open-llm-leaderboard-old/details_Charlie911__vicuna-7b-v1.5-lora-mctaco
收藏数据集概述
数据集摘要
该数据集是在对模型 Charlie911/vicuna-7b-v1.5-lora-mctaco 进行评估运行时自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 64 个配置,每个配置对应一个评估任务。
- 数据集从 3 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。
- 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_Charlie911__vicuna-7b-v1.5-lora-mctaco", "harness_winogrande_5", split="train")
最新结果
以下是 2023-09-17T20:27:23.554125 运行的最新结果: python { "all": { "em": 0.2488464765100671, "em_stderr": 0.004427614016278926, "f1": 0.28849937080536914, "f1_stderr": 0.00442953185165108, "acc": 0.372010258662628, "acc_stderr": 0.00929094831305589 }, "harness|drop|3": { "em": 0.2488464765100671, "em_stderr": 0.004427614016278926, "f1": 0.28849937080536914, "f1_stderr": 0.00442953185165108 }, "harness|gsm8k|5": { "acc": 0.04473085670962851, "acc_stderr": 0.005693886131407047 }, "harness|winogrande|5": { "acc": 0.6992896606156275, "acc_stderr": 0.012888010494704732 } }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2023_09_01T09_00_53.100273
- path: **/details_harness|arc:challenge|25_2023-09-01T09:00:53.100273.parquet
- split: 2023_09_01T09_03_24.370765
- path: **/details_harness|arc:challenge|25_2023-09-01T09:03:24.370765.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-01T09:03:24.370765.parquet
- split: 2023_09_01T09_00_53.100273
-
config_name: harness_drop_3
- split: 2023_09_17T20_27_23.554125
- path: **/details_harness|drop|3_2023-09-17T20-27-23.554125.parquet
- split: latest
- path: **/details_harness|drop|3_2023-09-17T20-27-23.554125.parquet
- split: 2023_09_17T20_27_23.554125
-
config_name: harness_gsm8k_5
- split: 2023_09_17T20_27_23.554125
- path: **/details_harness|gsm8k|5_2023-09-17T20-27-23.554125.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-09-17T20-27-23.554125.parquet
- split: 2023_09_17T20_27_23.554125
-
config_name: harness_hellaswag_10
- split: 2023_09_01T09_00_53.100273
- path: **/details_harness|hellaswag|10_2023-09-01T09:00:53.100273.parquet
- split: 2023_09_01T09_03_24.370765
- path: **/details_harness|hellaswag|10_2023-09-01T09:03:24.370765.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-01T09:03:24.370765.parquet
- split: 2023_09_01T09_00_53.100273
-
config_name: harness_hendrycksTest_5
- split: 2023_09_01T09_00_53.100273
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-management|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-09-01T09:00:53.100273.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-09-
- path:
- split: 2023_09_01T09_00_53.100273



