{
  "id": 210153,
  "title": "[Experimental] Different Learning Rate Schedulers",
  "url": "/competitions/cassava-leaf-disease-classification/discussion/210153",
  "author_name": "Sinan Calisir",
  "post_date": "2021-01-09T20:57:31.772000",
  "votes": 4,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi everyone,</p>\n<p>To understand how different LR schedulers work in practice, I have prepared a notebook which demonstrates the behaviours of different scheduling algorithms exist in Pytorch and Transformers libraries. I have used <code>CosineAnnealingWarmRestarts</code> so far. It seems to work well, but I'm not sure that I am using the full potential right now 🙄</p>\n<p>You can find the notebook here: <a href=\"https://www.kaggle.com/snnclsr/learning-rate-schedulers\" target=\"_blank\">Learning-Rate Schedulers</a></p>\n<p>How is your experience so far? Let's discuss!</p>",
  "messages": [
    {
      "id": 1146541,
      "postDate": "2021-01-09T20:57:31.773Z",
      "content": "<p>Hi everyone,</p>\n<p>To understand how different LR schedulers work in practice, I have prepared a notebook which demonstrates the behaviours of different scheduling algorithms exist in Pytorch and Transformers libraries. I have used <code>CosineAnnealingWarmRestarts</code> so far. It seems to work well, but I'm not sure that I am using the full potential right now 🙄</p>\n<p>You can find the notebook here: <a href=\"https://www.kaggle.com/snnclsr/learning-rate-schedulers\" target=\"_blank\">Learning-Rate Schedulers</a></p>\n<p>How is your experience so far? Let's discuss!</p>",
      "rawMarkdown": "Hi everyone,\n\nTo understand how different LR schedulers work in practice, I have prepared a notebook which demonstrates the behaviours of different scheduling algorithms exist in Pytorch and Transformers libraries. I have used `CosineAnnealingWarmRestarts` so far. It seems to work well, but I'm not sure that I am using the full potential right now 🙄\n\nYou can find the notebook here: [Learning-Rate Schedulers](https://www.kaggle.com/snnclsr/learning-rate-schedulers)\n\n How is your experience so far? Let's discuss!",
      "votes": 4
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1146541": "Hi everyone,\n\nTo understand how different LR schedulers work in practice, I have prepared a notebook which demonstrates the behaviours of different scheduling algorithms exist in Pytorch and Transformers libraries. I have used `CosineAnnealingWarmRestarts` so far. It seems to work well, but I'm not sure that I am using the full potential right now 🙄\n\nYou can find the notebook here: [Learning-Rate Schedulers](https://www.kaggle.com/snnclsr/learning-rate-schedulers)\n\n How is your experience so far? Let's discuss!"
  }
}