open-llm-leaderboard-old/details_openthaigpt__openthaigpt-1.0.0-13b-chat
收藏数据集概述
数据集摘要
该数据集是在对模型 openthaigpt/openthaigpt-1.0.0-13b-chat 进行评估运行期间自动创建的。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
数据集由多个配置组成，每个配置对应一个评估任务。每个配置包含多个分割，包括特定运行的时间戳分割和 "train" 分割（指向最新的结果）。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_openthaigpt__openthaigpt-1.0.0-13b-chat", "harness_winogrande_5", split="train")
最新结果
以下是来自最新运行 2024-04-08T09:21:56.323662 的结果：
python
{
"all": {
"acc": 0.47516245926389655,
"acc_stderr": 0.0344768226505747,
"acc_norm": 0.48134591980816616,
"acc_norm_stderr": 0.035254724316773664,
"mc1": 0.28886168910648713,
"mc1_stderr": 0.01586634640138431,
"mc2": 0.44667277374356995,
"mc2_stderr": 0.015557150825235011
},
"harness|arc:challenge|25": {
"acc": 0.4854948805460751,
"acc_stderr": 0.014605241081370056,
"acc_norm": 0.5170648464163823,
"acc_norm_stderr": 0.0146028783885366
},
"harness|hellaswag|10": {
"acc": 0.5918143796056562,
"acc_stderr": 0.00490493350025588,
"acc_norm": 0.7801234813782115,
"acc_norm_stderr": 0.004133163805317372
},
"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": 0.4222222222222222,
"acc_stderr": 0.04266763404099582,
"acc_norm": 0.4222222222222222,
"acc_norm_stderr": 0.04266763404099582
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.4144736842105263,
"acc_stderr": 0.04008973785779206,
"acc_norm": 0.4144736842105263,
"acc_norm_stderr": 0.04008973785779206
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.52,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.52,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.44528301886792454,
"acc_stderr": 0.030588052974270655,
"acc_norm": 0.44528301886792454,
"acc_norm_stderr": 0.030588052974270655
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.4791666666666667,
"acc_stderr": 0.041775789507399935,
"acc_norm": 0.4791666666666667,
"acc_norm_stderr": 0.041775789507399935
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.35,
"acc_stderr": 0.04793724854411019,
"acc_norm": 0.35,
"acc_norm_stderr": 0.04793724854411019
},
"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": 0.34,
"acc_stderr": 0.04760952285695235,
"acc_norm": 0.34,
"acc_norm_stderr": 0.04760952285695235
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.45664739884393063,
"acc_stderr": 0.03798106566014498,
"acc_norm": 0.45664739884393063,
"acc_norm_stderr": 0.03798106566014498
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.21568627450980393,
"acc_stderr": 0.04092563958237655,
"acc_norm": 0.21568627450980393,
"acc_norm_stderr": 0.04092563958237655
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620332,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620332
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.4340425531914894,
"acc_stderr": 0.03240038086792747,
"acc_norm": 0.4340425531914894,
"acc_norm_stderr": 0.03240038086792747
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.2631578947368421,
"acc_stderr": 0.04142439719489362,
"acc_norm": 0.2631578947368421,
"acc_norm_stderr": 0.04142439719489362
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.4068965517241379,
"acc_stderr": 0.04093793981266237,
"acc_norm": 0.4068965517241379,
"acc_norm_stderr": 0.04093793981266237
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.2857142857142857,
"acc_stderr": 0.02326651221373057,
"acc_norm": 0.2857142857142857,
"acc_norm_stderr": 0.02326651221373057
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.30158730158730157,
"acc_stderr": 0.04104947269903394,
"acc_norm": 0.30158730158730157,
"acc_norm_stderr": 0.04104947269903394
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.33,
"acc_stderr": 0.047258156262526045,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.5483870967741935,
"acc_stderr": 0.028310500348568385,
"acc_norm": 0.5483870967741935,
"acc_norm_stderr": 0.028310500348568385
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.3842364532019704,
"acc_stderr": 0.03422398565657551,
"acc_norm": 0.3842364532019704,
"acc_norm_stderr": 0.03422398565657551
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.43,
"acc_stderr": 0.049756985195624284,
"acc_norm": 0.43,
"acc_norm_stderr": 0.049756985195624284
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.6121212121212121,
"acc_stderr": 0.038049136539710114,
"acc_norm": 0.6121212121212121,
"acc_norm_stderr": 0.038049136539710114
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.5303030303030303,
"acc_stderr": 0.03555804051763929,
"acc_norm": 0.5303030303030303,
"acc_norm_stderr": 0.03555804051763929
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.6528497409326425,
"acc_stderr": 0.03435696168361355,
"acc_norm": 0.6528497409326425,
"acc_norm_stderr": 0.03435696168361355
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.43846153846153846,
"acc_stderr": 0.025158266016868578,
"acc_norm": 0.43846153846153846,
"acc_norm_stderr": 0.025158266016868578
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.3037037037037037,
"acc_stderr": 0.028037929969114982,
"acc_norm": 0.3037037037037037,
"acc_norm_stderr": 0.028037929969114982
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.4579831932773109,
"acc_stderr": 0.03236361111951941,
"acc_norm": 0.45798319327731
