model_name: wskan-1k-tinystories
architecture_family: WSKAN-11 (Wavelet-like State-Space KAN, fused Triton scan)
architecture:
  vocab_size: 256
  d_model: 4
  n_layers: 1
  n_states: 6
  use_feature_bc: true
  bc_rank: 4
  wz_diag: false
  g_rank: null
  oscillatory: true
  bf16_scan: true
tokenizer:
  type: byte-level
  description: raw UTF-8 bytes; vocab ids 0-255; no BPE, no special tokens
training:
  dataset: roneneldan/TinyStories
  steps: 30000
  checkpoint_step: 30000
  batch_size: 64
  block_size: 256
  lr: 0.003
  lr_schedule: cosine
  optimizer: AdamW (weight_decay=0.0, grad clip 1.0)
  seed: 42
  epochs: ~3
  precision: fp32 weights, bf16 scan
evaluation:
  final_eval_loss: 2.1416
  final_eval_byte_ppl: 8.51
generation_defaults:
  max_new: 400
  temperature: 0.8
  seed: 1234