open-llm-leaderboard-old/details_migtissera__Tess-10.7B-v1.5
收藏Hugging Face2024-01-27 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_migtissera__Tess-10.7B-v1.5
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migtissera/Tess-10.7B-v1.5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。它包含1次运行的结果,每次运行都作为每个配置中的一个特定分割存储。train分割始终指向最新的结果。此外,名为results的配置存储了所有运行的聚合结果,这些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`函数加载数据集的示例。
该数据集是在Open LLM Leaderboard上对模型migtissera/Tess-10.7B-v1.5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。它包含1次运行的结果,每次运行都作为每个配置中的一个特定分割存储。train分割始终指向最新的结果。此外,名为results的配置存储了所有运行的聚合结果,这些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`函数加载数据集的示例。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集摘要
该数据集是在评估模型 migtissera/Tess-10.7B-v1.5 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。数据集从 1 次运行中创建,每个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。
数据集结构
数据集包含多个配置,每个配置对应不同的评估任务。以下是部分配置的详细信息:
-
配置名称:
harness_arc_challenge_25- 数据文件:
- 分割:
2024_01_27T08_16_07.104140- 路径:
**/details_harness|arc:challenge|25_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|arc:challenge|25_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
- 数据文件:
-
配置名称:
harness_gsm8k_5- 数据文件:
- 分割:
2024_01_27T08_16_07.104140- 路径:
**/details_harness|gsm8k|5_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|gsm8k|5_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
- 数据文件:
-
配置名称:
harness_hellaswag_10- 数据文件:
- 分割:
2024_01_27T08_16_07.104140- 路径:
**/details_harness|hellaswag|10_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
latest- 路径:
**/details_harness|hellaswag|10_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
- 数据文件:
-
配置名称:
harness_hendrycksTest_5- 数据文件:
- 分割:
2024_01_27T08_16_07.104140- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-anatomy|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-astronomy|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_biology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-college_physics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-computer_security|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-econometrics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-global_facts|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-human_aging|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-international_law|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-management|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-marketing|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-nutrition|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-philosophy|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-prehistory|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-professional_law|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-professional_medicine|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-professional_psychology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-public_relations|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-security_studies|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-sociology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-virology|5_2024-01-27T08-16-07.104140.parquet**/details_harness|hendrycksTest-world_religions|5_2024-01-27T08-16-07.104140.parquet
- 路径:
- 分割:
- 数据文件:
最新结果
以下是 最新结果 的摘要:
python { "all": { "acc": 0.6513655424521041, "acc_stderr": 0.03165794538741113, "acc_norm": 0.6541051437423594, "acc_norm_stderr": 0.032296434557489546, "mc1": 0.32558139534883723, "mc1_stderr": 0.01640398946990783, "mc2": 0.47430080710659894, "mc2_stderr": 0.014677705750823734 }, "harness|arc:challenge|25": { "acc": 0.60580204778157, "acc_stderr": 0.01428052266746



