| { | |
| "project": { | |
| "name": "MitoSeqGen", | |
| "seed": 42 | |
| }, | |
| "data": { | |
| "raw_dir": "data/raw", | |
| "processed_dir": "data/processed", | |
| "qc_dir": "data/qc_reports", | |
| "splits_dir": "data/splits", | |
| "tokenized_file": "mito_cds_tokenized_augmented.json", | |
| "train_split": "train_augmented.json", | |
| "val_split": "val.json", | |
| "test_split": "test.json" | |
| }, | |
| "model": { | |
| "d_model": 384, | |
| "nhead": 6, | |
| "num_encoder_layers": 6, | |
| "num_decoder_layers": 6, | |
| "dim_feedforward": 1536, | |
| "dropout": 0.1, | |
| "max_position_embeddings": 768 | |
| }, | |
| "training": { | |
| "batch_size": 24, | |
| "gradient_accumulation_steps": 2, | |
| "learning_rate": 0.0003, | |
| "weight_decay": 0.01, | |
| "epochs": 30, | |
| "warmup_steps": 1000, | |
| "early_stopping_patience": 10, | |
| "grad_clip_norm": 1.0 | |
| }, | |
| "hardware": { | |
| "device": "auto", | |
| "mixed_precision": "bf16", | |
| "num_workers": 0, | |
| "pin_memory": true | |
| } | |
| } |