diff --git a/deepspeed_config/ds_stage3.json b/deepspeed_config/ds_stage3.json new file mode 100644 index 0000000..14b7b3e --- /dev/null +++ b/deepspeed_config/ds_stage3.json @@ -0,0 +1,28 @@ +{ + "fp16": { + "enabled": "auto", + "loss_scale": 0, + "loss_scale_window": 1000, + "initial_scale_power": 16, + "hysteresis": 2, + "min_loss_scale": 1 + }, + "bf16": { + "enabled": "auto" + }, + "train_micro_batch_size_per_gpu": "auto", + "train_batch_size": "auto", + "gradient_accumulation_steps": "auto", + "zero_optimization": { + "stage": 3, + "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 + } +}