open-llm-leaderboard-old/details_UCLA-AGI__test0
收藏Hugging Face2024-01-05 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_UCLA-AGI__test0
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UCLA-AGI/test0进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集由1次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个额外的配置results存储了运行的所有聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用提供的Python代码片段加载数据集。
该数据集是在Open LLM Leaderboard上对模型UCLA-AGI/test0进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集由1次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个额外的配置results存储了运行的所有聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用提供的Python代码片段加载数据集。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集名称
- Evaluation run of UCLA-AGI/test0
数据集来源
- 该数据集是在模型 UCLA-AGI/test0 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 数据集由63个配置组成,每个配置对应一个评估任务。
- 数据集从1次运行中创建,每个运行可以在每个配置中作为一个特定的分片找到,分片名称使用运行的时间戳。
- "train" 分片始终指向最新的结果。
- 一个额外的配置 "results" 存储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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_UCLA-AGI__test0", "harness_winogrande_5", split="train")
最新结果
- 这些是最新结果,来自2024-01-05T12:00:11.696869的运行。
配置详情
-
harness_arc_challenge_25
- 分片: 2024_01_05T12_00_11.696869, latest
- 路径: **/details_harness|arc:challenge|25_2024-01-05T12-00-11.696869.parquet
-
harness_gsm8k_5
- 分片: 2024_01_05T12_00_11.696869, latest
- 路径: **/details_harness|gsm8k|5_2024-01-05T12-00-11.696869.parquet
-
harness_hellaswag_10
- 分片: 2024_01_05T12_00_11.696869, latest
- 路径: **/details_harness|hellaswag|10_2024-01-05T12-00-11.696869.parquet
-
harness_hendrycksTest_5
- 分片: 2024_01_05T12_00_11.696869, latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-virology|5_2024-01-05T12-00-11.696869.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-01-05T12-00-11.696869.parquet



