T5DST/T5.py [111:153]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    train_loader, val_loader, test_loader, ALL_SLOTS, fewshot_loader_dev, fewshot_loader_test = prepare_data(args, task.tokenizer)

    #save model path
    save_path = os.path.join(args["saving_dir"],args["model_name"])
    if not os.path.exists(save_path):
        os.makedirs(save_path)

    trainer = Trainer(
                    default_root_dir=save_path,
                    accumulate_grad_batches=args["gradient_accumulation_steps"],
                    gradient_clip_val=args["max_norm"],
                    max_epochs=args["n_epochs"],
                    callbacks=[pl.callbacks.EarlyStopping(monitor='val_loss',min_delta=0.00, patience=5,verbose=False, mode='min')],
                    gpus=args["GPU"],
                    deterministic=True,
                    num_nodes=1,
                    #precision=16,
                    accelerator="ddp"
                    )

    trainer.fit(task, train_loader, val_loader)

    task.model.save_pretrained(save_path)
    task.tokenizer.save_pretrained(save_path)

    print("test start...")
    #evaluate model
    _ = evaluate_model(args, task.tokenizer, task.model, test_loader, save_path, ALL_SLOTS)

def evaluate_model(args, tokenizer, model, test_loader, save_path, ALL_SLOTS, prefix="zeroshot"):
    save_path = os.path.join(save_path,"results")
    if not os.path.exists(save_path):
        os.makedirs(save_path)
    predictions = {}
    # to gpu
    # gpu = args["GPU"][0]
    device = torch.device("cuda:0")
    model.to(device)
    model.eval()

    slot_logger = {slot_name:[0,0,0] for slot_name in ALL_SLOTS}

    for batch in tqdm(test_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



T5DST/train_GPT.py [90:133]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    train_loader, val_loader, test_loader, ALL_SLOTS, fewshot_loader_dev, fewshot_loader_test = prepare_data(args, task.tokenizer)

    #save model
    save_path = os.path.join(args["saving_dir"],args["model_name"])
    if not os.path.exists(save_path):
        os.makedirs(save_path)

    trainer = Trainer(
                    default_root_dir=save_path,
                    accumulate_grad_batches=args["gradient_accumulation_steps"],
                    gradient_clip_val=args["max_norm"],
                    max_epochs=args["n_epochs"],
                    callbacks=[pl.callbacks.EarlyStopping(monitor='val_loss',min_delta=0.00, patience=5,verbose=False, mode='min')],
                    gpus=args["GPU"],
                    deterministic=True,
                    num_nodes=1,
                    accelerator="ddp"
                    )

    trainer.fit(task, train_loader, val_loader)


    task.model.save_pretrained(save_path)
    task.tokenizer.save_pretrained(save_path)

    print("test start...")
    #evaluate model
    _ = evaluate_model(args, task.tokenizer, task.model, test_loader, save_path, ALL_SLOTS)



def evaluate_model(args, tokenizer, model, test_loader, save_path, ALL_SLOTS, prefix="zeroshot"):
    save_path = os.path.join(save_path,"results")
    if not os.path.exists(save_path):
        os.makedirs(save_path)
    predictions = {}
    # to gpu
    device = torch.device("cuda:0")
    model.to(device)
    model.eval()

    slot_logger = {slot_name:[0,0,0] for slot_name in ALL_SLOTS}

    for batch in tqdm(test_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -