open-llm-leaderboard-old/details_NousResearch__Hermes-2-Pro-Mistral-7B
收藏数据集概述
数据集简介
该数据集是在评估模型 NousResearch/Hermes-2-Pro-Mistral-7B 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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 2 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。
- 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_NousResearch__Hermes-2-Pro-Mistral-7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要: python { "all": { "acc": 0.623594315235678, "acc_stderr": 0.03260526973524088, "acc_norm": 0.625059006962056, "acc_norm_stderr": 0.03325770399160673, "mc1": 0.4222766217870257, "mc1_stderr": 0.017290733254248174, "mc2": 0.5900505040048408, "mc2_stderr": 0.015843008489660734 }, "harness|arc:challenge|25": { "acc": 0.6126279863481229, "acc_stderr": 0.014235872487909869, "acc_norm": 0.6399317406143344, "acc_norm_stderr": 0.014027516814585188 }, "harness|hellaswag|10": { "acc": 0.6484763991236805, "acc_stderr": 0.0047647031456802685, "acc_norm": 0.8275243975303724, "acc_norm_stderr": 0.0037702118591189287 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, # 其他任务的结果... }
配置详情
-
harness_arc_challenge_25
- 分割:2024_03_14T00_16_56.742861
- 路径:
**/details_harness|arc:challenge|25_2024-03-14T00-16-56.742861.parquet
- 路径:
- 分割:2024_03_14T07_29_13.041631
- 路径:
**/details_harness|arc:challenge|25_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:2024_03_14T00_16_56.742861
-
harness_gsm8k_5
- 分割:2024_03_14T00_16_56.742861
- 路径:
**/details_harness|gsm8k|5_2024-03-14T00-16-56.742861.parquet
- 路径:
- 分割:2024_03_14T07_29_13.041631
- 路径:
**/details_harness|gsm8k|5_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:2024_03_14T00_16_56.742861
-
harness_hellaswag_10
- 分割:2024_03_14T00_16_56.742861
- 路径:
**/details_harness|hellaswag|10_2024-03-14T00-16-56.742861.parquet
- 路径:
- 分割:2024_03_14T07_29_13.041631
- 路径:
**/details_harness|hellaswag|10_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2024-03-14T07-29-13.041631.parquet
- 路径:
- 分割:2024_03_14T00_16_56.742861
-
harness_hendrycksTest_5
- 分割:2024_03_14T00_16_56.742861
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-human_aging|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-international_law|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-management|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-marketing|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-03-14T00-16-56.742861.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-14T00-16-56.742861.parquet- `**/details_harness|hendrycksTest-nutrition|5_2024-0
- 路径:
- 分割:2024_03_14T00_16_56.742861



