Cuda Out of Memory Error even after reducing the batch size

Question

I'm trying to train a deep learning model in Azure Notebook which uses GPU from the DSVM-Ubuntu 18.04 which consists of Standard NC6 (6 vcpus, 56 GiB memory) and is getting the following Error:

RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB (GPU 0; 11.17 GiB total capacity; 10.76 GiB already allocated; 50.31 MiB free; 10.84 GiB reserved in total by PyTorch)

I've searched on this regard and couldn't find any solution in any of the questions on the web. And '10.84 GiB reserved in total by PyTorch' in the error message caught my attention, whether this can be configured to have a low memory value? I would like to receive any opinions in this regard. thank you.

This is my Code for Fine-tuning/training

for epoch in range(EPOCHS):

    for idx,article in tqdm_notebook(enumerate(article_loader)):

        article_tens = torch.tensor(tokenizer.encode(article[0], max_length=1024)).unsqueeze(0).to(device)

        outputs = model(article_tens, labels=article_tens)

        train_loss, prediction_scores = outputs[:2]                        
        train_loss.backward()
        train_sum_loss = train_sum_loss + train_loss.detach().data

        iteration_count=idx

        article_count = article_count + 1
        if article_count == BATCH_SIZE:
            article_count = 0    
            batch_count += 1
            optimizer.step()
            scheduler.step() 
            optimizer.zero_grad()
            model.zero_grad()

Whole Stack-trace of the error:

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-11-2c74a22e42f7> in <module>
     20         article_tens = torch.tensor(tokenizer.encode(article[0], max_length=1024)).unsqueeze(0).to(device)
     21 
---> 22         outputs = model(article_tens, labels=article_tens)
     23 
     24         train_loss, prediction_scores = outputs[:2]

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/transformers/modeling_gpt2.py in forward(self, input_ids, past, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, use_cache)
    602             head_mask=head_mask,
    603             inputs_embeds=inputs_embeds,
--> 604             use_cache=use_cache,
    605         )
    606         hidden_states = transformer_outputs[0]

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/transformers/modeling_gpt2.py in forward(self, input_ids, past, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, use_cache)
    486                 attention_mask=attention_mask,
    487                 head_mask=head_mask[i],
--> 488                 use_cache=use_cache,
    489             )
    490 

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/transformers/modeling_gpt2.py in forward(self, x, layer_past, attention_mask, head_mask, use_cache)
    240 
    241         x = x + a
--> 242         m = self.mlp(self.ln_2(x))
    243         x = x + m
    244 

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/transformers/modeling_gpt2.py in forward(self, x)
    215 
    216     def forward(self, x):
--> 217         h = self.act(self.c_fc(x))
    218         h2 = self.c_proj(h)
    219         return self.dropout(h2)

/anaconda/envs/py37_pytorch/lib/python3.7/site-packages/transformers/activations.py in gelu_new(x)
     27         Also see https://arxiv.org/abs/1606.08415
     28     """
---> 29     return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
     30 
     31 

RuntimeError: CUDA out of memory. Tried to allocate 16.00 MiB (GPU 0; 11.17 GiB total capacity; 10.74 GiB already allocated; 320.00 KiB free; 10.89 GiB reserved in total by PyTorch)