model.fit() training loop in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of model.fit() training metrics

What will be the output of the training metrics after running this code snippet?

TensorFlow

import tensorflow as tf
import numpy as np

# Simple dataset
x = np.array([[0.], [1.], [2.], [3.], [4.], [5.]], dtype=float)
y = np.array([[0.], [2.], [4.], [6.], [8.], [10.]], dtype=float)

# Simple linear model
model = tf.keras.Sequential([tf.keras.layers.Dense(1, input_shape=(1,))])
model.compile(optimizer='sgd', loss='mse', metrics=['mae'])

history = model.fit(x, y, epochs=3, verbose=0)

print(history.history)

A {"loss": [4.0, 0.25, 0.0625], "mae": [2.0, 1.0, 0.5]}

B {"loss": [4.0, 0.5, 0.125], "mae": [2.0, 1.0, 0.5]}

C {"loss": [4.0, 0.25, 0.0625], "mae": [1.5, 0.5, 0.25]}

D {"loss": [4.0, 0.5, 0.125], "mae": [1.5, 0.5, 0.25]}

💡 Hint

Look at how loss and mae decrease over epochs in a simple linear regression with SGD optimizer.

The mean squared error (loss) and mean absolute error (mae) decrease as the model learns. The values in option B match typical outputs for this simple training.

🧠 Conceptual

intermediate

Understanding batch size effect in model.fit()

Which statement correctly describes the effect of batch size in the model.fit() training loop?

A A larger batch size uses more memory but can lead to more stable gradient estimates during training.

B A smaller batch size always leads to faster training and better model accuracy.

C Batch size does not affect training speed or model performance.

D Batch size only affects the number of epochs, not the training steps per epoch.

💡 Hint

Think about how batch size influences memory use and gradient calculation.

Larger batch sizes use more memory but provide more stable gradient estimates, which can improve training stability. Smaller batches can be noisy but may generalize better.

❓ Hyperparameter

advanced

Choosing the right number of epochs in model.fit()

If a model is overfitting the training data during model.fit(), which adjustment is most appropriate?

A Decrease the number of epochs to stop training earlier.

B Increase the batch size to reduce overfitting.

C Increase the number of epochs to let the model learn more.

D Use a higher learning rate to speed up training.

💡 Hint

Overfitting means the model learns too much from training data and performs worse on new data.

Reducing epochs helps prevent the model from learning noise in the training data, which causes overfitting.

🔧 Debug

advanced

Identifying error in model.fit() usage

What error will this code raise when calling model.fit()?

TensorFlow

import tensorflow as tf

model = tf.keras.Sequential([tf.keras.layers.Dense(1)])
model.compile(optimizer='adam', loss='mse')

# Missing input data
model.fit(epochs=5)

A No error, training runs with default data

B ValueError: Data provided to model is empty

C RuntimeError: Model not compiled

D TypeError: fit() missing 1 required positional argument: 'x'

💡 Hint

Check the required arguments for model.fit()

model.fit() requires input data 'x' and target 'y' unless using a dataset. Omitting 'x' causes a TypeError.

❓ Model Choice

expert

Selecting model architecture for time series forecasting with model.fit()

You want to predict future values of a time series using model.fit(). Which model architecture is best suited for this task?

A A convolutional neural network (CNN) designed for image classification

B A simple feedforward neural network with Dense layers only

C A recurrent neural network (RNN) or LSTM model designed to handle sequences

D A clustering model like KMeans

💡 Hint

Time series data has order and depends on previous values.

RNNs and LSTMs are designed to process sequences and remember past information, making them ideal for time series forecasting.

Practice

1. What does the epochs parameter control in the model.fit() training loop?

easy

A. The number of times the entire dataset is shown to the model

B. The size of each batch of data during training

C. The learning rate of the optimizer

D. The number of layers in the model

Solution

1. Step 1: Understand the role of epochs in training

   Epochs define how many times the model sees the whole dataset during training.

2. Step 2: Differentiate epochs from batch size and other parameters

   Batch size controls data chunks per step, learning rate controls update speed, layers define model depth.

3. Final Answer:

   The number of times the entire dataset is shown to the model -> Option A

4. Quick Check:

   Epochs = full dataset passes [OK]

Hint: Epochs = full dataset passes through model [OK]

Common Mistakes:

• Confusing epochs with batch size
• Thinking epochs control learning rate
• Mixing epochs with model architecture

2. Which of the following is the correct way to call model.fit() with 10 epochs and batch size of 32?

easy

A. model.fit(x_train, y_train, epochs=10, batch_size=32)

B. model.fit(x_train, y_train, batch=10, size=32)

C. model.fit(x_train, y_train, epoch=10, batch=32)

D. model.fit(x_train, y_train, epochs=32, batch_size=10)

Solution

1. Step 1: Recall correct parameter names for model.fit()

   The correct parameters are epochs and batch_size.

2. Step 2: Check each option for correct syntax

   model.fit(x_train, y_train, epochs=10, batch_size=32) uses correct parameter names and values. Others use wrong names or swapped values.

3. Final Answer:

   model.fit(x_train, y_train, epochs=10, batch_size=32) -> Option A

4. Quick Check:

   Correct parameter names = model.fit(x_train, y_train, epochs=10, batch_size=32) [OK]

Hint: Use exact parameter names: epochs and batch_size [OK]

Common Mistakes:

• Using wrong parameter names like 'batch' or 'epoch'
• Swapping values of epochs and batch_size
• Missing required parameters

3. Given the code below, what will be printed after training?

model = tf.keras.Sequential([
  tf.keras.layers.Dense(1, input_shape=(1,))
])
model.compile(optimizer='sgd', loss='mse')
x = np.array([1, 2, 3, 4], dtype=float)
y = np.array([2, 4, 6, 8], dtype=float)
history = model.fit(x, y, epochs=3, batch_size=2, verbose=0)
print(history.history['loss'])

medium

A. [0, 0, 0]

B. [3, 2, 1]

C. [some decreasing loss values over 3 epochs]

D. An error because batch_size is too large

Solution

1. Step 1: Understand training with batch_size=2 and epochs=3

   The model trains 3 times over data in batches of 2, updating weights each batch.

2. Step 2: Predict loss values behavior

   Loss starts higher and decreases as model learns; exact values vary but should decrease over epochs.

3. Final Answer:

   [some decreasing loss values over 3 epochs] -> Option C

4. Quick Check:

   Loss decreases with training epochs [OK]

Hint: Loss decreases over epochs during training [OK]

Common Mistakes:

• Expecting exact loss numbers
• Thinking loss stays constant or zero
• Assuming batch_size causes error here

4. What is wrong with this model.fit() call?

model.fit(x_train, y_train, epochs=5, batch_size=0)

medium

A. No validation data provided

B. epochs cannot be less than 10

C. x_train and y_train must be lists, not arrays

D. batch_size cannot be zero; it must be a positive integer

Solution

1. Step 1: Check batch_size parameter validity

   Batch size must be a positive integer; zero is invalid and causes error.

2. Step 2: Verify other parameters

   Epochs can be any positive integer; data type arrays are allowed; validation data is optional.

3. Final Answer:

   batch_size cannot be zero; it must be a positive integer -> Option D

4. Quick Check:

   batch_size > 0 required [OK]

Hint: Batch size must be positive integer, not zero [OK]

Common Mistakes:

• Setting batch_size to zero
• Thinking epochs must be >=10
• Confusing data types for inputs

5. You want to train a model and check its performance on new data after each epoch. Which model.fit() parameter helps you do this?

hard

A. steps_per_epoch

B. validation_data

C. batch_size

D. shuffle

Solution

1. Step 1: Understand the purpose of validation_data

   Validation data is used to evaluate model performance after each epoch without training on it.

2. Step 2: Differentiate from other parameters

   Batch size controls training speed, steps_per_epoch controls iteration count, shuffle randomizes data order.

3. Final Answer:

   validation_data -> Option B

4. Quick Check:

   Validation data checks model after epochs [OK]

Hint: Use validation_data to check model after each epoch [OK]

Common Mistakes:

• Confusing batch_size with validation
• Using steps_per_epoch to validate
• Thinking shuffle affects validation