{ "base_checkpoint": "artifacts/runs/variant_v1_muon_500m/checkpoint-tokens-1500000000", "base_token_presentations": 1500000000, "checkpoint_selection": { "evaluated_continuation_checkpoints": [ 250000000, 500000000, 750000000, 1000000000 ], "reason": "highest observed chance-normalized Open SLM Intelligence Index", "selected_continuation_checkpoint": 500000000, "used_public_evaluations": true }, "continuation_checkpoint_metrics": { "elapsed_seconds": 4661.750659100002, "gradient_norm": 0.7176291942596436, "learning_rate": 0.0003, "step": 1908, "tokens_seen": 500170752, "train_loss": 2.8427783250808716, "validation_loss": 2.7994241237640383 }, "continuation_token_presentations": 500170752, "cumulative_token_presentations": 2000170752, "format_version": 1, "release_name": "Hummingbird-V1", "source_checkpoint": "artifacts/runs/natural20b_pilot_muon_b32/checkpoint-tokens-0500000000", "training_config": { "adam_beta1": 0.9, "adam_beta2": 0.95, "adam_eps": 1e-08, "compile": false, "context_length": 512, "corpus_path": "artifacts\\natural20b_pilot\\packed", "deterministic": false, "device": null, "gradient_accumulation_steps": 16, "init_from": "artifacts/runs/variant_v1_muon_500m/checkpoint-tokens-1500000000", "learning_rate": 0.0003, "lr_decay_fraction": 0.15, "lr_min_ratio": 0.1, "lr_schedule": "wsd", "lr_warmup_steps": 100, "max_grad_norm": 1.0, "micro_batch_size": 32, "model_config_path": "configs\\model_4k_14l_sdpa_qk_clamp.yaml", "mtp_final_loss_weight": null, "mtp_loss_weight": 0.0, "num_workers": 0, "optimizer": "muon", "pin_memory": true, "precision": "bf16", "prepared_data_dir": "artifacts\\natural20b_pilot\\packed", "run_dir": "artifacts\\runs\\natural20b_pilot_muon_b32", "save_every_steps": 500, "save_every_tokens": 250000000, "seed": 42, "tokenizer_path": "artifacts\\runs\\e3_tokenizers\\tok_4k_digit", "tokens_target": 1000000000, "validate_every_steps": 100, "validation_tokens": 65536, "weight_decay": 0.1 } }