config.json

{
    "model_type": "seq2seq_transformer_from_scratch",
    "architecture": "Encoder-Decoder Transformer",
    "framework": "pytorch",
    "source_language": "english",
    "target_language": "luganda",
    "pytorch_model_path": "pytorch_model.bin",
    "src_tokenizer_file": "english_tokenizer.json",
    "trg_tokenizer_file": "luganda_tokenizer.json",
    "model_parameters": {
        "input_dim_vocab_size_src": 10000,
        "output_dim_vocab_size_trg": 10000,
        "hidden_dim": 256,
        "encoder_layers": 3,
        "decoder_layers": 3,
        "encoder_heads": 8,
        "decoder_heads": 8,
        "encoder_pf_dim": 512,
        "decoder_pf_dim": 512,
        "encoder_dropout": 0.1,
        "decoder_dropout": 0.1,
        "max_seq_length": 128
    },
    "special_token_ids": {
        "pad_token_id": 0,
        "sos_token_id": 1,
        "eos_token_id": 2,
        "unk_token_id": 3
    },
    "dataset_used_for_training": "kambale/luganda-english-parallel-corpus",
    "training_epochs": 50,
    "batch_size": 128,
    "learning_rate": 0.0005,
    "best_validation_loss": 1.1906119108200073,
    "bleu_on_test_set": 27.901593935858266
}