{
  "step": 21400,
  "val_bpb": 0.8233318090316151,
  "model_config": {
    "sequence_len": 512,
    "vocab_size": 65536,
    "n_layer": 20,
    "n_head": 10,
    "n_kv_head": 10,
    "n_embd": 1280
  },
  "user_config": {
    "run": "dummy",
    "device_type": "cuda",
    "depth": 20,
    "max_seq_len": 512,
    "num_iterations": -1,
    "target_flops": -1.0,
    "target_param_data_ratio": 20,
    "device_batch_size": 4,
    "total_batch_size": 524288,
    "embedding_lr": 0.2,
    "unembedding_lr": 0.004,
    "weight_decay": 0.0,
    "matrix_lr": 0.02,
    "grad_clip": 1.0,
    "warmup_ratio": 0.0,
    "warmdown_ratio": 0.2,
    "final_lr_frac": 0.0,
    "resume_from_step": 20521,
    "eval_every": 1,
    "eval_tokens": 524288,
    "core_metric_every": 2000,
    "core_metric_max_per_task": 500,
    "sample_every": 2000,
    "save_every": 1,
    "model_tag": ""
  },
  "device_batch_size": 4,
  "max_seq_len": 512,
  "dataloader_state_dict": {
    "pq_idx": 214,
    "rg_idx": 28
  },
  "loop_state": {
    "min_val_bpb": 0.8233121174317459,
    "smooth_train_loss": 2.793240407600011,
    "total_training_time": 4008449.3674418926
  }
}