CUDA out of memory

问题

I am getting error when trying to run BERT model for NER task. "CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 3.82 GiB total capacity; 2.58 GiB already allocated; 25.38 MiB free; 6.33 MiB cached)I have also tried reducing batch size to 1c

enter code here
epochs = 10
max_grad_norm = 1.0

for _ in trange(epochs, desc="Epoch"):
    # TRAIN loop
    model.train()
    tr_loss = 0
    nb_tr_examples, nb_tr_steps = 0, 0
    for step, batch in enumerate(train_dataloader):
        # add batch to gpu
        batch = tuple(t.to(device) for t in batch)
        b_input_ids, b_input_mask, b_labels = batch
        # forward pass
        loss = model(b_input_ids, token_type_ids=None,
                     attention_mask=b_input_mask, labels=b_labels)
        # backward pass
        loss.backward()
        # track train loss
        tr_loss += loss.item()
        nb_tr_examples += b_input_ids.size(0)
        nb_tr_steps += 1
        # gradient clipping
        torch.nn.utils.clip_grad_norm_(parameters=model.parameters(), max_norm=max_grad_norm)
        # update parameters
        optimizer.step()
        model.zero_grad()
    # print train loss per epoch
    #print("Train loss: {}".format(tr_loss/nb_tr_steps))
    # VALIDATION on validation set
    model.eval()
    eval_loss, eval_accuracy = 0, 0
    nb_eval_steps, nb_eval_examples = 0, 0
    predictions , true_labels, true_inputs = [], [],[]
    for batch in valid_dataloader:
        batch = tuple(t.to(device) for t in batch)
        b_input_ids, b_input_mask, b_labels = batch

        with torch.no_grad():
            tmp_eval_loss = model(b_input_ids, token_type_ids=None,
                                  attention_mask=b_input_mask, labels=b_labels)
            logits = model(b_input_ids, token_type_ids=None,
                           attention_mask=b_input_mask)
        logits = logits.detach().cpu().numpy()
        label_ids = b_labels.to('cpu').numpy()
        inputs = b_input_ids.to('cpu').numpy()

        true_inputs.append(inputs)
        predictions.extend([list(p) for p in np.argmax(logits, axis=2)])
        true_labels.append(label_ids)

        tmp_eval_accuracy = flat_accuracy(logits, label_ids)

        eval_loss += tmp_eval_loss.mean().item()
        eval_accuracy += tmp_eval_accuracy

        nb_eval_examples += b_input_ids.size(0)
        nb_eval_steps += 1
    eval_loss = eval_loss/nb_eval_steps
    pred_tags = [tags_vals[p_i] for p in predictions for p_i in p]
    valid_tags = [tags_vals[l_ii] for l in true_labels for l_i in l for l_ii in l_i]
    valid_inputs = [[idx2word[l_ii] for l_ii in l_i] for l in  true_inputs  for l_i in l ]


    print("F1-Score: {}".format(f1_score(pred_tags, valid_tags)))
    print("Validation loss: {}".format(eval_loss))
    print("Validation Accuracy: {}".format(eval_accuracy/nb_eval_steps))

Attached is the output of nvidia-smi:-

nvidia-smi

来源：https://stackoverflow.com/questions/60926878/cuda-out-of-memory