{
  "id": 192871,
  "title": "does 9 hrs notebook time includes training of model?",
  "url": "/competitions/riiid-test-answer-prediction/discussion/192871",
  "author_name": "",
  "post_date": "2020-10-23T19:47:39.265774300Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>i'm not getting the idea of  what is 9 hrs of notebook run time??<br>\ndoes that include my pre processing and model training????</p>",
  "messages": [
    {
      "id": "1058507",
      "postDate": "10/23/2020 19:47:39",
      "content": "<p>i'm not getting the idea of  what is 9 hrs of notebook run time??<br>\ndoes that include my pre processing and model training????</p>",
      "rawMarkdown": "i'm not getting the idea of  what is 9 hrs of notebook run time??\ndoes that include my pre processing and model training????",
      "votes": null
    },
    {
      "id": "1058518",
      "postDate": "10/23/2020 20:08:19",
      "content": "<p>yes. But you can train models, and upload the model to a dataset. Create a kernel and use the model to perform predictions, and just submit this prediction model only.</p>",
      "rawMarkdown": "yes. But you can train models, and upload the model to a dataset. Create a kernel and use the model to perform predictions, and just submit this prediction model only.",
      "votes": null
    },
    {
      "id": "1058526",
      "postDate": "10/23/2020 20:28:56",
      "content": "<p>means i can train my model and save the parameters, then i create a new kernel , load the the pre-trained parameters and do the prediction on test set , or submission one, does that work?</p>",
      "rawMarkdown": "means i can train my model and save the parameters, then i create a new kernel , load the the pre-trained parameters and do the prediction on test set , or submission one, does that work?",
      "votes": null
    },
    {
      "id": "1058529",
      "postDate": "10/23/2020 20:35:15",
      "content": "<p>That's the most used way for competitions.</p>",
      "rawMarkdown": "That's the most used way for competitions.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1058518,
      "author_name": "yihdarshieh",
      "author_url": "",
      "post_date": "10/23/2020 20:08:19",
      "content": "<p>yes. But you can train models, and upload the model to a dataset. Create a kernel and use the model to perform predictions, and just submit this prediction model only.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1058526,
          "author_name": "dhyeypatel1234",
          "author_url": "",
          "post_date": "10/23/2020 20:28:56",
          "content": "<p>means i can train my model and save the parameters, then i create a new kernel , load the the pre-trained parameters and do the prediction on test set , or submission one, does that work?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1058529,
          "author_name": "yihdarshieh",
          "author_url": "",
          "post_date": "10/23/2020 20:35:15",
          "content": "<p>That's the most used way for competitions.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1058507": "i'm not getting the idea of  what is 9 hrs of notebook run time??\ndoes that include my pre processing and model training????",
    "1058518": "yes. But you can train models, and upload the model to a dataset. Create a kernel and use the model to perform predictions, and just submit this prediction model only.",
    "1058526": "means i can train my model and save the parameters, then i create a new kernel , load the the pre-trained parameters and do the prediction on test set , or submission one, does that work?",
    "1058529": "That's the most used way for competitions."
  },
  "source": "meta"
}