open-llm-leaderboard-old/details_louisbrulenaudet__Pearl-3x7B
收藏Hugging Face2024-02-09 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_louisbrulenaudet__Pearl-3x7B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在对louisbrulenaudet/Pearl-3x7B模型进行评估运行期间自动创建的,用于Open LLM排行榜。数据集包含63个配置,每个配置对应一个评估任务。数据集来自1次运行,每次运行以运行的时间戳命名为特定的分割。train分割始终指向最新结果。额外的results配置存储了运行的所有聚合结果,用于在排行榜上计算和显示聚合指标。数据集结构允许使用HuggingFace数据集库加载运行的详细信息。
该数据集是在对louisbrulenaudet/Pearl-3x7B模型进行评估运行期间自动创建的,用于Open LLM排行榜。数据集包含63个配置,每个配置对应一个评估任务。数据集来自1次运行,每次运行以运行的时间戳命名为特定的分割。train分割始终指向最新结果。额外的results配置存储了运行的所有聚合结果,用于在排行榜上计算和显示聚合指标。数据集结构允许使用HuggingFace数据集库加载运行的详细信息。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集基本信息
- 数据集名称: Evaluation run of louisbrulenaudet/Pearl-3x7B
- 数据集来源: 自动创建于模型 louisbrulenaudet/Pearl-3x7B 在 Open LLM Leaderboard 的评估运行中。
- 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 次运行中创建,每个运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
- 额外配置: 一个名为 "results" 的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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_louisbrulenaudet__Pearl-3x7B", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-02-09T22:08:19.014926 运行
- 结果示例:
python
{
"all": {
"acc": 0.6440565726482342,
"acc_stderr": 0.031991772306209865,
"acc_norm": 0.6465517429934861,
"acc_norm_stderr": 0.032625459341892864,
"mc1": 0.35495716034271724,
"mc1_stderr": 0.016750862381375898,
"mc2": 0.5216733642218897,
"mc2_stderr": 0.015427199436320826
},
"harness|arc:challenge|25": {
"acc": 0.6228668941979523,
"acc_stderr": 0.014163366896192601,
"acc_norm": 0.6552901023890785,
"acc_norm_stderr": 0.01388881628678211
},
"harness|hellaswag|10": {
"acc": 0.6701852220673172,
"acc_stderr": 0.00469184866539907,
"acc_norm": 0.8554072893845848,
"acc_norm_stderr": 0.0035097096477918386
},
更多任务结果...
}
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_02_09T22_08_19.014926
- 路径:
**/details_harness|arc:challenge|25_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: 2024_02_09T22_08_19.014926
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_02_09T22_08_19.014926
- 路径:
**/details_harness|gsm8k|5_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: 2024_02_09T22_08_19.014926
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_02_09T22_08_19.014926
- 路径:
**/details_harness|hellaswag|10_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-02-09T22-08-19.014926.parquet
- 路径:
- 分割: 2024_02_09T22_08_19.014926
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_02_09T22_08_19.014926
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-anatomy|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-astronomy|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_biology|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-college_physics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-computer_security|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-econometrics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-global_facts|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-human_aging|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-international_law|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-management|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-marketing|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-nutrition|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-philosophy|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-prehistory|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-02-09T22-08-19.014926.parquet**/details_harness|hendrycksTest-professional_law|5_2024-02-09T22-08-19.014926.parquet- `**/details_harness|hendrycksTest-professional_medicine|5_2024
- 路径:
- 分割: 2024_02_09T22_08_19.014926
- 数据文件:



