open-llm-leaderboard-old/details_gmonsoon__Delta-4B-notso-base
收藏数据集概述
该数据集是在模型 gmonsoon/Delta-4B-notso-base 的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。
- 数据集从 1 次运行中创建，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的 split 形式存储。
- "train" split 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_gmonsoon__Delta-4B-notso-base", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-07T14:15:31.284880 运行 的最新结果：
python { "all": { "acc": 0.566811467402178, "acc_stderr": 0.03360534211149504, "acc_norm": 0.5758330022436464, "acc_norm_stderr": 0.03443696006367741, "mc1": 0.3684210526315789, "mc1_stderr": 0.016886551261046042, "mc2": 0.5431268700767001, "mc2_stderr": 0.015963011709493005 }, "harness|arc:challenge|25": { "acc": 0.5546075085324232, "acc_stderr": 0.014523987638344078, "acc_norm": 0.575938566552901, "acc_norm_stderr": 0.014441889627464394 }, "harness|hellaswag|10": { "acc": 0.5826528579964151, "acc_stderr": 0.004921133864931888, "acc_norm": 0.7610037841067516, "acc_norm_stderr": 0.0042559884133957565 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5037037037037037, "acc_stderr": 0.04319223625811331, "acc_norm": 0.5037037037037037, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5657894736842105, "acc_stderr": 0.040335656678483205, "acc_norm": 0.5657894736842105, "acc_norm_stderr": 0.040335656678483205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5886792452830188, "acc_stderr": 0.030285009259009798, "acc_norm": 0.5886792452830188, "acc_norm_stderr": 0.030285009259009798 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5902777777777778, "acc_stderr": 0.04112490974670787, "acc_norm": 0.5902777777777778, "acc_norm_stderr": 0.04112490974670787 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5491329479768786, "acc_stderr": 0.0379401267469703, "acc_norm": 0.5491329479768786, "acc_norm_stderr": 0.0379401267469703 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.048108401480826346, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.048108401480826346 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.502127659574468, "acc_stderr": 0.03268572658667492, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4413793103448276, "acc_stderr": 0.04137931034482758, "acc_norm": 0.4413793103448276, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43915343915343913, "acc_stderr": 0.025559920550531006, "acc_norm": 0.43915343915343913, "acc_norm_stderr": 0.025559920550531006 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04444444444444449, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6741935483870968, "acc_stderr": 0.0266620105785671, "acc_norm": 0.6741935483870968, "acc_norm_stderr": 0.0266620105785671 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.42857142857142855, "acc_stderr": 0.03481904844438803, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.03481904844438803 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885415, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885415 }, "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": 0.8238341968911918, "acc_stderr": 0.02749350424454805, "acc_norm": 0.8238341968911918, "acc_norm_stderr": 0.02749350424454805 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6128205128205129, "acc_stderr": 0.024697216930878948, "acc_norm": 0.6128205128205129, "acc_norm_stderr": 0.024697216930878948 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114982, "acc_norm": 0.3037037037037037, "acc_norm_
