ds_config_zero1.json

{
    "fp16": {
        "enabled": true,
        "auto_cast": true
    },
    "zero_optimization": {
        "stage": 1,
        "offload_optimizer": {
            "device": "none"
        },
        "offload_param": {
            "device": "none"
        }
    },
    "gradient_accumulation_steps": 4,
    "gradient_clipping": 5.0,
    "steps_per_print": "inf",
    "train_batch_size": "auto",
    "train_micro_batch_size_per_gpu": "auto"
}