open-llm-leaderboard/details_Monero__WizardLM-Uncensored-SuperCOT-StoryTelling-30b
收藏Hugging Face2023-10-15 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Monero__WizardLM-Uncensored-SuperCOT-StoryTelling-30b
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Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b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次运行生成，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，一个名为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Python中的datasets库加载运行细节的示例。
This dataset was automatically generated during the evaluation of the model Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. It is generated from two runs, where each run is represented as a specific split under each configuration, with the split name being the timestamp of the corresponding run. The 'train' split always points to the latest evaluation results. Additionally, a configuration named 'results' stores the aggregated results across all runs, which is used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also includes examples of how to load run details using the `datasets` library in Python.
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 Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b 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。
- 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_Monero__WizardLM-Uncensored-SuperCOT-StoryTelling-30b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-15T18:31:20.676081 运行 的最新结果： python { "all": { "em": 0.24653942953020133, "em_stderr": 0.004413804668718679, "f1": 0.33164010067114214, "f1_stderr": 0.004375317074606664, "acc": 0.38205290535450254, "acc_stderr": 0.009533625550775153 }, "harness|drop|3": { "em": 0.24653942953020133, "em_stderr": 0.004413804668718679, "f1": 0.33164010067114214, "f1_stderr": 0.004375317074606664 }, "harness|gsm8k|5": { "acc": 0.05534495830174375, "acc_stderr": 0.006298221796179607 }, "harness|winogrande|5": { "acc": 0.7087608524072613, "acc_stderr": 0.012769029305370699 } }
配置详情
以下是数据集的配置详情：
-
harness_arc_challenge_25
- 分割：2023_07_19T22_17_39.123351
- 路径：
**/details_harness|arc:challenge|25_2023-07-19T22:17:39.123351.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|arc:challenge|25_2023-07-19T22:17:39.123351.parquet
- 路径：
- 分割：2023_07_19T22_17_39.123351
-
harness_drop_3
- 分割：2023_10_15T18_31_20.676081
- 路径：
**/details_harness|drop|3_2023-10-15T18-31-20.676081.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|drop|3_2023-10-15T18-31-20.676081.parquet
- 路径：
- 分割：2023_10_15T18_31_20.676081
-
harness_gsm8k_5
- 分割：2023_10_15T18_31_20.676081
- 路径：
**/details_harness|gsm8k|5_2023-10-15T18-31-20.676081.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|gsm8k|5_2023-10-15T18-31-20.676081.parquet
- 路径：
- 分割：2023_10_15T18_31_20.676081
-
harness_hellaswag_10
- 分割：2023_07_19T22_17_39.123351
- 路径：
**/details_harness|hellaswag|10_2023-07-19T22:17:39.123351.parquet
- 路径：
- 分割：latest
- 路径：
**/details_harness|hellaswag|10_2023-07-19T22:17:39.123351.parquet
- 路径：
- 分割：2023_07_19T22_17_39.123351
-
harness_hendrycksTest_5
- 分割：2023_07_19T22_17_39.123351
- 路径：
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-anatomy|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-astronomy|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_biology|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-college_physics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-computer_security|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-econometrics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-global_facts|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-human_aging|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-international_law|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-management|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-marketing|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T22:17:39.123351.parquet - 路径：
**/details_harness|hendrycksTest-nutrition|5_2023-07-19T22:17:39.123351.parquet - 路径：`**/details_harness|hendrycksTest-philosophy|5_2023-07-19T22:17:39.123351.parquet
- 路径：
- 分割：2023_07_19T22_17_39.123351
