open-llm-leaderboard-old/details_NeuralNovel__Gecko-7B-v0.1
收藏Hugging Face2024-01-16 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_NeuralNovel__Gecko-7B-v0.1
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NeuralNovel/Gecko-7B-v0.1在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从3次运行中创建的,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。一个名为results的额外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`函数加载运行细节的示例。README中还包含了特定运行的最新结果,展示了不同任务的各种指标,如准确率和错误率。
该数据集是在模型NeuralNovel/Gecko-7B-v0.1在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从3次运行中创建的,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。一个名为results的额外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`函数加载运行细节的示例。README中还包含了特定运行的最新结果,展示了不同任务的各种指标,如准确率和错误率。
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 NeuralNovel/Gecko-7B-v0.1
- 数据集来源: 在模型 NeuralNovel/Gecko-7B-v0.1 的评估运行期间自动创建。
- 评估平台: Open LLM Leaderboard
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。
- 创建次数: 从 3 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。
- 最新结果: "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,用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_NeuralNovel__Gecko-7B-v0.1", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-01-16T16:13:12.225780
- 结果示例: python { "all": { "acc": 0.6099096028262384, "acc_stderr": 0.03317410149444282, "acc_norm": 0.6143554464489048, "acc_norm_stderr": 0.03384780111199933, "mc1": 0.4638922888616891, "mc1_stderr": 0.017457800422268622, "mc2": 0.6260121840084173, "mc2_stderr": 0.015381860069987416 }, ... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_15T01_37_25.127753
- 路径: **/details_harness|arc:challenge|25_2024-01-15T01-37-25.127753.parquet
- 分割: 2024_01_16T02_41_01.393804
- 路径: **/details_harness|arc:challenge|25_2024-01-16T02-41-01.393804.parquet
- 分割: 2024_01_16T16_13_12.225780
- 路径: **/details_harness|arc:challenge|25_2024-01-16T16-13-12.225780.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-16T16-13-12.225780.parquet
- 分割: 2024_01_15T01_37_25.127753
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_15T01_37_25.127753
- 路径: **/details_harness|gsm8k|5_2024-01-15T01-37-25.127753.parquet
- 分割: 2024_01_16T02_41_01.393804
- 路径: **/details_harness|gsm8k|5_2024-01-16T02-41-01.393804.parquet
- 分割: 2024_01_16T16_13_12.225780
- 路径: **/details_harness|gsm8k|5_2024-01-16T16-13-12.225780.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-16T16-13-12.225780.parquet
- 分割: 2024_01_15T01_37_25.127753
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_15T01_37_25.127753
- 路径: **/details_harness|hellaswag|10_2024-01-15T01-37-25.127753.parquet
- 分割: 2024_01_16T02_41_01.393804
- 路径: **/details_harness|hellaswag|10_2024-01-16T02-41-01.393804.parquet
- 分割: 2024_01_16T16_13_12.225780
- 路径: **/details_harness|hellaswag|10_2024-01-16T16-13-12.225780.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-16T16-13-12.225780.parquet
- 分割: 2024_01_15T01_37_25.127753
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_15T01_37_25.127753
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-15T01-37-25.127753.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-15T01-37-25.127753.parquet
- ...
- 路径:
- 分割: 2024_01_16T02_41_01.393804
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-16T02-41-01.393804.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-16T02-41-01.393804.parquet
- ...
- 路径:
- 分割: 2024_01_16T16_13_12.225780
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-16T16-13-12.225780.parquet
- ...
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-16T16-13-12.225780.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-16T16-13-12.225780.parquet
- ...
- 路径:
- 分割: 2024_01_15T01_37_25.127753
- 数据文件:



