{
  "train_micro_batch_size_per_gpu": 12,
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 1e-05,
      "betas": [
        0.9,
        0.95
      ],
      "eps": 1e-08,
      "weight_decay": 0.0005
    }
  },
  "fp16": {
    "enabled": true
  },
  "zero_optimization": {
    "stage": 1,
    "offload_optimizer": {
      "device": "cpu",
      "pin_memory": true
    },
    "allgather_partitions": true,
    "allgather_bucket_size": 200000000.0,
    "overlap_comm": true,
    "reduce_scatter": true,
    "reduce_bucket_size": 200000000.0,
    "contiguous_gradients": true
  }
}