def create_and_check_bert_for_sequence_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
config.num_labels = self.num_labels
model = BertForSequenceClassification(config)
model.eval()
loss, logits = model(input_ids, token_type_ids, input_mask, sequence_labels)
result = {
"loss": loss,
"logits": logits,
}
self.parent.assertListEqual(
list(result["logits"].size()),
[self.batch_size, self.num_labels])
self.check_loss_output(result)
pred = torch.argmax(F.softmax(logits, dim=1), dim=1)
correct = pred.eq(batch.label)
total_correct += correct.sum().item()
total_len += len(batch.label)
total_loss += loss.item()
loss.backward()
optimizer.step()
print(
f" Train Accuracy: {total_correct / total_len:.3f}, Loss: {total_loss / total_len:.4f}"
)
total_loss = 0
total_len = 0
total_correct = 0
model.eval()
for batch in test_iterator:
outputs = model(batch.text, labels=batch.label)
loss, logits = outputs
pred = torch.argmax(F.softmax(logits, dim=1), dim=1)
correct = pred.eq(batch.label)
total_correct += correct.sum().item()
total_len += len(batch.label)
print(f" Test Accuracy: {total_correct / total_len:.3f}")
total_len = 0
total_correct = 0
itr += 1
