ds_config.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": 3,
        "overlap_comm": true,
        "stage3_gather_16bit_weights_on_model_save": true
    },
    "flops_profiler": {
        "enabled": false,
        "profile_step": 1,
        "module_depth": -1,
        "top_modules": 1,
        "detailed": true,
        "output_file": null
    }
}