| { | |
| "model_type": "nero_dense_control_mlx", | |
| "architectures": [ | |
| "DenseControlLM" | |
| ], | |
| "framework": "mlx", | |
| "optimizer": "simow", | |
| "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_simow_500m_ctx128", | |
| "checkpoint": "checkpoint_000500000000", | |
| "metrics": { | |
| "final_train_loss": 5.371432304382324, | |
| "final_tokens_seen": 500000000, | |
| "final_step": 122071, | |
| "final_tokens_per_second": 418987.66562184633, | |
| "tail_median_tokens_per_second": 419229.3335327129, | |
| "logged_metric_rows": 1221 | |
| }, | |
| "final_log_row": { | |
| "step": 122071, | |
| "tokens_seen": 500000000, | |
| "loss": 5.371432304382324, | |
| "lr": 1.1025e-06, | |
| "tokens_per_second": 418987.66562184633 | |
| } | |
| } | |