The best model's RMSE score doesn't match ..

Nobody has claimed this yet.

The best model's RMSE score doesn't match what's given by the validation data when scored by the best model.

I pass the following to the GameTrainingDriver:

...
--input-data-directories "glmm_in/train_data.avro" \
--validation-data-directories "glmm_in/test_data.avro" \
...

And, receive:

Best model has RMSE score of 10.212347636694373 and following config: ....

I'm assuming that the best model's RMSE score is computed on the validation data provided.
Yet, when I score the validation data using the best model and compute the RMSE score, the result is quite different from the best score announced.

Is the best score indeed based on the validation data?
Is a non-standard definition of RMSE being used here?
What could I be doing wrong? (Btw, the difference is significant enough to matter.)

Regards.

Start at the GameTrainingDriver invocation and trace how --input-data-directories and --validation-data-directories are used to calculate the reported best-model RMSE. Compare that calculation with scoring test_data.avro using the selected model, including the RMSE definition. Done means the discrepancy is explained and the expected scoring behavior is clear.

Written by the indexing model from the issue text.