playground/deepspeed_config_s3.json

{
    "fp16": {
        "enabled": "auto",
        "loss_scale": 0,
        "loss_scale_window": 1000,
        "initial_scale_power": 16,
        "hysteresis": 2,
        "min_loss_scale": 1
    },
    "zero_optimization": {
        "stage": 3,
        "offload_optimizer": {
            "device": "cpu",
            "pin_memory": true
        },
        "offload_param": {
            "device": "cpu",
            "pin_memory": true
        },
        "overlap_comm": true,
        "contiguous_gradients": true,
        "stage3_max_live_parameters" : 1e9,
        "stage3_max_reuse_distance" : 1e9,
        "stage3_prefetch_bucket_size" : 5e8,
        "stage3_param_persistence_threshold" : 1e6,
        "sub_group_size" : 1e12,
        "stage3_gather_16bit_weights_on_model_save": true
    },
    "train_batch_size": "auto",
    "train_micro_batch_size_per_gpu": "auto",
    "gradient_accumulation_steps": "auto"
}