{
  "batch_size": 32,
  "block_size": 256,
  "dropout": 0.1,
  "eval_interval": 250,
  "eval_iters": 50,
  "grad_accum": 2,
  "grad_clip": 1.0,
  "learning_rate": 0.0003,
  "max_iters": 5000,
  "min_lr": 3e-05,
  "n_embd": 512,
  "n_head": 8,
  "n_layer": 10,
  "vocab_size": 16000,
  "warmup_iters": 200,
  "weight_decay": 0.1
}