scripts/ds_zero2.json

{
    "bf16": {
        "enabled": true
    },
    "zero_optimization": {
        "stage": 2,
        "allgather_partitions": true,
        "allgather_bucket_size": 500000000.0,
        "overlap_comm": true,
        "reduce_scatter": true,
        "reduce_bucket_size": 500000000.0,
        "contiguous_gradients": true
    },
    "gradient_accumulation_steps": "auto",
    "gradient_clipping": "auto",
    "train_batch_size": "auto",
    "train_micro_batch_size_per_gpu": "auto"
}