open-llm-leaderboard-old/details_eren23__DistiLabelOrca-TinyLLama-1.1B
收藏数据集概述
数据集摘要
该数据集是在评估模型 eren23/DistiLabelOrca-TinyLLama-1.1B 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。数据集从 1 次运行中创建，每个运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
数据集结构
数据集包含多个配置，每个配置对应不同的评估任务。以下是部分配置的示例：
-
harness_arc_challenge_25
- 分割：2024_01_27T12_31_51.008876
- 路径：
**/details_harness|arc:challenge|25_2024-01-27T12-31-51.008876.parquet - 分割：latest
- 路径：
**/details_harness|arc:challenge|25_2024-01-27T12-31-51.008876.parquet
-
harness_gsm8k_5
- 分割：2024_01_27T12_31_51.008876
- 路径：
**/details_harness|gsm8k|5_2024-01-27T12-31-51.008876.parquet - 分割：latest
- 路径：
**/details_harness|gsm8k|5_2024-01-27T12-31-51.008876.parquet
-
harness_hellaswag_10
- 分割：2024_01_27T12_31_51.008876
- 路径：
**/details_harness|hellaswag|10_2024-01-27T12-31-51.008876.parquet - 分割：latest
- 路径：
**/details_harness|hellaswag|10_2024-01-27T12-31-51.008876.parquet
-
harness_hendrycksTest_5
- 分割：2024_01_27T12_31_51.008876
- 路径：多个路径，例如：
**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T12-31-51.008876.parquet**/details_harness|hendrycksTest-anatomy|5_2024-01-27T12-31-51.008876.parquet- ...
- 分割：latest
- 路径：多个路径，例如：
**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-27T12-31-51.008876.parquet**/details_harness|hendrycksTest-anatomy|5_2024-01-27T12-31-51.008876.parquet- ...
最新结果
以下是 最新结果 的示例：
python { "all": { "acc": 0.2579497336465992, "acc_stderr": 0.03077796101189773, "acc_norm": 0.25889304976710464, "acc_norm_stderr": 0.031529056639141094, "mc1": 0.23745410036719705, "mc1_stderr": 0.01489627744104183, "mc2": 0.38054949560093154, "mc2_stderr": 0.014019298506911837 }, "harness|arc:challenge|25": { "acc": 0.34897610921501704, "acc_stderr": 0.013928933461382494, "acc_norm": 0.36177474402730375, "acc_norm_stderr": 0.014041957945038073 }, "harness|hellaswag|10": { "acc": 0.45937064329814775, "acc_stderr": 0.004973280417705513, "acc_norm": 0.6115315674168492, "acc_norm_stderr": 0.004864058877626288 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.17037037037037037, "acc_stderr": 0.03247781185995593, "acc_norm": 0.17037037037037037, "acc_norm_stderr": 0.03247781185995593 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17105263157894737, "acc_stderr": 0.030643607071677077, "acc_norm": 0.17105263157894737, "acc_norm_stderr": 0.030643607071677077 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27547169811320754, "acc_stderr": 0.02749566368372406, "acc_norm": 0.27547169811320754, "acc_norm_stderr": 0.02749566368372406 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.03514697467862388, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.19653179190751446, "acc_stderr": 0.030299574664788147, "acc_norm": 0.19653179190751446, "acc_norm_stderr": 0.030299574664788147 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28085106382978725, "acc_stderr": 0.02937917046412482, "acc_norm": 0.28085106382978725, "acc_norm_stderr": 0.02937917046412482 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.03600105692727771, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.03600105692727771 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2804232804232804, "acc_stderr": 0.023135287974325635, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.023135287974325635 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276862, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276862 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.24838709677419354, "acc_stderr": 0.024580028921481003, "acc_norm": 0.24838709677419354, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694433, "acc_norm": 0.2512315270935961, "acc_norm_stderr": 0.030516530732694433 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-
