open-llm-leaderboard/details_nlpguy__T3QM7
收藏Hugging Face2024-03-21 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_nlpguy__T3QM7
下载链接
链接失效反馈官方服务:
资源简介:
数据集是在模型nlpguy/T3QM7的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。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,每次运行都可以在每个配置中找到特定的分割,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,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
数据集是在模型nlpguy/T3QM7的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。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,每次运行都可以在每个配置中找到特定的分割,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,results配置存储了所有运行的聚合结果,并用于计算和显示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 nlpguy/T3QM7
数据集来源
- dataset_summary: 该数据集是在评估模型nlpguy/T3QM7在Open LLM Leaderboard上的运行过程中自动创建的。
数据集构成
- 数据集结构: 由63个配置组成,每个配置对应一个评估任务。
- 创建次数: 数据集由1次运行创建。
- 数据分割: 每次运行作为一个特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新的结果。
- 额外配置: 存在一个名为"results"的额外配置,存储所有运行的聚合结果,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_nlpguy__T3QM7", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 最新结果来自run 2024-03-21T11:11:09.902176。
- 结果内容: 包括多个任务的准确率(acc)和标准误差(acc_stderr)等指标。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_03_21T11_11_09.902176
- path: /details_harness|arc:challenge|25_2024-03-21T11-11-09.902176.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-21T11-11-09.902176.parquet
- split: 2024_03_21T11_11_09.902176
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_21T11_11_09.902176
- path: /details_harness|gsm8k|5_2024-03-21T11-11-09.902176.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-21T11-11-09.902176.parquet
- split: 2024_03_21T11_11_09.902176
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_21T11_11_09.902176
- path: /details_harness|hellaswag|10_2024-03-21T11-11-09.902176.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-21T11-11-09.902176.parquet
- split: 2024_03_21T11_11_09.902176
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_21T11_11_09.902176
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-international_law|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-management|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-marketing|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-sociology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-virology|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-03-21T11-11-09.902176.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-21T11-11-09.902176.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-21T11-11-09.902176.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-21T11-11-09.902176.par
- path:
- split: 2024_03_21T11_11_09.902176
- data_files:



