open-llm-leaderboard-old/details_fblgit__una-cybertron-7b-v2-bf16
收藏数据集概述
数据集摘要
该数据集是在模型 fblgit/una-cybertron-7b-v2-bf16 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 1 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。
- 额外的 "results" 配置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_fblgit__una-cybertron-7b-v2-bf16", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-04T16:28:35.097444 运行的最新结果：
python { "all": { "acc": 0.6349296405755961, "acc_stderr": 0.03261211472247009, "acc_norm": 0.6370258261406261, "acc_norm_stderr": 0.03327308531523366, "mc1": 0.48714810281517745, "mc1_stderr": 0.017497717944299825, "mc2": 0.646322826116642, "mc2_stderr": 0.015041829082644448 }, "harness|arc:challenge|25": { "acc": 0.6552901023890785, "acc_stderr": 0.01388881628678211, "acc_norm": 0.6825938566552902, "acc_norm_stderr": 0.013602239088038167 }, "harness|hellaswag|10": { "acc": 0.6717785301732723, "acc_stderr": 0.004686062421158145, "acc_norm": 0.8584943238398726, "acc_norm_stderr": 0.0034783009945146925 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595853, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.028544793319055326, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5914893617021276, "acc_stderr": 0.032134180267015755, "acc_norm": 0.5914893617021276, "acc_norm_stderr": 0.032134180267015755 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4021164021164021, "acc_stderr": 0.02525303255499769, "acc_norm": 0.4021164021164021, "acc_norm_stderr": 0.02525303255499769 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7645161290322581, "acc_stderr": 0.024137632429337714, "acc_norm": 0.7645161290322581, "acc_norm_stderr": 0.024137632429337714 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7777777777777778, "acc_stderr": 0.02962022787479049, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.02962022787479049 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8497409326424871, "acc_stderr": 0.025787723180723875, "acc_norm": 0.8497409326424871, "acc_norm_stderr": 0.025787723180723875 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402534, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.02840653309060846, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.02840653309060846 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6932773109243697, "acc_stderr": 0.029953823891887037, "acc_norm": 0.6932773109243697, "acc_norm_stderr": 0.029953823891887037 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.33774834437086093, "acc_stderr": 0.038615575462551684, "acc_norm": 0.33774834437086093, "acc_norm_stderr": 0.038615575462551684 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8366972477064221, "acc_stderr": 0.01584825580650155, "acc_norm": 0.8366972477064221, "acc_norm_stderr": 0.01584825580650155 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5555555555555556, "acc_stderr": 0.03388857118502325, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.03388857118502325 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7990196078431373, "acc_stderr": 0.028125972265654373, "acc_norm": 0.7990196078431373, "acc_norm_stderr": 0.028125972265654373 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7848101265822784, "acc_stderr": 0.026750826994676177, "acc_norm": 0.7848101265822784, "acc_norm_stderr": 0.026750826994676177 }, "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": 0.7404580152671756, "acc_stderr": 0.03844876139785271, "acc_norm": 0.7404580152671756, "acc_norm_stderr": 0.03844876139785271 }, "harness|hendrycksTest-international_law|5": { "acc": 0.7520661157024794, "acc_stderr": 0.03941897526516302, "acc_norm": 0.7520661157024794, "acc_norm_stderr": 0.03941897526516302 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7314814814814815, "acc_stderr": 0.042844679680521934, "acc_norm": 0.7314814814814815, "acc_norm_stderr": 0.042844679680521934 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7300613496932515, "acc_stderr": 0.034878251684978906, "acc_norm": 0.7300613496932515, "acc_norm_stderr": 0.034878251684978906 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.49107142857142855, "acc_stderr": 0.04745033255489123, "acc_norm": 0.49107142857142855, "acc_norm_stderr": 0.04745033255489123 }, "harness|hendrycksTest-management|5": { "acc": 0.8058252427184466, "acc_stderr": 0.03916667762822584, "acc_norm": 0.8058252427184466, "acc_norm_stderr": 0.03916667762822584 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8547008547008547, "acc_stderr": 0.023086635086841403, "acc_norm": 0.8547008547008547, "acc_norm_stderr": 0.023086635086841403 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8160919540229885, "acc_stderr": 0.013853724170922534, "acc_norm": 0.8160919540229885, "acc_norm_stderr": 0.013853724170922534 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.6994219653179191, "acc_stderr": 0.024685316867257803, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.024685316867257803 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.3787709497206704, "acc_stderr": 0.01622353351036511, "acc_norm": 0.3787709497206704, "acc_norm_stderr": 0.01622353351036511 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.6797385620915033, "acc_stderr": 0.02671611838015685, "acc_norm": 0.6797385620915033, "acc_norm_stderr": 0.02671611838015685 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7009646302250804, "acc_stderr": 0.026003301117885142, "acc_norm": 0.7009646302250804, "acc_norm_stderr": 0.026003301117885142 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7222222222222222, "acc_stderr": 0.02492200116888633, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.02492200116888633 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.49645390070921985, "acc_stderr": 0.02982674915328092, "acc_norm": 0.49645390070921985, "acc_norm_stderr": 0.02982674915328092 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4452411994784876, "acc_stderr": 0.012693421303973294, "acc_norm": 0.4452411994784876, "acc_norm_stderr": 0.012693421303973294 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6544117647058824, "acc_stderr": 0.028888193103988633, "acc_norm": 0.6544117647058824, "acc_norm_stderr": 0.028888193103988633 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6503267973856209, "acc_stderr": 0.01929196189506638, "acc_norm": 0.6503267973856209, "acc_norm_stderr": 0.01929196189506638 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6454545454545455, "acc_stderr": 0.045820048415054174, "acc_norm": 0.6454545454545455, "acc_norm_stderr": 0.045820048415054174 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7020408163265306, "acc_stderr": 0.029279567411065677, "acc_norm": 0.7020408163265306, "acc_norm_stderr": 0.029279567411065677 }, "harness|hendrycksTest-sociology|5": { "acc": 0.845771144278607, "acc_stderr": 0.025538433368578327, "acc_norm": 0.845771144278607, "acc_norm_stderr": 0.025538433368578327 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.81, "acc_stderr": 0.03942772444036625, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-virology|5": { "acc": 0.5240963855421686, "acc_stderr": 0.03887971849597264, "acc_norm": 0.5240963855421686, "acc_norm_stderr": 0.03887971849597264 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.7953216374269005, "acc_stderr": 0.03094445977853321, "acc_norm": 0.7953216374269005, "acc_norm_stderr": 0.03094445977853321 }, "harness|truthfulqa:mc|0": { "mc1": 0.48714810281517745, "mc1_stderr": 0.017497717944299825, "mc2": 0.646322826116642, "mc2_stderr": 0.015041829082644448 }, "harness|winogrande|5": { "acc": 0.8097868981846882, "acc_stderr": 0.01103033579861744 }, "harness|gsm8k|5": { "acc": 0.5504169825625473, "acc_stderr": 0.013702290047884747 } }
配置详情
-
harness_arc_challenge_25
- 分割: 2023_12_04T16_28_35.097444
- 路径:
**/details_harness|arc:challenge|25_2023-12-04T16-28-35.097444.parquet - 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2023-12-04T16-28-35.097444.parquet
-
harness_gsm8k_5
- 分割: 2023_12_04T16_28_35.097444
- 路径:
**/details_harness|gsm8k|5_2023-12-04T16-28-35.097444.parquet - 分割: latest
- 路径:
**/details_harness|gsm8k|5_2023-12-04T16-28-35.097444.parquet
-
harness_hellaswag_10
- 分割: 2023_12_04T16_28_35.097444
- 路径:
**/details_harness|hellaswag|10_2023-12-04T16-28-35.097444.parquet - 分割: latest
- 路径:
**/details_harness|hellaswag|10_2023-12-04T16-28-35.097444.parquet
-
harness_hendrycksTest_5
- 分割: 2023_12_04T16_28_35.097444
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-anatomy|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-astronomy|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_biology|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-college_physics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-computer_security|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-econometrics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-12-04T16-28-35.097444.parquet**/details_harness|hendrycksTest-global_facts|5_2023-12-04T16-28-35.097444.parquet
以上是数据集的概述和配置详情，包括数据集的组成、加载示例以及最新的评估结果。
