{ "step": 485, "val_bpb": 0.31949859430277494, "model_config": { "sequence_len": 4096, "vocab_size": 32768, "n_layer": 20, "n_head": 10, "n_kv_head": 10, "n_embd": 1280 }, "user_config": { "run": "d20", "device_type": "", "model_tag": "d20", "model_step": null, "load_optimizer": 1, "num_iterations": -1, "max_seq_len": null, "device_batch_size": 16, "total_batch_size": null, "embedding_lr": null, "unembedding_lr": null, "matrix_lr": null, "init_lr_frac": 0.8, "warmup_ratio": 0.0, "warmdown_ratio": 0.5, "final_lr_frac": 0.0, "eval_every": 200, "eval_tokens": 20971520, "chatcore_every": 200, "chatcore_max_cat": -1, "chatcore_max_sample": 24, "mmlu_epochs": 3, "gsm8k_epochs": 4 } }