open-llm-leaderboard/details_Lazycuber__pyg-instruct-wizardlm
收藏数据集概述
该数据集是在评估模型 Lazycuber/pyg-instruct-wizardlm 在 Open LLM Leaderboard 上的自动创建的。数据集由 64 个配置组成,每个配置对应一个评估任务。
数据集结构
- 配置数量:64 个配置
- 数据来源:2 次运行结果
- 数据分割:每个配置包含特定运行的分割,分割名称使用运行的时间戳。"train" 分割指向最新结果。
- 结果汇总: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_Lazycuber__pyg-instruct-wizardlm", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-28T08:03:29.005419 运行的最新结果:
python { "all": { "em": 0.01971476510067114, "em_stderr": 0.0014236777096831824, "f1": 0.07215394295302006, "f1_stderr": 0.001870662901719372, "acc": 0.3264294001877723, "acc_stderr": 0.008481505569434104 }, "harness|drop|3": { "em": 0.01971476510067114, "em_stderr": 0.0014236777096831824, "f1": 0.07215394295302006, "f1_stderr": 0.001870662901719372 }, "harness|gsm8k|5": { "acc": 0.01592115238817286, "acc_stderr": 0.0034478192723889907 }, "harness|winogrande|5": { "acc": 0.6369376479873717, "acc_stderr": 0.01351519186647922 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-24T15:30:39.317119.parquet
-
harness_drop_3
- 分割:2023_10_28T08_03_29.005419, latest
- 路径:
**/details_harness|drop|3_2023-10-28T08-03-29.005419.parquet
-
harness_gsm8k_5
- 分割:2023_10_28T08_03_29.005419, latest
- 路径:
**/details_harness|gsm8k|5_2023-10-28T08-03-29.005419.parquet
-
harness_hellaswag_10
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hellaswag|10_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:多个路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_abstract_algebra_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_anatomy_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_astronomy_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_business_ethics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_biology_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_medicine_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_college_physics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_computer_security_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_econometrics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T15:30:39.317119.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分割:2023_07_24T15_30_39.317119, latest
- 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T15:30:39.317119.parquet



