open-llm-leaderboard-old/details_LordNoah__Alpaca_spin_tuned_gpt2_large
收藏数据集概述
数据集摘要
该数据集是在评估模型 LordNoah/Alpaca_spin_tuned_gpt2_large 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
- 配置数量:63
- 数据来源:1 次运行(run)
- 数据分割:每个配置包含特定分割,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置:"results" 存储所有运行结果的聚合,用于计算和显示在 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_LordNoah__Alpaca_spin_tuned_gpt2_large", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 from run 2024-01-22T13:42:11.763277 的摘要:
python { "all": { "acc": 0.27225604584142943, "acc_stderr": 0.03141590282455585, "acc_norm": 0.27399653003630087, "acc_norm_stderr": 0.03221603447267582, "mc1": 0.21909424724602203, "mc1_stderr": 0.014480038578757449, "mc2": 0.39429285512218326, "mc2_stderr": 0.01421822540176183 }, "harness|arc:challenge|25": { "acc": 0.2568259385665529, "acc_stderr": 0.0127669237941168, "acc_norm": 0.2790102389078498, "acc_norm_stderr": 0.013106784883601341 }, "harness|hellaswag|10": { "acc": 0.36297550288787095, "acc_stderr": 0.004798751281560822, "acc_norm": 0.45120493925512845, "acc_norm_stderr": 0.004965963647210318 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_22T13_42_11.763277
- path: **/details_harness|arc:challenge|25_2024-01-22T13-42-11.763277.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-22T13-42-11.763277.parquet
- split: 2024_01_22T13_42_11.763277
-
config_name: harness_gsm8k_5
- split: 2024_01_22T13_42_11.763277
- path: **/details_harness|gsm8k|5_2024-01-22T13-42-11.763277.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-22T13-42-11.763277.parquet
- split: 2024_01_22T13_42_11.763277
-
config_name: harness_hellaswag_10
- split: 2024_01_22T13_42_11.763277
- path: **/details_harness|hellaswag|10_2024-01-22T13-42-11.763277.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-22T13-42-11.763277.parquet
- split: 2024_01_22T13_42_11.763277
-
config_name: harness_hendrycksTest_5
- split: 2024_01_22T13_42_11.763277
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-22T13-42-11.763277.parquet
- **/details_harness|hendrycksTest-
- path:
- split: 2024_01_22T13_42_11.763277



