{
  "id": 219508,
  "title": "Checking for overfitting and monitoring learning rates",
  "url": "/competitions/cassava-leaf-disease-classification/discussion/219508",
  "author_name": "Trushant Kalyanpur",
  "post_date": "2021-02-15T07:09:23.058000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I wrote a small script to look at outputs of training logs to quickly check how the model performs for train and val loss over epochs and the effect of learning rate on val loss. This can help in checking for overfitting and finding optimal learning rates.</p>\n<p><a href=\"https://www.kaggle.com/trushk/model-validation-learning-rate-monitoring\" target=\"_blank\">https://www.kaggle.com/trushk/model-validation-learning-rate-monitoring</a></p>",
  "messages": [
    {
      "id": 1201105,
      "postDate": "2021-02-15T07:09:23.060Z",
      "content": "<p>I wrote a small script to look at outputs of training logs to quickly check how the model performs for train and val loss over epochs and the effect of learning rate on val loss. This can help in checking for overfitting and finding optimal learning rates.</p>\n<p><a href=\"https://www.kaggle.com/trushk/model-validation-learning-rate-monitoring\" target=\"_blank\">https://www.kaggle.com/trushk/model-validation-learning-rate-monitoring</a></p>",
      "rawMarkdown": "I wrote a small script to look at outputs of training logs to quickly check how the model performs for train and val loss over epochs and the effect of learning rate on val loss. This can help in checking for overfitting and finding optimal learning rates.\n\nhttps://www.kaggle.com/trushk/model-validation-learning-rate-monitoring",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1201105": "I wrote a small script to look at outputs of training logs to quickly check how the model performs for train and val loss over epochs and the effect of learning rate on val loss. This can help in checking for overfitting and finding optimal learning rates.\n\nhttps://www.kaggle.com/trushk/model-validation-learning-rate-monitoring"
  }
}