ds_config_func_scheduler.json

{
  "train_batch_size": 4,
  "gradient_accumulation_steps": 1,
  "steps_per_print": 1,
  "zero_optimization": {
    "stage":2
  },
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 0.00015
    }
  },
  "gradient_clipping": 1.0,
  "scheduler": {
    "type": "WarmupLR",
    "params": {
      "warmup_min_lr": 0,
      "warmup_max_lr": 0.001,
      "warmup_num_steps": 10
    }
  },

  "fp16": {
    "enabled": true,
    "loss_scale": 0,
    "loss_scale_window": 1000,
    "hysteresis": 2,
    "min_loss_scale": 1
  }
}