open-llm-leaderboard/details_vanillaOVO__merge_7B_state_1
收藏Hugging Face2024-03-24 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_vanillaOVO__merge_7B_state_1
下载链接
链接失效反馈官方服务:
资源简介:
数据集是在评估模型vanillaOVO/merge_7B_state_1在Open LLM Leaderboard上的表现时自动创建的。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命名。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。
数据集是在评估模型vanillaOVO/merge_7B_state_1在Open LLM Leaderboard上的表现时自动创建的。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命名。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 vanillaOVO/merge_7B_state_1
数据集描述
- dataset_summary: 该数据集是在评估模型vanillaOVO/merge_7B_state_1运行期间自动创建的,用于Open LLM Leaderboard。
- 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: 从1个运行中创建,每个运行作为特定分割存储,分割名称使用运行的时间戳命名。"train"分割始终指向最新结果。
- 额外配置: “results”配置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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_vanillaOVO__merge_7B_state_1", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 来自run 2024-03-24T15:13:36.617897。
- 结果内容: 包含多个任务的评估结果,如准确率(acc)、标准误差(acc_stderr)等。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_03_24T15_13_36.617897
- path: /details_harness|arc:challenge|25_2024-03-24T15-13-36.617897.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-24T15-13-36.617897.parquet
- split: 2024_03_24T15_13_36.617897
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_24T15_13_36.617897
- path: /details_harness|gsm8k|5_2024-03-24T15-13-36.617897.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-24T15-13-36.617897.parquet
- split: 2024_03_24T15_13_36.617897
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_24T15_13_36.617897
- path: /details_harness|hellaswag|10_2024-03-24T15-13-36.617897.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-24T15-13-36.617897.parquet
- split: 2024_03_24T15_13_36.617897
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_24T15_13_36.617897
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-24T15-13-36.617897.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-24T15-13-36.617897.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-24T15-13-36.617897.parquet
- path:
- split: 2024_03_24T15_13_36.617897
- data_files:



