Invalid Argument Error when classes missing

[gridcellcoder]

When you run the tool with a dataset with a feature class missing e.g. 4 missing below

1,1.13324,1351.0,6862.4800000000005,3338.6999999999994,6859.446551724133
2,1.132653246753247,1350.7333333333336,6859.446551724133,4640.164285714285,6858.642028985517
3,1.132447198697068,1351.0458970099692,6858.642028985517,4996.519021739133,6860.627397260285
0,1.1325953916004556,1350.2446681415893,6860.627397260285,4993.749596774188,6862.286111111106
5,1.13324,1351.0,6862.4800000000005,3338.6999999999994,6859.446551724133

It throws:

InvalidArgumentError (see above for traceback): Received a label value of 5 which is outside the valid range of [0, 5).  Label values: 1 2 3 0 5 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5 3 3 5 5
	 [[Node: SoftMax/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](Fully_Connected2/add, _recv_Ground_truth_0)]]

but is fine if all classes are present 1 to 5.

1,1.13324,1351.0,6862.4800000000005,3338.6999999999994,6859.446551724133
2,1.132653246753247,1350.7333333333336,6859.446551724133,4640.164285714285,6858.642028985517
3,1.132447198697068,1351.0458970099692,6858.642028985517,4996.519021739133,6860.627397260285
4,1.1325953916004556,1350.2446681415893,6860.627397260285,4993.749596774188,6862.286111111106
5,1.13324,1351.0,6862.4800000000005,3338.6999999999994,6859.446551724133

Is this expected or a bug or limitation?