open-llm-leaderboard-old/details_Qwen__Qwen2-beta-14B
收藏Hugging Face2024-01-30 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Qwen__Qwen2-beta-14B
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Qwen/Qwen2-beta-14B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。此外,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。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
该数据集是在Open LLM Leaderboard上对模型Qwen/Qwen2-beta-14B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。此外,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。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集简介
该数据集是在评估模型 Qwen/Qwen2-beta-14B 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 数据集包含 63 个配置,每个配置对应一个评估任务。
- 数据集从 2 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,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 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_Qwen__Qwen2-beta-14B_private", "harness_gsm8k_5", split="train")
最新结果
以下是 2024-01-30T11:39:41.356084 运行的最新结果: python { "all": { "acc": 0.6762699014404853, "acc_stderr": 0.012888247397371141 }, "harness|gsm8k|5": { "acc": 0.6762699014404853, "acc_stderr": 0.012888247397371141 } }
配置详情
以下是部分配置及其数据文件路径:
harness_arc_challenge_25
- 分割: 2024_01_29T15_38_03.755073
- 路径: **/details_harness|arc:challenge|25_2024-01-29T15-38-03.755073.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-29T15-38-03.755073.parquet
harness_gsm8k_5
- 分割: 2024_01_29T15_38_03.755073
- 路径: **/details_harness|gsm8k|5_2024-01-29T15-38-03.755073.parquet
- 分割: 2024_01_30T11_39_41.356084
- 路径: **/details_harness|gsm8k|5_2024-01-30T11-39-41.356084.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-30T11-39-41.356084.parquet
harness_hellaswag_10
- 分割: 2024_01_29T15_38_03.755073
- 路径: **/details_harness|hellaswag|10_2024-01-29T15-38-03.755073.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-29T15-38-03.755073.parquet
harness_hendrycksTest_5
- 分割: 2024_01_29T15_38_03.755073
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-virology|5_2024-01-29T15-38-03.755073.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-01-2
- 路径:



