open-llm-leaderboard-old/details_Himitsui__KuroMitsu-11B
收藏Hugging Face2024-01-28 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Himitsui__KuroMitsu-11B
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Himitsui/KuroMitsu-11B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。它包含一次运行的结果,每次运行在每个配置中表示为特定的分割。train分割始终指向最新结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。
该数据集是在模型Himitsui/KuroMitsu-11B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。它包含一次运行的结果,每次运行在每个配置中表示为特定的分割。train分割始终指向最新结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。
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 Himitsui/KuroMitsu-11B
- 来源: 自动创建于模型 Himitsui/KuroMitsu-11B 在 Open LLM Leaderboard 的评估运行。
- 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_Himitsui__KuroMitsu-11B", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自: 2024-01-28T06:24:13.290329
- 结果示例: python { "all": { "acc": 0.669725970836758, "acc_stderr": 0.031374936085536896, "acc_norm": 0.6708779488946179, "acc_norm_stderr": 0.03201341672594316, "mc1": 0.47613219094247244, "mc1_stderr": 0.017483547156961574, "mc2": 0.6136062654326809, "mc2_stderr": 0.01566923198966147 }, "harness|arc:challenge|25": { "acc": 0.6672354948805461, "acc_stderr": 0.013769863046192307, "acc_norm": 0.7030716723549488, "acc_norm_stderr": 0.013352025976725228 }, "harness|hellaswag|10": { "acc": 0.6974706233817964, "acc_stderr": 0.004584144014654944, "acc_norm": 0.8807010555666202, "acc_norm_stderr": 0.0032347749806479606 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, ... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_28T06_24_13.290329
- 路径: **/details_harness|arc:challenge|25_2024-01-28T06-24-13.290329.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-28T06-24-13.290329.parquet
- 分割: 2024_01_28T06_24_13.290329
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_28T06_24_13.290329
- 路径: **/details_harness|gsm8k|5_2024-01-28T06-24-13.290329.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-28T06-24-13.290329.parquet
- 分割: 2024_01_28T06_24_13.290329
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_28T06_24_13.290329
- 路径: **/details_harness|hellaswag|10_2024-01-28T06-24-13.290329.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-28T06-24-13.290329.parquet
- 分割: 2024_01_28T06_24_13.290329
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_28T06_24_13.290329
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-28T06-24-13.290329.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-28T06-24-13.290329.parquet ...
- 路径:
- 分割: 2024_01_28T06_24_13.290329
- 数据文件:



