set auto for other params that hf trainer sets for ds. include zero1 json (#570)

deepspeed/zero1.json

@@ -0,0 +1,39 @@
+{
+    "zero_optimization": {
+      "stage": 1,
+      "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": "auto",
+        "eps": "auto",
+        "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
+}

deepspeed/zero2.json

@@ -23,11 +23,8 @@
       "type": "AdamW",
       "params": {
         "lr": "auto",
-        "betas": [
-          0.9,
-          0.999
-        ],
-        "eps": 1e-8,
+        "betas": "auto",
+        "eps": "auto",
         "weight_decay": "auto"
       }
     },

deepspeed/zero3.json

@@ -36,7 +36,7 @@
     "params": {
       "lr": "auto",
       "betas": "auto",
-      "eps": 1e-8,
+      "eps": "auto",
       "weight_decay": "auto"
     }
   },