open-llm-leaderboard-old/details_psmathur__orca_mini_v2_13b
收藏数据集概述
数据集简介
该数据集是在评估模型 psmathur/orca_mini_v2_13b 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 数据集包含 64 个配置,每个配置对应一个评估任务。
- 数据集由 3 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" 分割总是指向最新的结果。
- 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_psmathur__orca_mini_v2_13b", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的示例: python { "all": { "em": 0.06040268456375839, "em_stderr": 0.002439712523172895, "f1": 0.14132655201342267, "f1_stderr": 0.0028412840520175065, "acc": 0.39529928978029205, "acc_stderr": 0.009624116592337587 }, "harness|drop|3": { "em": 0.06040268456375839, "em_stderr": 0.002439712523172895, "f1": 0.14132655201342267, "f1_stderr": 0.0028412840520175065 }, "harness|gsm8k|5": { "acc": 0.06368460955269144, "acc_stderr": 0.00672621307880572 }, "harness|winogrande|5": { "acc": 0.7269139700078927, "acc_stderr": 0.012522020105869456 } }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2023_07_19T19_28_41.797658
- path: **/details_harness|arc:challenge|25_2023-07-19T19:28:41.797658.parquet
- split: 2023_08_09T09_59_20.126364
- path: **/details_harness|arc:challenge|25_2023-08-09T09:59:20.126364.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-08-09T09:59:20.126364.parquet
- split: 2023_07_19T19_28_41.797658
-
config_name: harness_drop_3
- split: 2023_09_23T06_53_23.116359
- path: **/details_harness|drop|3_2023-09-23T06-53-23.116359.parquet
- split: latest
- path: **/details_harness|drop|3_2023-09-23T06-53-23.116359.parquet
- split: 2023_09_23T06_53_23.116359
-
config_name: harness_gsm8k_5
- split: 2023_09_23T06_53_23.116359
- path: **/details_harness|gsm8k|5_2023-09-23T06-53-23.116359.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-09-23T06-53-23.116359.parquet
- split: 2023_09_23T06_53_23.116359
-
config_name: harness_hellaswag_10
- split: 2023_07_19T19_28_41.797658
- path: **/details_harness|hellaswag|10_2023-07-19T19:28:41.797658.parquet
- split: 2023_08_09T09_59_20.126364
- path: **/details_harness|hellaswag|10_2023-08-09T09:59:20.126364.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-08-09T09:59:20.126364.parquet
- split: 2023_07_19T19_28_41.797658
-
config_name: harness_hendrycksTest_5
- split: 2023_07_19T19_28_41.797658
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-management|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T19:28:41.797658.parquet
- path: **/details_harness|hendrycksTest-nutrition|5_2023-07-19T19:28:41.797658
- split: 2023_07_19T19_28_41.797658



