Title: KAGGLE COMPETITION Proposal
Author: lkl, lkl#0997
Date posted: 2022/09/19
Summary
- In the Kaggle competition, I want to train huge model using GPU to get a high score.
- I want to publish one or more models so that AIN DAO can be advertisedment on Kaggle.
Background
Larger models can be trained with larger memory than when training at the 16GB limit, such as the V100 or P100 borrowed from existing colabs, which is expected to lead to higher scores.
Kaggle competition link: DFL - Bundesliga Data Shootout | Kaggle
Scope of Work
Achieving a score of 0.400 or higher, exceeding the top 6% grade of 0.396. (2022-09-19, 19/339)
Publish one or more trained models, stating that resources were supported by AINDAO.
Timeline
1W (Sep 19th, 2022): Train model
1W (Sep 22th, 2022): Publish model on Kaggle
Specification
Required Hardware Specifications
- A100@40GB * 4
- 200GB system memory
Operation:
- Train 10+ models and find good hyperparameters.
Targets
Achieving a score of 0.400 or higher.
Participants
Kaggle individual participants interested in AI
Voting
1st voting: 2022-09-19 03:10 ~ 2022-09-21 03:00 on AIN DAO (discord)
2nd voting: on Snapshot when 3 more people participated in the voting.