open-llm-leaderboard-old/details_NeverSleep__Noromaid-13b-v0.3
收藏数据集概述
数据集名称
Evaluation run of NeverSleep/Noromaid-13b-v0.3
数据集描述
该数据集是在模型NeverSleep/Noromaid-13b-v0.3在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
- 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2次运行中创建,每次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。
- 一个额外的配置"results"存储所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_NeverSleep__Noromaid-13b-v0.3", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-08T08:43:54.536488运行的最新结果:
python { "all": { "acc": 0.5677987077394565, "acc_stderr": 0.033653954046911065, "acc_norm": 0.5743169734927792, "acc_norm_stderr": 0.034368230343916395, "mc1": 0.35495716034271724, "mc1_stderr": 0.0167508623813759, "mc2": 0.5073138068542993, "mc2_stderr": 0.015726117257006858 }, "harness|arc:challenge|25": { "acc": 0.5972696245733788, "acc_stderr": 0.01433223630679015, "acc_norm": 0.6279863481228669, "acc_norm_stderr": 0.014124597881844461 }, "harness|hellaswag|10": { "acc": 0.6479784903405696, "acc_stderr": 0.004766245539606633, "acc_norm": 0.8441545508862777, "acc_norm_stderr": 0.0036196748640350256 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4888888888888889, "acc_stderr": 0.04318275491977976, "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.04318275491977976 }, "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": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6075471698113207, "acc_stderr": 0.03005258057955785, "acc_norm": 0.6075471698113207, "acc_norm_stderr": 0.03005258057955785 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04076663253918567, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.5317919075144508, "acc_stderr": 0.03804749744364764, "acc_norm": 0.5317919075144508, "acc_norm_stderr": 0.03804749744364764 }, "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": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.03246956919789958, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.03246956919789958 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.024594975128920935, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.024594975128920935 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6645161290322581, "acc_stderr": 0.02686020644472434, "acc_norm": 0.6645161290322581, "acc_norm_stderr": 0.02686020644472434 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6727272727272727, "acc_stderr": 0.036639749943912434, "acc_norm": 0.6727272727272727, "acc_norm_stderr": 0.036639749943912434 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.02717121368316455, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.02717121368316455 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5435897435897435, "acc_stderr": 0.02525448542479961, "acc_norm": 0.5435897435897435, "acc_norm_stderr": 0.02525448542479961 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028604, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.028493465091028604 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5798319327731093, "acc_stderr": 0.03206183783236153, "acc_norm": 0.5798319327731093, "acc_norm_stderr": 0.03206183783236153 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3509933774834437, "acc_stderr": 0.03896981964257375, "acc_norm": 0.3509933774834437, "acc_norm_stderr": 0.03896981964257375 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.7467889908256881, "acc_stderr": 0.01864407304137504, "acc_norm": 0.7467889908256881, "acc_norm_stderr": 0.01864407304137504 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.4166666666666667, "acc_stderr": 0.03362277436608044, "acc_norm": 0.4166666666666667, "acc_norm_stderr": 0.03362277436608044 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7892156862745098, "acc_stderr": 0.02862654791243739, "acc_norm": 0.7892156862745098, "acc_norm_stderr": 0.02862654791243739 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7552742616033755, "acc_stderr": 0.02798569938703643, "acc_norm": 0.7552742616033755, "acc_norm_stderr": 0.02798569938703643 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6816143497757847, "acc_stderr": 0.03126580522513713, "acc_norm": 0.6816143497757847, "acc_norm_stderr": 0.03126580522513713 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.648854961832061, "acc_stderr": 0.04186445163013751, "acc_norm": 0.648854961832061, "acc_norm_stderr": 0.04186445163013751 }, "harness|hendrycksTest-international_law|5": { "acc": 0.7272727272727273, "acc_stderr": 0.04065578140908706, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.04065578140908706 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7407407407407407, "acc_stderr": 0.04236511258094633, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.04236511258094633 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.6748466257668712, "acc_stderr": 0.036803503712864616, "acc_norm": 0.6748466257668712, "acc_norm_stderr": 0.036803503712864616 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.35714285714285715, "acc_stderr": 0.04547960999764376, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04547960999764376 }, "harness|hendrycksTest-management|5": { "acc": 0.7378640776699029, "acc_stderr": 0.04354631077260595, "acc_norm": 0.7378640776699029, "acc_norm_stderr": 0.04354631077260595 }, "harness|hendrycksTest-marketing|5": { "acc": 0.7991452991452992, "acc_stderr": 0.02624677294689048, "acc_norm": 0.7991452991452992, "acc_norm_stderr": 0.02624677294689048 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.7586206896551724, "acc_stderr": 0.015302380123542106, "acc_norm": 0.7586206896551724, "acc_norm_stderr": 0.015302380123542106 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.6473988439306358, "acc_stderr": 0.025722802200895817, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.025722802200895817 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.4592178770949721, "acc_stderr": 0.016666783616525772, "acc_norm": 0.4592178770949721, "acc_norm_stderr": 0.016666783616525772 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.6535947712418301, "acc_stderr": 0.027245613047215355, "acc_norm": 0.6535947712418301, "acc_norm_stderr": 0.027245613047215355 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.6302250803858521, "acc_stderr": 0.027417996705630988, "acc_norm": 0.6302250803858521, "acc_norm_stderr": 0.027417996705630988 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.6265432098765432, "acc_stderr": 0.026915003011380154, "acc_norm": 0.6265432098765432, "acc_norm_stderr": 0.026915003011380154 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.4432624113475177, "acc_stderr": 0.029634838473766, "acc_norm": 0.4432624113475177, "acc_norm_stderr": 0.029634838473766 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4335071707953064, "acc_stderr": 0.012656810383983965, "acc_norm": 0.4335071707953064, "acc_norm_stderr": 0.012656810383983965 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.5404411764705882, "acc_stderr": 0.03027332507734575, "acc_norm": 0.5404411764705882, "acc_norm_stderr": 0.03027332507734575 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.5718954248366013, "acc_stderr": 0.020017629214213094, "acc_norm": 0.5718954248366013, "acc_norm_stderr": 0.020017629214213094 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6090909090909091, "acc_stderr": 0.046737523336702384, "acc_norm": 0.6090909090909091, "acc_norm_stderr": 0.046737523336702384 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.6326530612244898, "acc_stderr": 0.03086214492108756, "acc_norm": 0.6326530612244898, "acc_norm_stderr": 0.03086214492108756 }, "harness|hendrycksTest-sociology|5": { "acc": 0.7562189054726368, "acc_stderr": 0.030360490154014638, "acc_norm": 0.7562189054726368, "acc_norm_stderr": 0.030360490154014638 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.82, "acc_stderr": 0.038612291966536934, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-virology|5": { "acc": 0.463855421686747, "acc_stderr": 0.03882310850890594, "acc_norm": 0.463855421686747, "acc_norm_stderr": 0.03882310850890594 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.7777777777777778, "acc_stderr": 0.031885780176863984, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.031885780176863984 }, "harness|truthfulqa:mc|0": { "mc1": 0.35495716034271724, "mc1_stderr": 0.0167508623813759, "mc2": 0.5073138068542993, "mc2_stderr": 0.015726117257006858 }, "harness|winogrande|5": { "acc": 0.7474348855564326, "acc_stderr": 0.012211148449394105 }, "harness|gsm8k|5": { "acc": 0.2304776345716452, "acc_stderr": 0.011600249020595825 } }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_07T22_16_01.123734
- path: **/details_harness|arc:challenge|25_2024-01-07T22-16-01.123734.parquet
- split: 2024_01_08T08_43_54.536488
- path: **/details_harness|arc:challenge|25_2024-01-08T08-43-54.536488.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-08T08-43-54.536488.parquet
- split: 2024_01_07T22_16_01.123734
-
config_name: harness_gsm8k_5
- split: 2024_01_07T22_16_01.123734
- path: **/details_harness|gsm8k|5_2024-01-07T22-16-01.123734.parquet
- split: 2024_01_08T08_43_54.536488
- path: **/details_harness|gsm8k|5_2024-01-08T08-43-54.536488.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-08T08-43-54.536488.parquet
- split: 2024_01_07T22_16_01.123734
-
config_name: harness_hellaswag_10
- split: 2024_01_07T22_16_01.123734
- path: **/details_harness|hellaswag|10_2024-01-07T22-16-01.123734.parquet
- split: 2024_01_08T08_43_54.536488
- path: **/details_harness|hellaswag|10_2024-01-08T08-43-54.536488.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-08T08-43-54.536488.parquet
- split: 2024_01_07T22_16_01.123734
-
config_name: harness_hendrycksTest_5
- split: 2024_01_07T22_16_01.123734
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-virology|5_2024-01-07T22-16-01.123734.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-01-07T22-16-01.123734.parquet
- path:
- split: 2024_01_07T22_16_01.123734



