open-llm-leaderboard-old/details_vihangd__smartyplats-3b-v1
收藏数据集概述
该数据集是在评估模型 vihangd/smartyplats-3b-v1 在 Open LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建,每次运行可以在每个配置中找到特定的拆分,拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。
结果配置
一个额外的配置 "results" 存储所有运行结果的聚合,用于计算并在 Open LLM Leaderboard 上显示聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_vihangd__smartyplats-3b-v1", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的示例:
python { "all": { "em": 0.0017827181208053692, "em_stderr": 0.0004320097346039121, "f1": 0.054003775167785366, "f1_stderr": 0.0013390559797939118, "acc": 0.33403633256401344, "acc_stderr": 0.008080098450731814 }, "harness|drop|3": { "em": 0.0017827181208053692, "em_stderr": 0.0004320097346039121, "f1": 0.054003775167785366, "f1_stderr": 0.0013390559797939118 }, "harness|gsm8k|5": { "acc": 0.01061410159211524, "acc_stderr": 0.002822713322387704 }, "harness|winogrande|5": { "acc": 0.6574585635359116, "acc_stderr": 0.013337483579075925 } }
配置详情
-
harness_arc_challenge_25
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|arc:challenge|25_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|arc:challenge|25_2023-09-13T04-45-46.348158.parquet
-
harness_drop_3
- 拆分:2023_10_23T05_25_12.646031
- 路径:
**/details_harness|drop|3_2023-10-23T05-25-12.646031.parquet - 拆分:latest
- 路径:
**/details_harness|drop|3_2023-10-23T05-25-12.646031.parquet
-
harness_gsm8k_5
- 拆分:2023_10_23T05_25_12.646031
- 路径:
**/details_harness|gsm8k|5_2023-10-23T05-25-12.646031.parquet - 拆分:latest
- 路径:
**/details_harness|gsm8k|5_2023-10-23T05-25-12.646031.parquet
-
harness_hellaswag_10
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hellaswag|10_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hellaswag|10_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T04-45-46.348158.parquet等 - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T04-45-46.348158.parquet等
-
harness_hendrycksTest_abstract_algebra_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_anatomy_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_astronomy_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_business_ethics_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_biology_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_chemistry_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_computer_science_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_mathematics_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_medicine_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_college_physics_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_computer_security_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_econometrics_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-13T04-45-46.348158.parquet - 拆分:latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-13T04-45-46.348158.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 拆分:2023_09_13T04_45_46.348158
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T04-45-46.348158.parquet - 拆分:



