zero3_cp.json

{
  "compile": {
    "enabled": true,
    "backend": "inductor"
  },
  "fp16": {
    "enabled": false
  },
  "bf16": {
    "enabled": "auto"
  },
  "train_micro_batch_size_per_gpu": "auto",
  "train_batch_size": "auto",
  "gradient_accumulation_steps": "auto",
  "gradient_clipping": "auto",
  "zero_optimization": {
    "stage": 3,
    "overlap_comm": true,
    "contiguous_gradients": true,
    "sub_group_size": 1e9,
    "reduce_bucket_size": "auto",
    "stage3_prefetch_bucket_size": "auto",
    "stage3_param_persistence_threshold": "auto",
    "stage3_max_live_parameters": 1e9,
    "stage3_max_reuse_distance": 1e9,
    "stage3_gather_16bit_weights_on_model_save": true
  }
}