from torch import tensor
from torchmetrics.text.bert import BERTScore
preds = ["hello there", "general kenobi"]
target = ["hello there", "master kenobi"]
metric = BERTScore()
values = []
for _ in range(10):
    val = metric(preds, target)
    val = {k: tensor(v).mean() for k,v in val.items()}  # convert into single value per key
    values.append(val)
fig_, ax_ = metric.plot(values)