编码bert时Colab崩溃

Question

我正在尝试使用BERT进行培训 这是创建遮罩的代码

def bert_encode(texts, tokenizer, max_len=512):
    all_tokens = []
    all_masks = []
    all_segments = []

    for text in texts:
        text = tokenizer.tokenize(text)

        text = text[:max_len-2]
        input_sequence = ["[CLS]"] + text + ["[SEP]"]
        pad_len = max_len - len(input_sequence)

        tokens = tokenizer.convert_tokens_to_ids(input_sequence)
        tokens += [0] * pad_len
        pad_masks = [1] * len(input_sequence) + [0] * pad_len
        segment_ids = [0] * max_len

        all_tokens.append(tokens)
        all_masks.append(pad_masks)
        all_segments.append(segment_ids)

    return np.array(all_tokens), np.array(all_masks), np.array(all_segments)

当我运行它

train_input = bert_encode(train.text.values, tokenizer, max_len=160)
test_input = bert_encode(test.tweet.values, tokenizer, max_len=160)
train_labels = train.average.values

由于ram用完了，我的Google colab崩溃了。任何解决方案