{
  "id": 205734,
  "title": "Dataset for KT Transformers/Seq models",
  "url": "/competitions/riiid-test-answer-prediction/discussion/205734",
  "author_name": "Ultron",
  "post_date": "2020-12-21T16:05:17.503000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>As I was facing difficulties, particularly RAM reallocation error, I searched for ways to save the dataset once and then use it again and again instead of creating the same run time each time. Thankfully, I got these awesome notebooks:</p>\n<p><a href=\"https://www.kaggle.com/leadbest\" target=\"_blank\">@leadbest</a> 's: <br>\n<a href=\"https://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook\" target=\"_blank\">https://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook</a><br>\n<a href=\"https://www.kaggle.com/leadbest/sakt-with-randomization-state-updates\" target=\"_blank\">https://www.kaggle.com/leadbest/sakt-with-randomization-state-updates</a></p>\n<p>I saved the data in pkl as mentioned in these notebooks.<br>\nHere is the link to the dataset: <a href=\"https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset\" target=\"_blank\">https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset</a><br>\nHere is the link to that dedicated script: <a href=\"https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt\" target=\"_blank\">https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt</a></p>\n<p>Feel free to use it and save your inference time.</p>\n<p><strong><em>Important</em></strong>: If a thread like this already exists, let me know, I will move the info there, and if unknowingly I violate any guidelines or anyone has any issues with it, let me know, I would be happier to remove it ;) Thanks</p>",
  "messages": [
    {
      "id": 1121395,
      "postDate": "2020-12-21T16:05:17.503Z",
      "content": "<p>As I was facing difficulties, particularly RAM reallocation error, I searched for ways to save the dataset once and then use it again and again instead of creating the same run time each time. Thankfully, I got these awesome notebooks:</p>\n<p><a href=\"https://www.kaggle.com/leadbest\" target=\"_blank\">@leadbest</a> 's: <br>\n<a href=\"https://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook\" target=\"_blank\">https://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook</a><br>\n<a href=\"https://www.kaggle.com/leadbest/sakt-with-randomization-state-updates\" target=\"_blank\">https://www.kaggle.com/leadbest/sakt-with-randomization-state-updates</a></p>\n<p>I saved the data in pkl as mentioned in these notebooks.<br>\nHere is the link to the dataset: <a href=\"https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset\" target=\"_blank\">https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset</a><br>\nHere is the link to that dedicated script: <a href=\"https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt\" target=\"_blank\">https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt</a></p>\n<p>Feel free to use it and save your inference time.</p>\n<p><strong><em>Important</em></strong>: If a thread like this already exists, let me know, I will move the info there, and if unknowingly I violate any guidelines or anyone has any issues with it, let me know, I would be happier to remove it ;) Thanks</p>",
      "rawMarkdown": "As I was facing difficulties, particularly RAM reallocation error, I searched for ways to save the dataset once and then use it again and again instead of creating the same run time each time. Thankfully, I got these awesome notebooks:\n\n@leadbest 's: \nhttps://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook\nhttps://www.kaggle.com/leadbest/sakt-with-randomization-state-updates\n\nI saved the data in pkl as mentioned in these notebooks.\nHere is the link to the dataset: https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset\nHere is the link to that dedicated script: https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt\n\nFeel free to use it and save your inference time.\n\n***Important***: If a thread like this already exists, let me know, I will move the info there, and if unknowingly I violate any guidelines or anyone has any issues with it, let me know, I would be happier to remove it ;) Thanks",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1121395": "As I was facing difficulties, particularly RAM reallocation error, I searched for ways to save the dataset once and then use it again and again instead of creating the same run time each time. Thankfully, I got these awesome notebooks:\n\n@leadbest 's: \nhttps://www.kaggle.com/leadbest/sakt-riiid-lgbm-bagging2/notebook\nhttps://www.kaggle.com/leadbest/sakt-with-randomization-state-updates\n\nI saved the data in pkl as mentioned in these notebooks.\nHere is the link to the dataset: https://www.kaggle.com/mrutyunjaybiswal/riiid-train-sequential-dataset\nHere is the link to that dedicated script: https://www.kaggle.com/mrutyunjaybiswal/riiid-dataset-for-transformer-models-for-kt\n\nFeel free to use it and save your inference time.\n\n***Important***: If a thread like this already exists, let me know, I will move the info there, and if unknowingly I violate any guidelines or anyone has any issues with it, let me know, I would be happier to remove it ;) Thanks"
  }
}