I received this message in exercise 2
Failed test case: Wrong values in ‘attn_w_b2’. Check the call to self.mha2.
Expected: [0.34003818, 0.32569194, 0.33426988]
Got: [0.33410928 0.31997102 0.34591973]
Failed test case: Wrong values in ‘out’.
Expected: [1.1810006, -1.5600019, 0.41289005, -0.03388882]
Got: [ 1.1806822 -1.5725896 0.3635105 0.02839699]
It seems there are errors in your code, and the messages tell you which variables to check into.
why are you using training=training for multi attention head 1 and 2 layers, are you sure assignment instruct you to use?
Also I noticed there are no code markers, this can cause you autograder failure. kindly only write codes between assigned markers START AND END CODE HERE, AND THAT WHERE IT IS MENTIONED AS None (replace with the instructed codes)
I would highly recommend you to get a fresh copy of you have deleted/edited/added anything outside the code markers and re do your assignment