open-llm-leaderboard-old/details_Nekochu__Llama-2-13B-German-ORPO
收藏数据集概述
数据集摘要
该数据集是在评估模型Nekochu/Llama-2-13B-German-ORPO在Open LLM Leaderboard上的运行过程中自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行创建,每次运行的详细信息可以在每个配置中找到,以运行的时间戳命名的特定分割形式存储。"train"分割始终指向最新的结果。
数据集结构
数据集包含多个配置,每个配置对应不同的评估任务。以下是部分配置的详细信息:
配置示例
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_15T13_20_29.082617
- path: **/details_harness|arc:challenge|25_2024-04-15T13-20-29.082617.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-04-15T13-20-29.082617.parquet
- split: 2024_04_15T13_20_29.082617
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_15T13_20_29.082617
- path: **/details_harness|gsm8k|5_2024-04-15T13-20-29.082617.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-04-15T13-20-29.082617.parquet
- split: 2024_04_15T13_20_29.082617
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_15T13_20_29.082617
- path: **/details_harness|hellaswag|10_2024-04-15T13-20-29.082617.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-04-15T13-20-29.082617.parquet
- split: 2024_04_15T13_20_29.082617
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_15T13_20_29.082617
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-15T13-20-29.082617.parquet
- **/details_harness|hendrycksTest-high_school_biology|
- path:
- split: 2024_04_15T13_20_29.082617
- data_files:
最新结果
以下是2024-04-15T13:20:29.082617运行的最新结果:
python { "all": { "acc": 0.532542366507223, "acc_stderr": 0.03382149520120546, "acc_norm": 0.5390973221013382, "acc_norm_stderr": 0.03456643230807577, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608763, "mc2": 0.4243655679693484, "mc2_stderr": 0.015193280285346479 }, "harness|arc:challenge|25": { "acc": 0.507679180887372, "acc_stderr": 0.014609667440892567, "acc_norm": 0.5477815699658704, "acc_norm_stderr": 0.014544519880633832 }, "harness|hellaswag|10": { "acc": 0.599681338378809, "acc_stderr": 0.004889615413144191, "acc_norm": 0.790479984066919, "acc_norm_stderr": 0.004061343422198776 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411022, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411022 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750574, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5460526315789473, "acc_stderr": 0.04051646342874142, "acc_norm": 0.5460526315789473, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5622641509433962, "acc_stderr": 0.030533338430467516, "acc_norm": 0.5622641509433962, "acc_norm_stderr": 0.030533338430467516 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5416666666666666, "acc_stderr": 0.04166666666666665, "acc_norm": 0.5416666666666666, "acc_norm_stderr": 0.04166666666666665 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4393063583815029, "acc_stderr": 0.037842719328874674, "acc_norm": 0.4393063583815029, "acc_norm_stderr": 0.037842719328874674 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.043898699568087785, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.043898699568087785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39574468085106385, "acc_stderr": 0.031967586978353627, "acc_norm": 0.39574468085106385, "acc_norm_stderr": 0.031967586978353627 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.0415863276209



