{
  "id": 414185,
  "title": "Question regarding to the code requirements -- GPU used in train script?",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/414185",
  "author_name": "",
  "post_date": "2023-05-31T17:27:29.622396100Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi All,</p>\n<p>I have a question regarding to the competition code requirement.</p>\n<p>Per the statements in the competition overview:</p>\n<p>\"Note: this competition is aimed at producing models that are small and lightweight. We have introduced compute constraints to match - your VMs will have only 2 CPUs, 8GB of RAM, and no GPU available. You will still have a maximum of 9 hours to complete the task, but between the constraints and the efficiency prize there will be some interesting sub-problems to solve. Good luck!</p>\n<p>This is a Code Competition<br>\nSubmissions to this competition must be made through Notebooks. In order for the \"Submit\" button to be active after a commit, the following conditions must be met:</p>\n<p>CPU Notebook &lt;= 9 hours run-time<br>\nGPU Notebook &lt;= Disabled<br>\nInternet access disabled<br>\nFreely &amp; publicly available external data is allowed, including pre-trained models<br>\nSubmission file must be named submission.csv. The API will generate this submission file for you.\"</p>\n<p>I divided my code into a training part and a inference part. In the training part I used GPU to train a XGboost model. Will this break the requirements above?</p>\n<p>Or I should not use the gpu and see if cpu based XGboost training part can be finished within 9 hours?</p>\n<p>Thank you for your help!</p>",
  "messages": [
    {
      "id": "2282607",
      "postDate": "05/31/2023 17:27:29",
      "content": "<p>Hi All,</p>\n<p>I have a question regarding to the competition code requirement.</p>\n<p>Per the statements in the competition overview:</p>\n<p>\"Note: this competition is aimed at producing models that are small and lightweight. We have introduced compute constraints to match - your VMs will have only 2 CPUs, 8GB of RAM, and no GPU available. You will still have a maximum of 9 hours to complete the task, but between the constraints and the efficiency prize there will be some interesting sub-problems to solve. Good luck!</p>\n<p>This is a Code Competition<br>\nSubmissions to this competition must be made through Notebooks. In order for the \"Submit\" button to be active after a commit, the following conditions must be met:</p>\n<p>CPU Notebook &lt;= 9 hours run-time<br>\nGPU Notebook &lt;= Disabled<br>\nInternet access disabled<br>\nFreely &amp; publicly available external data is allowed, including pre-trained models<br>\nSubmission file must be named submission.csv. The API will generate this submission file for you.\"</p>\n<p>I divided my code into a training part and a inference part. In the training part I used GPU to train a XGboost model. Will this break the requirements above?</p>\n<p>Or I should not use the gpu and see if cpu based XGboost training part can be finished within 9 hours?</p>\n<p>Thank you for your help!</p>",
      "rawMarkdown": "Hi All,\n\nI have a question regarding to the competition code requirement.\n\nPer the statements in the competition overview:\n\n\"Note: this competition is aimed at producing models that are small and lightweight. We have introduced compute constraints to match - your VMs will have only 2 CPUs, 8GB of RAM, and no GPU available. You will still have a maximum of 9 hours to complete the task, but between the constraints and the efficiency prize there will be some interesting sub-problems to solve. Good luck!\n\nThis is a Code Competition\nSubmissions to this competition must be made through Notebooks. In order for the \"Submit\" button to be active after a commit, the following conditions must be met:\n\nCPU Notebook <= 9 hours run-time\nGPU Notebook <= Disabled\nInternet access disabled\nFreely & publicly available external data is allowed, including pre-trained models\nSubmission file must be named submission.csv. The API will generate this submission file for you.\"\n\nI divided my code into a training part and a inference part. In the training part I used GPU to train a XGboost model. Will this break the requirements above?\n\nOr I should not use the gpu and see if cpu based XGboost training part can be finished within 9 hours?\n\nThank you for your help!",
      "votes": null
    },
    {
      "id": "2283764",
      "postDate": "06/01/2023 13:38:15",
      "content": "<p>It should be ok as long as you keep the training part, so it can be reproduced.</p>",
      "rawMarkdown": "It should be ok as long as you keep the training part, so it can be reproduced.",
      "votes": null
    },
    {
      "id": "2283864",
      "postDate": "06/01/2023 14:47:13",
      "content": "<p>Thank you so much!</p>",
      "rawMarkdown": "Thank you so much!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2283764,
      "author_name": "oleksiistreltsov",
      "author_url": "",
      "post_date": "06/01/2023 13:38:15",
      "content": "<p>It should be ok as long as you keep the training part, so it can be reproduced.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2283864,
          "author_name": "xiaosufrankhu",
          "author_url": "",
          "post_date": "06/01/2023 14:47:13",
          "content": "<p>Thank you so much!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2282607": "Hi All,\n\nI have a question regarding to the competition code requirement.\n\nPer the statements in the competition overview:\n\n\"Note: this competition is aimed at producing models that are small and lightweight. We have introduced compute constraints to match - your VMs will have only 2 CPUs, 8GB of RAM, and no GPU available. You will still have a maximum of 9 hours to complete the task, but between the constraints and the efficiency prize there will be some interesting sub-problems to solve. Good luck!\n\nThis is a Code Competition\nSubmissions to this competition must be made through Notebooks. In order for the \"Submit\" button to be active after a commit, the following conditions must be met:\n\nCPU Notebook <= 9 hours run-time\nGPU Notebook <= Disabled\nInternet access disabled\nFreely & publicly available external data is allowed, including pre-trained models\nSubmission file must be named submission.csv. The API will generate this submission file for you.\"\n\nI divided my code into a training part and a inference part. In the training part I used GPU to train a XGboost model. Will this break the requirements above?\n\nOr I should not use the gpu and see if cpu based XGboost training part can be finished within 9 hours?\n\nThank you for your help!",
    "2283764": "It should be ok as long as you keep the training part, so it can be reproduced.",
    "2283864": "Thank you so much!"
  },
  "source": "meta"
}