open-llm-leaderboard-old/details_bongchoi__MoMo-70B-LoRA-V1.1
收藏数据集概述
数据集摘要
该数据集是在评估模型 bongchoi/MoMo-70B-LoRA-V1.1 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，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。
结果配置
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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bongchoi__MoMo-70B-LoRA-V1.1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-09T12:57:45.545472 运行的最新结果：
python { "all": { "acc": 0.6664015038261123, "acc_stderr": 0.03100518950503553, "acc_norm": 0.6709955972660262, "acc_norm_stderr": 0.03161767962532908, "mc1": 0.38310893512851896, "mc1_stderr": 0.01701846167938986, "mc2": 0.5498134743824588, "mc2_stderr": 0.014557620111754889 }, "harness|arc:challenge|25": { "acc": 0.6313993174061433, "acc_stderr": 0.014097810678042194, "acc_norm": 0.6663822525597269, "acc_norm_stderr": 0.013778687054176534 }, "harness|hellaswag|10": { "acc": 0.6716789484166501, "acc_stderr": 0.004686425851253281, "acc_norm": 0.8716391157140012, "acc_norm_stderr": 0.0033380760156172563 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.042561937679014075, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.75, "acc_stderr": 0.03523807393012047, "acc_norm": 0.75, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.04461960433384741, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6716981132075471, "acc_stderr": 0.028901593612411784, "acc_norm": 0.6716981132075471, "acc_norm_stderr": 0.028901593612411784 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.046550104113196177, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196177 }, "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": 0.574468085106383, "acc_stderr": 0.03232146916224468, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.0407032901370707, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.0407032901370707 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.02507598176760168, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.02507598176760168 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8096774193548387, "acc_stderr": 0.02233170761182307, "acc_norm": 0.8096774193548387, "acc_norm_stderr": 0.02233170761182307 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "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": 0.8585858585858586, "acc_stderr": 0.02482590979334334, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.02482590979334334 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.018088393839078915, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.018088393839078915 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7025641025641025, "acc_stderr": 0.02317740813146595, "acc_norm": 0.7025641025641025, "acc_norm_stderr": 0.02317740813146595 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524572, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524572 }, "harness|hendry
