open-llm-leaderboard/details_Aratako__Beyonder-4x7B-random-lora
收藏Hugging Face2024-04-02 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Aratako__Beyonder-4x7B-random-lora
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Aratako/Beyonder-4x7B-random-lora时自动创建的,主要用于在Open LLM Leaderboard上进行评估。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,每次运行的结果存储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,还有一个名为results的配置,存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型Aratako/Beyonder-4x7B-random-lora时自动创建的,主要用于在Open LLM Leaderboard上进行评估。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,每次运行的结果存储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,还有一个名为results的配置,存储了所有运行的聚合结果,并用于计算和显示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 Aratako/Beyonder-4x7B-random-lora
数据集描述
- dataset_summary: 该数据集是在评估模型Aratako/Beyonder-4x7B-random-lora的过程中自动创建的,用于Open LLM Leaderboard。
数据集构成
- 数据集组成: 包含63个配置,每个配置对应一个评估任务。
- 数据集创建: 数据集由1次运行创建,每次运行作为一个特定的分割存在,分割名称使用运行的时间戳命名。
- 额外配置: “results”配置存储了所有运行的聚合结果,用于计算和显示聚合指标。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Aratako__Beyonder-4x7B-random-lora", "harness_winogrande_5", split="train")
最新结果
- 结果示例: 展示了不同任务的准确率(acc)和标准误差(acc_stderr)等指标。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_02T20_16_42.836942
- path: /details_harness|arc:challenge|25_2024-04-02T20-16-42.836942.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-02T20-16-42.836942.parquet
- split: 2024_04_02T20_16_42.836942
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_02T20_16_42.836942
- path: /details_harness|gsm8k|5_2024-04-02T20-16-42.836942.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-02T20-16-42.836942.parquet
- split: 2024_04_02T20_16_42.836942
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_02T20_16_42.836942
- path: /details_harness|hellaswag|10_2024-04-02T20-16-42.836942.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-02T20-16-42.836942.parquet
- split: 2024_04_02T20_16_42.836942
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_02T20_16_42.836942
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-02T20-16-42.836942.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-02T20-16-42.836942.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-02T20-16-42.836942.parquet
- path:
- split: 2024_04_02T20_16_42.836942
- data_files:
-
config_name: harness_winogrande_5
- data_files:
- split: 2024_04_02T20_16_42.836942
- path: /details_harness|winogrande|5_2024-04-02T20-16-42.836942.parquet
- split: latest
- path: /details_harness|winogrande|5_2024-04-02T20-16-42.836942.parquet
- split: 2024_04_02T20_16_42.836942
- data_files:



