Update results for DSGDm

README.md

@@ -28,9 +28,9 @@ datasets:
     - Number of workers: 8
     - Communication topology: one-peer ring (time-varying topology)
   - Results:
-    - Top-1 Accuracy:
-    - Top-5 Accuracy:
-    - Average training loss in the last epoch:
+    - Top-1 Accuracy: 77.4233 ± 0.1227
+    - Top-5 Accuracy: 93.5407 ± 0.0546
+    - Val Loss: 1.9332 ± 0.0031
 
 - `/DSGDm-8-complete`: ResNet-50 models trained with decentralized SGD with momentum
   - Training Details:
@@ -43,6 +43,6 @@ datasets:
     - Number of workers: 8
     - Communication topology: complete
   - Results:
-    - Top-1 Accuracy:
-    - Top-5 Accuracy:
-    - Average training loss in the last epoch:
+    - Top-1 Accuracy: 77.4440 ± 0.0694
+    - Top-5 Accuracy: 93.6567 ± 0.0197
+    - Val Loss: ± 1.9361 0.0040