ds_config.json

{
  "train_batch_size": "auto",
  "train_micro_batch_size_per_gpu": "auto",
  "gradient_accumulation_steps": "auto",
  "zero_optimization": {
    "stage": 3,
    "offload_optimizer": {
      "device": "cpu",
      "pin_memory": true
    },
    "offload_param": {
      "device": "cpu",
      "pin_memory": true
    },
    "overlap_comm": true,
    "contiguous_gradients": true,
    "sub_group_size": 1000000000.0,
    "reduce_bucket_size": "auto",
    "stage3_prefetch_bucket_size": "auto",
    "stage3_param_persistence_threshold": "auto",
    "stage3_max_live_parameters": 1000000000.0,
    "stage3_max_reuse_distance": 1000000000.0,
    "stage3_gather_16bit_weights_on_model_save": true
  },
  "bf16": {
    "enabled": true
  },
  "gradient_clipping": 0.3,
  "prescale_gradients": false,
  "wall_clock_breakdown": false
}