trainer.py [98:110]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    loss_all = 0
    actual_nb_batches_per_iter = 0
    for _ in range(nb_batches_per_iter_max):
        actual_nb_batches_per_iter += 1
        X = data[:, train_pos: train_pos + block_size].contiguous()
        Y = data[:, train_pos + 1: train_pos + block_size + 1].contiguous()

        loss, h_cache = _train_batch(
            model=model,
            optimizer=optimizer,
            scheduler=scheduler,
            X=X, Y=Y,
            h_cache=h_cache,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



trainer.py [138:150]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    loss_all = 0
    actual_nb_batches_per_iter = 0
    for _ in range(nb_batches_per_iter_max):
        actual_nb_batches_per_iter += 1
        X = data[:, train_pos: train_pos + block_size].contiguous()
        Y = data[:, train_pos + 1: train_pos + block_size + 1].contiguous()

        loss, h_cache = _train_batch(
            model=model,
            optimizer=optimizer,
            scheduler=scheduler,
            X=X, Y=Y,
            h_cache=h_cache,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -