```yml { "fp16": { "enabled": "auto", "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 16, "hysteresis": 2, "min_loss_scale": 1 }, "optimizer": { "type": "AdamW", "params": { "lr": "auto", "betas": "auto", "eps": "auto", "weight_decay": "auto" } }, "scheduler": { "type": "WarmupLR", "params": { "warmup_min_lr": "auto", "warmup_max_lr": "auto", "warmup_num_steps": "auto" } }, "zero_optimization": { "stage": 3, "offload_optimizer": { "device": "nvme", "nvme_path": "/local_nvme", "pin_memory": true, "buffer_count": 4, "fast_init": false }, "offload_param": { "device": "nvme", "nvme_path": "/local_nvme", "pin_memory": true, "buffer_count": 5, "buffer_size": 1e8, "max_in_cpu": 1e9 }, "aio": { "block_size": 262144, "queue_depth": 32, "thread_count": 1, "single_submit": false, "overlap_events": true }, "overlap_comm": true, "contiguous_gradients": true, "sub_group_size": 1e9, "reduce_bucket_size": "auto", "stage3_prefetch_bucket_size": "auto", "stage3_param_persistence_threshold": "auto", "stage3_max_live_parameters": 1e9, "stage3_max_reuse_distance": 1e9, "stage3_gather_16bit_weights_on_model_save": true }, "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "steps_per_print": 2000, "train_batch_size": "auto", "train_micro_batch_size_per_gpu": "auto", "wall_clock_breakdown": false } DeepSpeed features There are a number of important parameters to specify in the DeepSpeed configuration file which are briefly described in this section.