Train Error

[LuluW8071]

Resolving calling of lr_scheduler.step() before optimizer.step()
In PyTorch 1.1.0 and later,
you should call them in the opposite order: optimizer.step() before lr_scheduler.step().

[LuluW8071]

Optimizer param error

[LuluW8071]

GPU warn is solved

[LuluW8071]

Resolved Above Issues.
Training Epoch shows no warning and no exits.

[LuluW8071]

If Train Epoch exits due to less GPU memory

decrease batch_size to 32

parser.add_argument('--batch_size', default=64, type=int, help='size of batch')

Also, if train.json and test.json are too less
REPLACE

val_check_interval=args.valid_every

WITH

val_check_interval=10