Create new file

4-A100-config.json

@@ -0,0 +1,66 @@
+{
+
+
+    "pipe-parallel-size": 1,
+    "model-parallel-size": 1,
+
+ 
+    "scaled-upper-triang-masked-softmax-fusion": false,
+    "bias-gelu-fusion": false,
+
+    "fp16": {
+        "enabled": "auto",
+        "auto_cast": false,
+        "loss_scale": 0,
+        "initial_scale_power": 32,
+        "loss_scale_window": 1000,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "tensorboard": {
+        "enabled": true,
+        "output_path": "output/ds_logs/",
+        "job_name": "train_bert"
+    },
+
+    "optimizer": {
+        "type": "AdamW",
+        "params": {
+            "lr": "auto",
+            "betas": "auto",
+            "eps": "auto",
+            "weight_decay": "auto"
+        }
+    },
+
+    "scheduler": {
+        "type": "WarmupLR",
+        "params": {
+            "warmup_min_lr": "auto",
+            "warmup_max_lr": "auto",
+            "warmup_num_steps": "auto"
+        }
+    },
+
+    "zero_optimization": {
+        "stage": 2,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": true,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}