{
    "train_micro_batch_size_per_gpu": 64,
    "gradient_accumulation_steps": 1,
    "steps_per_print": 100,
    "gradient_clipping": 1.0,
    "zero_optimization": {
      "stage": 2,
      "contiguous_gradients": false,
      "overlap_comm": true,
      "reduce_scatter": true,
      "reduce_bucket_size": 5e7,
      "allgather_bucket_size": 5e7,
      "cpu_offload": true
    },
    "scheduler": {
      "type": "WarmupLR",
      "params": {
          "warmup_min_lr": 0,
          "warmup_max_lr": 1e-5,
          "warmup_num_steps": 2000
      }
   },
    "zero_allow_untested_optimizer": true,
    "fp16": {
      "enabled": true,
      "loss_scale": 0,
      "loss_scale_window": 1000,
      "hysteresis": 2,
      "min_loss_scale": 1
    },
    "optimizer": {
      "type": "Adam",
      "params": {
        "lr": 1e-5,
        "weight_decay": 0.1,
        "betas": [
          0.9,
          0.98
        ],
        "eps": 1e-6
      }
    },
    "activation_checkpointing": {
      "partition_activations": true,
      "contiguous_memory_optimization": false
    },
    "wall_clock_breakdown": false
  }