open-llm-leaderboard/details_Danielbrdz__Barcenas-13b
收藏数据集概述
数据集描述
该数据集是在评估模型 Danielbrdz/Barcenas-13b 在 Open LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建,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。此外,一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。
数据加载示例
以下是加载特定运行详细信息的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Danielbrdz__Barcenas-13b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-28T10:25:35.376129 运行 的最新结果: python { "all": { "em": 0.004718959731543624, "em_stderr": 0.0007018360183131106, "f1": 0.07556837248322182, "f1_stderr": 0.001653769461736285, "acc": 0.44339933687296285, "acc_stderr": 0.010506321335992158 }, "harness|drop|3": { "em": 0.004718959731543624, "em_stderr": 0.0007018360183131106, "f1": 0.07556837248322182, "f1_stderr": 0.001653769461736285 }, "harness|gsm8k|5": { "acc": 0.12357846853677028, "acc_stderr": 0.009065050306776923 }, "harness|winogrande|5": { "acc": 0.7632202052091555, "acc_stderr": 0.011947592365207394 } }
配置详情
以下是数据集的配置详情:
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2023_09_13T03_48_16.128379
- path: **/details_harness|arc:challenge|25_2023-09-13T03-48-16.128379.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-13T03-48-16.128379.parquet
- split: 2023_09_13T03_48_16.128379
- data_files:
-
config_name: harness_drop_3
- data_files:
- split: 2023_10_28T10_25_35.376129
- path: **/details_harness|drop|3_2023-10-28T10-25-35.376129.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-28T10-25-35.376129.parquet
- split: 2023_10_28T10_25_35.376129
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2023_10_28T10_25_35.376129
- path: **/details_harness|gsm8k|5_2023-10-28T10-25-35.376129.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-28T10-25-35.376129.parquet
- split: 2023_10_28T10_25_35.376129
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2023_09_13T03_48_16.128379
- path: **/details_harness|hellaswag|10_2023-09-13T03-48-16.128379.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-13T03-48-16.128379.parquet
- split: 2023_09_13T03_48_16.128379
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2023_09_13T03_48_16.128379
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-management|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-09-13T03-48-16.128379.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-09-13T03-48-16.128379.parquet
- **/
- path:
- split: 2023_09_13T03_48_16.128379
- data_files:



