open-llm-leaderboard-old/details_liminerity__Multiverse-Experiment-slerp-7b
收藏Hugging Face2024-03-09 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_liminerity__Multiverse-Experiment-slerp-7b
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型liminerity/Multiverse-Experiment-slerp-7b时自动创建的,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分割始终指向最新结果。此外,results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。
该数据集是在评估模型liminerity/Multiverse-Experiment-slerp-7b时自动创建的,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分割始终指向最新结果。此外,results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
- 数据集名称: Evaluation run of liminerity/Multiverse-Experiment-slerp-7b
- 数据集来源: 自动创建于模型 liminerity/Multiverse-Experiment-slerp-7b 在 Open LLM Leaderboard 的评估运行。
- 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1次运行中创建,每个运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
- 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_liminerity__Multiverse-Experiment-slerp-7b", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-03-09T12:02:01.054194
- 结果示例: python { "all": { "acc": 0.6518510677976063, "acc_stderr": 0.03203683002461246, "acc_norm": 0.6505703294705394, "acc_norm_stderr": 0.03271494006314174, "mc1": 0.631578947368421, "mc1_stderr": 0.016886551261046046, "mc2": 0.7792924999444771, "mc2_stderr": 0.013713064522592473 }, "harness|arc:challenge|25": { "acc": 0.7167235494880546, "acc_stderr": 0.013167478735134575, "acc_norm": 0.7286689419795221, "acc_norm_stderr": 0.012993807727545796 }, "harness|hellaswag|10": { "acc": 0.7177853017327226, "acc_stderr": 0.0044915745394418834, "acc_norm": 0.8914558852818164, "acc_norm_stderr": 0.003104306434972473 }, ... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_09T12_02_01.054194
- 路径:
**/details_harness|arc:challenge|25_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: 2024_03_09T12_02_01.054194
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_09T12_02_01.054194
- 路径:
**/details_harness|gsm8k|5_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: 2024_03_09T12_02_01.054194
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_09T12_02_01.054194
- 路径:
**/details_harness|hellaswag|10_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-03-09T12-02-01.054194.parquet
- 路径:
- 分割: 2024_03_09T12_02_01.054194
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_09T12_02_01.054194
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-09T12-02-01.054194.parquet- ...
- 路径:
- 分割: latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-09T12-02-01.054194.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-09T12-02-01.054194.parquet- ...
- 路径:
- 分割: 2024_03_09T12_02_01.054194
- 数据文件:



