open-llm-leaderboard-old/details_InnerI__InnerILLM-7B-slerp
收藏Hugging Face2024-02-13 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_InnerI__InnerILLM-7B-slerp
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型InnerI/InnerILLM-7B-slerp时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。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,用于计算和展示Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型InnerI/InnerILLM-7B-slerp时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。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,用于计算和展示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
- 数据集名称: Evaluation run of InnerI/InnerILLM-7B-slerp
- 数据集来源: 自动创建于模型 InnerI/InnerILLM-7B-slerp 在 Open LLM Leaderboard 的评估运行中。
- 数据集组成: 包含63个配置,每个配置对应一个评估任务。
- 数据集创建: 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_InnerI__InnerILLM-7B-slerp", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-02-13T05:45:44.319472
- 结果示例: 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 }, ... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_02_13T05_39_48.992789
- 路径: **/details_harness|arc:challenge|25_2024-02-13T05-39-48.992789.parquet
- 分割: 2024_02_13T05_45_44.319472
- 路径: **/details_harness|arc:challenge|25_2024-02-13T05-45-44.319472.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-02-13T05-45-44.319472.parquet
- 分割: 2024_02_13T05_39_48.992789
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_02_13T05_39_48.992789
- 路径: **/details_harness|gsm8k|5_2024-02-13T05-39-48.992789.parquet
- 分割: 2024_02_13T05_45_44.319472
- 路径: **/details_harness|gsm8k|5_2024-02-13T05-45-44.319472.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-02-13T05-45-44.319472.parquet
- 分割: 2024_02_13T05_39_48.992789
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_02_13T05_39_48.992789
- 路径: **/details_harness|hellaswag|10_2024-02-13T05-39-48.992789.parquet
- 分割: 2024_02_13T05_45_44.319472
- 路径: **/details_harness|hellaswag|10_2024-02-13T05-45-44.319472.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-02-13T05-45-44.319472.parquet
- 分割: 2024_02_13T05_39_48.992789
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_02_13T05_39_48.992789
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-management|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-13T05-39-48.992789.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-02-13T05-39-48.992789.parquet
- 路径:
- 分割: 2024_02_13T05_39_48.992789
- 数据文件:



