Mean Squared Error Too Big (>6)

Course Q&A TensorFlow Developer Professional Sequences, Time Series and Prediction
1

C4A4: Mean Square Error Too Big. Getting MSE 6.14, expected <6.

TestCase Failure:

Failed test case: Mean Squared Error is too big.
Expected:
a value less than 6,
but got:
6.14.

Can anyone please let me know how I can resolve this? Do I need to reduce LR?

2

Please see this topic for tips on NN optimizer and architecture.

3

Thanks @balaji.ambresh I was able to submit this time successfully. I did following changes:

  1. Changed #of filters in Conv layer
  2. Made dense layer #of neurons to 2s power
  3. Used Adam optimizer