open-llm-leaderboard-old/details_Weyaxi__Nous-Hermes-2-SUS-Chat-34B-Linear
收藏数据集概述
该数据集是在对模型 Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
- 数据集是从 1 次运行中创建的。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。
- 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_Weyaxi__Nous-Hermes-2-SUS-Chat-34B-Linear", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-05T02:55:53.055850 运行的最新结果：
python { "all": { "acc": 0.764443488582266, "acc_stderr": 0.027937497173221686, "acc_norm": 0.7677629955053134, "acc_norm_stderr": 0.028472131263495265, "mc1": 0.42472460220318237, "mc1_stderr": 0.017304000957167477, "mc2": 0.591909971390079, "mc2_stderr": 0.014849538386220443 }, "harness|arc:challenge|25": { "acc": 0.6450511945392492, "acc_stderr": 0.013983036904094089, "acc_norm": 0.6638225255972696, "acc_norm_stderr": 0.013804855026205761 }, "harness|hellaswag|10": { "acc": 0.6530571599283012, "acc_stderr": 0.004750245757533323, "acc_norm": 0.8494323839872535, "acc_norm_stderr": 0.003568960247101696 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.725925925925926, "acc_stderr": 0.03853254836552003, "acc_norm": 0.725925925925926, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.02564834125169361, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.02564834125169361 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8888888888888888, "acc_stderr": 0.02628055093284808, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.02628055093284808 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7225433526011561, "acc_stderr": 0.03414014007044036, "acc_norm": 0.7225433526011561, "acc_norm_stderr": 0.03414014007044036 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7872340425531915, "acc_stderr": 0.02675439134803978, "acc_norm": 0.7872340425531915, "acc_norm_stderr": 0.02675439134803978 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594963, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7793103448275862, "acc_stderr": 0.03455930201924812, "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.03455930201924812 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6851851851851852, "acc_stderr": 0.023919984164047736, "acc_norm": 0.6851851851851852, "acc_norm_stderr": 0.023919984164047736 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5634920634920635, "acc_stderr": 0.04435932892851466, "acc_norm": 0.5634920634920635, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657248, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657248 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6206896551724138, "acc_stderr": 0.03413963805906235, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.03413963805906235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.85, "acc_stderr": 0.03588702812826371, "acc_norm": 0.85, "acc_norm_stderr": 0.03588702812826371 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.026024657651656187, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.026024657651656187 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8205128205128205, "acc_stderr": 0.01945739078768181, "acc_norm": 0.8205128205128205, "acc_norm_stderr": 0.01945739078768181 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4222222222222222, "acc_stderr": 0.0301144420196681, "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.0301144420196681 }, "harness|hendrycksTest-high_school_microeconomics|
