open-llm-leaderboard-old/details_Technoculture__Medtulu-2x7b
收藏Hugging Face2024-01-16 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Technoculture__Medtulu-2x7b
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Technoculture/Medtulu-2x7b时自动创建的,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特定配置中的一个分割,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,用于计算和展示在Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型Technoculture/Medtulu-2x7b时自动创建的,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特定配置中的一个分割,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,用于计算和展示在Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集简介
该数据集是在评估模型Technoculture/Medtulu-2x7b在Open LLM Leaderboard上的运行过程中自动创建的。
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。
- 数据集来自1次运行,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。
- 额外的"results"配置存储所有运行的聚合结果,用于计算和显示在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_Technoculture__Medtulu-2x7b", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-01-16T08:08:44.091130的摘要: python { "all": { "acc": 0.4912286252834545, "acc_stderr": 0.03450140674623141, "acc_norm": 0.4966099863528162, "acc_norm_stderr": 0.035271481019980566, "mc1": 0.34394124847001223, "mc1_stderr": 0.016629087514276775, "mc2": 0.500358139155482, "mc2_stderr": 0.015732799808200134 }, ... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_16T08_08_44.091130
- path: **/details_harness|arc:challenge|25_2024-01-16T08-08-44.091130.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-16T08-08-44.091130.parquet
- split: 2024_01_16T08_08_44.091130
-
config_name: harness_gsm8k_5
- split: 2024_01_16T08_08_44.091130
- path: **/details_harness|gsm8k|5_2024-01-16T08-08-44.091130.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-16T08-08-44.091130.parquet
- split: 2024_01_16T08_08_44.091130
-
config_name: harness_hellaswag_10
- split: 2024_01_16T08_08_44.091130
- path: **/details_harness|hellaswag|10_2024-01-16T08-08-44.091130.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-16T08-08-44.091130.parquet
- split: 2024_01_16T08_08_44.091130
-
config_name: harness_hendrycksTest_5
- split: 2024_01_16T08_08_44.091130
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-virology|5_2024-01-16T08-08-44.091130.parquet
- **/details_harness|hendrycksTest-world_religions|5_
- path:
- split: 2024_01_16T08_08_44.091130



