[mrothroc]

Simple example to show how configs are defined:

{ "name": "plain_3L",

  // Minimal causal transformer baseline: 3 attention layers plus 3 SwiGLU layers.
  "model_dim": 128,
  "vocab_size": 1024,
  "seq_len": 128,

  // Blocks execute sequentially, alternating token mixing and feed-forward mixing.
  "blocks": [
    {"type": "plain", "heads": 4},
    {"type": "swiglu"},
    {"type": "plain", "heads": 4},
    {"type": "swiglu"},
    {"type": "plain", "heads": 4},
    {"type": "swiglu"}
  ],

  // Slightly longer than smoke-test configs so the baseline loss moves visibly.
  "training": {
    "steps": 200,
    "lr": 3e-4,
    "grad_clip": 1.0,
    "weight_decay": 0.01,
    "seed": 42,
    "batch_tokens": 1024
  }
}