{
  "id": 138524,
  "title": "how to score 0.9+ ? ",
  "url": "/competitions/jigsaw-multilingual-toxic-comment-classification/discussion/138524",
  "author_name": "",
  "post_date": "2020-03-25T10:23:11.573918800Z",
  "votes": 14,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Check out these kernels :) </p>\n\n<p><a href=\"https://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid\">https://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid</a></p>\n\n<p><a href=\"https://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation\">https://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation</a></p>",
  "messages": [
    {
      "id": "785733",
      "postDate": "03/25/2020 10:23:11",
      "content": "<p>Check out these kernels :) </p>\n\n<p><a href=\"https://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid\">https://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid</a></p>\n\n<p><a href=\"https://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation\">https://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation</a></p>",
      "rawMarkdown": "Check out these kernels :) \n\nhttps://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid\n\nhttps://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation",
      "votes": null
    },
    {
      "id": "785996",
      "postDate": "03/25/2020 15:05:44",
      "content": "<p>Is using multi-cores possible in Kaggle kernels?</p>",
      "rawMarkdown": "Is using multi-cores possible in Kaggle kernels?",
      "votes": null
    },
    {
      "id": "786034",
      "postDate": "03/25/2020 15:31:59",
      "content": "<p>yeah, in a way, you can see the kernel in OP</p>",
      "rawMarkdown": "yeah, in a way, you can see the kernel in OP",
      "votes": null
    },
    {
      "id": "787047",
      "postDate": "03/26/2020 13:30:27",
      "content": "<p>for 8 cores we are having trouble in colab</p>",
      "rawMarkdown": "for 8 cores we are having trouble in colab",
      "votes": null
    },
    {
      "id": "788338",
      "postDate": "03/27/2020 15:26:35",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4283726%2F208c87bd9c15236de533dbbd9a6ff25f%2FSnipaste_2020-03-28_00-24-42.png?generation=1585322707354913&amp;alt=media\" alt=\"\"></p>\n\n<p>Thanks for the great notebooks. When I was running the 8 cores script, the TPU's usage was not more than 10% but the usage of CPU and RAM were almost 100%, is that normal?</p>",
      "rawMarkdown": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4283726%2F208c87bd9c15236de533dbbd9a6ff25f%2FSnipaste_2020-03-28_00-24-42.png?generation=1585322707354913&amp;alt=media)\n\nThanks for the great notebooks. When I was running the 8 cores script, the TPU's usage was not more than 10% but the usage of CPU and RAM were almost 100%, is that normal?",
      "votes": null
    },
    {
      "id": "797895",
      "postDate": "04/05/2020 02:02:40",
      "content": "<p>thank you <a href=\"/abhishek\">@abhishek</a> </p>",
      "rawMarkdown": "thank you @abhishek",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 785996,
      "author_name": "faraksuli",
      "author_url": "",
      "post_date": "03/25/2020 15:05:44",
      "content": "<p>Is using multi-cores possible in Kaggle kernels?</p>",
      "votes": null,
      "replies": [
        {
          "id": 786034,
          "author_name": "abhishek",
          "author_url": "",
          "post_date": "03/25/2020 15:31:59",
          "content": "<p>yeah, in a way, you can see the kernel in OP</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 787047,
          "author_name": "mobassir",
          "author_url": "",
          "post_date": "03/26/2020 13:30:27",
          "content": "<p>for 8 cores we are having trouble in colab</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 788338,
      "author_name": "oohara",
      "author_url": "",
      "post_date": "03/27/2020 15:26:35",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4283726%2F208c87bd9c15236de533dbbd9a6ff25f%2FSnipaste_2020-03-28_00-24-42.png?generation=1585322707354913&amp;alt=media\" alt=\"\"></p>\n\n<p>Thanks for the great notebooks. When I was running the 8 cores script, the TPU's usage was not more than 10% but the usage of CPU and RAM were almost 100%, is that normal?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 797895,
      "author_name": "mahdhiashraf",
      "author_url": "",
      "post_date": "04/05/2020 02:02:40",
      "content": "<p>thank you <a href=\"/abhishek\">@abhishek</a> </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "785733": "Check out these kernels :) \n\nhttps://www.kaggle.com/abhishek/bert-multi-lingual-tpu-training-8-cores-w-valid\n\nhttps://www.kaggle.com/abhishek/inference-of-bert-tpu-model-ml-w-validation",
    "785996": "Is using multi-cores possible in Kaggle kernels?",
    "786034": "yeah, in a way, you can see the kernel in OP",
    "787047": "for 8 cores we are having trouble in colab",
    "788338": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4283726%2F208c87bd9c15236de533dbbd9a6ff25f%2FSnipaste_2020-03-28_00-24-42.png?generation=1585322707354913&amp;alt=media)\n\nThanks for the great notebooks. When I was running the 8 cores script, the TPU's usage was not more than 10% but the usage of CPU and RAM were almost 100%, is that normal?",
    "797895": "thank you @abhishek"
  },
  "source": "meta"
}