diff --git a/deepspeed/zero2.json b/deepspeed/zero2.json new file mode 100644 index 000000000..9b8a2a9b6 --- /dev/null +++ b/deepspeed/zero2.json @@ -0,0 +1,46 @@ +{ + "zero_optimization": { + "stage": 2, + "offload_optimizer": { + "device": "cpu" + }, + "contiguous_gradients": true, + "overlap_comm": true + }, + "bf16": { + "enabled": "auto" + }, + "fp16": { + "enabled": "auto", + "auto_cast": false, + "loss_scale": 0, + "initial_scale_power": 32, + "loss_scale_window": 1000, + "hysteresis": 2, + "min_loss_scale": 1 + }, + "optimizer": { + "type": "AdamW", + "params": { + "lr": "auto", + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-8, + "weight_decay": "auto" + } + }, + "scheduler": { + "type": "WarmupDecayLR", + "params": { + "warmup_min_lr": "auto", + "warmup_max_lr": "auto", + "warmup_num_steps": "auto", + "total_num_steps": "auto" + } + }, + "train_batch_size": "auto", + "train_micro_batch_size_per_gpu": "auto", + "wall_clock_breakdown": false +}