"Training stopped due to internal errors." -

[rosariofndz]

I've been trying to train a CEM processor in a Template Based traininig. Even though the labels statistics are shown to be ok, when Training I keep receiving the message "Training stopped due to internal errors." and when checking the .json file i found this:

{

  "name": "projects/367155390453/locations/eu/operations/4348715903612879701",

  "done": true,

  "result": "error",

  "response": {},

  "metadata": {

    "@type": "type.googleapis.com/google.cloud.documentai.uiv1beta3.TrainProcessorVersionMetadata",

    "commonMetadata": {

      "state": "FAILED",

      "createTime": "2023-12-01T11:15:09.112482Z",

      "updateTime": "2023-12-01T11:20:16.962808Z",

      "resource": "projects/367155390453/locations/eu/processors/f99093cd9d52d1e9/processorVersions/3c59be12e7f00a87"

    },

    "trainingDatasetValidation": {},

    "testDatasetValidation": {}

  },

  "error": {

    "code": 13,

    "message": "Internal error encountered.",

    "details": []

  }

}

Can anyone give me a hint on how to move forward?

[lsolatorio]

Hi @rosariofndz, 

Welcome and thank you for reaching out to our community.

I understand that you are having challenges with your CEM processor training, unfortunately the error message isn't informative enough will need further troubleshooting to determine the cause of the problem. This may also be a temporary glitch that will resolve itself in a later time since no incidents have been reported. 

You can reach out to Google Cloud Support for better assistance and you can also submit this in our Issue tracking system and product feature requests.