# 217th Place Solution for the CommonLit - Evaluate Student Summaries Competition

First of all, I would like to thank the Learning Agency Lab and Kaggle for organizing and running this competition. I would also like to thank all the competitors who shared their views and notebooks.
Congratulations to all the winners! Although I am not one of the winners, I would like to share with you what I did and the results. I am interested in NLP but have never had good results in competitions. So I started to study in public notebooks. All I could finally do was change a few parameters due to my lack of ability and the GPU's time limit, but the private score improved very slightly.
Context
Business context:
[https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview](https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview)
Data context:
[https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data](https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data)
![](assets/4f48168a526f9f1598fc262b.png)
Overview of the Approach
Since I did not have the ability to create my own notebook, I started by modifying the excellent notebook [
[1](https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect?scriptVersionId=141032742)
] by
[Cody_Null](https://www.kaggle.com/cody11null)
. The main modification was to change the batch size.
Details of the submission
I changed all random seed values to 0 just because I like 0, although it may not make sense. Then, I decided to try changing the batch size. First, the batch size was changed from the original 12 to 16, but the result was out of memory. Second, the batch size was decreased to 8, but the public score was worsened from 0.45021 to 0.46446. Third, the batch size was changed to 10, but the public score further worsened to 0.46992. So I stopped.
I saw only the public scores and thought there was no improvement, but the changes in the private scores were different. When the batch size was decreased to 8, contrary to the worsening in the public score (0.45021 -> 0.46446), the private score had improved very slightly (0.48972 -> 0.48483).
![](assets/67da338473ac0ccf9d0f143b.png)
I always tend to worry only about the public scores. I want to have a firm standard for myself.
Sources
[1]
[Cody_Null](https://www.kaggle.com/cody11null)
,
[Tuned Debertav3+LGBM+autocorrect](https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect?scriptVersionId=141032742)
.