finetune.py 文件源码

def train():
    # Turn on training mode which enables dropout.
    if args.model == 'QRNN': model.reset()
    total_loss = 0
    start_time = time.time()
    ntokens = len(corpus.dictionary)
    hidden = model.init_hidden(args.batch_size)
    batch, i = 0, 0
    while i < train_data.size(0) - 1 - 1:
        bptt = args.bptt if np.random.random() < 0.95 else args.bptt / 2.
        # Prevent excessively small or negative sequence lengths
        seq_len = max(5, int(np.random.normal(bptt, 5)))
        # There's a very small chance that it could select a very long sequence length resulting in OOM
        seq_len = min(seq_len, args.bptt + 10)

        lr2 = optimizer.param_groups[0]['lr']
        optimizer.param_groups[0]['lr'] = lr2 * seq_len / args.bptt
        model.train()
        data, targets = get_batch(train_data, i, args, seq_len=seq_len)

        # Starting each batch, we detach the hidden state from how it was previously produced.
        # If we didn't, the model would try backpropagating all the way to start of the dataset.
        hidden = repackage_hidden(hidden)
        optimizer.zero_grad()

        output, hidden, rnn_hs, dropped_rnn_hs = model(data, hidden, return_h=True)
        raw_loss = criterion(output.view(-1, ntokens), targets)

        loss = raw_loss
        # Activiation Regularization
        loss = loss + sum(args.alpha * dropped_rnn_h.pow(2).mean() for dropped_rnn_h in dropped_rnn_hs[-1:])
        # Temporal Activation Regularization (slowness)
        loss = loss + sum(args.beta * (rnn_h[1:] - rnn_h[:-1]).pow(2).mean() for rnn_h in rnn_hs[-1:])
        loss.backward()

        # `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs.
        torch.nn.utils.clip_grad_norm(model.parameters(), args.clip)
        optimizer.step()

        total_loss += raw_loss.data
        optimizer.param_groups[0]['lr'] = lr2
        if batch % args.log_interval == 0 and batch > 0:
            cur_loss = total_loss[0] / args.log_interval
            elapsed = time.time() - start_time
            print('| epoch {:3d} | {:5d}/{:5d} batches | lr {:02.2f} | ms/batch {:5.2f} | '
                    'loss {:5.2f} | ppl {:8.2f}'.format(
                epoch, batch, len(train_data) // args.bptt, optimizer.param_groups[0]['lr'],
                elapsed * 1000 / args.log_interval, cur_loss, math.exp(cur_loss)))
            total_loss = 0
            start_time = time.time()
        ###
        batch += 1
        i += seq_len


# Load the best saved model.