.parquet
- 分割: 2024_01_24T01_36_29.411153
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_24T01_36_29.411153
- 路径: **/details_harness|hellaswag|10_2024-01-24T01-36-29.411153.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-24T01-36-29.411153.parquet
- 分割: 2024_01_24T01_36_29.411153
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_24T01_36_29.411153
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-24T01-36-29.411153.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-24T01-36-29.411153.parquet
- **/
- 路径:
- 分割: 2024_01_24T01_36_29.411153
- 数据文件:



