Update deepspeed.json

ptuning/deepspeed.json

-{
-  "train_micro_batch_size_per_gpu": "auto",
-  "gradient_accumulation_steps": "auto",
-  "zero_allow_untested_optimizer": true,
-  "fp16": {
-    "enabled": "auto",
-    "loss_scale": 0,
-    "initial_scale_power": 16,
-    "loss_scale_window": 1000,
-    "hysteresis": 2,
-    "min_loss_scale": 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": false,
-    "reduce_scatter": true,
-    "reduce_bucket_size": 5e8,
-    "contiguous_gradients" : true
-  }
-}
\ No newline at end of file
+{
+  "train_micro_batch_size_per_gpu": "auto",
+  "gradient_accumulation_steps": "auto",
+  "zero_allow_untested_optimizer": true,
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "optimizer": {
+    "type": "AdamW",
+    "params": {
+        "lr": "auto",
+        "betas": "auto",
+        "eps": "auto",
+        "weight_decay": "auto"
+    }
+  },
+  "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": false,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients" : true
+  }
+}