For your submission to be successful, the execution time of the notebook must be less than 900 seconds. If the execution time exceeds this limit, the submission is destined to get a Notebook Inference Server Error, even if submission.paraquet is generated.
", "messages": [ { "id": "3032544", "postDate": "10/31/2024 03:53:58", "content": "For your submission to be successful, the execution time of the notebook must be less than 900 seconds. If the execution time exceeds this limit, the submission is destined to get a Notebook Inference Server Error, even if submission.paraquet is generated.
", "rawMarkdown": "For your submission to be successful, the execution time of the notebook must be less than 900 seconds. If the execution time exceeds this limit, the submission is destined to get a Notebook Inference Server Error, even if submission.paraquet is generated.", "votes": null }, { "id": "3032562", "postDate": "10/31/2024 04:52:17", "content": "Yes. Reduce the data loading time and processing time
", "rawMarkdown": "Yes. Reduce the data loading time and processing time", "votes": null }, { "id": "3032596", "postDate": "10/31/2024 06:13:59", "content": "what about this ? shouldn't this extend the 900s limit?
\n\n", "rawMarkdown": "what about this ? shouldn't this extend the 900s limit? \n>When your notebook is run on the hidden test set, inference_server.serve must be called within 15 minutes of the notebook starting or the gateway will throw an error. If you need more than 15 minutes to load your model you can do so during the very first predict call, which does not have the usual 1 minute response deadline.", "votes": null }, { "id": "3032667", "postDate": "10/31/2024 07:56:03", "content": "When your notebook is run on the hidden test set, inference_server.serve must be called within 15 minutes of the notebook starting or the gateway will throw an error. If you need more than 15 minutes to load your model you can do so during the very first predict call, which does not have the usual 1 minute response deadline.
\n
“If you need more than 15 minutes to load your model you can do so during the very first predict call.”
\nYes. This article seems to claim that there is a way to avoid runtime over. There should be a usage example in the public notes, so I will look for it. If I find it, I will report it.
You can prepare your model and dataset after you run .serve(), this way the 15min limit can be solved.
", "rawMarkdown": "You can prepare your model and dataset after you run .serve(), this way the 15min limit can be solved.", "votes": null }, { "id": "3032996", "postDate": "10/31/2024 16:55:44", "content": "The thing that helped me regarding the time limit was to split my notebook into two - one for training and one for submission. This way most of the hard the long work get executed in the training notebook, making the submission one much shorter so it can fit the time limit restriction.
", "rawMarkdown": "The thing that helped me regarding the time limit was to split my notebook into two - one for training and one for submission. This way most of the hard the long work get executed in the training notebook, making the submission one much shorter so it can fit the time limit restriction.", "votes": null }, { "id": "3078506", "postDate": "12/22/2024 11:57:18", "content": "I am experiencing Notebook Inference Server Error on several of my recent submissions. It is an inference only code to reduce data loading time. The submission file has the correct format and output. It doesn't seem to have any timeout issues. Tried to change from T4 to P100, as suggested by some to no avail. I don't know what else to do to rectify this issue! Any other suggestions to look into? Thanks.
", "rawMarkdown": "I am experiencing Notebook Inference Server Error on several of my recent submissions. It is an inference only code to reduce data loading time. The submission file has the correct format and output. It doesn't seem to have any timeout issues. Tried to change from T4 to P100, as suggested by some to no avail. I don't know what else to do to rectify this issue! Any other suggestions to look into? Thanks.", "votes": null }, { "id": "3094853", "postDate": "01/12/2025 15:58:55", "content": "Thanks !
\nWhere is it written?
Yes. Reduce the data loading time and processing time
", "votes": null, "replies": [] }, { "id": 3032596, "author_name": "younesbenalia", "author_url": "", "post_date": "10/31/2024 06:13:59", "content": "what about this ? shouldn't this extend the 900s limit?
\n\n", "votes": null, "replies": [ { "id": 3032667, "author_name": "stpeteishii", "author_url": "", "post_date": "10/31/2024 07:56:03", "content": "When your notebook is run on the hidden test set, inference_server.serve must be called within 15 minutes of the notebook starting or the gateway will throw an error. If you need more than 15 minutes to load your model you can do so during the very first predict call, which does not have the usual 1 minute response deadline.
\n
“If you need more than 15 minutes to load your model you can do so during the very first predict call.”
\nYes. This article seems to claim that there is a way to avoid runtime over. There should be a usage example in the public notes, so I will look for it. If I find it, I will report it.
You can prepare your model and dataset after you run .serve(), this way the 15min limit can be solved.
", "votes": null, "replies": [ { "id": 3094853, "author_name": "chronobcelp", "author_url": "", "post_date": "01/12/2025 15:58:55", "content": "Thanks !
\nWhere is it written?
The thing that helped me regarding the time limit was to split my notebook into two - one for training and one for submission. This way most of the hard the long work get executed in the training notebook, making the submission one much shorter so it can fit the time limit restriction.
", "votes": null, "replies": [] }, { "id": 3078506, "author_name": "neuralfive", "author_url": "", "post_date": "12/22/2024 11:57:18", "content": "I am experiencing Notebook Inference Server Error on several of my recent submissions. It is an inference only code to reduce data loading time. The submission file has the correct format and output. It doesn't seem to have any timeout issues. Tried to change from T4 to P100, as suggested by some to no avail. I don't know what else to do to rectify this issue! Any other suggestions to look into? Thanks.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "3032544": "For your submission to be successful, the execution time of the notebook must be less than 900 seconds. If the execution time exceeds this limit, the submission is destined to get a Notebook Inference Server Error, even if submission.paraquet is generated.", "3032562": "Yes. Reduce the data loading time and processing time", "3032596": "what about this ? shouldn't this extend the 900s limit? \n>When your notebook is run on the hidden test set, inference_server.serve must be called within 15 minutes of the notebook starting or the gateway will throw an error. If you need more than 15 minutes to load your model you can do so during the very first predict call, which does not have the usual 1 minute response deadline.", "3032667": "“If you need more than 15 minutes to load your model you can do so during the very first predict call.”\nYes. This article seems to claim that there is a way to avoid runtime over. There should be a usage example in the public notes, so I will look for it. If I find it, I will report it.", "3032700": "You can prepare your model and dataset after you run .serve(), this way the 15min limit can be solved.", "3032996": "The thing that helped me regarding the time limit was to split my notebook into two - one for training and one for submission. This way most of the hard the long work get executed in the training notebook, making the submission one much shorter so it can fit the time limit restriction.", "3078506": "I am experiencing Notebook Inference Server Error on several of my recent submissions. It is an inference only code to reduce data loading time. The submission file has the correct format and output. It doesn't seem to have any timeout issues. Tried to change from T4 to P100, as suggested by some to no avail. I don't know what else to do to rectify this issue! Any other suggestions to look into? Thanks.", "3094853": "Thanks !\nWhere is it written?" }, "source": "meta" }