open-llm-leaderboard/details_louisgrc__Marengoli_7B_SLERP
收藏Hugging Face2024-03-25 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_louisgrc__Marengoli_7B_SLERP
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louisgrc/Marengoli_7B_SLERP时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集由1次运行生成,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。此外,results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louisgrc/Marengoli_7B_SLERP时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集由1次运行生成,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。此外,results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 louisgrc/Marengoli_7B_SLERP
数据集来源
- dataset_summary: 该数据集是在评估模型louisgrc/Marengoli_7B_SLERP在Open LLM Leaderboard上的运行过程中自动创建的。
数据集组成
- 配置数量: 63个配置
- 每个配置对应任务: 每个配置对应一个评估任务
- 数据集创建次数: 1次运行
- 数据集分割: 每个运行作为一个特定的分割,分割名称使用运行的时间戳命名
- 额外配置: “results”配置存储所有运行的聚合结果,用于计算和显示聚合指标
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_louisgrc__Marengoli_7B_SLERP", "harness_winogrande_5", split="train")
最新结果
- 结果来源: latest results from run 2024-03-25T07:32:30.978278
- 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_25T07_32_30.978278
- path: /details_harness|arc:challenge|25_2024-03-25T07-32-30.978278.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-25T07-32-30.978278.parquet
- split: 2024_03_25T07_32_30.978278
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_25T07_32_30.978278
- path: /details_harness|gsm8k|5_2024-03-25T07-32-30.978278.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-25T07-32-30.978278.parquet
- split: 2024_03_25T07_32_30.978278
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_25T07_32_30.978278
- path: /details_harness|hellaswag|10_2024-03-25T07-32-30.978278.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-25T07-32-30.978278.parquet
- split: 2024_03_25T07_32_30.978278
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_25T07_32_30.978278
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-25T07-32-30.978278.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-25T07-32-30.978278.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03
- path:
- split: 2024_03_25T07_32_30.978278
- data_files:



