open-llm-leaderboard-old/details_yihan6324__llama2-7b-instructmining-40k-sharegpt
收藏数据集概述
该数据集是在对模型 yihan6324/llama2-7b-instructmining-40k-sharegpt 进行评估运行期间自动创建的。数据集包含61个配置,每个配置对应一个评估任务。数据集从1次运行中创建,每个运行的详细信息可以在每个配置中找到,并以运行的时间戳命名。"train" 分割始终指向最新的结果。
数据集结构
配置
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2023_08_09T21_00_12.284244
- 路径: **/details_harness|arc:challenge|25_2023-08-09T21:00:12.284244.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2023-08-09T21:00:12.284244.parquet
- 分割: 2023_08_09T21_00_12.284244
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2023_08_09T21_00_12.284244
- 路径: **/details_harness|hellaswag|10_2023-08-09T21:00:12.284244.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2023-08-09T21:00:12.284244.parquet
- 分割: 2023_08_09T21_00_12.284244
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2023_08_09T21_00_12.284244
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T21:00:12.284244.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T21:00:12.284244.parquet
- ...
- 路径:
- 分割: 2023_08_09T21_00_12.284244
- 数据文件:
最新结果
以下是 2023-08-09T21:00:12.284244 运行的最新结果:
python { "all": { "acc": 0.506231001015833, "acc_stderr": 0.03505018845563652, "acc_norm": 0.5099522031118208, "acc_norm_stderr": 0.035035258453899244, "mc1": 0.36474908200734396, "mc1_stderr": 0.01685096106172012, "mc2": 0.5317717765572597, "mc2_stderr": 0.015775374488304787 }, "harness|arc:challenge|25": { "acc": 0.5170648464163823, "acc_stderr": 0.014602878388536595, "acc_norm": 0.5511945392491467, "acc_norm_stderr": 0.014534599585097664 }, "harness|hellaswag|10": { "acc": 0.6041625174268074, "acc_stderr": 0.004880303863138504, "acc_norm": 0.7895837482573193, "acc_norm_stderr": 0.0040677125640782895 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4605263157894737, "acc_stderr": 0.04056242252249034, "acc_norm": 0.4605263157894737, "acc_norm_stderr": 0.04056242252249034 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5245283018867924, "acc_stderr": 0.030735822206205608, "acc_norm": 0.5245283018867924, "acc_norm_stderr": 0.030735822206205608 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4930555555555556, "acc_stderr": 0.04180806750294938, "acc_norm": 0.4930555555555556, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4682080924855491, "acc_stderr": 0.03804749744364763, "acc_norm": 0.4682080924855491, "acc_norm_stderr": 0.03804749744364763 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.17647058823529413, "acc_stderr": 0.03793281185307809, "acc_norm": 0.17647058823529413, "acc_norm_stderr": 0.03793281185307809 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4723404255319149, "acc_stderr": 0.03263597118409769, "acc_norm": 0.4723404255319149, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.04166567577101579, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.04166567577101579 },



