open-llm-leaderboard-old/details_vicgalle__ConfigurableSOLAR-10.7B
收藏Hugging Face2024-03-11 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_vicgalle__ConfigurableSOLAR-10.7B
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vicgalle/ConfigurableSOLAR-10.7B时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为一个特定的分割存储,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,用于在Open LLM Leaderboard上计算和展示聚合指标。
该数据集是在评估模型vicgalle/ConfigurableSOLAR-10.7B时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为一个特定的分割存储,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,用于在Open LLM Leaderboard上计算和展示聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集摘要
该数据集是在对模型 vicgalle/ConfigurableSOLAR-10.7B 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 63 个配置,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找到特定的拆分,拆分名称使用运行的时间戳。
- "train" 拆分始终指向最新的结果。
- 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_vicgalle__ConfigurableSOLAR-10.7B", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果,来自 2024-03-11T05:22:07.852754 的运行。每个任务的结果包括准确率(acc)、标准化准确率(acc_norm)、以及它们的误差(stderr)。
配置详情
-
config_name: harness_arc_challenge_25
- 拆分: 2024_03_11T05_22_07.852754
- 路径: **/details_harness|arc:challenge|25_2024-03-11T05-22-07.852754.parquet
- 拆分: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-11T05-22-07.852754.parquet
-
config_name: harness_gsm8k_5
- 拆分: 2024_03_11T05_22_07.852754
- 路径: **/details_harness|gsm8k|5_2024-03-11T05-22-07.852754.parquet
- 拆分: latest
- 路径: **/details_harness|gsm8k|5_2024-03-11T05-22-07.852754.parquet
-
config_name: harness_hellaswag_10
- 拆分: 2024_03_11T05_22_07.852754
- 路径: **/details_harness|hellaswag|10_2024-03-11T05-22-07.852754.parquet
- 拆分: latest
- 路径: **/details_harness|hellaswag|10_2024-03-11T05-22-07.852754.parquet
-
config_name: harness_hendrycksTest_5
- 拆分: 2024_03_11T05_22_07.852754
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-virology|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-03-11T05-22-07.852754.parquet
- 拆分: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-11T05-22-07.852754.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-11T05-22-07.852



