What this tutorial covers
Inspect training/validation curves to judge convergence and generalization.
Before you start：You need access to the product and should ideally follow the tutorial using your own real parameters or data. The screenshots below were manually rematched to avoid the image/topic mismatches seen in the previous version.
Step-by-step workflow
1Open the module
After training, open the Results page. Confirm that the visible page really matches the tutorial topic before changing any settings.
2Configure the input
Prepare and check the logs and metrics from a completed training run.
3Run and watch the status
Inspect how loss and accuracy evolve across epochs. Watch the visible status, plot or log area while the workflow is running.
4Inspect the result
Pay special attention to loss/accuracy curves and their trends.
5Verify and iterate
A widening training-versus-validation gap is often a sign of overfitting. Change one meaningful parameter and rerun so you can verify whether the output changes in the expected direction.
How to read the result
- The main output of this workflow is loss/accuracy curves and their trends.
- Read the result together with the exact inputs used for the run; a screenshot alone rarely tells the whole story.
- A widening training-versus-validation gap is often a sign of overfitting.
Troubleshooting & practical tips
- If nothing changes, first confirm that the correct module is open.
- If the output looks unrealistic, check units, field mapping and input scale first.
- For comparisons, change one key parameter at a time whenever possible.