name: medium_model best_checkpoint_path: ./outputs/checkpoints/medium_model/best.ckpt latest_checkpoint_path: ./outputs/checkpoints/medium_model/latest.ckpt tokenizer: bpe_16k d_model: 1024 num_heads: 16 num_layers: 8 d_ff: 2048 dropout_rate: 0.1 vocab_size: 16384 max_seq_len: 128 pad_id: 0 bos_id: 1 eos_id: 2 layer_norm_style: pre