{
  "bf16": {
    "enabled": true
  },

  "zero_optimization": {
    "stage": 3,

    "overlap_comm": true,
    "contiguous_gradients": true,

    "reduce_bucket_size": 50000000,
    "stage3_prefetch_bucket_size": 50000000,
    "stage3_param_persistence_threshold": 100000
  },

  "gradient_clipping": 1.0,

  "train_micro_batch_size_per_gpu": 1,

  "steps_per_print": 100
}