open-llm-leaderboard/details_mayacinka__Open-StaMis-v02-stock
收藏Hugging Face2024-04-17 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_mayacinka__Open-StaMis-v02-stock
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mayacinka/Open-StaMis-v02-stock在Open LLM Leaderboard上的评估运行期间自动创建的。它由63个配置组成,每个配置对应一个被评估的任务。数据集是从1次运行中生成的,每次运行作为每个配置中的一个特定拆分,使用运行的时间戳命名。train拆分始终指向最新结果。一个额外的配置results存储了运行的所有聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用Python中的datasets库加载该数据集。
该数据集是在模型mayacinka/Open-StaMis-v02-stock在Open LLM Leaderboard上的评估运行期间自动创建的。它由63个配置组成,每个配置对应一个被评估的任务。数据集是从1次运行中生成的,每次运行作为每个配置中的一个特定拆分,使用运行的时间戳命名。train拆分始终指向最新结果。一个额外的配置results存储了运行的所有聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用Python中的datasets库加载该数据集。
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 mayacinka/Open-StaMis-v02-stock
数据集来源
- 自动创建于模型 mayacinka/Open-StaMis-v02-stock 在 Open LLM Leaderboard 的评估运行中。
数据集组成
- 配置数量: 63
- 每个配置: 对应一个评估任务
- 创建自: 1次运行
- 数据分割: 每个运行作为特定分割,以运行时间戳命名
- "train" 分割: 指向最新结果
- 额外配置 "results": 存储所有聚合结果,用于计算和显示聚合指标
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_mayacinka__Open-StaMis-v02-stock", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自 run 2024-04-17T06:19:01.550319
- 包含多个任务的评估结果,每个任务在 "results" 和 "latest" 分割中可找到
数据集配置详情
配置列表
- harness_arc_challenge_25
- 数据文件:
- 分割: 2024_04_17T06_19_01.550319, latest
- 路径: /details_harness|arc:challenge|25_2024-04-17T06-19-01.550319.parquet
- 数据文件:
- harness_gsm8k_5
- 数据文件:
- 分割: 2024_04_17T06_19_01.550319, latest
- 路径: /details_harness|gsm8k|5_2024-04-17T06-19-01.550319.parquet
- 数据文件:
- harness_hellaswag_10
- 数据文件:
- 分割: 2024_04_17T06_19_01.550319, latest
- 路径: /details_harness|hellaswag|10_2024-04-17T06-19-01.550319.parquet
- 数据文件:
- harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_04_17T06_19_01.550319, latest
- 路径:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-international_law|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-management|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-marketing|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-sociology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-virology|5_2024-04-17T06-19-01.550319.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-04-17T06-19-01.550319.parquet
- 数据文件:
以上信息总结了数据集的基本结构、来源、组成以及如何访问和使用数据集中的特定配置。



