configs/deepspeed_zero_offload.json

{
  "train_batch_size": "auto",
  "train_micro_batch_size_per_gpu": "auto",
  "gradient_accumulation_steps": "auto",
  "fp16": {
    "enabled": true
  },
  "zero_optimization": {
    "stage": 2,
    "offload_optimizer": {
      "device": "cpu",
      "pin_memory": true
    },
    "allgather_partitions": true,
    "allgather_bucket_size": 200000000,
    "overlap_comm": true,
    "reduce_scatter": true,
    "reduce_bucket_size": 200000000,
    "contiguous_gradients": true
  }
}