ds_config_gpt_TEMPLATE.json

{
  "train_batch_size": GBSIZE,
  "train_micro_batch_size_per_gpu": MBSIZE,
  "steps_per_print": LOG_INTERVAL,

  "zero_optimization": {
    "stage": ZERO_STAGE
  },

  "gradient_clipping": 1.0,
  "prescale_gradients": PRESCALE_GRAD,

  "fp16": {
    "enabled": true,
    "loss_scale": 0,
    "loss_scale_window": 500,
    "hysteresis": 2,
    "min_loss_scale": 1,
    "initial_scale_power": 11
  },

  "wall_clock_breakdown" : false
}