{
  "val_bpb": 0.8119751250726281,
  "model_config": {
    "sequence_len": 2048,
    "vocab_size": 65536,
    "n_layer": 20,
    "n_head": 10,
    "n_kv_head": 10,
    "n_embd": 1280
  },
  "user_config": {
    "run": "dummy",
    "depth": 20,
    "max_seq_len": 2048,
    "num_iterations": -1,
    "target_flops": -1.0,
    "target_param_data_ratio": 20,
    "device_batch_size": 32,
    "total_batch_size": 524288,
    "embedding_lr": 0.2,
    "unembedding_lr": 0.004,
    "weight_decay": 0.0,
    "matrix_lr": 0.02,
    "grad_clip": 1.0,
    "eval_every": 250,
    "eval_tokens": 10485760,
    "core_metric_every": 2000,
    "core_metric_max_per_task": 500,
    "sample_every": 2000,
    "model_tag": ""
  },
  "device_batch_size": 32,
  "max_seq_len": 2048
}