Error while Using Mutiple GPUs

I am trying to train a model and It works fine with GPU = 1. But if I am using more than 1 GPU, or using num_worker more than 0, I am getting following error :

`-- Process 3 terminated with the following error:
Traceback (most recent call last):
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 20, in _wrap
fn(i, *args)
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/accelerators/ddp_spawn_accelerator.py", line 152, in ddp_train
results = self.train_or_test()
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 66, in train_or_test
results = self.trainer.train()
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 483, in train
self.train_loop.run_training_epoch()
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 541, in run_training_epoch
batch_output = self.run_training_batch(batch, batch_idx, dataloader_idx)
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 673, in run_training_batch
opt_closure_result = self.training_step_and_backward(
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 769, in training_step_and_backward
self.backward(result, optimizer, opt_idx)
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 783, in backward
result.closure_loss = self.trainer.accelerator_backend.backward(
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 89, in backward
closure_loss = self.trainer.precision_connector.backend.backward(
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/plugins/native_amp.py", line 32, in backward
model.backward(closure_loss, optimizer, opt_idx)
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/pytorch_lightning/core/lightning.py", line 1105, in backward
loss.backward()
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/torch/tensor.py", line 185, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/pathania/data-private/longformer/lib/python3.8/site-packages/torch/autograd/__init__.py", line 125, in backward
Variable._execution_engine.run_backward(
RuntimeError: Expected to mark a variable ready only once. This error is caused by one of the following reasons: 1) Use of a module parameter outside the `forward` function. Please make sure model parameters are not shared across multiple concurrent forward-backward passes2) Reused parameters in multiple reentrant backward passes. For example, if you use multiple `checkpoint` functions to wrap the same part of your model, it would result in the same set of parameters been used by different reentrant backward passes multiple times, and hence marking a variable ready multiple times. DDP does not support such use cases yet.
Exception raised from mark_variable_ready at /pytorch/torch/csrc/distributed/c10d/reducer.cpp:453 (most recent call first):`

If I am using mutiple gpu with
`trainer = Trainer(gpus=4,auto_lr_find=True,distributed_backend='dp')`
Its give : `TypeError: cannot unpack non-iterable NoneType object
terminate called after throwing an instance of 'c10::Error'
what(): CUDA error: device-side assert triggered`
My code : https://colab.research.google.com/drive/1uj3obOeVysbAxpdAuqXWSScx0EOTefDB?usp=sharing