ds_config_gpt_TEMPLATE.json

{
  "train_batch_size" : CONFIG_BATCH_SIZE,
  "train_micro_batch_size_per_gpu": CONFIG_MBSIZE,
  "steps_per_print": LOG_INTERVAL,

  "zero_optimization": {
    "stage": 3,
    "offload_optimizer": {
      "device": "cpu",
      "pin_memory": true,
      "ratio": 0.3
    }
  },

  "gradient_clipping": 1.0,
  "prescale_gradients":false,

  "fp16": {
    "enabled": CONFIG_FP16_ENABLED,
    "loss_scale": 0,
    "loss_scale_window": 500,
    "hysteresis": 2,
    "min_loss_scale": 1,
    "initial_scale_power": 11
  },

  "bf16": {
    "enabled": CONFIG_BF16_ENABLED
  },

  "wall_clock_breakdown" : false
}