open-llm-leaderboard/details_xzuyn__Alpacino-SuperCOT-13B
收藏Hugging Face2023-10-14 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_xzuyn__Alpacino-SuperCOT-13B
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xzuyn/Alpacino-SuperCOT-13B进行评估时自动生成的。数据集包含64个配置，每个配置对应一个评估任务。数据集由2次运行的数据组成，每次运行在每个配置中表示为特定的分割，分割名称由运行的时间戳命名。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，用于计算和显示Open LLM Leaderboard上的指标。README还提供了如何使用Hugging Face datasets库加载数据集的示例。
This dataset was automatically generated during the evaluation of the model xzuyn/Alpacino-SuperCOT-13B on the Open LLM Leaderboard. It includes 64 configurations, each corresponding to one evaluation task. The dataset comprises data from two runs, where each run is represented as a specific split within each configuration, and the names of these splits are derived from the timestamp of the corresponding run. The `train` split always points to the most recent evaluation results. Additionally, the `results` configuration stores aggregated results across all runs, which are used to calculate and display the metrics on the Open LLM Leaderboard. The README also provides examples of how to load the dataset using the Hugging Face Datasets library.
提供机构：
open-llm-leaderboard
原始信息汇总
数据集概述
数据集来源
- 数据集是在评估模型 xzuyn/Alpacino-SuperCOT-13B 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 64 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_xzuyn__Alpacino-SuperCOT-13B", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自 2023-10-14T21:25:30.263923 运行，包含以下指标： python { "all": { "em": 0.034710570469798654, "em_stderr": 0.001874559812477868, "f1": 0.09780201342281894, "f1_stderr": 0.002213982622562692, "acc": 0.4222955971643869, "acc_stderr": 0.00954675265516166 }, "harness|drop|3": { "em": 0.034710570469798654, "em_stderr": 0.001874559812477868, "f1": 0.09780201342281894, "f1_stderr": 0.002213982622562692 }, "harness|gsm8k|5": { "acc": 0.07505686125852919, "acc_stderr": 0.007257633145486642 }, "harness|winogrande|5": { "acc": 0.7695343330702447, "acc_stderr": 0.011835872164836676 } }
配置详情
- 数据集包含多个配置，每个配置对应不同的任务和运行时间戳。以下是部分配置示例：
harness_arc_challenge_25harness_drop_3harness_gsm8k_5harness_hellaswag_10harness_hendrycksTest_5harness_hendrycksTest_abstract_algebra_5harness_hendrycksTest_anatomy_5harness_hendrycksTest_astronomy_5harness_hendrycksTest_business_ethics_5harness_hendrycksTest_clinical_knowledge_5harness_hendrycksTest_college_biology_5harness_hendrycksTest_college_chemistry_5harness_hendrycksTest_college_computer_science_5harness_hendrycksTest_college_mathematics_5harness_hendrycksTest_college_medicine_5harness_hendrycksTest_college_physics_5harness_hendrycksTest_computer_security_5harness_hendrycksTest_conceptual_physics_5harness_hendrycksTest_econometrics_5harness_hendrycksTest_electrical_engineering_5harness_hendrycksTest_elementary_mathematics_5
