Grader Error: Grader feedback not found C3_W2 NLP specialisation

Course Q&A Natural Language Processing NLP with Sequence Models
1

Hi Team,

I am running into Grader Error: Grader feedback not found error while submitting the Week 2 assignment in sequence models with NLP week 2 assignment. Tried submitting several times across two days still stuck at the same error. Test cases seem to be passing fine however the grader is throwing an error. Please look into this for resolution.

Thanks,
Dhaval

2

Hi @Dhaval_Trivedi,

Can you share your lab ID with me ? In the assignment, when you click the top right “Help” button, a panel will open and your lab ID will be shown at the bottom.
I shall take a look.

When you reply back, kindly tag me in the post so that I’m notified.

Thanks,
Mubsi

3

Hi @Mubsi

Here’s my lab ID : ggtkxmyh

Thanks
Dhaval

4

Hi @Dhaval_Trivedi,

You are actually not passing all of your tests.

Your test for Ex 5 is failing:

Screenshot 2022-05-19 at 2.27.10 PM
Screenshot 2022-05-19 at 2.27.10 PM1434×1360 229 KB

Moreover, there’s a clear note at the start of assignment:

Screenshot 2022-05-19 at 2.29.45 PM
Screenshot 2022-05-19 at 2.29.45 PM1296×732 119 KB

You are clearly violating (5), by introducing your own variables in Ex 5, as well as reducing the total number of variables in that exercise.

This is the original code skeleton for Ex 5:

# UNQ_C5 (UNIQUE CELL IDENTIFIER, DO NOT EDIT)
# GRADED FUNCTION: test_model
def test_model(preds, target):
    """Function to test the model.

    Args:
        preds (jax.interpreters.xla.DeviceArray): Predictions of a list of batches of tensors corresponding to lines of text.
        target (jax.interpreters.xla.DeviceArray): Actual list of batches of tensors corresponding to lines of text.

    Returns:
        float: log_perplexity of the model.
    """
    ### START CODE HERE ###

    log_p = np.sum(None * None, axis= -1) # HINT: tl.one_hot() should replace one of the Nones

    non_pad = 1.0 - np.equal(None, None)          # You should check if the target equals 0
    log_p = None * None                             # Get rid of the padding    
    
    log_ppx = np.sum(None, None) / np.sum(None, None) # Remember to set the axis properly when summing up
    log_ppx = np.mean(None) # Compute the mean of the previous expression
    
    
    ### END CODE HERE ###
    
    return -log_ppx

Kindly work on your Ex 5 and see if you can get it correct. Otherwise, let me know.

Cheers,
Mubsi

5

Hi @Mubsi ,

Could you please help me with the same problem on the same exercise? The lab id is mcizdoykmtlk.

All of my checks pass, and I can’t see any contradictions in my notebook with the 5 conditions you pointed out. I’ve also cleared my cache & followed other points from the coursera help.

Many thanks,
Will

6

Hi @Will_Gannon,

Everything looks good in your notebook. Maybe something changed which shouldn’t have had. I’d recommend to get a fresh copy of the assignment by following these instructions, copy/paste your solutions in it and try submitting it then.

Best,
Mubsi

7

Thanks for checking @Mubsi, that worked!

Thanks,
Will