{ "step": 813, "val_bpb": 0.3282147496335069, "model_config": { "sequence_len": 2048, "vocab_size": 65536, "n_layer": 34, "n_head": 17, "n_kv_head": 17, "n_embd": 2176 }, "user_config": { "run": "d34-mid", "device_type": "", "dtype": "bfloat16", "model_tag": "d34", "model_step": 169150, "num_iterations": -1, "max_seq_len": 2048, "device_batch_size": 4, "total_batch_size": 524288, "embedding_lr": 0.2, "unembedding_lr": 0.004, "matrix_lr": 0.02, "weight_decay": 0.0, "init_lr_frac": 1.0, "eval_every": 150, "eval_tokens": 10485760, "dry_run": false } }