training_protocol.json

{
  "architecture": "causal_transwave_blocklifting_meyer_byte_lm_g4_v2",
  "source_commit": "5cae31b81e15160379ded79f32bcbb443d7db9f7",
  "parameters": 96130040,
  "dataset": "allenai/c4:en",
  "objective": "exact causal next-byte NLL",
  "context_tokens": 20480,
  "physical_batch": 280,
  "tokens_per_full_step": 5734400,
  "maximum_training_tokens": 4499996672,
  "usable_training_tokens": 4499988480,
  "target_ppl": 3.0,
  "base_lr": 0.0001,
  "min_lr": 1e-05,
  "warmup_fraction": 0.01,
  "grad_clip": 1.0,
  "model_seed": 20261010,
  "order_seed": 20261011,
  "allocator": "expandable_segments:True,garbage_collection_threshold:0.80",
  "fingerprint": "370d05a6d2672fc7838726e78e8fe267b4b9c480b4f3708b64e7136beea128fd"
}