open-llm-leaderboard/details_ndavidson__Phi-2-openassistant
收藏Hugging Face2024-04-15 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_ndavidson__Phi-2-openassistant
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ndavidson/Phi-2-openassistant时自动生成的,评估是在Open LLM Leaderboard上进行的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,运行的时间戳作为分割名称。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,用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型ndavidson/Phi-2-openassistant时自动生成的,评估是在Open LLM Leaderboard上进行的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,运行的时间戳作为分割名称。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,用于计算和显示Open LLM Leaderboard上的聚合指标。
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 ndavidson/Phi-2-openassistant
数据集来源
- 自动创建于模型 ndavidson/Phi-2-openassistant 在 Open LLM Leaderboard 上的评估运行。
数据集构成
- 配置数量: 63
- 每个配置对应任务: 一个评估任务
- 数据集创建自: 1次运行
- 数据分割方式: 每个配置中的特定分割,以运行的时间戳命名。"train"分割始终指向最新结果。
额外配置
- 配置名称: "results"
- 用途: 存储所有运行结果的聚合结果,用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ndavidson__Phi-2-openassistant", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自 run 2024-04-15T19:54:23.691350。
配置详情
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_15T19_54_23.691350
- path: /details_harness|arc:challenge|25_2024-04-15T19-54-23.691350.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-15T19-54-23.691350.parquet
- split: 2024_04_15T19_54_23.691350
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_15T19_54_23.691350
- path: /details_harness|gsm8k|5_2024-04-15T19-54-23.691350.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-15T19-54-23.691350.parquet
- split: 2024_04_15T19_54_23.691350
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_15T19_54_23.691350
- path: /details_harness|hellaswag|10_2024-04-15T19-54-23.691350.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-15T19-54-23.691350.parquet
- split: 2024_04_15T19_54_23.691350
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_15T19_54_23.691350
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-international_law|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-management|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-marketing|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-sociology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-virology|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-04-15T19-54-23.691350.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-15T19-54-23.691350.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-15T19-54-23.691350.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_20
- path:
- split: 2024_04_15T19_54_23.691350
- data_files:



