{
  "fp16": {"enabled": false},
  "bf16": {"enabled": true},
  "train_micro_batch_size_per_gpu": "auto",
  "train_batch_size": "auto",
  "gradient_accumulation_steps": "auto",
  "zero_optimization": {
    "stage": 2,
    "allgather_partitions": true,
    "allgather_bucket_size": 50000000,
    "reduce_scatter": true,
    "reduce_bucket_size": 50000000,
    "overlap_comm": true,
    "contiguous_gradients": true,
    "cpu_offload": false
  },
  "gradient_clipping": 1.0,
  "steps_per_print": 10
}