vocab,
is_factorized=args.is_factorized,
r=args.r)
else:
logging.info("The model is not supported, check args --h")
loss_type = args.loss
if USE_CUDA:
model = model.cuda()
logging.info(model)
num_epochs = args.epochs
print("Parameters: {}(trainable), {}(non-trainable)".format(
compute_num_params(model)[0],
compute_num_params(model)[1]))
trainer = JointTrainer()
trainer.train(model,
vocab,
train_data_list,
valid_loader_list,
loss_type,
start_epoch,
num_epochs,
args,
evaluate_every=args.evaluate_every,
last_metrics=metrics,
early_stop=args.early_stop,
cpu_state_dict=args.cpu_state_dict,
valid_loader = AudioDataLoader(pad_token_id=0, dataset=valid_data, num_workers=args.num_workers)
valid_loader_list.append(valid_loader)
start_epoch = 0
metrics = None
loaded_args = None
if args.continue_from != "":
logging.info("Continue from checkpoint:" + args.continue_from)
model, vocab, opt, epoch, metrics, loaded_args = load_model(args.continue_from)
start_epoch = (epoch) # index starts from zero
verbose = args.verbose
else:
if args.model == "TRFS":
model = init_transformer_model(args, vocab, is_factorized=args.is_factorized, r=args.r)
opt = init_optimizer(args, model, "noam")
else:
logging.info("The model is not supported, check args --h")
loss_type = args.loss
if USE_CUDA:
model = model.cuda()
logging.info(model)
num_epochs = args.epochs
print("Parameters: {}(trainable), {}(non-trainable)".format(compute_num_params(model)[0], compute_num_params(model)[1]))
trainer = Trainer()
trainer.train(model, vocab, train_loader, train_sampler, valid_loader_list, opt, loss_type, start_epoch, num_epochs, args, metrics, early_stop=args.early_stop)