Cross validation visualization

Hi, i tried to make the graphics for the cross validation. but i dont know how i can do this.

all_preds = []

for i in range(3):
dls = get_data(i,256,64)
learn = cnn_learner(dls, resnet34, metrics=[partial(accuracy_multi, thresh=0.2),partial(F_score, threshold=0.2)],cbs=mixup).to_fp16()
learn.fit_one_cycle(1, cbs=EarlyStoppingCallback(monitor=‘valid_loss’))
learn.dls = get_data(i,512,32)
learn.fine_tune(1,cbs=EarlyStoppingCallback(monitor=‘valid_loss’))
tst_dl = learn.dls.test_dl(tstpng)
preds, _ = learn.get_preds(dl=tst_dl)
all_preds.append(preds)
del learn
torch.cuda.empty_cache()
gc.collect()

as you can see, i have 3 folds and i wanna make graphics in one plot to compare to each loss.
how can i do this?