deepspeed_config.json

{
  "fp16": {
    "enabled": true,
    "hysteresis": 2,
    "loss_scale": 0,
    "loss_scale_window": 1000,
    "min_loss_scale": 1
  },
  "gradient_clipping": 0.0,
  "steps_per_print": 100,
  "train_batch_size": 4096,
  "train_micro_batch_size_per_gpu": 128,
  "wall_clock_breakdown": false
}