{ "architecture": "ByteGPT", "config": { "vocab_size": 256, "block_size": 8192, "n_layer": 12, "n_head": 12, "n_embd": 768, "dropout": 0.0, "rope_theta": 100000.0 }, "iter": 19999, "n_params": 85150464, "tied_weights": { "lm_head.weight": "embed.weight" }, "training_args": { "preset": "small", "micro_bs": 4, "grad_accum": 8, "max_iters": 20000, "lr": 0.0006, "min_lr_frac": 0.1, "warmup_iters": 500, "weight_decay": 0.1, "grad_clip": 1.0, "eval_every": 500, "eval_windows": 64, "ckpt_every": 2000, "log_every": 20, "compile": true, "seed": 1337 } }