def train_model_simple(
    model,train_loader, val_loader, optimizer, device, num_epochs, eval_freq,eval_iter,start_context,tokenizer
):
    train_losses = []
    val_losses = []
    track_tokens_seen = []

    tokens_seen = 0
    global_step = -1

    for epoch in range(num_epochs):
        model.train()

        for input_batch, target_batch in train_loader:
            optimizer.zero_grad()

            loss = calc_loss_batch(
                input_batch,
                target_batch,
                model,
                device
            )

            loss.backward()
            optimizer.step()

            tokens_seen += input_batch.numel()
            global_step += 1

            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"Epoch: {epoch + 1}, "
                    f"Global Step: {global_step}, "
                    f"Train Loss: {train_loss:.4f}, "
                    f"Val Loss: {val_loss:.4f}"
                )

        generate_and_print_sample(model,tokenizer,device,
            start_context)

    return train_losses, val_losses, track_tokens_seen

        __
        __