open-llm-leaderboard-old/details_AurelPx__Dare-k-7B-ties
收藏Hugging Face2024-03-22 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_AurelPx__Dare-k-7B-ties
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型AurelPx/Dare-k-7B-ties的评估运行期间自动创建的,用于Open LLM Leaderboard。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到特定的分割,分割以运行的时间戳命名。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在模型AurelPx/Dare-k-7B-ties的评估运行期间自动创建的,用于Open LLM Leaderboard。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到特定的分割,分割以运行的时间戳命名。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示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
数据集创建
- 数据集名称: Evaluation run of AurelPx/Dare-k-7B-ties
- 创建目的: 自动创建用于评估模型 AurelPx/Dare-k-7B-ties 在 Open LLM Leaderboard 上的表现。
数据集结构
- 配置数量: 63 个配置,每个配置对应一个评估任务。
- 数据来源: 数据集由 1 次运行生成,每个运行结果存储在特定的分割中,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。
- 聚合结果: 一个额外的配置 "results" 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_AurelPx__Dare-k-7B-ties", "harness_winogrande_5", split="train")
最新结果
- 运行时间: 2024-03-22T01:51:21.252099
- 结果示例: python { "all": { "acc": 0.6549505412275739, "acc_stderr": 0.0318457403527982, "acc_norm": 0.6545951827427666, "acc_norm_stderr": 0.03250570751010229, "mc1": 0.47123623011015914, "mc1_stderr": 0.017474513848525525, "mc2": 0.639077073664674, "mc2_stderr": 0.015151703268240214 }, "harness|arc:challenge|25": { "acc": 0.6680887372013652, "acc_stderr": 0.01376098820088054, "acc_norm": 0.6911262798634812, "acc_norm_stderr": 0.013501770929344003 }, "harness|hellaswag|10": { "acc": 0.6890061740689106, "acc_stderr": 0.004619542392006391, "acc_norm": 0.8708424616610237, "acc_norm_stderr": 0.0033468881153524573 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, # 其他任务的结果... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_22T01_51_21.252099
- 路径: **/details_harness|arc:challenge|25_2024-03-22T01-51-21.252099.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-22T01-51-21.252099.parquet
- 分割: 2024_03_22T01_51_21.252099
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_22T01_51_21.252099
- 路径: **/details_harness|gsm8k|5_2024-03-22T01-51-21.252099.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-03-22T01-51-21.252099.parquet
- 分割: 2024_03_22T01_51_21.252099
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_22T01_51_21.252099
- 路径: **/details_harness|hellaswag|10_2024-03-22T01-51-21.252099.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-03-22T01-51-21.252099.parquet
- 分割: 2024_03_22T01_51_21.252099
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_22T01_51_21.252099
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-22T01-51-21.252099.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-22T01-51-21.2520
- 路径:
- 分割: 2024_03_22T01_51_21.252099
- 数据文件:



