open-llm-leaderboard-old/details_Enno-Ai__ennodata-raw-pankajmathur-13b-peft
收藏数据集概述
该数据集是在评估模型 Enno-Ai/ennodata-raw-pankajmathur-13b-peft 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 数据集由 64 个配置组成,每个配置对应一个评估任务。
- 数据集从 2 次运行中创建,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。
- 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_Enno-Ai__ennodata-raw-pankajmathur-13b-peft", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-27T00:11:39.294015 运行的最新结果: python { "all": { "em": 0.364618288590604, "em_stderr": 0.00492919762439365, "f1": 0.4364775587248332, "f1_stderr": 0.004726102649724112, "acc": 0.38608121361462877, "acc_stderr": 0.007561230239361926 }, "harness|drop|3": { "em": 0.364618288590604, "em_stderr": 0.00492919762439365, "f1": 0.4364775587248332, "f1_stderr": 0.004726102649724112 }, "harness|gsm8k|5": { "acc": 0.01288855193328279, "acc_stderr": 0.0031069012664996687 }, "harness|winogrande|5": { "acc": 0.7592738752959748, "acc_stderr": 0.012015559212224183 } }
配置详情
以下是部分配置及其数据文件路径:
-
config_name: harness_arc_challenge_25
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|arc:challenge|25_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_drop_3
- split: 2023_10_27T00_11_39.294015
- path: **/details_harness|drop|3_2023-10-27T00-11-39.294015.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-27T00-11-39.294015.parquet
- split: 2023_10_27T00_11_39.294015
-
config_name: harness_gsm8k_5
- split: 2023_10_27T00_11_39.294015
- path: **/details_harness|gsm8k|5_2023-10-27T00-11-39.294015.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-27T00-11-39.294015.parquet
- split: 2023_10_27T00_11_39.294015
-
config_name: harness_hellaswag_10
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hellaswag|10_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_5
- split: 2023_10_04T05_26_18.448610
- path: [多个路径]
- split: latest
- path: [多个路径]
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_abstract_algebra_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_anatomy_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-anatomy|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-anatomy|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_astronomy_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-astronomy|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-astronomy|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_business_ethics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_clinical_knowledge_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_biology_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_biology|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_biology|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_chemistry_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_computer_science_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_mathematics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_medicine_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_college_physics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-college_physics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-college_physics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_computer_security_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-computer_security|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-computer_security|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_conceptual_physics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_econometrics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-econometrics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-econometrics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_electrical_engineering_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610
-
config_name: harness_hendrycksTest_elementary_mathematics_5
- split: 2023_10_04T05_26_18.448610
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T05-26-18.448610.parquet
- split: latest
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T05-26-18.448610.parquet
- split: 2023_10_04T05_26_18.448610



