i want to train this model on colab and it has 1000 epoches ..but its takes too long.

this is my code with python:

its training a model for 1000 epoches ,

and i want to save epoches every 20 times(for example) and load model again and continue from last epoch .

example : train from 1 to 20 , then save model…then load model and continue from 20 to 40 and so .

for epoch in range(NUM_EPOCHS):
  hidden,cell = model.init_hidden(batch_size=TRAIN_BATCH_SIZE)
  train(model, device, train_loader, optimizer, epoch+1,hidden,cell)
  G,P = predicting(model, device, test_loader,hidden,cell)
  ret = [rmse(G,P),mse(G,P),pearson(G,P),spearman(G,P),ci(G,P),get_rm2(G.reshape(G.shape[0],-1),P.reshape(P.shape[0],-1))]
  if ret[1]<best_mse:
    if args.save_file:
      model_file_name = args.save_file + '.model'
      torch.save(model.state_dict(), model_file_name)
    
    
    with open(result_file_name,'w') as f:
      f.write('rmse,mse,pearson,spearman,ci,rm2n')
      f.write(','.join(map(str,ret)))
    best_epoch = epoch+1
    best_mse = ret[1]
    best_ci = ret[-2]
    print('rmse improved at epoch ', best_epoch, '; best_mse,best_ci:', best_mse,best_ci,model_st,dataset)
  else:
    print(ret[1],'No improvement since epoch ', best_epoch, '; best_mse,best_ci:', best_mse,best_ci,model_st,dataset)

what shoud i do for my code ?