open-llm-leaderboard-old/details_feeltheAGI__mistral-maths7B
收藏Hugging Face2024-03-10 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_feeltheAGI__mistral-maths7B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型`feeltheAGI/mistral-maths7B`进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,并且每个配置的`train`分割指向最新的结果。此外,`results`配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
该数据集是在Open LLM Leaderboard上对模型`feeltheAGI/mistral-maths7B`进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,并且每个配置的`train`分割指向最新的结果。此外,`results`配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
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 feeltheAGI/mistral-maths7B
- 数据集描述: 该数据集是在对模型 feeltheAGI/mistral-maths7B 进行评估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。
- 数据集来源: 从1次运行中创建,每次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: "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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_feeltheAGI__mistral-maths7B", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2024-03-10T12:11:08.454866
- 结果示例:
python
{
"all": {
"acc": 0.5469269437334953,
"acc_stderr": 0.03410012829437269,
"acc_norm": 0.5483740722847594,
"acc_norm_stderr": 0.03479918880134391,
"mc1": 0.40636474908200737,
"mc1_stderr": 0.017193835812093904,
"mc2": 0.5730029044942812,
"mc2_stderr": 0.01530435216141352
},
"harness|arc:challenge|25": {
"acc": 0.5042662116040956,
"acc_stderr": 0.014610858923956948,
"acc_norm": 0.5204778156996587,
"acc_norm_stderr": 0.014599131353035009
},
"harness|hellaswag|10": {
"acc": 0.5595498904600678,
"acc_stderr": 0.004954265595373459,
"acc_norm": 0.7476598287193786,
"acc_norm_stderr": 0.004334676952703863
},
其他任务结果...
}
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_10T12_11_08.454866
- 路径: **/details_harness|arc:challenge|25_2024-03-10T12-11-08.454866.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-10T12-11-08.454866.parquet
- 分割: 2024_03_10T12_11_08.454866
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_10T12_11_08.454866
- 路径: **/details_harness|gsm8k|5_2024-03-10T12-11-08.454866.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-03-10T12-11-08.454866.parquet
- 分割: 2024_03_10T12_11_08.454866
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_10T12_11_08.454866
- 路径: **/details_harness|hellaswag|10_2024-03-10T12-11-08.454866.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-03-10T12-11-08.454866.parquet
- 分割: 2024_03_10T12_11_08.454866
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_10T12_11_08.454866
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-10T12-11-08.454866.parquet
- **/details_harness|hend
- 路径:
- 分割: 2024_03_10T12_11_08.454866
- 数据文件:



