Progress tracking and reporting in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to print the training loss after each epoch.

Agentic AI

for epoch in range(5):
    loss = model.train_one_epoch(data)
    print('Epoch', epoch, 'Loss:', [1])

Drag options to blanks, or click blank then click option'

Aepoch

Bloss

Cdata

Dmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Printing the epoch number instead of the loss.

Printing the model object.

The variable loss holds the training loss for the current epoch, so printing it shows progress.

2fill in blank

medium

Complete the code to update the progress bar with the current accuracy.

Agentic AI

for batch in data_loader:
    predictions = model.predict(batch)
    accuracy = compute_accuracy(predictions, batch.labels)
    progress_bar.update([1]=accuracy)

Drag options to blanks, or click blank then click option'

Ascore

Baccuracy

Cvalue

Dprogress

Attempts:

3 left

💡 Hint

Common Mistakes

Using the variable name accuracy as the parameter name.

Using score which is undefined.

The progress bar's update method expects the current progress as the value argument.

3fill in blank

hard

Fix the error in the code to correctly log the validation accuracy after each epoch.

Agentic AI

for epoch in range(10):
    val_acc = evaluate(model, val_data)
    logger.log('Validation Accuracy:', [1])

Drag options to blanks, or click blank then click option'

Aval_acc()

Bmodel

Cevaluate

Dval_acc

Attempts:

3 left

💡 Hint

Common Mistakes

Calling val_acc as a function.

Logging the model object instead of accuracy.

The variable val_acc stores the accuracy value. Calling it as a function causes an error.

4fill in blank

hard

Fill both blanks to create a dictionary that maps epoch numbers to their loss values.

Agentic AI

loss_history = { [1]: [2] for [1] in range(1, 6) }

Drag options to blanks, or click blank then click option'

Aepoch

Bloss

Cval_loss

Daccuracy

Attempts:

3 left

💡 Hint

Common Mistakes

Using the same variable for both key and value.

Using validation loss or accuracy instead of training loss.

The dictionary keys are epoch numbers stored in epoch, and values are the corresponding loss values.

5fill in blank

hard

Fill all three blanks to filter and store epochs where accuracy is above 0.8.

Agentic AI

high_acc_epochs = { [1]: [2] for [1] in epochs if [3][[1]] > 0.8 }

Drag options to blanks, or click blank then click option'

Aepoch

Baccuracy

Cacc_dict

Dloss

Attempts:

3 left

💡 Hint

Common Mistakes

Using loss instead of accuracy.

Using wrong variable names for dictionary or keys.

We use epoch as the key, accuracy as the value, and check if acc_dict[epoch] is greater than 0.8.