{
  "train_batch_size": 8,
  "steps_per_print": 2000,
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 0.001,
      "betas": [
        0.8,
        0.999
      ],
      "eps": 1e-8,
      "weight_decay": 3e-7
    }
  },
  "scheduler": {
    "type": "WarmupLR",
    "params": {
      "warmup_min_lr": 0,
      "warmup_max_lr": 0.001,
      "warmup_num_steps": 1000
    }
  },
  "gradient_clipping": 1.0,
  "prescale_gradients": false,
  "bf16": {
      "enabled": true
  },
  "wall_clock_breakdown": false,
  "zero_optimization": {
      "stage": 3,
      "reduce_scatter": true,
      "overlap_comm": false,
      "contiguous_gradients": false
  }
}