beiyaoovo

self.train_batch_size = 1 if 'WebNLG' in corpus_type else 4 要改后面那个数字，前面的数字只能修改WebNLG的batchsize

me too...

> me,too I found that this problem can be solved by modifying the learning rate, # learning rate self.fin_tuning_lr = 1e-4 self.downs_en_lr = 1e-3 self.clip_grad = 2. self.drop_prob = 0.3...