open-llm-leaderboard/details_0-hero__Matter-0.2-32B
收藏Hugging Face2024-04-16 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_0-hero__Matter-0.2-32B
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0-hero/Matter-0.2-32B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行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,还有一个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Open LLM Leaderboard上对模型0-hero/Matter-0.2-32B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行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,还有一个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 0-hero/Matter-0.2-32B
数据集创建
- Source: Dataset automatically created during the evaluation run of model 0-hero/Matter-0.2-32B on the Open LLM Leaderboard.
数据集结构
- Composition: Composed of 63 configurations, each corresponding to one of the evaluated tasks.
- Creation: Created from 1 run(s). Each run is found as a specific split in each configuration, named using the timestamp of the run.
- Special Split: "train" split always points to the latest results.
- Additional Configuration: "results" stores all the aggregated results of the run, used to compute and display aggregated metrics on the Open LLM Leaderboard.
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_0-hero__Matter-0.2-32B", "harness_winogrande_5", split="train")
最新结果
- Latest Results: Latest results from run 2024-04-16T00:58:41.781770
数据集详细配置
配置列表
-
harness_arc_challenge_25
- Data Files:
- Split: 2024_04_16T00_58_41.781770
- Path: /details_harness|arc:challenge|25_2024-04-16T00-58-41.781770.parquet
- Split: latest
- Path: /details_harness|arc:challenge|25_2024-04-16T00-58-41.781770.parquet
- Split: 2024_04_16T00_58_41.781770
- Data Files:
-
harness_gsm8k_5
- Data Files:
- Split: 2024_04_16T00_58_41.781770
- Path: /details_harness|gsm8k|5_2024-04-16T00-58-41.781770.parquet
- Split: latest
- Path: /details_harness|gsm8k|5_2024-04-16T00-58-41.781770.parquet
- Split: 2024_04_16T00_58_41.781770
- Data Files:
-
harness_hellaswag_10
- Data Files:
- Split: 2024_04_16T00_58_41.781770
- Path: /details_harness|hellaswag|10_2024-04-16T00-58-41.781770.parquet
- Split: latest
- Path: /details_harness|hellaswag|10_2024-04-16T00-58-41.781770.parquet
- Split: 2024_04_16T00_58_41.781770
- Data Files:
-
harness_hendrycksTest_5
- Data Files:
- Split: 2024_04_16T00_58_41.781770
- Path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-international_law|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-management|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-marketing|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-sociology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-virology|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-04-16T00-58-41.781770.parquet
- Path:
- Split: latest
- Path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-16T00-58-41.781770.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-16T00-58-41.781770.parquet
- **/details_harness|hendrycksTest-business_ethics
- Path:
- Split: 2024_04_16T00_58_41.781770
- Data Files:



