My aim is to make a five-category text classification
I am running transformers fine tuning bert with cnnbase
model but my program stops at loss.backward()
without any prompt in cmd
.
I debug find that the program stop at the loss.backward line without any error prompt
My program executed successfully in rnn base
such as lstm
and rcnn
.
But when I am running some cnnbase
model the strange bug appears.
My cnn model code:
import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers.modeling_bert import BertPreTrainedModel, BertModel
n_filters = 200
filter_sizes = [2,3,4]
class BertCNN(BertPreTrainedModel):
def __init__(self, config):
super(BertPreTrainedModel, self).__init__(config)
self.num_filters = n_filters
self.filter_sizes = filter_sizes
self.bert = BertModel(config)
for param in self.bert.parameters():
param.requires_grad = True
self.convs = nn.ModuleList(
[nn.Conv2d(1, self.num_filters, (k, config.hidden_size))
for k in self.filter_sizes])
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.fc_cnn = nn.Linear(self.num_filters *
len(self.filter_sizes), config.num_labels)
def conv_and_pool(self, x, conv):
x = F.relu(conv(x)).squeeze(3)
x = F.max_pool1d(x, x.size(2)).squeeze(2)
return x
def forward(self, input_ids,
attention_mask=None, token_type_ids=None, head_mask=None):
outputs = self.bert(input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
head_mask=head_mask)
encoder_out, text_cls = outputs
out = encoder_out.unsqueeze(1)
out = torch.cat([self.conv_and_pool(out, conv)
for conv in self.convs], 1)
out = self.dropout(out)
out = self.fc_cnn(out)
return out
My train code:
for step, batch in enumerate(data):
self.model.train()
batch = tuple(t.to(self.device) for t in batch)
input_ids, input_mask, segment_ids, label_ids = batch
print("input_ids, input_mask, segment_ids, label_ids SIZE: \n")
print(input_ids.size(), input_mask.size(),segment_ids.size(), label_ids.size())
# torch.Size([2, 80]) torch.Size([2, 80]) torch.Size([2, 80]) torch.Size([2])
logits = self.model(input_ids, segment_ids, input_mask)
print("logits and label ids size: ",logits.size(), label_ids.size())
# torch.Size([2, 5]) torch.Size([2])
loss = self.criterion(output=logits, target=label_ids) #loss function:CrossEntropyLoss()
if len(self.n_gpu) >= 2:
loss = loss.mean()
if self.gradient_accumulation_steps > 1:
loss = loss / self.gradient_accumulation_steps
if self.fp16:
with amp.scale_loss(loss, self.optimizer) as scaled_loss:
scaled_loss.backward()
clip_grad_norm_(amp.master_params(self.optimizer), self.grad_clip)
else:
loss.backward() # I debug find that the program stop at this line without any error prompt
HELP~!~ 、
I posted my questions on various community platforms,stackoverflow、other github repositories.
No one replied to me.
I changed the batch size to 1 the bug still occured. sad…