open-llm-leaderboard-old/details_Eang__Marcoro14-7B-slerp
收藏Hugging Face2024-04-11 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Eang__Marcoro14-7B-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Open LLM Leaderboard上对模型Eang/Marcoro14-7B-slerp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。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的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Eang/Marcoro14-7B-slerp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。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的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
- 名称: Evaluation run of Eang/Marcoro14-7B-slerp
- 来源: 自动创建于模型 Eang/Marcoro14-7B-slerp 在 Open LLM Leaderboard 的评估运行。
- 组成: 包含 63 个配置,每个配置对应一个评估任务。
- 创建次数: 从 2 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: "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_Eang__Marcoro14-7B-slerp", "harness_winogrande_5", split="train")
最新结果
- 来源: 最新结果来自 run 2024-04-11T06:29:09.312845
- 详细指标: python { "all": { "acc": 0.6453218800457399, "acc_stderr": 0.03212887690836472, "acc_norm": 0.6457679471487517, "acc_norm_stderr": 0.032784859928949854, "mc1": 0.4283965728274174, "mc1_stderr": 0.017323088597314754, "mc2": 0.598389086821388, "mc2_stderr": 0.015156739153282793 }, "harness|arc:challenge|25": { "acc": 0.64419795221843, "acc_stderr": 0.013990571137918762, "acc_norm": 0.6757679180887372, "acc_norm_stderr": 0.013678810399518827 }, "harness|hellaswag|10": { "acc": 0.6697868950408286, "acc_stderr": 0.004693285694663837, "acc_norm": 0.8618801035650269, "acc_norm_stderr": 0.003443206472757467 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, ... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_04_11T06_28_30.403172
- 路径: **/details_harness|arc:challenge|25_2024-04-11T06-28-30.403172.parquet
- 分割: 2024_04_11T06_29_09.312845
- 路径: **/details_harness|arc:challenge|25_2024-04-11T06-29-09.312845.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-04-11T06-29-09.312845.parquet
- 分割: 2024_04_11T06_28_30.403172
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_04_11T06_28_30.403172
- 路径: **/details_harness|gsm8k|5_2024-04-11T06-28-30.403172.parquet
- 分割: 2024_04_11T06_29_09.312845
- 路径: **/details_harness|gsm8k|5_2024-04-11T06-29-09.312845.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-04-11T06-29-09.312845.parquet
- 分割: 2024_04_11T06_28_30.403172
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_04_11T06_28_30.403172
- 路径: **/details_harness|hellaswag|10_2024-04-11T06-28-30.403172.parquet
- 分割: 2024_04_11T06_29_09.312845
- 路径: **/details_harness|hellaswag|10_2024-04-11T06-29-09.312845.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-04-11T06-29-09.312845.parquet
- 分割: 2024_04_11T06_28_30.403172
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_04_11T06_28_30.403172
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-11T06-28-30.403172.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-11T06-28-30.403172.parquet
- ...
- 路径:
- 分割: 2024_04_11T06_29_09.312845
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-11T06-29-09.312845.parquet
- ...
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-11T06-29-09.312845.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-11T06-29-09.312845.parquet
- ... }
- 路径:
- 分割: 2024_04_11T06_28_30.403172
- 数据文件:



