Fine-Tuning DistilBertForSequenceClassification：不是学习，为什么loss没有变化？权重没有更新？

我对 PyTorch 和 Huggingface-transformers 比较陌生，并对此尝试了 DistillBertForSequenceClassificationKaggle-数据集 https://www.kaggle.com/c/nlp-getting-started.

from transformers import DistilBertForSequenceClassification
import torch.optim as optim
import torch.nn as nn
from transformers import get_linear_schedule_with_warmup

n_epochs = 5 # or whatever
batch_size = 32 # or whatever

bert_distil = DistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')
#bert_distil.classifier = nn.Sequential(nn.Linear(in_features=768, out_features=1), nn.Sigmoid())
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(bert_distil.parameters(), lr=0.1)

X_train = []
Y_train = []

for row in train_df.iterrows():
    seq = tokenizer.encode(preprocess_text(row[1]['text']),  add_special_tokens=True, pad_to_max_length=True)
    X_train.append(torch.tensor(seq).unsqueeze(0))
    Y_train.append(torch.tensor([row[1]['target']]).unsqueeze(0))
X_train = torch.cat(X_train)
Y_train = torch.cat(Y_train)

running_loss = 0.0
bert_distil.cuda()
bert_distil.train(True)
for epoch in range(n_epochs):
    permutation = torch.randperm(len(X_train))
    j = 0
    for i in range(0,len(X_train), batch_size):
        optimizer.zero_grad()
        indices = permutation[i:i+batch_size]
        batch_x, batch_y = X_train[indices], Y_train[indices]
        batch_x.cuda()
        batch_y.cuda()
        outputs = bert_distil.forward(batch_x.cuda())
        loss = criterion(outputs[0],batch_y.squeeze().cuda())
        loss.requires_grad = True
   
        loss.backward()
        optimizer.step()
   
        running_loss += loss.item()  
        j+=1
        if j == 20:   
            #print(outputs[0])
            print('[%d, %5d] running loss: %.3f loss: %.3f ' %
              (epoch + 1, i*1, running_loss / 20, loss.item()))
            running_loss = 0.0
            j = 0

[1, 608] 运行损失：0.689 损失：0.687 [1、1248]运行损失：0.693 损失：0.694 [1, 1888] 运行损失：0.693 损失：0.683 [1, 2528] 运行损失：0.689 损失：0.701 [1、3168]运行损失：0.690 损失：0.684 [1、3808]运行损失：0.689 损失：0.688 [1, 4448] 运行损失：0.689 损失：0.692 等等...

无论我尝试什么，损失从未减少，甚至增加，预测也没有变得更好。在我看来，我忘记了一些事情，所以权重实际上没有更新。有人有主意吗？ 氧

我尝试过什么

• Different loss functions
  • BCE
  • 交叉熵
  • 甚至MSE损失
• One-Hot 编码与单个神经元输出
• 不同的学习率和优化器
• 我什至将所有目标更改为只有一个标签，但即便如此，网络也没有收敛。

关注运行损失和小批量损失很容易产生误导。您应该查看纪元损失，因为每个损失的输入都是相同的。

此外，您的代码中存在一些问题，修复所有这些问题并且行为符合预期：每个时期后损失缓慢减少，并且它也可能过度适合小批量。请看代码，改动包括：使用model(x)代替model.forward(x), cuda()只调用一次，较小的学习率等。

调整和微调 ML 模型是一项艰巨的工作。

n_epochs = 5
batch_size = 1

bert_distil = DistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(bert_distil.parameters(), lr=1e-3)

X_train = []
Y_train = []
for row in train_df.iterrows():
    seq = tokenizer.encode(row[1]['text'],  add_special_tokens=True, pad_to_max_length=True)[:100]
    X_train.append(torch.tensor(seq).unsqueeze(0))
    Y_train.append(torch.tensor([row[1]['target']]))
X_train = torch.cat(X_train)
Y_train = torch.cat(Y_train)

running_loss = 0.0
bert_distil.cuda()
bert_distil.train(True)
for epoch in range(n_epochs):
    permutation = torch.randperm(len(X_train))
    for i in range(0,len(X_train), batch_size):
        optimizer.zero_grad()
        indices = permutation[i:i+batch_size]
        batch_x, batch_y = X_train[indices].cuda(), Y_train[indices].cuda()
        outputs = bert_distil(batch_x)
        loss = criterion(outputs[0], batch_y)
        loss.backward()
        optimizer.step()
   
        running_loss += loss.item()  

    print('[%d] epoch loss: %.3f' %
      (epoch + 1, running_loss / len(X_train) * batch_size))
    running_loss = 0.0

Output:

[1] epoch loss: 0.695
[2] epoch loss: 0.690
[3] epoch loss: 0.687
[4] epoch loss: 0.685
[5] epoch loss: 0.684