{
  "architectures": [
    "BDH"
  ],
  "vocab_size": 256,
  "n_layer": 8,
  "n_embd": 256,
  "n_head": 4,
  "mlp_internal_dim_multiplier": 768,
  "dropout": 0.1,
  "seq_len": 2048,
  "model_type": "bdh",
  "size_m": 150,
  "training": {
    "steps": 30000,
    "data": "research-mix-v1 970M tok byte-level (80% EN fineweb-edu / 20% PL speakleash)",
    "optimizer": "AdamW lr=1e-3 wd=0.1 cos->1e-4 warmup1000",
    "clip": "ZClip",
    "final_val_loss": 1.099
  }
}