Binary classification of IMDB data using Transformer model pytorch에 있는 Transformer Layer 연습 setting torch == 1.12.0+cu116 datasets == 2.3.2 tqdm == 4.62.3 nltk == 3.6.5 Hyper Parameter Setting (Default) attn_heads: 4 epoch: 100 batch_size: 32 hidden_size: 64 max_len: 200 learning_rate: 0.001