open-llm-leaderboard-old/details_DrNicefellow__Mistral-3-from-Mixtral-8x7B-v0.1
收藏Hugging Face2024-04-15 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_DrNicefellow__Mistral-3-from-Mixtral-8x7B-v0.1
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DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行可以在每个配置中找到特定的分割,分割以运行的时间戳命名。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在模型DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行可以在每个配置中找到特定的分割,分割以运行的时间戳命名。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,并用于计算和显示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
数据集名称
- 名称: Evaluation run of DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1
数据集描述
- 创建背景: 该数据集是在评估模型 DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1 在 Open LLM Leaderboard 上的自动创建的。
- 组成: 数据集包含 63 个配置,每个配置对应一个评估任务。
- 创建方式: 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。
- 额外配置: 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_DrNicefellow__Mistral-3-from-Mixtral-8x7B-v0.1", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2024-04-15T14:28:15.409639
- 结果示例:
python
{
"all": {
"acc": 0.25665938109738223,
"acc_stderr": 0.03078324218540209,
"acc_norm": 0.2580411998975106,
"acc_norm_stderr": 0.03160481806166394,
"mc1": 0.23745410036719705,
"mc1_stderr": 0.01489627744104185,
"mc2": 0.4819046042054843,
"mc2_stderr": 0.016210606003522837
},
"harness|arc:challenge|25": {
"acc": 0.23464163822525597,
"acc_stderr": 0.012383873560768673,
"acc_norm": 0.2935153583617747,
"acc_norm_stderr": 0.013307250444941129
},
"harness|hellaswag|10": {
"acc": 0.2593108942441745,
"acc_stderr": 0.004373608212561027,
"acc_norm": 0.2658832901812388,
"acc_norm_stderr": 0.0044089948686501
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.24,
"acc_stderr": 0.04292346959909284,
"acc_norm": 0.24,
"acc_norm_stderr": 0.04292346959909284
},
其他任务的结果...
}
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_04_15T14_28_15.409639
- 路径: **/details_harness|arc:challenge|25_2024-04-15T14-28-15.409639.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-04-15T14-28-15.409639.parquet
- 分割: 2024_04_15T14_28_15.409639
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_04_15T14_28_15.409639
- 路径: **/details_harness|gsm8k|5_2024-04-15T14-28-15.409639.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-04-15T14-28-15.409639.parquet
- 分割: 2024_04_15T14_28_15.409639
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_04_15T14_28_15.409639
- 路径: **/details_harness|hellaswag|10_2024-04-15T14-28-15.409639.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-04-15T14-28-15.409639.parquet
- 分割: 2024_04_15T14_28_15.409639
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_04_15T14_28_15.409639
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-management|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-04-15T14-28-15.409639.parquet
- **/details_harness|hendrycksTest-professional_psych
- 路径:
- 分割: 2024_04_15T14_28_15.409639
- 数据文件:



