open-llm-leaderboard-old/details_TeeZee__DarkForest-20B-v2.0
收藏数据集概述
数据集简介
该数据集是在模型 TeeZee/DarkForest-20B-v2.0 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_TeeZee__DarkForest-20B-v2.0", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-04T21:27:17.007447 运行的最新结果：
python { "all": { "acc": 0.5964441416229264, "acc_stderr": 0.032881026881289174, "acc_norm": 0.6030801125496515, "acc_norm_stderr": 0.033576438313295896, "mc1": 0.39657282741738065, "mc1_stderr": 0.017124930942023518, "mc2": 0.5614370444891642, "mc2_stderr": 0.016024264839771908 }, "harness|arc:challenge|25": { "acc": 0.6092150170648464, "acc_stderr": 0.014258563880513778, "acc_norm": 0.6373720136518771, "acc_norm_stderr": 0.014049106564955014 }, "harness|hellaswag|10": { "acc": 0.6809400517825135, "acc_stderr": 0.004651597209993089, "acc_norm": 0.8631746664011153, "acc_norm_stderr": 0.0034296051062163674 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.039105257528497236, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.039105257528497236 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6452830188679245, "acc_stderr": 0.029445175328199586, "acc_norm": 0.6452830188679245, "acc_norm_stderr": 0.029445175328199586 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.03899073687357335, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.03899073687357335 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5202312138728323, "acc_stderr": 0.03809342081273956, "acc_norm": 0.5202312138728323, "acc_norm_stderr": 0.03809342081273956 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.047240073523838876, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.047240073523838876 }, "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": 0.5574468085106383, "acc_stderr": 0.032469569197899575, "acc_norm": 0.5574468085106383, "acc_norm_stderr": 0.032469569197899575 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.0414243971948936, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.0414243971948936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr": 0.02455229220934265, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.02455229220934265 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.043435254289490965, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.043435254289490965 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6967741935483871, "acc_stderr": 0.026148685930671746, "acc_norm": 0.6967741935483871, "acc_norm_stderr": 0.026148685930671746 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.03374402644139404, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139404 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124498, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124498 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593556, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593556 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6102564102564103, "acc_stderr": 0.024726967886647078, "acc_norm": 0.6102564102564103, "acc_norm_stderr": 0.024726967886647078 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815632, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.02813325257881
