train/models/deepspeed_config.json

{
  "gradient_accumulation_steps": 1,
  "train_micro_batch_size_per_gpu":1,
  "steps_per_print": 100,
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 1e-4,
      "weight_decay": 1e-2
    }
  },
  "flops_profiler": {
    "enabled": false,
    "profile_step": 1,
    "module_depth": -1,
    "top_modules": 3,
    "detailed": true
  },
  "fp16": {
    "enabled": true,
    "loss_scale": 0,
    "loss_scale_window": 1000,
    "hysteresis": 2,
    "min_loss_scale": 1
  },
  "zero_optimization": {
    "stage": 1,
    "cpu_offload": true,
    "contiguous_gradients": true,
    "overlap_comm": true,
    "reduce_scatter": false,
    "reduce_bucket_size": 5e7,
    "allgather_bucket_size": 5e7
  },
  "activation_checkpointing": {
    "partition_activations": false,
    "contiguous_memory_optimization": false,
    "cpu_checkpointing": false
  },
  "wall_clock_breakdown": false,
  "zero_allow_untested_optimizer": true
}