open-llm-leaderboard-old/details_Sao10K__Shiki-v2-m7
收藏Hugging Face2024-03-13 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Sao10K__Shiki-v2-m7
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Sao10K/Shiki-v2-m7进行评估运行过程中自动创建的。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次运行创建,每次运行的结果作为特定配置中的一个分割,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,一个名为results的配置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。
该数据集是在Open LLM Leaderboard上对模型Sao10K/Shiki-v2-m7进行评估运行过程中自动创建的。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次运行创建,每次运行的结果作为特定配置中的一个分割,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,一个名为results的配置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。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集基本信息
- 名称: Evaluation run of Sao10K/Shiki-v2-m7
- 创建目的: 自动创建于模型 Sao10K/Shiki-v2-m7 在 Open LLM Leaderboard 的评估运行期间。
- 组成: 包含 63 个配置,每个配置对应一个评估任务。
- 创建次数: 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_Sao10K__Shiki-v2-m7", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2024-03-13T17:49:43.794987
- 聚合结果: python { "all": { "acc": 0.6090667848880721, "acc_stderr": 0.032530951263176094, "acc_norm": 0.621800577116862, "acc_norm_stderr": 0.033376434421744074, "mc1": 0.4467564259485924, "mc1_stderr": 0.017403977522557148, "mc2": 0.6197903771040616, "mc2_stderr": 0.015744954084186934 }, ... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_13T17_49_43.794987
- 路径:
**/details_harness|arc:challenge|25_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: 2024_03_13T17_49_43.794987
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_13T17_49_43.794987
- 路径:
**/details_harness|gsm8k|5_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: 2024_03_13T17_49_43.794987
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_13T17_49_43.794987
- 路径:
**/details_harness|hellaswag|10_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-03-13T17-49-43.794987.parquet
- 路径:
- 分割: 2024_03_13T17_49_43.794987
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_13T17_49_43.794987
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-13T17-49-43.794987.parquet- ...
- 路径:
- 分割: latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-13T17-49-43.794987.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-13T17-49-43.794987.parquet- ...
- 路径:
- 分割: 2024_03_13T17_49_43.794987
- 数据文件:



