ds_config_zero3.json

{
  "scheduler": {
    "type": "WarmupDecayLR",
    "params": {
          "warmup_min_lr": 0,
          "warmup_type": "linear"
      }
  },
  "optimizer": {
    "type": "Adam",
    "params": {
      "betas": [
        0.9,
        0.999
      ]
        }
  },
  "fp16": {
    "enabled": true,
    "auto_cast": false,
    "loss_scale": 0,
    "initial_scale_power": 16,
    "loss_scale_window": 1000,
    "hysteresis": 2,
    "min_loss_scale": 1
  },
  "zero_optimization": {
     "stage": 3,
     "offload_optimizer": {
       "device": "cpu",
       "pin_memory": true
     },
     "offload_param": {
       "device": "cpu",
       "pin_memory": true
     },
     "memory_efficient_linear": false,
     "overlap_comm": true,
     "contiguous_gradients": true,
     "sub_group_size": 1.000000e+09,
     "reduce_bucket_size": "auto",
     "stage3_prefetch_bucket_size": "auto",
     "stage3_param_persistence_threshold": "auto",
     "stage3_max_live_parameters": 1.000000e+09,
     "stage3_max_reuse_distance": 1.000000e+09,
     "stage3_gather_16bit_weights_on_model_save": true
  }
}