open-llm-leaderboard-old/details_PulsarAI__MythoMax-L2-LoRA-Assemble-13B
收藏数据集概述
数据集摘要
该数据集是在对模型 PulsarAI/MythoMax-L2-LoRA-Assemble-13B 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。
数据集结构
数据集包含以下配置：
-
harness_arc_challenge_25
- 分割：2023_10_03T14_58_01.778055
- 路径：
**/details_harness|arc:challenge|25_2023-10-03T14-58-01.778055.parquet - 分割：latest
- 路径：
**/details_harness|arc:challenge|25_2023-10-03T14-58-01.778055.parquet
-
harness_hellaswag_10
- 分割：2023_10_03T14_58_01.778055
- 路径：
**/details_harness|hellaswag|10_2023-10-03T14-58-01.778055.parquet - 分割：latest
- 路径：
**/details_harness|hellaswag|10_2023-10-03T14-58-01.778055.parquet
-
harness_hendrycksTest_5
- 分割：2023_10_03T14_58_01.778055
- 路径：
**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-astronomy|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_biology|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-college_physics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-computer_security|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-econometrics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-global_facts|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-03T14-58-01.778055.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-10-03T14-58-01.778055.parquet
最新结果
以下是最新结果（来自 2023-10-03T14:58:01.778055 运行）的摘要： python { "all": { "acc": 0.598938175511998, "acc_stderr": 0.03385413189247629, "acc_norm": 0.6028583107012461, "acc_norm_stderr": 0.03383158640553202, "mc1": 0.40514075887392903, "mc1_stderr": 0.01718561172775337, "mc2": 0.5594181501740189, "mc2_stderr": 0.015699414732693026 }, "harness|arc:challenge|25": { "acc": 0.6040955631399317, "acc_stderr": 0.014291228393536587, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068283 }, "harness|hellaswag|10": { "acc": 0.6358295160326628, "acc_stderr": 0.004802133511654241, "acc_norm": 0.8346942840071699, "acc_norm_stderr": 0.003706970856410953 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5185185185185185, "acc_stderr": 0.043163785995113245, "acc_norm": 0.5185185185185185, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6188679245283019, "acc_stderr": 0.029890609686286637, "acc_norm": 0.6188679245283019, "acc_norm_stderr": 0.029890609686286637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6597222222222222, "acc_stderr": 0.039621355734862175, "acc_norm": 0.6597222222222222, "acc_norm_stderr": 0.039621355734862175 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.037336266553835096, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201942, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4978723404255319, "acc_stderr": 0.03268572658667492, "acc_norm": 0.4978723404255319, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.04514496132873634, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.04514496132873634 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370333, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr":
