open-llm-leaderboard/details_allknowingroger__DolphinChat-7B-slerp
收藏Hugging Face2024-04-10 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_allknowingroger__DolphinChat-7B-slerp
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型allknowingroger/DolphinChat-7B-slerp性能过程中自动创建的,用于记录和分析模型在Open LLM Leaderboard上的表现。数据集包含63个配置,每个配置对应一个特定的评估任务。数据集的创建基于单次运行,每个运行在不同的配置中以特定的时间戳命名的分割形式存在。此外,还有一个名为"results"的配置,用于存储所有运行的聚合结果,以便计算和展示Leaderboard上的综合指标。
该数据集是在评估模型allknowingroger/DolphinChat-7B-slerp性能过程中自动创建的,用于记录和分析模型在Open LLM Leaderboard上的表现。数据集包含63个配置,每个配置对应一个特定的评估任务。数据集的创建基于单次运行,每个运行在不同的配置中以特定的时间戳命名的分割形式存在。此外,还有一个名为"results"的配置,用于存储所有运行的聚合结果,以便计算和展示Leaderboard上的综合指标。
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
数据集名称
- pretty_name: Evaluation run of allknowingroger/DolphinChat-7B-slerp
数据集描述
- dataset_summary: 该数据集是模型allknowingroger/DolphinChat-7B-slerp在Open LLM Leaderboard评估运行期间自动创建的。
数据集组成
- 配置数量: 63个
- 每个配置对应任务: 一个评估任务
- 数据集创建自: 1次运行
- 数据集分割: 每个运行作为一个特定分割,分割名使用运行的时间戳命名。"train"分割指向最新结果。
- 额外配置: "results",存储所有运行结果的聚合结果,用于计算和显示聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_allknowingroger__DolphinChat-7B-slerp", "harness_winogrande_5", split="train")
最新结果
数据集详细配置
配置列表
-
harness_arc_challenge_25
- 数据文件:
- split: 2024_04_10T20_18_07.777421
- path: **/details_harness|arc:challenge|25_2024-04-10T20-18-07.777421.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-04-10T20-18-07.777421.parquet
- split: 2024_04_10T20_18_07.777421
- 数据文件:
-
harness_gsm8k_5
- 数据文件:
- split: 2024_04_10T20_18_07.777421
- path: **/details_harness|gsm8k|5_2024-04-10T20-18-07.777421.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-04-10T20-18-07.777421.parquet
- split: 2024_04_10T20_18_07.777421
- 数据文件:
-
harness_hellaswag_10
- 数据文件:
- split: 2024_04_10T20_18_07.777421
- path: **/details_harness|hellaswag|10_2024-04-10T20-18-07.777421.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-04-10T20-18-07.777421.parquet
- split: 2024_04_10T20_18_07.777421
- 数据文件:
-
harness_hendrycksTest_5
- 数据文件:
- split: 2024_04_10T20_18_07.777421
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-management|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-virology|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-04-10T20-18-07.777421.parquet
- path:
- split: latest
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-10T20-18-07.777421.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-10T20-18-07.77742
- path:
- split: 2024_04_10T20_18_07.777421
- 数据文件:



