Update README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8667
+      value: 0.8735
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the cifar100 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4956
-- Accuracy: 0.8667
+- Loss: 0.4223
+- Accuracy: 0.8735
 
 ## Model description
 
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 20 (with early stopping)
 
 ### Training results
 
@@ -69,9 +69,9 @@ The following hyperparameters were used during training:
 | 0.2912        | 3.0   | 2343 | 0.861    | 0.4452          |
 | 0.2234        | 4.0   | 3124 | 0.8679   | 0.4330          |
 | 0.121         | 5.0   | 3905 | 0.8735   | 0.4223          |
-| 0.2589        | 6.0   | 4686 | 0.4775   | 0.8622          |
-| 0.1419        | 7.0   | 5467 | 0.4900   | 0.8642          |
-| 0.1513        | 8.0   | 6248 | 0.4956   | 0.8667          |
+| 0.2589        | 6.0   | 4686 | 0.8622   | 0.4775          |
+| 0.1419        | 7.0   | 5467 | 0.8642   | 0.4900          |
+| 0.1513        | 8.0   | 6248 | 0.8667   | 0.4956          |
 
 
 ### Framework versions