ds_config.json

{
  "train_batch_size": 64,
  "fp16": {
    "enabled": true,
    "initial_scale_power": 8
  },
  "gradient_clipping": 1.0,
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 3e-5,
      "betas": [
        0.9,
        0.999
      ],
      "eps": 1e-8,
      "weight_decay": 3e-7
    }
  },
  "scheduler": {
    "type": "WarmupLR",
    "params": {
      "warmup_min_lr": 0,
      "warmup_max_lr": 3e-5,
      "warmup_num_steps": 100
    }
  },
  "zero_optimization": {
    "stage": 2,
    "allgather_partitions": true,
    "allgather_bucket_size": 1e8,
    "overlap_comm": true,
    "reduce_scatter": true,
    "reduce_bucket_size": 1e8,
    "contiguous_gradients": true,
    "offload_optimizer": {
      "device": "cpu",
      "pin_memory": true,
      "fast_init": false
    }
  },
  "activation_checkpointing": {
    "partition_activations": true,
    "cpu_checkpointing": true,
    "contiguous_memory_optimization": true,
    "number_checkpoints": 1,
    "synchronize_checkpoint_boundary": false,
    "profile": false
  },
  "zero_allow_untested_optimizer": true,
  "wall_clock_breakdown": false,
  "step_per_print": 100
}