open-llm-leaderboard-old/details_kekmodel__StopCarbon-10.7B-v1
收藏Hugging Face2023-12-30 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_kekmodel__StopCarbon-10.7B-v1
下载链接
链接失效反馈官方服务:
资源简介:
数据集是在模型kekmodel/StopCarbon-10.7B-v1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。数据集从1次运行中创建,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。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。
数据集是在模型kekmodel/StopCarbon-10.7B-v1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。数据集从1次运行中创建,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。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
数据集基本信息
- 名称: Evaluation run of kekmodel/StopCarbon-10.7B-v1
- 创建目的: 自动创建用于评估模型 kekmodel/StopCarbon-10.7B-v1 在 Open LLM Leaderboard 上的表现。
- 组成: 包含 63 个配置,每个配置对应一个评估任务。
- 创建次数: 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。
- 额外配置: "results" 配置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_kekmodel__StopCarbon-10.7B-v1", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2023-12-30T10:11:02.213915
- 结果示例:
python
{
"all": {
"acc": 0.666816860137451,
"acc_stderr": 0.031599000003369335,
"acc_norm": 0.6677161238426604,
"acc_norm_stderr": 0.03224247655400503,
"mc1": 0.572827417380661,
"mc1_stderr": 0.017316834410963926,
"mc2": 0.7170820046876212,
"mc2_stderr": 0.014999711441421053
},
"harness|arc:challenge|25": {
"acc": 0.6825938566552902,
"acc_stderr": 0.013602239088038167,
"acc_norm": 0.7090443686006825,
"acc_norm_stderr": 0.013273077865907595
},
"harness|hellaswag|10": {
"acc": 0.7123083051185023,
"acc_stderr": 0.004517614647703243,
"acc_norm": 0.8840868352917746,
"acc_norm_stderr": 0.003194665266078602
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.42,
"acc_stderr": 0.049604496374885836,
"acc_norm": 0.42,
"acc_norm_stderr": 0.049604496374885836
},
其他任务结果省略...
}
配置信息
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2023_12_30T10_11_02.213915
- 路径: **/details_harness|arc:challenge|25_2023-12-30T10-11-02.213915.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2023-12-30T10-11-02.213915.parquet
- 分割: 2023_12_30T10_11_02.213915
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2023_12_30T10_11_02.213915
- 路径: **/details_harness|gsm8k|5_2023-12-30T10-11-02.213915.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2023-12-30T10-11-02.213915.parquet
- 分割: 2023_12_30T10_11_02.213915
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2023_12_30T10_11_02.213915
- 路径: **/details_harness|hellaswag|10_2023-12-30T10-11-02.213915.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2023-12-30T10-11-02.213915.parquet
- 分割: 2023_12_30T10_11_02.213915
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2023_12_30T10_11_02.213915
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-management|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-12-30T10-11-02.213915.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-12-30T10-11-02.213915.parquet
- **/
- 路径:
- 分割: 2023_12_30T10_11_02.213915
- 数据文件:



