{"architecture": "Seq2SeqTransformer", "vocab_size": 30522, "num_layers": 8, "num_heads": 8, "batch_size": 4, "num_epochs": 3} |
{"architecture": "Seq2SeqTransformer", "vocab_size": 30522, "num_layers": 8, "num_heads": 8, "batch_size": 4, "num_epochs": 3} |