{
  "id": 93827,
  "title": "Whats is your best single model",
  "url": "/competitions/champs-scalar-coupling/discussion/93827",
  "author_name": "",
  "post_date": "2019-05-30T10:09:56.753529900Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I am using Lightgbm.\nMore details to follow.</p>",
  "messages": [
    {
      "id": "539627",
      "postDate": "05/30/2019 10:09:56",
      "content": "<p>I am using Lightgbm.\nMore details to follow.</p>",
      "rawMarkdown": "I am using Lightgbm.\nMore details to follow.",
      "votes": null
    },
    {
      "id": "540022",
      "postDate": "05/30/2019 21:50:25",
      "content": "<p>I've been trying LightGBM. I haven't used gradient boosting before, and I'm wondering what kind of hardware you need to train models in a reasonable time. My best model so far (which uses the distance features which other people have been trying) took 55 minutes using 76 CPUs (although I didn't used early stopping). </p>\n\n<p>Are gradient boosting models supposed to take this long to train? Am I just pushing the limits of a relatively simple feature?</p>",
      "rawMarkdown": "I've been trying LightGBM. I haven't used gradient boosting before, and I'm wondering what kind of hardware you need to train models in a reasonable time. My best model so far (which uses the distance features which other people have been trying) took 55 minutes using 76 CPUs (although I didn't used early stopping). \n\nAre gradient boosting models supposed to take this long to train? Am I just pushing the limits of a relatively simple feature?",
      "votes": null
    },
    {
      "id": "540030",
      "postDate": "05/30/2019 22:43:25",
      "content": "<p>I'm using <a href=\"https://www.kaggle.com/rakibilly/fastai-tabular-starter\">fastai tabular learner</a> and can get 0.516 PLB</p>",
      "rawMarkdown": "I'm using [fastai tabular learner](https://www.kaggle.com/rakibilly/fastai-tabular-starter) and can get 0.516 PLB",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 540022,
      "author_name": "ollieperree",
      "author_url": "",
      "post_date": "05/30/2019 21:50:25",
      "content": "<p>I've been trying LightGBM. I haven't used gradient boosting before, and I'm wondering what kind of hardware you need to train models in a reasonable time. My best model so far (which uses the distance features which other people have been trying) took 55 minutes using 76 CPUs (although I didn't used early stopping). </p>\n\n<p>Are gradient boosting models supposed to take this long to train? Am I just pushing the limits of a relatively simple feature?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 540030,
      "author_name": "rakibilly",
      "author_url": "",
      "post_date": "05/30/2019 22:43:25",
      "content": "<p>I'm using <a href=\"https://www.kaggle.com/rakibilly/fastai-tabular-starter\">fastai tabular learner</a> and can get 0.516 PLB</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "539627": "I am using Lightgbm.\nMore details to follow.",
    "540022": "I've been trying LightGBM. I haven't used gradient boosting before, and I'm wondering what kind of hardware you need to train models in a reasonable time. My best model so far (which uses the distance features which other people have been trying) took 55 minutes using 76 CPUs (although I didn't used early stopping). \n\nAre gradient boosting models supposed to take this long to train? Am I just pushing the limits of a relatively simple feature?",
    "540030": "I'm using [fastai tabular learner](https://www.kaggle.com/rakibilly/fastai-tabular-starter) and can get 0.516 PLB"
  },
  "source": "meta"
}