{ "zero_optimization": { "stage": 3, "allgather_partitions": true, "allgather_bucket_size": 5e8, "overlap_comm": false, "reduce_scatter": true, "reduce_bucket_size": 5e8, "contiguous_gradients": false, "stage3_max_live_parameters": 1e9, "stage3_max_reuse_distance": 1e9, "stage3_prefetch_bucket_size": 5e8, "stage3_param_persistence_threshold": 1e6, "stage3_gather_16bit_weights_on_model_save": false, "sub_group_size": 1e12 } }