open-llm-leaderboard/details_CoolWP__llama-2-13b-guanaco-fp16
收藏数据集概述
数据集摘要
该数据集是在评估模型 CoolWP/llama-2-13b-guanaco-fp16 在 Open LLM Leaderboard 上的自动创建的。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" 分割总是指向最新的结果。
数据集结构
数据集包含以下配置：
-
harness_arc_challenge_25
- 分割：2023_08_17T18_49_30.894423
- 路径：
**/details_harness|arc:challenge|25_2023-08-17T18:49:30.894423.parquet - 分割：latest
- 路径：
**/details_harness|arc:challenge|25_2023-08-17T18:49:30.894423.parquet
-
harness_hellaswag_10
- 分割：2023_08_17T18_49_30.894423
- 路径：
**/details_harness|hellaswag|10_2023-08-17T18:49:30.894423.parquet - 分割：latest
- 路径：
**/details_harness|hellaswag|10_2023-08-17T18:49:30.894423.parquet
-
harness_hendrycksTest_5
- 分割：2023_08_17T18_49_30.894423
- 路径：
**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-anatomy|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-astronomy|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_biology|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-college_physics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-computer_security|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-econometrics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-global_facts|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-17T18:49:30.894423.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-08-17T18:49:30.894423.parquet
最新结果
以下是 2023-08-17T18:49:30.894423 的最新结果：
python { "all": { "acc": 0.5557402565625233, "acc_stderr": 0.03433097920024075, "acc_norm": 0.5600027152011281, "acc_norm_stderr": 0.03430992590405376, "mc1": 0.29865361077111385, "mc1_stderr": 0.016021570613768542, "mc2": 0.43400538092704843, "mc2_stderr": 0.014284105671223521 }, "harness|arc:challenge|25": { "acc": 0.552901023890785, "acc_stderr": 0.014529380160526843, "acc_norm": 0.5955631399317406, "acc_norm_stderr": 0.014342036483436177 }, "harness|hellaswag|10": { "acc": 0.615116510655248, "acc_stderr": 0.004855733568540267, "acc_norm": 0.8239394542919737, "acc_norm_stderr": 0.003800932770597752 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "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": 0.5263157894736842, "acc_stderr": 0.04063302731486671, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.04063302731486671 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6037735849056604, "acc_stderr": 0.030102793781791197, "acc_norm": 0.6037735849056604, "acc_norm_stderr": 0.030102793781791197 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5763888888888888, "acc_stderr": 0.0413212501972337, "acc_norm": 0.5763888888888888, "acc_norm_stderr": 0.0413212501972337 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5144508670520231, "acc_stderr": 0.03810871630454764, "acc_norm": 0.5144508670520231, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.03227834510146268, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.53
