deepspeed.json

{
    "train_micro_batch_size_per_gpu": "auto",
    "train_batch_size": "auto",
    "zero_allow_untested_optimizer": true,
    "fp16": {
      "enabled": "auto",
      "loss_scale": 0,
      "initial_scale_power": 16, 
      "loss_scale_window": 1000,
      "hysteresis": 2,
      "min_loss_scale": 1
    }, 
    "zero_force_ds_cpu_optimizer": false,
    "zero_optimization": {
      "stage": 3,
      "offload_param": {
        "device": "cpu",
        "pin_memory": true
    },
    "offload_optimizer": {
        "device": "cpu",
        "pin_memory": true
    },
    "stage3_gather_16bit_weights_on_model_save": true,
    "allgather_partitions": true,
    "allgather_bucket_size": 5e8,
    "overlap_comm": false,
    "reduce_scatter": true,
    "reduce_bucket_size": 5e8,
    "contiguous_gradients" : true
    }
  }