ds_config.json

{
  "train_batch_size": 16,
  "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,
  "fp16": {
      "enabled": true,
      "fp16_master_weights_and_grads": false,
      "loss_scale": 0,
      "loss_scale_window": 500,
      "hysteresis": 2,
      "min_loss_scale": 1,
      "initial_scale_power": 15
  },
  "wall_clock_breakdown": false,
  "zero_optimization": {
      "stage": 0,
      "allgather_partitions": true,
      "reduce_scatter": true,
      "allgather_bucket_size": 50000000,
      "reduce_bucket_size": 50000000,
      "overlap_comm": true,
      "contiguous_gradients": true,
      "cpu_offload": false
  }
}