open-llm-leaderboard/details_4season__alignment-model-test9
收藏Hugging Face2024-04-08 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_4season__alignment-model-test9
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型4season/alignment-model-test9在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。它包含1次运行的结果,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。一个名为results的额外配置存储了运行的所有聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
该数据集是在模型4season/alignment-model-test9在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。它包含1次运行的结果,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。一个名为results的额外配置存储了运行的所有聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
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 4season/alignment-model-test9
数据集描述
- dataset_summary: 该数据集是在评估模型4season/alignment-model-test9运行期间自动创建的,用于Open LLM Leaderboard。
数据集组成
- 配置数量: 63个
- 每个配置对应一个评估任务
- 数据集来源: 1次运行
- 数据集分割: 每个配置中的特定分割,以运行的时间戳命名
- 额外配置: "results",存储所有运行结果的聚合结果
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_4season__alignment-model-test9", "harness_winogrande_5", split="train")
最新结果
- 结果来源: latest results from run 2024-04-08T15:04:12.877958
- 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。
配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_08T15_04_12.877958
- path: /details_harness|arc:challenge|25_2024-04-08T15-04-12.877958.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-08T15-04-12.877958.parquet
- split: 2024_04_08T15_04_12.877958
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_08T15_04_12.877958
- path: /details_harness|gsm8k|5_2024-04-08T15-04-12.877958.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-08T15-04-12.877958.parquet
- split: 2024_04_08T15_04_12.877958
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_08T15_04_12.877958
- path: /details_harness|hellaswag|10_2024-04-08T15-04-12.877958.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-08T15-04-12.877958.parquet
- split: 2024_04_08T15_04_12.877958
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_08T15_04_12.877958
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-08T15-04-12.877958.parquet
- /details_harness|hendrycksTest-high_school_biology
- path:
- split: 2024_04_08T15_04_12.877958
- data_files:



