import torch
from torchmetrics.multimodal import CLIPScore
metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
values = [ ]
for _ in range(10):
    values.append(metric(torch.randint(255, (3, 224, 224)), "a photo of a cat"))
fig_, ax_ = metric.plot(values)