Course 5 week1 dinosaur model, loss drops below 1.0 after 6k iterations: Any guidance is appreciated

Course Q&A Deep Learning Specialization Sequence Models
1

Hi, My problem is that, nstead of exploding, loss seems to drop very quickly. All tests pass before exercise 4. The algorithm starts fine, then drops in loss immediately. Is there any place to me to, so I can see what I’m doing wrong? I have reloaded the Workspace twice, tried rebooting the server, restarted kernel and and cleared output, but same problem.

j = 0 idx = 0
single_example = turiasaurus
single_example_chars [‘t’, ‘u’, ‘r’, ‘i’, ‘a’, ‘s’, ‘a’, ‘u’, ‘r’, ‘u’, ‘s’]
single_example_ix [20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19]
X = [None, 20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19]
Y = [20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19, 0]

Iteration: 0, Loss: 23.087336

Nkzxwtdmfqoeyhsqwasjkjvu
Kneb
Kzxwtdmfqoeyhsqwasjkjvu
Neb
Zxwtdmfqoeyhsqwasjkjvu
Eb
Xwtdmfqoeyhsqwasjkjvu

j = 1535 idx = 2
j = 1536 idx = 3
Iteration: 2000, Loss: 9.894264

Iavosaurus
Dosaurus
Esitosaurus
Iaecerus
Unus
Amanonelhoneris
Tosaurus

…

Iteration: 22000, Loss: 0.294620

Iavesaqr
Esitoriasaurus
Esitoriasaurus
Iaeaurus
Urus
Andoravenator
Saurur

Thanks, Mark N.

2

Your “idx” values are not correct.
What code did you use to set the “idx” value?

3

Ok. Thanks for making me take another look. I was thrown, since it seemed fine in the test. Found it now, though. Tests passed entirely - it was a simple mistake that I simply just kept looking past. Oh, well. Again, much thanks.

1 Like