open-llm-leaderboard-old/details_Lvxy1117__amber_fine_tune_001
收藏Hugging Face2024-01-28 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Lvxy1117__amber_fine_tune_001
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型Lvxy1117/amber_fine_tune_001的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。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上的聚合指标。
该数据集是在模型Lvxy1117/amber_fine_tune_001的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。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
数据集信息
- 名称: Evaluation run of Lvxy1117/amber_fine_tune_001
- 来源: 自动创建于模型 Lvxy1117/amber_fine_tune_001 在 Open LLM Leaderboard 的评估运行中。
- 组成: 包含 63 个配置,每个配置对应一个评估任务。
- 创建: 数据集从 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。"train" 分割始终指向最新的结果。
- 结果汇总: 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_Lvxy1117__amber_fine_tune_001", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-01-28T13:46:59.201897 运行
- 详细结果: python { "all": { "acc": 0.31138101151746983, "acc_stderr": 0.0325934760300863, "acc_norm": 0.3139371329907083, "acc_norm_stderr": 0.033375512329911525, "mc1": 0.2876376988984088, "mc1_stderr": 0.015846315101394805, "mc2": 0.429338384075007, "mc2_stderr": 0.015517791037983605 }, "harness|arc:challenge|25": { "acc": 0.4121160409556314, "acc_stderr": 0.014383915302225398, "acc_norm": 0.44795221843003413, "acc_norm_stderr": 0.01453201149821167 }, "harness|hellaswag|10": { "acc": 0.5683130850428202, "acc_stderr": 0.0049429906231311166, "acc_norm": 0.7378012348137821, "acc_norm_stderr": 0.004389312748012154 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, # 其他任务的结果省略... }
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_28T13_46_59.201897
- 路径: **/details_harness|arc:challenge|25_2024-01-28T13-46-59.201897.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-28T13-46-59.201897.parquet
- 分割: 2024_01_28T13_46_59.201897
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_28T13_46_59.201897
- 路径: **/details_harness|gsm8k|5_2024-01-28T13-46-59.201897.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-28T13-46-59.201897.parquet
- 分割: 2024_01_28T13_46_59.201897
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_28T13_46_59.201897
- 路径: **/details_harness|hellaswag|10_2024-01-28T13-46-59.201897.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-28T13-46-59.201897.parquet
- 分割: 2024_01_28T13_46_59.201897
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_28T13_46_59.201897
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-28T13-46-59.201897.parquet
- **/details_harness|hendrycksTest-professional_account
- 路径:
- 分割: 2024_01_28T13_46_59.201897
- 数据文件:



