ds_config_zero1.json

{
    "train_batch_size": "auto",
    "train_micro_batch_size_per_gpu" :"auto",
    "gradient_accumulation_steps": "auto",
    "gradient_clipping": 1.0,
    "bf16": {
        "enabled": "auto"
    },
    "zero_optimization": {
        "stage": 1
    }
}