我正在尝试使用 BERT（使用库）微调模型transformers，但我对优化器和调度器有点不确定。
首先，我知道我应该使用transformers.AdamW它而不是 Pytorch 的版本。此外，我们应该使用论文中建议的预热调度程序，因此调度程序是使用包中的get_linear_scheduler_with_warmup函数创建的transformers。
我的主要问题是：
get_linear_scheduler_with_warmup应该在热身时调用。可以在 10 个 epoch 中使用 2 进行热身吗？- 我应该什么时候打电话
scheduler.step()？如果我在之后做train，第一个时期的学习率为零。我应该为每批调用它吗？
我做错了什么吗？
from transformers import AdamW
from transformers.optimization import get_linear_scheduler_with_warmup
N_EPOCHS = 10
model = BertGRUModel(finetune_bert=True,...)
num_training_steps = N_EPOCHS+1
num_warmup_steps = 2
warmup_proportion = float(num_warmup_steps) / float(num_training_steps) # 0.1
optimizer = AdamW(model.parameters())
criterion = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([class_weights[1]]))
scheduler = get_linear_schedule_with_warmup(
optimizer, num_warmup_steps=num_warmup_steps,
num_training_steps=num_training_steps
)
for epoch in range(N_EPOCHS):
scheduler.step() #If I do after train, LR = 0 for the first epoch
print(optimizer.param_groups[0]["lr"])
train(...) # here we call optimizer.step()
evaluate(...)
我的模型和训练例程（和这个笔记本很相似）
class BERTGRUSentiment(nn.Module):
def __init__(self,
bert,
hidden_dim,
output_dim,
n_layers=1,
bidirectional=False,
finetune_bert=False,
dropout=0.2):
super().__init__()
self.bert = bert
embedding_dim = bert.config.to_dict()['hidden_size']
self.finetune_bert = finetune_bert
self.rnn = nn.GRU(embedding_dim,
hidden_dim,
num_layers = n_layers,
bidirectional = bidirectional,
batch_first = True,
dropout = 0 if n_layers < 2 else dropout)
self.out = nn.Linear(hidden_dim * 2 if bidirectional else hidden_dim, output_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, text):
#text = [batch size, sent len]
if not self.finetune_bert:
with torch.no_grad():
embedded = self.bert(text)[0]
else:
embedded = self.bert(text)[0]
#embedded = [batch size, sent len, emb dim]
_, hidden = self.rnn(embedded)
#hidden = [n layers * n directions, batch size, emb dim]
if self.rnn.bidirectional:
hidden = self.dropout(torch.cat((hidden[-2,:,:], hidden[-1,:,:]), dim = 1))
else:
hidden = self.dropout(hidden[-1,:,:])
#hidden = [batch size, hid dim]
output = self.out(hidden)
#output = [batch size, out dim]
return output
import torch
from sklearn.metrics import accuracy_score, f1_score
def train(model, iterator, optimizer, criterion, max_grad_norm=None):
"""
Trains the model for one full epoch
"""
epoch_loss = 0
epoch_acc = 0
model.train()
for i, batch in enumerate(iterator):
optimizer.zero_grad()
text, lens = batch.text
predictions = model(text)
target = batch.target
loss = criterion(predictions.squeeze(1), target)
prob_predictions = torch.sigmoid(predictions)
preds = torch.round(prob_predictions).detach().cpu()
acc = accuracy_score(preds, target.cpu())
loss.backward()
# Gradient clipping
if max_grad_norm:
torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm)
optimizer.step()
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)