0% accuracy during evaluation from trained model. - GLOVE

[rkdey95]

Hey guys,

I've downloaded and managed to preprocess and train the model for the problem.

Training was done using the GloVe configuration.

During training Accuracy and Loss was printed on screen.

However during evaluation, the results seem to show 0% accuracy. I noticed that during inferencing, the results from decoding came out as an empty list "[]".

Anyone faced this problem before? Appreciate any advise / workaround. Thanks.

I have also attached the .infer and .eval files in for reference.

glove_run_true_1-step30100.zip

[manzambi11]

Please share the screenshot