open-llm-leaderboard/details_TheBloke__wizard-vicuna-13B-HF
收藏数据集概述
数据集简介
该数据集是在对模型 TheBloke/wizard-vicuna-13B-HF 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集结构
- 配置数量:64个配置,每个配置对应一个评估任务。
- 数据来源:数据集由2次运行结果组成,每次运行的结果可以在每个配置中找到,以运行的时间戳命名。
- 最新结果:"train" 分割总是指向最新的结果。
- 汇总结果:一个额外的配置 "results" 存储所有运行的汇总结果,用于计算和显示在 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_TheBloke__wizard-vicuna-13B-HF", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-22T05:16:09.820423 运行 的最新结果: python { "all": { "em": 0.0350251677852349, "em_stderr": 0.0018827287598880416, "f1": 0.10088821308724859, "f1_stderr": 0.0023095858218995214, "acc": 0.4207383077634691, "acc_stderr": 0.010104088969294184 }, "harness|drop|3": { "em": 0.0350251677852349, "em_stderr": 0.0018827287598880416, "f1": 0.10088821308724859, "f1_stderr": 0.0023095858218995214 }, "harness|gsm8k|5": { "acc": 0.0932524639878696, "acc_stderr": 0.008009688838328585 }, "harness|winogrande|5": { "acc": 0.7482241515390686, "acc_stderr": 0.012198489100259785 } }
配置详情
以下是数据集的部分配置详情:
-
harness_arc_challenge_25
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-18T15:41:31.806863.parquet
-
harness_drop_3
- 分割:2023_10_22T05_16_09.820423, latest
- 路径:
**/details_harness|drop|3_2023-10-22T05-16-09.820423.parquet
-
harness_gsm8k_5
- 分割:2023_10_22T05_16_09.820423, latest
- 路径:
**/details_harness|gsm8k|5_2023-10-22T05-16-09.820423.parquet
-
harness_hellaswag_10
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hellaswag|10_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:多个路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_abstract_algebra_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_anatomy_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_astronomy_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_business_ethics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_biology_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_medicine_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_college_physics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_computer_security_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_econometrics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-18T15:41:31.806863.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分割:2023_07_18T15_41_31.806863, latest
- 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-18T15:41:31.806863.parquet



