{
  "model_type": "t5",
  "architectures": ["T5ForConditionalGeneration"],
  "d_model": 512,
  "d_ff": 2048,
  "num_layers": 6,
  "num_heads": 8,
  "vocab_size": 32128,
  "run_id": "run_D",
  "learning_rate": 2e-4,
  "batch_size": 32,
  "seed": 42
}