open-llm-leaderboard-old/details_MSL7__INEX12-7b
收藏Hugging Face2024-03-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_MSL7__INEX12-7b
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MSL7/INEX12-7b进行评估时自动创建的。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,每次运行的结果作为一个特定的分割存储在配置中,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Open LLM Leaderboard上对模型MSL7/INEX12-7b进行评估时自动创建的。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,每次运行的结果作为一个特定的分割存储在配置中,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
数据集名称
- 名称: Evaluation run of MSL7/INEX12-7b
数据集组成
- 配置数量: 63个配置,每个配置对应一个评估任务。
- 创建来源: 数据集是从1次运行中自动创建的。每个运行结果作为一个特定的分割存储在每个配置中,分割名称使用运行的时间戳。
- 最新结果: "train"分割始终指向最新的结果。
- 汇总结果: 一个额外的配置"results"存储所有运行的汇总结果,用于计算和显示在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_MSL7__INEX12-7b", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2024-03-03T14:55:00.850734
- 结果示例: python { "all": { "acc": 0.6507693403220257, "acc_stderr": 0.03203662001217349, "acc_norm": 0.6496481941817072, "acc_norm_stderr": 0.03271343575112632, "mc1": 0.6303549571603427, "mc1_stderr": 0.016898180706973878, "mc2": 0.780369069282656, "mc2_stderr": 0.013689166115894536 }, "harness|arc:challenge|25": { "acc": 0.7167235494880546, "acc_stderr": 0.013167478735134575, "acc_norm": 0.7295221843003413, "acc_norm_stderr": 0.012980954547659556 }, "harness|hellaswag|10": { "acc": 0.7173869747062338, "acc_stderr": 0.004493495872000108, "acc_norm": 0.8913563035251942, "acc_norm_stderr": 0.0031055566317393897 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, # 更多任务结果... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_03T14_55_00.850734
- 路径: **/details_harness|arc:challenge|25_2024-03-03T14-55-00.850734.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-03T14-55-00.850734.parquet
- 分割: 2024_03_03T14_55_00.850734
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_03T14_55_00.850734
- 路径: **/details_harness|gsm8k|5_2024-03-03T14-55-00.850734.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-03-03T14-55-00.850734.parquet
- 分割: 2024_03_03T14_55_00.850734
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_03T14_55_00.850734
- 路径: **/details_harness|hellaswag|10_2024-03-03T14-55-00.850734.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-03-03T14-55-00.850734.parquet
- 分割: 2024_03_03T14_55_00.850734
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_03T14_55_00.850734
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-03T14-55-00.850734.parquet
- **/details_harness|hendry
- 路径:
- 分割: 2024_03_03T14_55_00.850734
- 数据文件:



