strange results of training and validation

[ABexit]

In "aishell"and "Merged_Arabic_Corpus_of_Isolated_Words" datasets, the predicted results looks like a random guess when training, and will always get a same result when validation. Have you encountered this problem? Thanks.
""" The validation results as follows, left: label, right: prediction------
[25] [11]
[39] [11]
[41] [11]
[130] [11]
[2] [11]
"""