{ "model_type": "nano-dates", "architecture": "decoder-only transformer (pre-norm)", "vocab_size": 256, "tokenizer": "byte (raw UTF-8 bytes, no vocab file)", "dim": 128, "n_layers": 4, "n_heads": 4, "n_kv_heads": 2, "head_dim": 32, "ffn": "swiglu", "ffn_mult": 4, "norm": "rmsnorm", "norm_eps": 1e-05, "positional": "rope", "rope_theta": 10000.0, "max_seq_len": 64, "tie_word_embeddings": true, "params": 1016960, "training": { "task": "natural date phrase -> ISO 8601", "data": "100% code-generated (answer sampled first, then rendered in 17 natural forms)", "objective": "SFT, prompt-masked cross-entropy (only the 10-char ISO target is supervised)", "steps": 12000, "batch_size": 64, "seq_len": 64, "optimizer": "adamw", "lr": 0.003, "schedule": "cosine", "warmup_steps": 200, "final_val_loss": 0.0358 } }