{
    "batch_size": 16,
    "grad_accum_steps": 4,
    "max_iters": 40000,
    "warmup_iters": 2000,

    "max_lr": 3e-4,
    "weight_decay": 0.1,

    "beta1": 0.9,
    "beta2": 0.95,
    "eps": 1e-8,

    "eval_interval": 500,
    "eval_iters": 100,

    "grad_clip": 1.0,

    "device": "cuda",

    "seed": 42,

    "n_vocab": 50257,

    "seq_len": 128, 

    "n_layers": 4,
    "n_head": 4,
    "d_model": 256,

    "dropout": 0.1,
    "bias": false
}