Get tag-specific accuracy for pos tagger in spacy tagger evaluation

I'm using the code below for evaluate the pos tagger that I trained in spacy 2.3.0 (built from source- last commit : 9860b8399ed2a3d1d680e1c1cd31d85926422709):

  def evaluate(nlp, examples):
    scorer = Scorer()
    nlp.tokenizer = Tokenizer(nlp.vocab)
    for input_, annot in examples:
        doc_gold_text = nlp.make_doc(input_)
        gold = GoldParse(doc_gold_text, tags=annot['tags'])
        pred_value = nlp(input_)
        scorer.score(pred_value, gold)
    return scorer.scores


def main(model='model'):
    test_data = train_data_getter()[80000:]
    nlp = spacy.load(model)
    # nlp = None
    pp = pprint.PrettyPrinter()
    pp.pprint(evaluate(nlp, test_data))

and the result is:

 {'ents_f': 0.0,
 'ents_p': 0.0,
 'ents_per_type': {},
 'ents_r': 0.0,
 'las': 0.0,
 'las_per_type': {'': {'f': 0.0, 'p': 0.0, 'r': 0.0}},
 'tags_acc': 88.9152111081426,
 'textcat_score': 0.0,
 'textcats_per_cat': {},
 'token_acc': 100.0,
 'uas': 0.0}

I wonder if there is a way to get accuracy per every part-of-speech tag?