from torch import randn, randint
from torchmetrics.classification import MulticlassCalibrationError
metric = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='l1')
values = []
for _ in range(20):
    values.append(metric(randn(20,3).softmax(dim=-1), randint(3, (20,))))
fig_, ax_ = metric.plot(values)