Trainer

The trainer is a separate machine, designed to handle resource-heavy operations, such as training models. It runs independently from the main Hyperscience application and connects to it through the API. This setup prevents training workloads from slowing down document processing and submission handling.

Using features for Semi-structured documents

This article mentions features used in the processing of Semi-structured documents. Your access to those features depends on your license package and pricing plan.

To learn which features are available to your organization and how to add more, contact your Hyperscience representative.

Training Identification models like invoices, paystubs, or bills of landing requires substantial computing power.

Install a Trainer

For best performance, install the trainer on a dedicated machine with at least 64GB of RAM.

See the following links for more information on all of the jobs that run in the trainer: 

• Training an Identification Model

• Document Drift Management (Layout Triage)

• Transcription Settings

• Document Classification Settings

Navigating the Trainer page

Navigate to Administration > Trainer to view and manage all running jobs.  

On the Trainer page, you can:

• View all running, pending, failed, finished, and canceled jobs.

• Cancel pending and running jobs.

• View how many and which trainers are connected to the application.

  • If no trainer model is detected, a warning message will show at the top of the Trainer Queue.

  • If an incompatible trainer model is connected (e.g., a trainer version that is older than the version of the application), the UI will indicate this incompatibility. You should uninstall the incompatible trainer because it will use up memory even while idle.

Guidelines for Running the Trainer 

1. Separate from the main application, you must also install the trainer application on a dedicated machine with at least 64GB of RAM. You can also run multiple trainers on one machine, but only one job will run at a time per machine. 

2. You can have multiple trainers on multiple machines to run different jobs simultaneously, including two trainers of the same version. Only one job can run at a time per machine.

   • All jobs are cancellable in the Trainer Queue.

   • If a job fails, the trainer will retry it two additional times before entering a terminal failed state. 

Canceling or Retrying a Training Job

Canceling a Training Job

To take action on the Field Locator model training, or any training job for that matter, navigate to Administration > Trainer.

Follow these steps to cancel a job in the Trainer:

1. Navigate to Administration > Trainer to get to the Trainer UI.

2. Find the Queue section, where you can use the "Running" or "Queued" dropdowns to find the training job that you would like to cancel.

3. Once you have located the job card, click on the Cancel button in the upper right corner of the card to stop the job.

   • This will cancel that training job and will move the job card to the Completed section just below, in the "Canceled" dropdown.

Retrying a Training job

Follow these steps to retry a job in the Trainer:

1. Navigate to Administration > Trainer to get to the Trainer UI.

2. Find the Completed section, where you can use the "Failed" dropdown to locate the training job that you would like to cancel.