{
  "train_batch_size": 256,
  "train_micro_batch_size_per_gpu": 1,
  "steps_per_print": 10,
  "optimizer": {
    "type": "AdamW",
    "params": {
      "lr": 0.001,
      "betas": [
        0.8,
        0.999
      ],
      "eps": 1e-8,
      "weight_decay": 3e-7
    }
  },
  "scheduler": {
    "type": "WarmupLR",
    "params": {
      "warmup_min_lr": 0,
      "warmup_max_lr": 0.001,
      "warmup_num_steps": 1000
    }
  },
  "fp16": {
    "enabled": false
  },
  "zero_optimization": {
    "stage": 3,
    "overlap_comm": true,
    "allgather_bucket_size": 5e4,
    "contiguous_gradients": true,
    "reduce_bucket_size":  5e4,
    "stage3_prefetch_bucket_size": 5e4,
    "stage3_max_live_parameters": 1e9,
    "stage3_max_reuse_distance": 1e9,
    "stage3_gather_16bit_weights_on_model_save": true,
  }
}