def train_model_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
                       eval_freq, eval_iter, start_context, tokenizer):
    # Initialize lists to track losses and tokens seen
    train_losses, val_losses, track_tokens_seen = [], [], []
    tokens_seen, global_step = 0, -1

    # Main training loop
    for epoch in range(num_epochs):
        model.train()  # Set model to training mode
        
        for input_batch, target_batch in train_loader:
            optimizer.zero_grad() # Reset loss gradients from previous batch iteration
            loss = calc_loss_batch(input_batch, target_batch, model, device)
            loss.backward() # Calculate loss gradients
            optimizer.step() # Update model weights using loss gradients
            tokens_seen += input_batch.numel()
            global_step += 1

            # Optional evaluation step
            if global_step % eval_freq == 0:
                train_loss, val_loss = evaluate_model(
                    model, train_loader, val_loader, device, eval_iter)
                train_losses.append(train_loss)
                val_losses.append(val_loss)
                track_tokens_seen.append(tokens_seen)
                print(f"Ep {epoch+1} (Step {global_step:06d}): "
                      f"Train loss {train_loss:.3f}, Val loss {val_loss:.3f}")

        # Print a sample text after each epoch
        generate_and_print_sample(
            model, tokenizer, device, start_context
        )

    return train_losses, val_losses, track_tokens_seen

def evaluate_model(model, train_loader, val_loader, device, eval_iter):
    model.eval()
    with torch.no_grad():
        train_loss = calc_loss_loader(train_loader, model, device, num_batches=eval_iter)
        val_loss = calc_loss_loader(val_loader, model, device, num_batches=eval_iter)
    model.train()
    return train_loss, val_loss

def generate_and_print_sample(model, tokenizer, device, start_context):
    model.eval()
    context_size = model.pos_emb.weight.shape[0]
    encoded = text_to_token_ids(start_context, tokenizer).to(device)
    with torch.no_grad():
        token_ids = generate_text_simple(
            model=model, idx=encoded,
            max_new_tokens=50, context_size=context_size
        )
    decoded_text = token_ids_to_text(token_ids, tokenizer)
    print(decoded_text.replace("\n", " "))  # Compact print format
    model.train()

# Note:
# Uncomment the following code to calculate the execution time
# import time
# start_time = time.time()

torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=0.0004, weight_decay=0.1)

num_epochs = 10
train_losses, val_losses, tokens_seen = train_model_simple(
    model, train_loader, val_loader, optimizer, device,
    num_epochs=num_epochs, eval_freq=5, eval_iter=5,
    start_context="Every effort moves you", tokenizer=tokenizer
)

# Note:
# Uncomment the following code to show the execution time
# end_time = time.time()
# execution_time_minutes = (end_time - start_time) / 60
# print(f"Training completed in {execution_time_minutes:.2f} minutes.")

Ep 1 (Step 000000): Train loss 9.781, Val loss 9.933
Ep 1 (Step 000005): Train loss 8.111, Val loss 8.339
Every effort moves you,,,,,,,,,,,,.                                     
Ep 2 (Step 000010): Train loss 6.661, Val loss 7.048
Ep 2 (Step 000015): Train loss 5.961, Val loss 6.616

Every effort moves you, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and, and,, and, and,

Ep 3 (Step 000020): Train loss 5.726, Val loss 6.600
Ep 3 (Step 000025): Train loss 5.201, Val loss 6.348
Every effort moves you, and I had been.                                            
Ep 4 (Step 000030): Train loss 4.417, Val loss 6.278
Ep 4 (Step 000035): Train loss 4.069, Val loss 6.226
Every effort moves you know the                          "I he had the donkey and I had the and I had the donkey and down the room, I had

Ep 5 (Step 000040): Train loss 3.732, Val loss 6.160
Every effort moves you know it was not that the picture--I had the fact by the last I had been--his, and in the            "Oh, and he said, and down the room, and in

Ep 6 (Step 000045): Train loss 2.850, Val loss 6.179
Ep 6 (Step 000050): Train loss 2.427, Val loss 6.141
Every effort moves you know," was one of the picture. The--I had a little of a little: "Yes, and in fact, and in the picture was, and I had been at my elbow and as his pictures, and down the room, I had

Ep 7 (Step 000055): Train loss 2.104, Val loss 6.134
Ep 7 (Step 000060): Train loss 1.882, Val loss 6.233
Every effort moves you know," was one of the picture for nothing--I told Mrs.  "I was no--as! The women had been, in the moment--as Jack himself, as once one had been the donkey, and were, and in his

Ep 8 (Step 000065): Train loss 1.320, Val loss 6.238
Ep 8 (Step 000070): Train loss 0.985, Val loss 6.242
Every effort moves you know," was one of the axioms he had been the tips of a self-confident moustache, I felt to see a smile behind his close grayish beard--as if he had the donkey. "strongest," as his

Ep 9 (Step 000075): Train loss 0.717, Val loss 6.293
Ep 9 (Step 000080): Train loss 0.541, Val loss 6.393
Every effort moves you?"  "Yes--quite insensible to the irony. She wanted him vindicated--and by me!"  He laughed again, and threw back the window-curtains, I had the donkey. "There were days when I

Ep 10 (Step 000085): Train loss 0.391, Val loss 6.452
Every effort moves you know," was one of the axioms he laid down across the Sevres and silver of an exquisitely appointed luncheon-table, when, on a later day, I had again run over from Monte Carlo; and Mrs. Gis

import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator

def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
    fig, ax1 = plt.subplots(figsize=(5, 3))

    # Plot training and validation loss against epochs
    ax1.plot(epochs_seen, train_losses, label="Training loss")
    ax1.plot(epochs_seen, val_losses, linestyle="-.", label="Validation loss")
    ax1.set_xlabel("Epochs")
    ax1.set_ylabel("Loss")
    ax1.legend(loc="upper right")
    ax1.xaxis.set_major_locator(MaxNLocator(integer=True))  # only show integer labels on x-axis

    # Create a second x-axis for tokens seen
    ax2 = ax1.twiny()  # Create a second x-axis that shares the same y-axis
    ax2.plot(tokens_seen, train_losses, alpha=0)  # Invisible plot for aligning ticks
    ax2.set_xlabel("Tokens seen")

    fig.tight_layout()  # Adjust layout to make room
    plt.savefig("loss-plot.pdf")
    plt.show()

epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
plot_losses(epochs_tensor, tokens_seen, train_losses, val_losses)