{
  "id": 449210,
  "title": "214th Place Solution",
  "content": "<p>I am a student majoring in computer science and technology. Due to my love for mathematical modeling, I have been exposed to machine learning algorithms and kaggle. However, for a long time, due to the limits of my ability, I can only choose to participate in contests of notebook type.<br>\nThis was the first NLP task I have participated in.Although I achieved a very regrettable ranking , I have learned a lot through the journey.<br>\n<strong>Model</strong><br>\nI choose Debertav3+LGBM &amp; LGBM+autocorrect+Debertav3 in public notebook as a basic model。A few days after this, I tried to focus on developing the preprocessing part &amp; the LGBM part of the code.
And Optuna for finding the best parameter for LGBM.<br>\n<strong>Submissions overview</strong></p>\n<table>\n<thead>\n<tr>\n<th>model</th>\n<th>private score</th>\n<th>public score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>CommonLit-ESS lgbm+autocorrect+DeBERTa V3 (Tuned) - Version 5</td>\n<td>0.484</td>\n<td>0.447</td>\n</tr>\n<tr>\n<td>Explained Tuned Debertav3+LGBM - Version 3</td>\n<td>0.485</td>\n<td>0.445</td>\n</tr>\n<tr>\n<td>Tuned Debertav3+LGBM+autocorrect - Version 2</td>\n<td>0.487</td>\n<td>0.450</td>\n</tr>\n</tbody>\n</table>\n<p>Unfortunately, I didn't get better results based on the original model.Finally, my score stabilized at 190th place in the public list.After sharking ,I ended up falling out of the prize zone.<br>\n<strong>Summary</strong><br>\nThrough this competition, I understand my shortcomings, my machine learning is still at a entry level.<br>\nAs a side note, I have always thought that the model with the same score is ranked by the order of submission time. After this competition, I found that even notebooks with the same code will have slightly different scores when submitted，my notebook has a score of 0.48475 on the first submission and 0.48497 on the second submission, which is an uncertain factor.</p>",
  "comments": [
    {
      "id": 2493700,
      "author_name": "",
      "author_url": "",
      "post_date": "2023-10-23T14:27:26.013000",
      "content": "",
      "votes": 1,
      "replies": []
    }
  ],
  "comment_count": 1,
  "messages": [
    {
      "id": 2493669,
      "postDate": "2023-10-23T14:18:15.687Z",
      "content": "<p>I am a student majoring in computer science and technology. Due to my love for mathematical modeling, I have been exposed to machine learning algorithms and kaggle. However, for a long time, due to the limits of my ability, I can only choose to participate in contests of notebook type.<br>\nThis was the first NLP task I have participated in.Although I achieved a very regrettable ranking , I have learned a lot through the journey.<br>\n<strong>Model</strong><br>\nI choose Debertav3+LGBM &amp; LGBM+autocorrect+Debertav3 in public notebook as a basic model。A few days after this, I tried to focus on developing the preprocessing part &amp; the LGBM part of the code.
And Optuna for finding the best parameter for LGBM.<br>\n<strong>Submissions overview</strong></p>\n<table>\n<thead>\n<tr>\n<th>model</th>\n<th>private score</th>\n<th>public score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>CommonLit-ESS lgbm+autocorrect+DeBERTa V3 (Tuned) - Version 5</td>\n<td>0.484</td>\n<td>0.447</td>\n</tr>\n<tr>\n<td>Explained Tuned Debertav3+LGBM - Version 3</td>\n<td>0.485</td>\n<td>0.445</td>\n</tr>\n<tr>\n<td>Tuned Debertav3+LGBM+autocorrect - Version 2</td>\n<td>0.487</td>\n<td>0.450</td>\n</tr>\n</tbody>\n</table>\n<p>Unfortunately, I didn't get better results based on the original model.Finally, my score stabilized at 190th place in the public list.After sharking ,I ended up falling out of the prize zone.<br>\n<strong>Summary</strong><br>\nThrough this competition, I understand my shortcomings, my machine learning is still at a entry level.<br>\nAs a side note, I have always thought that the model with the same score is ranked by the order of submission time. After this competition, I found that even notebooks with the same code will have slightly different scores when submitted，my notebook has a score of 0.48475 on the first submission and 0.48497 on the second submission, which is an uncertain factor.</p>",
      "rawMarkdown": "I am a student majoring in computer science and technology. Due to my love for mathematical modeling, I have been exposed to machine learning algorithms and kaggle. However, for a long time, due to the limits of my ability, I can only choose to participate in contests of notebook type.\nThis was the first NLP task I have participated in.Although I achieved a very regrettable ranking , I have learned a lot through the journey.\n**Model**\nI choose Debertav3+LGBM & LGBM+autocorrect+Debertav3 in public notebook as a basic model。A few days after this, I tried to focus on developing the preprocessing part & the LGBM part of the code.
And Optuna for finding the best parameter for LGBM.\n**Submissions overview**\n| model | private score | public score |\n| --- | --- |\n| CommonLit-ESS lgbm+autocorrect+DeBERTa V3 (Tuned) - Version 5 | 0.484 | 0.447 |\n| Explained Tuned Debertav3+LGBM - Version 3 | 0.485 | 0.445 |\n| Tuned Debertav3+LGBM+autocorrect - Version 2 | 0.487 | 0.450 |\n\nUnfortunately, I didn't get better results based on the original model.Finally, my score stabilized at 190th place in the public list.After sharking ,I ended up falling out of the prize zone.\n**Summary**\nThrough this competition, I understand my shortcomings, my machine learning is still at a entry level.\nAs a side note, I have always thought that the model with the same score is ranked by the order of submission time. After this competition, I found that even notebooks with the same code will have slightly different scores when submitted，my notebook has a score of 0.48475 on the first submission and 0.48497 on the second submission, which is an uncertain factor.",
      "votes": 4
    },
    {
      "id": 2493700,
      "postDate": "2023-10-23T14:27:26.013Z",
      "rawMarkdown": "",
      "votes": 1,
      "isDeleted": true
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T23:09:14Z",
  "competition_id": 53482,
  "competition_slug": "commonlit-evaluate-student-summaries",
  "team_id": 10904012,
  "solution_url": "/competitions/commonlit-evaluate-student-summaries/writeups/wisszom-214th-place-solution"
}