open-llm-leaderboard/details_bofenghuang__vigogne-2-7b-chat
收藏Hugging Face2023-09-22 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_bofenghuang__vigogne-2-7b-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bofenghuang/vigogne-2-7b-chat进行评估时自动创建的。数据集由64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，每次运行的结果作为特定配置中的一个分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置存储了所有运行的聚合结果，并用于在Open LLM Leaderboard上计算和显示聚合指标。
This dataset was automatically created during the evaluation of the model bofenghuang/vigogne-2-7b-chat on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, with the results of each run serving as a split under its respective configuration, where the split names use the timestamps of the runs. The "train" split always points to the most recent results. In addition, there is a configuration named "results" that stores the aggregated results of all runs, and is used to calculate and display aggregated metrics on the Open LLM Leaderboard.
提供机构：
open-llm-leaderboard
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 bofenghuang/vigogne-2-7b-chat 在 Open LLM Leaderboard 上的自动创建的。
数据集结构
- 配置数量：64个配置，每个配置对应一个评估任务。
- 数据来源：数据集由2次运行结果组成，每个运行结果作为一个特定的分割存在于每个配置中，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_bofenghuang__vigogne-2-7b-chat", "harness_winogrande_5", split="train")
最新结果
以下是 2023-09-22T13:35:42.061271 运行的最新结果： python { "all": { "em": 0.2779991610738255, "em_stderr": 0.0045880722162316605, "f1": 0.32825188758389273, "f1_stderr": 0.004516960799751206, "acc": 0.41080456661279235, "acc_stderr": 0.00980948368433141 }, "harness|drop|3": { "em": 0.2779991610738255, "em_stderr": 0.0045880722162316605, "f1": 0.32825188758389273, "f1_stderr": 0.004516960799751206 }, "harness|gsm8k|5": { "acc": 0.07733131159969674, "acc_stderr": 0.007357713523222347 }, "harness|winogrande|5": { "acc": 0.744277821625888, "acc_stderr": 0.012261253845440473 } }
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：2023_08_22T13_29_32.035608
- 路径：
**/details_harness|arc:challenge|25_2023-08-22T13:29:32.035608.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|arc:challenge|25_2023-08-22T13:29:32.035608.parquet
- 路径：
- 分割：2023_08_22T13_29_32.035608
-
harness_drop_3
- 分割：2023_09_22T13_35_42.061271
- 路径：
**/details_harness|drop|3_2023-09-22T13-35-42.061271.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|drop|3_2023-09-22T13-35-42.061271.parquet
- 路径：
- 分割：2023_09_22T13_35_42.061271
-
harness_gsm8k_5
- 分割：2023_09_22T13_35_42.061271
- 路径：
**/details_harness|gsm8k|5_2023-09-22T13-35-42.061271.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|gsm8k|5_2023-09-22T13-35-42.061271.parquet
- 路径：
- 分割：2023_09_22T13_35_42.061271
-
harness_hellaswag_10
- 分割：2023_08_22T13_29_32.035608
- 路径：
**/details_harness|hellaswag|10_2023-08-22T13:29:32.035608.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|hellaswag|10_2023-08-22T13:29:32.035608.parquet
- 路径：
- 分割：2023_08_22T13_29_32.035608
-
harness_hendrycksTest_5
- 分割：2023_08_22T13_29_32.035608
- 路径：
**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-anatomy|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-astronomy|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_biology|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-college_physics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-computer_security|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-econometrics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-global_facts|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-human_aging|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-international_law|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-management|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-marketing|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-nutrition|5_2023-08-22T13:29:32.035608.parquet - 路径：
**/details_harness|hendrycksTest-philosophy|5_2023-08-22T13:29:32.035608.parquet - 路径：`**/details_harness|hendry
- 路径：
- 分割：2023_08_22T13_29_32.035608
