{
  "id": 210344,
  "title": "Is Our Score for this Competition based on the f1_score?",
  "url": "/competitions/tpu-getting-started/discussion/210344",
  "author_name": "samuel adeshina",
  "post_date": "2021-01-10T13:26:15.038000",
  "votes": 0,
  "comment_count": 1,
  "views": null,
  "content": "<p>Hi Kagglers. I just want to know if the score on this competition is based on the f1 score between the training and validation dataset and the test dataset. If that is not the case, then how is the score calculated?</p>\n<p>Thanks.</p>",
  "messages": [
    {
      "id": 1150937,
      "postDate": "2021-01-13T01:31:21.747Z",
      "content": "<p>As you can check on the Overview tab --&gt; Evaluation, the f1 score comes from this formula calculated from your answers in the test set, so it doesn't really matter your train and validation accuracy, they are just to give you \"internal\" feedback while developing the model.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3317928%2F3a924e2b3571f042cbf19c6319f69283%2FScreenshot_2021-01-13%20Petals%20to%20the%20Metal%20-%20Flower%20Classification%20on%20TPU%20Kaggle.png?generation=1610501317575261&amp;alt=media\" alt=\"\"></p>",
      "rawMarkdown": "As you can check on the Overview tab --> Evaluation, the f1 score comes from this formula calculated from your answers in the test set, so it doesn't really matter your train and validation accuracy, they are just to give you \"internal\" feedback while developing the model.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3317928%2F3a924e2b3571f042cbf19c6319f69283%2FScreenshot_2021-01-13%20Petals%20to%20the%20Metal%20-%20Flower%20Classification%20on%20TPU%20Kaggle.png?generation=1610501317575261&alt=media)"
    },
    {
      "id": 1147379,
      "postDate": "2021-01-10T13:26:15.037Z",
      "content": "<p>Hi Kagglers. I just want to know if the score on this competition is based on the f1 score between the training and validation dataset and the test dataset. If that is not the case, then how is the score calculated?</p>\n<p>Thanks.</p>",
      "rawMarkdown": "Hi Kagglers. I just want to know if the score on this competition is based on the f1 score between the training and validation dataset and the test dataset. If that is not the case, then how is the score calculated?\n\nThanks."
    }
  ],
  "comments": [
    {
      "id": 1150937,
      "author_name": "Enric Domingo",
      "author_url": "",
      "post_date": "2021-01-13T01:31:21.747000",
      "content": "<p>As you can check on the Overview tab --&gt; Evaluation, the f1 score comes from this formula calculated from your answers in the test set, so it doesn't really matter your train and validation accuracy, they are just to give you \"internal\" feedback while developing the model.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3317928%2F3a924e2b3571f042cbf19c6319f69283%2FScreenshot_2021-01-13%20Petals%20to%20the%20Metal%20-%20Flower%20Classification%20on%20TPU%20Kaggle.png?generation=1610501317575261&amp;alt=media\" alt=\"\"></p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1150937": "As you can check on the Overview tab --> Evaluation, the f1 score comes from this formula calculated from your answers in the test set, so it doesn't really matter your train and validation accuracy, they are just to give you \"internal\" feedback while developing the model.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3317928%2F3a924e2b3571f042cbf19c6319f69283%2FScreenshot_2021-01-13%20Petals%20to%20the%20Metal%20-%20Flower%20Classification%20on%20TPU%20Kaggle.png?generation=1610501317575261&alt=media)",
    "1147379": "Hi Kagglers. I just want to know if the score on this competition is based on the f1 score between the training and validation dataset and the test dataset. If that is not the case, then how is the score calculated?\n\nThanks."
  }
}