{
  "model_type": "nero_dense_control_mlx",
  "architectures": [
    "DenseControlLM"
  ],
  "framework": "mlx",
  "optimizer": "navier",
  "vocab_size": 2048,
  "context_length": 128,
  "width": 128,
  "blocks": 6,
  "head_dim": 32,
  "mlp_width": 148,
  "stored_parameters": 999680,
  "training_tokens": 500000000,
  "batch_size": 32,
  "requested_learning_rate": null,
  "momentum_beta": null,
  "source_run": "mlx_navier_500m_ctx128",
  "checkpoint": "checkpoint_000500000000",
  "metrics": {
    "final_train_loss": 3.3394856452941895,
    "final_tokens_seen": 500000000,
    "final_step": 122071,
    "final_tokens_per_second": 363230.275137849,
    "tail_median_tokens_per_second": 363332.1438834451,
    "logged_metric_rows": 1221
  },
  "final_log_row": {
    "step": 122071,
    "tokens_seen": 500000000,
    "loss": 3.3394856452941895,
    "lr": 1.05e-06,
    "tokens_per_second": 363230.275137849
  }
}