Status Update
No update yet.
Comments
pu...@google.com
je...@google.com
Hello,
To assist us in conducting thorough investigation, we kindly request your cooperation in providing the following information regarding the reported issue:
- Has this scenario ever worked as expected in the past?
- Do you see this issue constantly or intermittently ?
- If this issue is seen intermittently, then how often do you observe this issue ? Is there any specific scenario or time at which this issue is observed ?
- To help us understand the issue better, please provide detailed steps to reliably reproduce the problem.
- It would be greatly helpful if you could attach screenshots of the output related to this issue.
Your cooperation in providing these details will enable us to dive deeper into the matter and work towards a prompt resolution. We appreciate your assistance and look forward to resolving this issue for you.
Thank you for your understanding and cooperation.
je...@google.com
Thank you for reaching out. Here is the information requested regarding the reported issue:
In response to the first point, I previously conducted an uptraining with approximately twenty bank statements, and this issue did not occur.
For the second point, I have attempted the uptraining three times, and the same error appeared each time.
To reproduce the issue: I labeled 76 bank statements, dividing them as follows—59 in the training dataset and 17 in the test dataset. I also modified the label schema by deactivating the following labels: account_types, bank_address, bank_name, client_address, and client_name. Additionally, I created a new label for rib (bank account identifier). I then proceeded to uptrain a new version, and the issue arises during this process.
I hope this information helps clarify the situation. Please let me know if you need any further details.
Thank you for your assistance in resolving this matter.
cl...@epic-ai.com
Hello,
Thank you for reaching out to us with your request.
We have duly noted your feedback and will thoroughly validate it. While we cannot provide an estimated time of implementation or guarantee the fulfillment of the issue, please be assured that your input is highly valued. Your feedback enables us to enhance our products and services.
If you are looking for a faster resolution and dedicated support for your issue, I kindly request you to file a support ticket by clicking
We appreciate your continued trust and support in improving our Google Cloud Platform products. In case you want to report a new issue, Please do not hesitate to create a new issue on the
Once again, we sincerely appreciate your valuable feedback; Thank you for your understanding and collaboration.
fl...@abrico.eco
Any update on the issue ?
Florent
fl...@abrico.eco
Florent
jm...@securis.com
st...@mekari.com
ra...@google.com
Errors at CDE1 (Custom Model) Training are one thing.
Errors on GenAI CDE2 at prediction (processing) time (and if fine tuned or few shot) are something completely different.
We appreciate your input as we dig into these various issues.
fl...@abrico.eco
Though I just checked this morning and they are still there, cf screenshot.
I would expect that you have some logs / monitoring somewhere but if you need some help to dig let me know.
da...@clearance.solutions
re...@gmail.com
We reduced the labels, training documents, and testing documents to the minimum allowed to get the classifier to train, but it always fails.
Labels = 2
Training Documents = 10
Testing Documents = 2
Training fails with the following error:
Here is the error if it helps.
{
"name": "xxxx",
"done": true,
"result": "error",
"response": {},
"metadata": {
"@type": "
"commonMetadata": {
"state": "FAILED",
"createTime": "2024-09-27T16:04:48.662993Z",
"updateTime": "2024-09-27T16:16:25.687423Z",
"resource": "xxx"
},
"trainingDatasetValidation": {},
"testDatasetValidation": {}
},
"error": {
"code": 13,
"message": "Internal error encountered.",
"details": []
}
}
ji...@infodevsolve.com
sw...@marlowgroup.com
Adding my initial report here too, while attempting to training a large(r) classifier:
Total documents: 25743 Training document: 23755 Test document: 1988 Estimated total File Size: ~11GB PDF Page Limits <10 max on a few selected documents only, mainly image files
fails during training (more then 10 attempts to build have been performed) with the following error in the Operation.json:
{
"name": "projects/XXXXXX/locations/eu/operations/XXXXXX",
"done": true,
"result": "error",
"response": {},
"metadata": {
"@type": "type.googleapis.com/google.cloud.documentai.uiv1beta3.TrainProcessorVersionMetadata",
"commonMetadata": {
"state": "FAILED",
"createTime": "2024-11-21T18:04:28.628919Z",
"updateTime": "2024-11-22T04:13:37.885333Z",
"resource": "projects/XXXXXX/locations/eu/processors/XXXXXX/processorVersions/XXXXXX"
},
"trainingDatasetValidation": {},
"testDatasetValidation": {}
},
"error": {
"code": 13,
"message": "Internal error encountered.",
"details": []
}
}
Reviewing the Cloud Console Log shows:
Model server never became ready. Please validate that your model file or container configuration are valid.
There are some other elements which seems to be out of place:
There is no base model which can be selected during training of a classifier which could be referenced.
Description
Follow up to this issue
We are frequently experiencing Document AI internal errors on some of our documents with the following cryptic error "Error: 13 INTERNAL: Internal error encountered." (online processing on a Custom Extractor)
I can happily provide more info & a document to reproduce in a more private setting.
All the best,
Florent Chehab