本节代码将展示如何在预训练的BERT模型基础上进行微调，以适应特定的下游任务。
⭐学习建议直接看文章最后的需复现代码，不懂得地方再回看
微调是自然语言处理中常见的方法，通过在预训练模型的基础上添加额外的层，并在特定任务的数据集上进行训练，可以快速适应新的任务。以下是从模型微调的角度对代码的详细说明：
1. 加载预训练模型
self.bert = BertModel.from_pretrained(model_path)-
预训练模型：使用
transformers库的BertModel.from_pretrained方法加载一个预训练的BERT模型。model_path是预训练模型的路径或名称，例如"bert-base-chinese"。 -
优势：
-
预训练模型已经在大规模语料上进行了训练，学习了通用的语言表示。
-
微调可以利用这些预训练的参数，快速适应新的任务，通常只需要较少的数据和训练时间。
-
2. 添加任务特定的头
self.mlm_head = nn.Linear(d_model, vocab_size)
self.nsp_head = nn.Linear(d_model, 2)-
MLM头：
mlm_head是一个线性层，用于预测被掩盖的单词。输入是BERT模型的输出，输出是词汇表大小的预测概率。 -
NSP头：
nsp_head是一个线性层，用于预测两个句子是否相邻。输入是BERT模型的[CLS]标记的输出，输出是二分类的概率。
3. 前向传播
def forward(self, mlm_tok_ids, seg_ids, mask):bert_out = self.bert(mlm_tok_ids, seg_ids, mask)output = bert_out.last_hidden_statecls_token = output[:, 0, :]mlm_logits = self.mlm_head(output)nsp_logits = self.nsp_head(cls_token)return mlm_logits, nsp_logits-
BERT模型的输出：
-
bert_out.last_hidden_state：BERT模型的输出，形状为(batch_size, seq_len, d_model)。 -
[CLS]标记的输出：output[:, 0, :]，用于NSP任务。
-
-
任务特定的输出：
-
mlm_logits：MLM任务的预测结果。 -
nsp_logits：NSP任务的预测结果。
-
4. 数据处理
class BERTDataset(Dataset):def __init__(self, nsp_dataset, tokenizer: BertTokenizer, max_length):self.nsp_dataset = nsp_datasetself.tokenizer = tokenizerself.max_length = max_lengthself.cls_id = tokenizer.cls_token_idself.sep_id = tokenizer.sep_token_idself.pad_id = tokenizer.pad_token_idself.mask_id = tokenizer.mask_token_iddef __getitem__(self, idx):sent1, sent2, nsp_label = self.nsp_dataset[idx]sent1_ids = self.tokenizer.encode(sent1, add_special_tokens=False)sent2_ids = self.tokenizer.encode(sent2, add_special_tokens=False)tok_ids = [self.cls_id] + sent1_ids + [self.sep_id] + sent2_ids + [self.sep_id]seg_ids = [0]*(len(sent1_ids)+2) + [1]*(len(sent2_ids) + 1)mlm_tok_ids, mlm_labels = self.build_mlm_dataset(tok_ids)mlm_tok_ids = self.pad_to_seq_len(mlm_tok_ids, 0)seg_ids = self.pad_to_seq_len(seg_ids, 2)mlm_labels = self.pad_to_seq_len(mlm_labels, -100)mask = (mlm_tok_ids != 0)return {"mlm_tok_ids": mlm_tok_ids,"seg_ids": seg_ids,"mask": torch.tensor(mask, dtype=torch.long),"mlm_labels": mlm_labels,"nsp_labels": torch.tensor(nsp_label)}-
数据处理：
-
将文本数据转换为词索引（
tok_ids）。 -
添加特殊标记（
[CLS]和[SEP]）。 -
生成段嵌入（
seg_ids）。 -
生成MLM任务的数据（
mlm_tok_ids和mlm_labels）。 -
填充或截断序列到固定长度（
max_length）。
-
-
掩码：生成掩码，用于标记哪些位置是有效的输入（非填充部分）。
5. 训练过程
for epoch in range(epochs):for batch in tqdm(trainloader, desc="Training"):batch_mlm_tok_ids = batch["mlm_tok_ids"]batch_seg_ids = batch["seg_ids"]batch_mask = batch["mask"]batch_mlm_labels = batch["mlm_labels"]batch_nsp_labels = batch["nsp_labels"]mlm_logits, nsp_logits = model(batch_mlm_tok_ids, batch_seg_ids, batch_mask)loss_mlm = loss_fn(mlm_logits.view(-1, vocab_size), batch_mlm_labels.view(-1))loss_nsp = loss_fn(nsp_logits, batch_nsp_labels)loss = loss_mlm + loss_nsploss.backward()optim.step()optim.zero_grad()print("Epoch: {}, MLM Loss: {}, NSP Loss: {}".format(epoch, loss_mlm, loss_nsp))-
训练步骤：
-
前向传播：将输入数据通过模型，得到MLM和NSP任务的预测结果。
-
计算损失：分别计算MLM和NSP任务的损失。
-
反向传播：计算梯度并更新模型参数。
-
优化器：使用Adam优化器，学习率设置为
1e-3。
-
-
进度条：使用
tqdm显示训练进度，使训练过程更加直观。
6. 微调的优势
-
快速适应新任务：预训练模型已经学习了通用的语言表示，微调可以快速适应新的任务，通常只需要较少的数据和训练时间。
-
节省计算资源：从头训练BERT模型需要大量的计算资源和时间，而微调只需要在预训练模型的基础上进行少量的训练。
-
更好的性能：预训练模型在大规模数据上进行了训练，通常具有更好的性能。微调可以进一步提升模型在特定任务上的表现。
需复现代码
import re
import math
import torch
import random
import torch.nn as nnfrom tqdm import tqdm
from transformers import BertTokenizer, BertModel
from torch.utils.data import Dataset, DataLoaderclass BERT(nn.Module):def __init__(self, vocab_size, d_model, seq_len, N_blocks, num_heads, dropout, dff):super().__init__()self.bert = BertModel.from_pretrained(model_path)self.mlm_head = nn.Linear(d_model, vocab_size)self.nsp_head = nn.Linear(d_model, 2)def forward(self, mlm_tok_ids, seg_ids, mask):bert_out = self.bert(mlm_tok_ids, seg_ids, mask)output = bert_out.last_hidden_statecls_token = output[:, 0, :]mlm_logits = self.mlm_head(output)nsp_logits = self.nsp_head(cls_token)return mlm_logits, nsp_logitsdef read_data(file):with open(file, "r", encoding="utf-8") as f:data = f.read().strip().replace("\n", "")corpus = re.split(r'[。，“”：；！、]', data)corpus = [sentence for sentence in corpus if sentence.strip()]return corpusdef create_nsp_dataset(corpus):nsp_dataset = []for i in range(len(corpus)-1):next_sentence = corpus[i+1]rand_id = random.randint(0, len(corpus) - 1)while abs(rand_id - i) <= 1:rand_id = random.randint(0, len(corpus) - 1)negt_sentence = corpus[rand_id]nsp_dataset.append((corpus[i], next_sentence, 1)) # 正样本nsp_dataset.append((corpus[i], negt_sentence, 0)) # 负样本return nsp_datasetclass BERTDataset(Dataset):def __init__(self, nsp_dataset, tokenizer: BertTokenizer, max_length):self.nsp_dataset = nsp_datasetself.tokenizer = tokenizerself.max_length = max_lengthself.cls_id = tokenizer.cls_token_idself.sep_id = tokenizer.sep_token_idself.pad_id = tokenizer.pad_token_idself.mask_id = tokenizer.mask_token_iddef __len__(self):return len(self.nsp_dataset)def __getitem__(self, idx):sent1, sent2, nsp_label = self.nsp_dataset[idx]sent1_ids = self.tokenizer.encode(sent1, add_special_tokens=False)sent2_ids = self.tokenizer.encode(sent2, add_special_tokens=False)tok_ids = [self.cls_id] + sent1_ids + [self.sep_id] + sent2_ids + [self.sep_id]seg_ids = [0]*(len(sent1_ids)+2) + [1]*(len(sent2_ids) + 1)mlm_tok_ids, mlm_labels = self.build_mlm_dataset(tok_ids)mlm_tok_ids = self.pad_to_seq_len(mlm_tok_ids, 0)seg_ids = self.pad_to_seq_len(seg_ids, 2)mlm_labels = self.pad_to_seq_len(mlm_labels, -100)mask = (mlm_tok_ids != 0)return {"mlm_tok_ids": mlm_tok_ids,"seg_ids": seg_ids,"mask": torch.tensor(mask, dtype=torch.long),"mlm_labels": mlm_labels,"nsp_labels": torch.tensor(nsp_label)}def pad_to_seq_len(self, seq, pad_value):seq = seq[:self.max_length]pad_num = self.max_length - len(seq)return torch.tensor(seq + pad_num * [pad_value], dtype=torch.long)def build_mlm_dataset(self, tok_ids):mlm_tok_ids = tok_ids.copy()mlm_labels = [-100] * len(tok_ids)for i in range(len(tok_ids)):if tok_ids[i] not in [self.cls_id, self.sep_id, self.pad_id]:if random.random() < 0.15:mlm_labels[i] = tok_ids[i]if random.random() < 0.8:mlm_tok_ids[i] = self.mask_idelif random.random() < 0.9:mlm_tok_ids[i] = random.randint(106, self.tokenizer.vocab_size - 1)return mlm_tok_ids, mlm_labelsif __name__ == "__main__":data_file = "4.10-BERT/背影.txt"model_path = "/Users/azen/Desktop/llm/models/bert-base-chinese"tokenizer = BertTokenizer.from_pretrained(model_path)corpus = read_data(data_file)max_length = 25 # len(max(corpus, key=len))print("Max length of dataset: {}".format(max_length))nsp_dataset = create_nsp_dataset(corpus)trainset = BERTDataset(nsp_dataset, tokenizer, max_length)batch_size = 16trainloader = DataLoader(trainset, batch_size, shuffle=True)vocab_size = tokenizer.vocab_sized_model = 768N_blocks = 2num_heads = 12dropout = 0.1dff = 4*d_modelmodel = BERT(vocab_size, d_model, max_length, N_blocks, num_heads, dropout, dff)lr = 1e-3optim = torch.optim.Adam(model.parameters(), lr=lr)loss_fn = nn.CrossEntropyLoss()epochs = 20for epoch in range(epochs):for batch in tqdm(trainloader, desc = "Training"):batch_mlm_tok_ids = batch["mlm_tok_ids"]batch_seg_ids = batch["seg_ids"]batch_mask = batch["mask"]batch_mlm_labels = batch["mlm_labels"]batch_nsp_labels = batch["nsp_labels"]mlm_logits, nsp_logits = model(batch_mlm_tok_ids, batch_seg_ids, batch_mask)loss_mlm = loss_fn(mlm_logits.view(-1, vocab_size), batch_mlm_labels.view(-1))loss_nsp = loss_fn(nsp_logits, batch_nsp_labels)loss = loss_mlm + loss_nsploss.backward()optim.step()optim.zero_grad()print("Epoch: {}, MLM Loss: {}, NSP Loss: {}".format(epoch, loss_mlm, loss_nsp))passpass
