open-llm-leaderboard-old/details_venkycs__ZySec-1B
收藏Hugging Face2024-01-27 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_venkycs__ZySec-1B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型venkycs/ZySec-1B时自动创建的,用于Open LLM Leaderboard。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储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,用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型venkycs/ZySec-1B时自动创建的,用于Open LLM Leaderboard。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储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,用于计算和显示Open LLM Leaderboard上的聚合指标。
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 venkycs/ZySec-1B
- 来源: 自动创建于模型 venkycs/ZySec-1B 在 Open LLM Leaderboard 的评估运行期间。
- 配置数量: 63个配置,每个配置对应一个评估任务。
- 创建次数: 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_venkycs__ZySec-1B", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 最新结果来自 run 2024-01-27T19:58:01.944130
- 结果示例: python { "all": { "acc": 0.2578838995098124, "acc_stderr": 0.030721943510218043, "acc_norm": 0.25894411476824014, "acc_norm_stderr": 0.0314742515286692, "mc1": 0.21909424724602203, "mc1_stderr": 0.014480038578757447, "mc2": 0.3565914064488495, "mc2_stderr": 0.014002389029353163 }, "harness|arc:challenge|25": { "acc": 0.3583617747440273, "acc_stderr": 0.014012883334859866, "acc_norm": 0.3839590443686007, "acc_norm_stderr": 0.014212444980651889 }, "harness|hellaswag|10": { "acc": 0.4649472216689902, "acc_stderr": 0.004977504446609, "acc_norm": 0.6153156741684923, "acc_norm_stderr": 0.004855262903270809 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, ... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_27T19_58_01.944130
- 路径: **/details_harness|arc:challenge|25_2024-01-27T19-58-01.944130.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-27T19-58-01.944130.parquet
- 分割: 2024_01_27T19_58_01.944130
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_27T19_58_01.944130
- 路径: **/details_harness|gsm8k|5_2024-01-27T19-58-01.944130.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-27T19-58-01.944130.parquet
- 分割: 2024_01_27T19_58_01.944130
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_27T19_58_01.944130
- 路径: **/details_harness|hellaswag|10_2024-01-27T19-58-01.944130.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-27T19-58-01.944130.parquet
- 分割: 2024_01_27T19_58_01.944130
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_27T19_58_01.944130
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-27T19-58-01.944130.parquet
- ...
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-27T19-58-01.944130.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-27T19-58-01.944130.parquet
- ...
- 路径:
- 分割: 2024_01_27T19_58_01.944130
- 数据文件:



