{ "fp16": { "enabled": "auto", "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 16, "hysteresis": 2, "min_loss_scale": 1 }, "bf16": { "enabled": "auto" }, "optimizer": { "type": "AdamW", "params": { "lr": "auto", "betas": "auto", "eps": "auto", "weight_decay": "auto" } }, "scheduler": { "type": "WarmupCosineLR", "params": { "total_num_steps": "auto", "warmup_min_ratio": 0, "warmup_num_steps": "auto", "cos_min_ratio": 0.1 } }, "zero_optimization": { "stage": 3, "offload_optimizer": { "device": "cpu", "pin_memory": true }, "offload_param": { "device": "cpu", "pin_memory": true }, "allgather_partitions": true, "allgather_bucket_size": 5e8, "overlap_comm": true, "reduce_scatter": true, "reduce_bucket_size": 5e8, "contiguous_gradients": true, "round_robin_gradients": true, "sub_group_size": 1e12, "stage3_prefetch_bucket_size": 5e8, "stage3_param_persistence_threshold": 1e5, "stage3_max_live_parameters": 1e9, "stage3_max_reuse_distance": 1e9, "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 }, "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "steps_per_print": 100, "train_batch_size": "auto", "train_micro_batch_size_per_gpu": "auto", "wall_clock_breakdown": false, "dump_state": false }