{
  "parameter_count": 1028128768,
  "parameter_summary": {
    "total": 1028128768,
    "parts": {
      "blocks": 822083584,
      "lm_head": 103022592,
      "other": 103022592
    }
  },
  "n_layer": 16,
  "n_head": 16,
  "n_embd": 2048,
  "head_dim": 128,
  "depth_scale_mode": "loop",
  "core_repetitions": 2,
  "core_layer_count": 6,
  "resolved_core_layer_count": 6,
  "prelude_layer_count": 5,
  "resolved_prelude_layer_count": 5,
  "coda_layer_count": 5,
  "resolved_coda_layer_count": 5,
  "effective_depth": 22,
  "expected_effective_depth": 22.0,
  "recurrence_rmsnorm": "recurrence_only",
  "recurrence_emb_alpha": 0.707106781187,
  "decoder_inject": true,
  "core_residual_branch_scale": 1.0,
  "resolved_core_residual_branch_scale": null,
  "core_repetition_schedule": "none",
  "core_repetition_crossover_fraction": null,
  "core_repetition_low": 1,
  "core_repetition_breakpoints": null,
  "lsched_lr_warmup_steps": 0,
  "lsched_lr_change_steps": [],
  "dep_grow_events": [],
  "target_core_repetitions": 2,
  "final_eval_active_core_repetitions": 2,
  "observed_train_core_repetitions_mean": null,
  "observed_train_core_repetitions_min": null,
  "observed_train_core_repetitions_max": null,
  "observed_train_core_repetitions_histogram": null,
  "recurrence_truncation_schedule": "none",
  "recurrence_bp_window": 0,
  "matrix_lr": 0.015236219889264189,
  "embedding_lr": 0.004875590364564541,
  "unembedding_lr": 0.001723781504538011,
  "lr_multiplier": 1.0,
  "effective_matrix_lr": 0.015236219889264189,
  "effective_embedding_lr": 0.004875590364564541,
  "effective_unembedding_lr": 0.001723781504538011,
  "weight_decay": 0.05,
  "matrix_weight_decay": 0.05,
  "embedding_weight_decay": 0.05,
  "unembedding_weight_decay": 0.05,
  "embedding_wd_skip_norm": 0.0,
  "adam_betas": [
    0.8,
    0.95
  ],
  "adam_eps": 1e-10,
  "lr_schedule": "wsd",
  "warmup_steps": 40,
  "warmdown_ratio": 1.0,
  "output_multiplier": 1.0,
  "residual_branch_multiplier": 0.25,
  "wte_init_std": 0.02,
  "uniform_init_scale": 0.0441941738242,
  "total_batch_size": 524288,
  "device_batch_size": 8,
  "num_epochs": 1,
  "estimated_num_iterations": 11877,
  "lr_schedule_steps": 11766,
  "resolved_lr_schedule_steps": 11766,
  "max_train_steps": 11766,
  "resolved_max_train_steps": 11766,
  "completed_epochs": 0,
  "seed": 42,
  "train_token_limit": 6230460334,
  "val_token_limit": 10000000,
  "token_limit_cutoff_devices": 32,
  "active_train_tokens": 6230460334,
  "packed_train_sequences_per_epoch": 3040512,
  "packed_train_tokens_per_epoch": 6226968576,
  "active_val_packed_sequences": 4864,
  "active_val_packed_tokens": 9961472,
  "val_loss": 2.74274364270662,
  "final_val_loss": 2.74274364270662,
  "final_train_loss": 2.7822152201976946,
  "best_val_loss": 2.74274364270662,
  "best_val_bpb": 0.8914082939695644,
  "best_val_epoch": 1.0,
  "train_val_per_epoch": [
    {
      "epoch": 1,
      "step": 11766,
      "train_loss": 2.7822152201976946,
      "val_loss": 2.74274364270662,
      "val_bpb": 0.8914082939695644
    }
  ],
  "core_block_residual_rms": 1.073198676109314,
  "last_train_mfu": 48.88768618209757,
  "last_train_tok_per_sec": 486280,
  "last_train_step_time_seconds": 1.0781595706939697,
  "total_training_time_seconds": 12653.63653421402,
  "total_wall_time_seconds": 12837.853096485138,
  "sequence_len": 2048,
  "window_pattern": "L"
}