config/main.json

{
    "train_batch_size": 18, 
    "train_micro_batch_size_per_gpu": 3, 
    "gradient_accumulation_steps": 1, 
    "zero_optimization": {
        "stage": 3, 
        "offload_optimizer": {
            "device": "none", 
            "nvme_path": null
        }, 
        "offload_param": {
            "device": "none", 
            "nvme_path": null
        }, 
        "stage3_gather_16bit_weights_on_model_save": true
    }, 
    "steps_per_print": 2, 
    "fp16": {
        "enabled": true, 
        "auto_cast": true
    }, 
    "bf16": {
        "enabled": false
    }
}