open-llm-leaderboard-old/details_kalisai__Nusantara-1.8b-Indo-Chat
收藏Hugging Face2024-03-10 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_kalisai__Nusantara-1.8b-Indo-Chat
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kalisai/Nusantara-1.8b-Indo-Chat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。数据集从1次运行中创建,每次运行可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。train分割始终指向最新结果。此外,还有一个名为results的配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在Open LLM Leaderboard上对模型kalisai/Nusantara-1.8b-Indo-Chat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。数据集从1次运行中创建,每次运行可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。train分割始终指向最新结果。此外,还有一个名为results的配置存储了所有运行的聚合结果,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
数据集简介
该数据集是在评估模型 kalisai/Nusantara-1.8b-Indo-Chat 在 Open LLM Leaderboard 上的自动创建的。
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1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。
- 训练分割:"train" 分割始终指向最新的结果。
- 结果配置: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 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_kalisai__Nusantara-1.8b-Indo-Chat", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要: python { "all": { "acc": 0.3062721042670704, "acc_stderr": 0.032674268588055555, "acc_norm": 0.30890953699867585, "acc_norm_stderr": 0.0334717817480905, "mc1": 0.22766217870257038, "mc1_stderr": 0.014679255032111075, "mc2": 0.37265340146580295, "mc2_stderr": 0.013950530613032723 }, ... }
配置详情
-
config_name: harness_arc_challenge_25
- 分割: 2024_03_10T22_20_55.643139
- 路径: **/details_harness|arc:challenge|25_2024-03-10T22-20-55.643139.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-10T22-20-55.643139.parquet
- 分割: 2024_03_10T22_20_55.643139
-
config_name: harness_gsm8k_5
- 分割: 2024_03_10T22_20_55.643139
- 路径: **/details_harness|gsm8k|5_2024-03-10T22-20-55.643139.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-03-10T22-20-55.643139.parquet
- 分割: 2024_03_10T22_20_55.643139
-
config_name: harness_hellaswag_10
- 分割: 2024_03_10T22_20_55.643139
- 路径: **/details_harness|hellaswag|10_2024-03-10T22-20-55.643139.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-03-10T22-20-55.643139.parquet
- 分割: 2024_03_10T22_20_55.643139
-
config_name: harness_hendrycksTest_5
- 分割: 2024_03_10T22_20_55.643139
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-10T22-20-55.643139.parquet
- ...
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-10T22-20-55.643139.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-10T22-20-55.643139.parquet
- ...
- 路径:
- 分割: 2024_03_10T22_20_55.643139



