def train([train_dataloader](https://docs.pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader "torch.utils.data.DataLoader"), encoder, decoder, n_epochs, learning_rate=0.001,
               print_every=100, plot_every=100):
    start = time.time()
    plot_losses = []
    print_loss_total = 0  # Reset every print_every
    plot_loss_total = 0  # Reset every plot_every

    encoder_optimizer = [optim.Adam](https://docs.pytorch.org/docs/stable/generated/torch.optim.Adam.html#torch.optim.Adam "torch.optim.Adam")([encoder.parameters](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.parameters "torch.nn.Module.parameters")(), lr=learning_rate)
    decoder_optimizer = [optim.Adam](https://docs.pytorch.org/docs/stable/generated/torch.optim.Adam.html#torch.optim.Adam "torch.optim.Adam")([decoder.parameters](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.parameters "torch.nn.Module.parameters")(), lr=learning_rate)
    criterion = [nn.NLLLoss](https://docs.pytorch.org/docs/stable/generated/torch.nn.NLLLoss.html#torch.nn.NLLLoss "torch.nn.NLLLoss")()

    for epoch in range(1, n_epochs + 1):
        loss = train_epoch([train_dataloader](https://docs.pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader "torch.utils.data.DataLoader"), encoder, decoder, encoder_optimizer, decoder_optimizer, criterion)
        print_loss_total += loss
        plot_loss_total += loss

        if epoch % print_every == 0:
            print_loss_avg = print_loss_total / print_every
            print_loss_total = 0
            print('%s (%d %d%%) %.4f' % (timeSince(start, epoch / n_epochs),
                                        epoch, epoch / n_epochs * 100, print_loss_avg))

        if epoch % plot_every == 0:
            plot_loss_avg = plot_loss_total / plot_every
            plot_losses.append(plot_loss_avg)
            plot_loss_total = 0

    showPlot(plot_losses)