{
  "id": 554885,
  "title": "How is the 9-hour time limit calculated?",
  "url": "/competitions/jane-street-real-time-market-data-forecasting/discussion/554885",
  "author_name": "",
  "post_date": "2025-01-03T22:53:17.301765Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I have a question regarding the 9-hour time limit at the end of the forecasting phase. Is this limit cumulative only for the execution time of each predict() call? I’ve noticed that the time taken between predict() calls (possibly for processing the input data frame) is often more significant than the actual execution time of predict() itself. Is anyone clear about how the 9-hour limit is calculated? I believe it would be reasonable to consider only the time spent in predict(). Thanks for any information!</p>",
  "messages": [
    {
      "id": "3087807",
      "postDate": "01/03/2025 22:53:17",
      "content": "<p>I have a question regarding the 9-hour time limit at the end of the forecasting phase. Is this limit cumulative only for the execution time of each predict() call? I’ve noticed that the time taken between predict() calls (possibly for processing the input data frame) is often more significant than the actual execution time of predict() itself. Is anyone clear about how the 9-hour limit is calculated? I believe it would be reasonable to consider only the time spent in predict(). Thanks for any information!</p>",
      "rawMarkdown": "I have a question regarding the 9-hour time limit at the end of the forecasting phase. Is this limit cumulative only for the execution time of each predict() call? I’ve noticed that the time taken between predict() calls (possibly for processing the input data frame) is often more significant than the actual execution time of predict() itself. Is anyone clear about how the 9-hour limit is calculated? I believe it would be reasonable to consider only the time spent in predict(). Thanks for any information!",
      "votes": null
    },
    {
      "id": "3087830",
      "postDate": "01/03/2025 23:54:41",
      "content": "<blockquote>\n  <p>Is this limit cumulative only for the execution time of each predict() call?</p>\n</blockquote>\n<p>No. It is the total running time of your notebook.</p>",
      "rawMarkdown": ">Is this limit cumulative only for the execution time of each predict() call?\n\nNo. It is the total running time of your notebook.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3087830,
      "author_name": "shiyili",
      "author_url": "",
      "post_date": "01/03/2025 23:54:41",
      "content": "<blockquote>\n  <p>Is this limit cumulative only for the execution time of each predict() call?</p>\n</blockquote>\n<p>No. It is the total running time of your notebook.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3087807": "I have a question regarding the 9-hour time limit at the end of the forecasting phase. Is this limit cumulative only for the execution time of each predict() call? I’ve noticed that the time taken between predict() calls (possibly for processing the input data frame) is often more significant than the actual execution time of predict() itself. Is anyone clear about how the 9-hour limit is calculated? I believe it would be reasonable to consider only the time spent in predict(). Thanks for any information!",
    "3087830": ">Is this limit cumulative only for the execution time of each predict() call?\n\nNo. It is the total running time of your notebook."
  },
  "source": "meta"
}