《昇思25天学习打卡营第22天|基于MindSpore的GPT2文本摘要》

news2024/9/22 3:45:38

#学习打卡第22天#

1. 数据集

1.1 数据下载

使用nlpcc2017摘要数据，内容为新闻正文及其摘要，总计50000个样本。

from mindnlp.utils import http_get
from mindspore.dataset import TextFileDataset

# download dataset
url = 'https://download.mindspore.cn/toolkits/mindnlp/dataset/text_generation/nlpcc2017/train_with_summ.txt'
path = http_get(url, './')

# load dataset
dataset = TextFileDataset(str(path), shuffle=False, num_samples=2500)
dataset.get_dataset_size()

# split into training and testing dataset
train_dataset, test_dataset = dataset.split([0.9, 0.1], randomize=False)

1.2 数据预处理

原始数据格式：

article: [CLS] article_context [SEP]
summary: [CLS] summary_context [SEP]
预处理后的数据格式：

[CLS] article_context [SEP] summary_context [SEP]

import json
import numpy as np
from mindnlp.transformers import BertTokenizer

# preprocess dataset
def process_dataset(dataset, tokenizer, batch_size=6, max_seq_len=1024, shuffle=False):
    def read_map(text):
        data = json.loads(text.tobytes())
        return np.array(data['article']), np.array(data['summarization'])

    def merge_and_pad(article, summary):
        # tokenization
        # pad to max_seq_length, only truncate the article
        tokenized = tokenizer(text=article, text_pair=summary,
                              padding='max_length', truncation='only_first', max_length=max_seq_len)
        return tokenized['input_ids'], tokenized['input_ids']
    
    dataset = dataset.map(read_map, 'text', ['article', 'summary'])
    # change column names to input_ids and labels for the following training
    dataset = dataset.map(merge_and_pad, ['article', 'summary'], ['input_ids', 'labels'])

    dataset = dataset.batch(batch_size)
    if shuffle:
        dataset = dataset.shuffle(batch_size)

    return dataset


# We use BertTokenizer for tokenizing chinese context.
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
len(tokenizer)

train_dataset = process_dataset(train_dataset, tokenizer, batch_size=4)

2. 模型构建

构建GPT2ForSummarization模型

from mindspore import ops
from mindnlp.transformers import GPT2LMHeadModel
from mindspore.nn.learning_rate_schedule import LearningRateSchedule

class LinearWithWarmUp(LearningRateSchedule):
    """
    Warmup-decay learning rate.
    """
    def __init__(self, learning_rate, num_warmup_steps, num_training_steps):
        super().__init__()
        self.learning_rate = learning_rate
        self.num_warmup_steps = num_warmup_steps
        self.num_training_steps = num_training_steps

    def construct(self, global_step):
        if global_step < self.num_warmup_steps:
            return global_step / float(max(1, self.num_warmup_steps)) * self.learning_rate
        return ops.maximum(
            0.0, (self.num_training_steps - global_step) / (max(1, self.num_training_steps - self.num_warmup_steps))
        ) * self.learning_rate

class GPT2ForSummarization(GPT2LMHeadModel):
    def construct(
        self,
        input_ids = None,
        attention_mask = None,
        labels = None,
    ):
        outputs = super().construct(input_ids=input_ids, attention_mask=attention_mask)
        shift_logits = outputs.logits[..., :-1, :]
        shift_labels = labels[..., 1:]
        # Flatten the tokens
        loss = ops.cross_entropy(shift_logits.view(-1, shift_logits.shape[-1]), shift_labels.view(-1), ignore_index=tokenizer.pad_token_id)
        return loss

3. 模型训练

from mindspore import nn
from mindnlp.transformers import GPT2Config, GPT2LMHeadModel

from mindnlp._legacy.engine import Trainer
from mindnlp._legacy.engine.callbacks import CheckpointCallback


num_epochs = 1
warmup_steps = 2000
learning_rate = 1.5e-4
num_training_steps = num_epochs * train_dataset.get_dataset_size()


config = GPT2Config(vocab_size=len(tokenizer))
model = GPT2ForSummarization(config)
# 记录模型参数数量
print('number of model parameters: {}'.format(model.num_parameters()))

lr_scheduler = LinearWithWarmUp(learning_rate=learning_rate, num_warmup_steps=warmup_steps, num_training_steps=num_training_steps)
optimizer = nn.AdamWeightDecay(model.trainable_params(), learning_rate=lr_scheduler)


ckpoint_cb = CheckpointCallback(save_path='checkpoint', ckpt_name='gpt2_summarization',
                                epochs=1, keep_checkpoint_max=2)

trainer = Trainer(network=model, train_dataset=train_dataset,
                  epochs=1, optimizer=optimizer, callbacks=ckpoint_cb)
trainer.set_amp(level='O1')  # 开启混合精度
trainer.run(tgt_columns="labels")

4. 模型推理

def process_test_dataset(dataset, tokenizer, batch_size=1, max_seq_len=1024, max_summary_len=100):
    def read_map(text):
        data = json.loads(text.tobytes())
        return np.array(data['article']), np.array(data['summarization'])

    def pad(article):
        tokenized = tokenizer(text=article, truncation=True, max_length=max_seq_len-max_summary_len)
        return tokenized['input_ids']

    dataset = dataset.map(read_map, 'text', ['article', 'summary'])
    dataset = dataset.map(pad, 'article', ['input_ids'])
    
    dataset = dataset.batch(batch_size)

    return dataset

test_dataset = process_test_dataset(test_dataset, tokenizer, batch_size=1)

model = GPT2LMHeadModel.from_pretrained('./checkpoint/gpt2_summarization_epoch_0.ckpt', config=config)
model.set_train(False)
model.config.eos_token_id = model.config.sep_token_id

i = 0
for (input_ids, raw_summary) in test_dataset.create_tuple_iterator():
    output_ids = model.generate(input_ids, max_new_tokens=50, num_beams=5, no_repeat_ngram_size=2)
    output_text = tokenizer.decode(output_ids[0].tolist())
    print(output_text)
    i += 1
    if i == 1:
        break