{
  "model_family": "tessera",
  "architecture": "ProtoGPT (custom decoder-only transformer \u2014 NOT transformers-compatible)",
  "parameter_count": 1013024256,
  "tie_word_embeddings": true,
  "tied_aliases_dropped": [
    "head.weight"
  ],
  "checkpoint_step": 373500,
  "torch_dtype": "bfloat16",
  "loader": "model.py::load_base() \u2014 see USAGE.md",
  "root": "/root/stage07_shards_tessera64k_4k",
  "out_dir": "/root/runs/20260615T061150_1b_GATED_h100",
  "device": "cuda",
  "steps": 376000,
  "seq_len": 4096,
  "micro_batch": 4,
  "grad_accum": 4,
  "d_model": 1536,
  "layers": 32,
  "heads": 16,
  "dropout": 0.0,
  "vocab_size": 65536,
  "lr": 0.0002,
  "min_lr": 1e-05,
  "warmup_steps": 200,
  "weight_decay": 0.1,
  "optimizer": "adamw",
  "eval_every": 100,
  "eval_batches": 64,
  "checkpoint_every": 500,
  "log_every": 10,
  "seed": 20260614,
  "param_dtype": "bfloat16",
  "autocast_dtype": "bfloat16",
  "min_free_gb": 8.0,
  "max_runtime_min": 0.0,
  "resume": "/root/checkpoint_resume.pt",
  "save_optimizer": true,
  "no_final_checkpoint": false,
  "no_grad_checkpointing": true,
  "reset_step": true,
  "gated_epoch": true,
  "gated_trust_cursor": true
}