open-llm-leaderboard-old/details_OpenAssistant__pythia-12b-sft-v8-2.5k-steps
收藏数据集概述
数据集名称
- Evaluation run of OpenAssistant/pythia-12b-sft-v8-2.5k-steps
数据集描述
- 该数据集是在对模型 OpenAssistant/pythia-12b-sft-v8-2.5k-steps 进行评估运行期间自动创建的。
- 数据集包含 64 个配置,每个配置对应一个评估任务。
- 数据集由 2 次运行创建,每次运行可以在每个配置中作为一个特定的分片找到,分片名称使用运行的时间戳。"train" 分片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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_OpenAssistant__pythia-12b-sft-v8-2.5k-steps", "harness_winogrande_5", split="train")
最新结果
- 这些是最新的结果,来自 2023-10-19T06:05:53.274569 的运行: python { "all": { "em": 0.0008389261744966443, "em_stderr": 0.0002964962989801232, "f1": 0.04918729026845652, "f1_stderr": 0.0011958323498480873, "acc": 0.3760981059411563, "acc_stderr": 0.010720714478256874 }, "harness|drop|3": { "em": 0.0008389261744966443, "em_stderr": 0.0002964962989801232, "f1": 0.04918729026845652, "f1_stderr": 0.0011958323498480873 }, "harness|gsm8k|5": { "acc": 0.09552691432903715, "acc_stderr": 0.008096605771155738 }, "harness|winogrande|5": { "acc": 0.6566692975532754, "acc_stderr": 0.013344823185358009 } }
配置详情
-
harness_arc_challenge_25
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-19T18:14:20.845496.parquet
-
harness_drop_3
- 分片:2023_10_19T06_05_53.274569, latest
- 路径:
**/details_harness|drop|3_2023-10-19T06-05-53.274569.parquet
-
harness_gsm8k_5
- 分片:2023_10_19T06_05_53.274569, latest
- 路径:
**/details_harness|gsm8k|5_2023-10-19T06-05-53.274569.parquet
-
harness_hellaswag_10
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hellaswag|10_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:多个文件路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_abstract_algebra_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_anatomy_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_astronomy_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_business_ethics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_biology_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_medicine_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_college_physics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_computer_security_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_econometrics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:14:20.845496.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分片:2023_07_19T18_14_20.845496, latest
- 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:14:20.845496.parquet
以上是数据集的详细概述,包括数据集的名称、描述、加载示例、最新结果以及各个配置的详细信息。



