{
  "id": 175329,
  "title": "Missed Opportunity - 4th place - Solo Gold ",
  "url": "/competitions/siim-isic-melanoma-classification/writeups/yagana-sheriff-hussaini-missed-opportunity-4th-pla",
  "author_name": "",
  "post_date": "2020-08-19T02:36:44.590Z",
  "votes": 9,
  "comment_count": 21,
  "views": 0,
  "content": "<p>Congratulations to the winners.</p>\n<p><strong>Scores:-</strong><br>\n<strong>public LB=0.9618</strong><br>\n<strong>private LB=0.9482</strong> </p>\n<p>I am Gutted.</p>\n<p><a href=\"https://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place\" target=\"_blank\">https://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place</a></p>\n<p><strong>UPDATE</strong></p>\n<p>In late submission, using the mean ensemble of 27 models which gave my private LB score in the above ensemble script scores :-<br>\n<strong>public LB=0.9618</strong><br>\n<strong>private LB=0.9487</strong> </p>",
  "messages": [
    {
      "id": "974454",
      "postDate": "08/18/2020 00:28:24",
      "content": "<p>Congratulations to the winners.</p>\n<p><strong>Scores:-</strong><br>\n<strong>public LB=0.9618</strong><br>\n<strong>private LB=0.9482</strong> </p>\n<p>I am Gutted.</p>\n<p><a href=\"https://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place\" target=\"_blank\">https://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place</a></p>\n<p><strong>UPDATE</strong></p>\n<p>In late submission, using the mean ensemble of 27 models which gave my private LB score in the above ensemble script scores :-<br>\n<strong>public LB=0.9618</strong><br>\n<strong>private LB=0.9487</strong> </p>",
      "rawMarkdown": "Congratulations to the winners.\n\n**Scores:-**\n**public LB=0.9618**\n**private LB=0.9482** \n\nI am Gutted.\n\n\nhttps://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place\n\n\n**UPDATE**\n\nIn late submission, using the mean ensemble of 27 models which gave my private LB score in the above ensemble script scores :-\n**public LB=0.9618**\n**private LB=0.9487**",
      "votes": null
    },
    {
      "id": "974540",
      "postDate": "08/18/2020 01:22:03",
      "content": "<p>Congratulations on the 89th position <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>. <br>\nSorry to hear you missed the 4th place :(<br>\nYour solo gold will come soon. <br>\nAll the best to you for the future</p>",
      "rawMarkdown": "Congratulations on the 89th position @sheriytm. \nSorry to hear you missed the 4th place :(\nYour solo gold will come soon. \nAll the best to you for the future",
      "votes": null
    },
    {
      "id": "974545",
      "postDate": "08/18/2020 01:23:50",
      "content": "<p><a href=\"https://www.kaggle.com/mpsampat\" target=\"_blank\">@mpsampat</a>, thanks for your kind words. Congrats on your silver medal.</p>",
      "rawMarkdown": "mpsampat, thanks for your kind words. Congrats on your silver medal.",
      "votes": null
    },
    {
      "id": "974555",
      "postDate": "08/18/2020 01:28:56",
      "content": "<p>Thats a strong model.</p>",
      "rawMarkdown": "Thats a strong model.",
      "votes": null
    },
    {
      "id": "974564",
      "postDate": "08/18/2020 01:32:30",
      "content": "<p><a href=\"https://www.kaggle.com/roydatascience\" target=\"_blank\">@roydatascience</a>, it is an ensemble without CV hence there is no way I would have chosen it. I went with trusting my CV and chose a simple averaged ensemble and the other 2 based on CV ensemble.</p>",
      "rawMarkdown": "roydatascience, it is an ensemble without CV hence there is no way I would have chosen it. I went with trusting my CV and chose a simple averaged ensemble and the other 2 based on CV ensemble.",
      "votes": null
    },
    {
      "id": "974571",
      "postDate": "08/18/2020 01:35:19",
      "content": "<p>Not sure how, but the simple average ensemble failed in this competition.</p>",
      "rawMarkdown": "Not sure how, but the simple average ensemble failed in this competition.",
      "votes": null
    },
    {
      "id": "974585",
      "postDate": "08/18/2020 01:45:54",
      "content": "<p>I have also a gold submission </p>\n<p><img src=\"https://i.ibb.co/sJV9TH4/Capturebest.png\" alt=\"capturebest\"></p>\n<p>But this was not my best model, so choosing it would be just luck. </p>\n<p>My current score however, is my best CV and it scored just 0.9594 on public LB </p>\n<p><img src=\"https://i.ibb.co/BsXN56b/Capture-CV.png\" alt=\"CaptureCV\"></p>",
      "rawMarkdown": "I have also a gold submission \n\n![capturebest](https://i.ibb.co/sJV9TH4/Capturebest.png)\n\nBut this was not my best model, so choosing it would be just luck. \n\nMy current score however, is my best CV and it scored just 0.9594 on public LB \n\n![CaptureCV](https://i.ibb.co/BsXN56b/Capture-CV.png)",
      "votes": null
    },
    {
      "id": "974598",
      "postDate": "08/18/2020 01:53:30",
      "content": "<p>Congrats <a href=\"https://www.kaggle.com/serigne\" target=\"_blank\">@serigne</a> on a strong finish. </p>\n<p>My current position public LB= 0.9571, private LB=0.9424 is a lower scoring one on the public LB but I went with trusting my CV as well. The best in private LB submission I did not choose was one of my ensembles that does not have a CV score. With a systematic approach there is no way I would have chosen it. I am only disappointed because I have been waiting so long for the elusive solo gold.</p>",
      "rawMarkdown": "Congrats @serigne on a strong finish. \n\nMy current position public LB= 0.9571, private LB=0.9424 is a lower scoring one on the public LB but I went with trusting my CV as well. The best in private LB submission I did not choose was one of my ensembles that does not have a CV score. With a systematic approach there is no way I would have chosen it. I am only disappointed because I have been waiting so long for the elusive solo gold.",
      "votes": null
    },
    {
      "id": "974618",
      "postDate": "08/18/2020 02:02:15",
      "content": "<p><a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>   <br>\nThanks !  Congrats for your result too. </p>\n<p>I know this feelings</p>\n<p>I was rooting  for solo too gold during Jigsaw 3rd edition competition. And just applying <a href=\"https://www.kaggle.com/christofhenkel\" target=\"_blank\">@christofhenkel</a> PP approach would put me in the upper golden area ;)</p>\n<p>But don't worry,  ton tour viendra :)</p>",
      "rawMarkdown": "sheriytm   \nThanks !  Congrats for your result too. \n\n\nI know this feelings\n\nI was rooting  for solo too gold during Jigsaw 3rd edition competition. And just applying @christofhenkel PP approach would put me in the upper golden area ;)\n\nBut don't worry,  ton tour viendra :)",
      "votes": null
    },
    {
      "id": "974639",
      "postDate": "08/18/2020 02:09:30",
      "content": "<p>I'm rooting for you to get a solo gold. If ever there was a Kaggler that deserves to be a GM, clearly based on merit, it is you <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>.</p>",
      "rawMarkdown": "I'm rooting for you to get a solo gold. If ever there was a Kaggler that deserves to be a GM, clearly based on merit, it is you @sheriytm.",
      "votes": null
    },
    {
      "id": "974641",
      "postDate": "08/18/2020 02:10:59",
      "content": "<p><a href=\"https://www.kaggle.com/roydatascience\" target=\"_blank\">@roydatascience</a>, my 2nd best submission on the private LB which is my current LB position is a submissions mean of 27 models.</p>",
      "rawMarkdown": "roydatascience, my 2nd best submission on the private LB which is my current LB position is a submissions mean of 27 models.",
      "votes": null
    },
    {
      "id": "974646",
      "postDate": "08/18/2020 02:15:20",
      "content": "<p><a href=\"https://www.kaggle.com/serigne\" target=\"_blank\">@serigne</a>, thanks.</p>\n<p>I had similar result to yours in the Jigsaw Multilingual competition as well hence my feeling a little sad this time.  J'espère bientôt pour l'or en solo.</p>",
      "rawMarkdown": "serigne, thanks.\n\nI had similar result to yours in the Jigsaw Multilingual competition as well hence my feeling a little sad this time.  J'espère bientôt pour l'or en solo.",
      "votes": null
    },
    {
      "id": "974647",
      "postDate": "08/18/2020 02:15:26",
      "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> - you took my words. Rooting for you <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a> !</p>",
      "rawMarkdown": "authman - you took my words. Rooting for you @sheriytm !",
      "votes": null
    },
    {
      "id": "974659",
      "postDate": "08/18/2020 02:20:47",
      "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a>, <br>\n<a href=\"https://www.kaggle.com/robikscube\" target=\"_blank\">@robikscube</a>, <br>\nThanks so much for your kind words. <br>\nI am thankful for experiencing this competition because I learnt so much about the use of TPU and a few TF tricks.</p>",
      "rawMarkdown": "authman, \n@robikscube, \nThanks so much for your kind words. \nI am thankful for experiencing this competition because I learnt so much about the use of TPU and a few TF tricks.",
      "votes": null
    },
    {
      "id": "976581",
      "postDate": "08/19/2020 00:50:52",
      "content": "<p>I forgot to say that yesterday. </p>\n<p><a href=\"https://www.kaggle.com/robikscube\" target=\"_blank\">@robikscube</a> congrats to you and your team for another strong finish.</p>\n<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> congrats to you and your team on the silver medal.</p>",
      "rawMarkdown": "I forgot to say that yesterday. \n\n@robikscube congrats to you and your team for another strong finish.\n\n@authman congrats to you and your team on the silver medal.",
      "votes": null
    },
    {
      "id": "976636",
      "postDate": "08/19/2020 02:06:21",
      "content": "<p>YaGana, I am always inspired by your hard work and thoughtful contributions. You have a lot of passion, you will get gold soon!</p>",
      "rawMarkdown": "YaGana, I am always inspired by your hard work and thoughtful contributions. You have a lot of passion, you will get gold soon!",
      "votes": null
    },
    {
      "id": "976641",
      "postDate": "08/19/2020 02:17:09",
      "content": "<p>Congrats on another strong finish and thanks for your kind words <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a>.</p>\n<p>Your contributions here and always is well apreciated. I joined the Flower competition to try out TPU and I learnt a lot from you there as well as here on that subject. Your triple stratified dataset made life easier for so many of us. So thanks so much.</p>",
      "rawMarkdown": "Congrats on another strong finish and thanks for your kind words @cdeotte.\n\nYour contributions here and always is well apreciated. I joined the Flower competition to try out TPU and I learnt a lot from you there as well as here on that subject. Your triple stratified dataset made life easier for so many of us. So thanks so much.",
      "votes": null
    },
    {
      "id": "979989",
      "postDate": "08/21/2020 08:49:34",
      "content": "<p><a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a> you'll get it soon enough! Keep on!</p>",
      "rawMarkdown": "sheriytm you'll get it soon enough! Keep on!",
      "votes": null
    },
    {
      "id": "980197",
      "postDate": "08/21/2020 11:46:04",
      "content": "<p>Thanks <a href=\"https://www.kaggle.com/mightyrains\" target=\"_blank\">@mightyrains</a>.</p>",
      "rawMarkdown": "Thanks @mightyrains.",
      "votes": null
    },
    {
      "id": "980208",
      "postDate": "08/21/2020 12:07:47",
      "content": "<p>The only question you should ask is how could you have selected this submission?</p>",
      "rawMarkdown": "The only question you should ask is how could you have selected this submission?",
      "votes": null
    },
    {
      "id": "980229",
      "postDate": "08/21/2020 12:26:34",
      "content": "<p><a href=\"https://www.kaggle.com/cpmpml\" target=\"_blank\">@cpmpml</a>, nope I would not have chosen using any reasonable intuition because it is  my own conservative blend of blends which is usually risky.</p>",
      "rawMarkdown": "cpmpml, nope I would not have chosen using any reasonable intuition because it is  my own conservative blend of blends which is usually risky.",
      "votes": null
    },
    {
      "id": "980333",
      "postDate": "08/21/2020 14:13:56",
      "content": "<p>ok.  I see you're improving competition after competition, keep pushing!</p>",
      "rawMarkdown": "ok.  I see you're improving competition after competition, keep pushing!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 974540,
      "author_name": "mpsampat",
      "author_url": "",
      "post_date": "08/18/2020 01:22:03",
      "content": "<p>Congratulations on the 89th position <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>. <br>\nSorry to hear you missed the 4th place :(<br>\nYour solo gold will come soon. <br>\nAll the best to you for the future</p>",
      "votes": null,
      "replies": [
        {
          "id": 974545,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 01:23:50",
          "content": "<p><a href=\"https://www.kaggle.com/mpsampat\" target=\"_blank\">@mpsampat</a>, thanks for your kind words. Congrats on your silver medal.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 974555,
      "author_name": "roydatascience",
      "author_url": "",
      "post_date": "08/18/2020 01:28:56",
      "content": "<p>Thats a strong model.</p>",
      "votes": null,
      "replies": [
        {
          "id": 974564,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 01:32:30",
          "content": "<p><a href=\"https://www.kaggle.com/roydatascience\" target=\"_blank\">@roydatascience</a>, it is an ensemble without CV hence there is no way I would have chosen it. I went with trusting my CV and chose a simple averaged ensemble and the other 2 based on CV ensemble.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 974571,
          "author_name": "roydatascience",
          "author_url": "",
          "post_date": "08/18/2020 01:35:19",
          "content": "<p>Not sure how, but the simple average ensemble failed in this competition.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 974641,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 02:10:59",
          "content": "<p><a href=\"https://www.kaggle.com/roydatascience\" target=\"_blank\">@roydatascience</a>, my 2nd best submission on the private LB which is my current LB position is a submissions mean of 27 models.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 974585,
      "author_name": "serigne",
      "author_url": "",
      "post_date": "08/18/2020 01:45:54",
      "content": "<p>I have also a gold submission </p>\n<p><img src=\"https://i.ibb.co/sJV9TH4/Capturebest.png\" alt=\"capturebest\"></p>\n<p>But this was not my best model, so choosing it would be just luck. </p>\n<p>My current score however, is my best CV and it scored just 0.9594 on public LB </p>\n<p><img src=\"https://i.ibb.co/BsXN56b/Capture-CV.png\" alt=\"CaptureCV\"></p>",
      "votes": null,
      "replies": [
        {
          "id": 974598,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 01:53:30",
          "content": "<p>Congrats <a href=\"https://www.kaggle.com/serigne\" target=\"_blank\">@serigne</a> on a strong finish. </p>\n<p>My current position public LB= 0.9571, private LB=0.9424 is a lower scoring one on the public LB but I went with trusting my CV as well. The best in private LB submission I did not choose was one of my ensembles that does not have a CV score. With a systematic approach there is no way I would have chosen it. I am only disappointed because I have been waiting so long for the elusive solo gold.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 974618,
          "author_name": "serigne",
          "author_url": "",
          "post_date": "08/18/2020 02:02:15",
          "content": "<p><a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>   <br>\nThanks !  Congrats for your result too. </p>\n<p>I know this feelings</p>\n<p>I was rooting  for solo too gold during Jigsaw 3rd edition competition. And just applying <a href=\"https://www.kaggle.com/christofhenkel\" target=\"_blank\">@christofhenkel</a> PP approach would put me in the upper golden area ;)</p>\n<p>But don't worry,  ton tour viendra :)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 974646,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 02:15:20",
          "content": "<p><a href=\"https://www.kaggle.com/serigne\" target=\"_blank\">@serigne</a>, thanks.</p>\n<p>I had similar result to yours in the Jigsaw Multilingual competition as well hence my feeling a little sad this time.  J'espère bientôt pour l'or en solo.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 974639,
      "author_name": "authman",
      "author_url": "",
      "post_date": "08/18/2020 02:09:30",
      "content": "<p>I'm rooting for you to get a solo gold. If ever there was a Kaggler that deserves to be a GM, clearly based on merit, it is you <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a>.</p>",
      "votes": null,
      "replies": [
        {
          "id": 974647,
          "author_name": "robikscube",
          "author_url": "",
          "post_date": "08/18/2020 02:15:26",
          "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> - you took my words. Rooting for you <a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a> !</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 974659,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/18/2020 02:20:47",
          "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a>, <br>\n<a href=\"https://www.kaggle.com/robikscube\" target=\"_blank\">@robikscube</a>, <br>\nThanks so much for your kind words. <br>\nI am thankful for experiencing this competition because I learnt so much about the use of TPU and a few TF tricks.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 976581,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/19/2020 00:50:52",
          "content": "<p>I forgot to say that yesterday. </p>\n<p><a href=\"https://www.kaggle.com/robikscube\" target=\"_blank\">@robikscube</a> congrats to you and your team for another strong finish.</p>\n<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> congrats to you and your team on the silver medal.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 976636,
          "author_name": "cdeotte",
          "author_url": "",
          "post_date": "08/19/2020 02:06:21",
          "content": "<p>YaGana, I am always inspired by your hard work and thoughtful contributions. You have a lot of passion, you will get gold soon!</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 976641,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/19/2020 02:17:09",
          "content": "<p>Congrats on another strong finish and thanks for your kind words <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a>.</p>\n<p>Your contributions here and always is well apreciated. I joined the Flower competition to try out TPU and I learnt a lot from you there as well as here on that subject. Your triple stratified dataset made life easier for so many of us. So thanks so much.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 979989,
      "author_name": "mightyrains",
      "author_url": "",
      "post_date": "08/21/2020 08:49:34",
      "content": "<p><a href=\"https://www.kaggle.com/sheriytm\" target=\"_blank\">@sheriytm</a> you'll get it soon enough! Keep on!</p>",
      "votes": null,
      "replies": [
        {
          "id": 980197,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/21/2020 11:46:04",
          "content": "<p>Thanks <a href=\"https://www.kaggle.com/mightyrains\" target=\"_blank\">@mightyrains</a>.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 980208,
      "author_name": "cpmpml",
      "author_url": "",
      "post_date": "08/21/2020 12:07:47",
      "content": "<p>The only question you should ask is how could you have selected this submission?</p>",
      "votes": null,
      "replies": [
        {
          "id": 980229,
          "author_name": "sheriytm",
          "author_url": "",
          "post_date": "08/21/2020 12:26:34",
          "content": "<p><a href=\"https://www.kaggle.com/cpmpml\" target=\"_blank\">@cpmpml</a>, nope I would not have chosen using any reasonable intuition because it is  my own conservative blend of blends which is usually risky.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 980333,
          "author_name": "cpmpml",
          "author_url": "",
          "post_date": "08/21/2020 14:13:56",
          "content": "<p>ok.  I see you're improving competition after competition, keep pushing!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "974454": "Congratulations to the winners.\n\n**Scores:-**\n**public LB=0.9618**\n**private LB=0.9482** \n\nI am Gutted.\n\n\nhttps://www.kaggle.com/sheriytm/melanoma-clf-xgb-missed-opportunity-4th-place\n\n\n**UPDATE**\n\nIn late submission, using the mean ensemble of 27 models which gave my private LB score in the above ensemble script scores :-\n**public LB=0.9618**\n**private LB=0.9487**",
    "974540": "Congratulations on the 89th position @sheriytm. \nSorry to hear you missed the 4th place :(\nYour solo gold will come soon. \nAll the best to you for the future",
    "974545": "mpsampat, thanks for your kind words. Congrats on your silver medal.",
    "974555": "Thats a strong model.",
    "974564": "roydatascience, it is an ensemble without CV hence there is no way I would have chosen it. I went with trusting my CV and chose a simple averaged ensemble and the other 2 based on CV ensemble.",
    "974571": "Not sure how, but the simple average ensemble failed in this competition.",
    "974585": "I have also a gold submission \n\n![capturebest](https://i.ibb.co/sJV9TH4/Capturebest.png)\n\nBut this was not my best model, so choosing it would be just luck. \n\nMy current score however, is my best CV and it scored just 0.9594 on public LB \n\n![CaptureCV](https://i.ibb.co/BsXN56b/Capture-CV.png)",
    "974598": "Congrats @serigne on a strong finish. \n\nMy current position public LB= 0.9571, private LB=0.9424 is a lower scoring one on the public LB but I went with trusting my CV as well. The best in private LB submission I did not choose was one of my ensembles that does not have a CV score. With a systematic approach there is no way I would have chosen it. I am only disappointed because I have been waiting so long for the elusive solo gold.",
    "974618": "sheriytm   \nThanks !  Congrats for your result too. \n\n\nI know this feelings\n\nI was rooting  for solo too gold during Jigsaw 3rd edition competition. And just applying @christofhenkel PP approach would put me in the upper golden area ;)\n\nBut don't worry,  ton tour viendra :)",
    "974639": "I'm rooting for you to get a solo gold. If ever there was a Kaggler that deserves to be a GM, clearly based on merit, it is you @sheriytm.",
    "974641": "roydatascience, my 2nd best submission on the private LB which is my current LB position is a submissions mean of 27 models.",
    "974646": "serigne, thanks.\n\nI had similar result to yours in the Jigsaw Multilingual competition as well hence my feeling a little sad this time.  J'espère bientôt pour l'or en solo.",
    "974647": "authman - you took my words. Rooting for you @sheriytm !",
    "974659": "authman, \n@robikscube, \nThanks so much for your kind words. \nI am thankful for experiencing this competition because I learnt so much about the use of TPU and a few TF tricks.",
    "976581": "I forgot to say that yesterday. \n\n@robikscube congrats to you and your team for another strong finish.\n\n@authman congrats to you and your team on the silver medal.",
    "976636": "YaGana, I am always inspired by your hard work and thoughtful contributions. You have a lot of passion, you will get gold soon!",
    "976641": "Congrats on another strong finish and thanks for your kind words @cdeotte.\n\nYour contributions here and always is well apreciated. I joined the Flower competition to try out TPU and I learnt a lot from you there as well as here on that subject. Your triple stratified dataset made life easier for so many of us. So thanks so much.",
    "979989": "sheriytm you'll get it soon enough! Keep on!",
    "980197": "Thanks @mightyrains.",
    "980208": "The only question you should ask is how could you have selected this submission?",
    "980229": "cpmpml, nope I would not have chosen using any reasonable intuition because it is  my own conservative blend of blends which is usually risky.",
    "980333": "ok.  I see you're improving competition after competition, keep pushing!"
  },
  "source": "meta"
}