open-llm-leaderboard/details_caisarl76__Mistral-7B-OpenOrca-Guanaco-accu16
收藏Hugging Face2023-10-26 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_caisarl76__Mistral-7B-OpenOrca-Guanaco-accu16
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caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16进行评估时自动创建的。它由64个配置组成,每个配置对应一个评估任务。数据集由2次运行创建,每次运行作为每个配置中的一个特定分割,分割名称使用运行的时间戳。train分割始终指向最新结果。一个额外的配置results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。
This dataset was automatically created during the evaluation of the model caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16 on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to one evaluation task. The dataset is constructed from two runs, with each run serving as a specific split for every configuration, and the split names are based on the timestamps of the runs. The 'train' split always points to the most recent evaluation results. An additional configuration named 'results' stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard.
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
该数据集是在对模型 caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16 进行评估运行期间自动创建的。数据集包含64个配置,每个配置对应一个评估任务。数据集从2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。
数据集结构
配置详情
-
harness_arc_challenge_25
- 分割:
2023_10_09T15_53_10.944584- 路径:
**/details_harness|arc:challenge|25_2023-10-09T15-53-10.944584.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|arc:challenge|25_2023-10-09T15-53-10.944584.parquet
- 路径:
- 分割:
-
harness_drop_3
- 分割:
2023_10_26T08_32_33.327127- 路径:
**/details_harness|drop|3_2023-10-26T08-32-33.327127.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|drop|3_2023-10-26T08-32-33.327127.parquet
- 路径:
- 分割:
-
harness_gsm8k_5
- 分割:
2023_10_26T08_32_33.327127- 路径:
**/details_harness|gsm8k|5_2023-10-26T08-32-33.327127.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|gsm8k|5_2023-10-26T08-32-33.327127.parquet
- 路径:
- 分割:
-
harness_hellaswag_10
- 分割:
2023_10_09T15_53_10.944584- 路径:
**/details_harness|hellaswag|10_2023-10-09T15-53-10.944584.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|hellaswag|10_2023-10-09T15-53-10.944584.parquet
- 路径:
- 分割:
-
harness_hendrycksTest_5
- 分割:
2023_10_09T15_53_10.944584- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-anatomy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-astronomy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_biology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_physics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-computer_security|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-econometrics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-global_facts|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-human_aging|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-international_law|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-management|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-marketing|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-nutrition|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-philosophy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-prehistory|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-professional_law|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-professional_medicine|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-professional_psychology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-public_relations|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-security_studies|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-sociology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-virology|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-world_religions|5_2023-10-09T15-53-10.944584.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-anatomy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-astronomy|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T15-53-10.944584.parquet**/details_harness|hendrycksTest-college_biology|5_2023-10-09T15-53-10.944584.parquet- `**/details_harness|hendrycksTest-college_
- 路径:
- 分割:



