update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.92
+      value: 0.939
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1596
-- Accuracy: 0.92
+- Loss: 0.3194
+- Accuracy: 0.939
 
 ## Model description
 
@@ -60,15 +60,22 @@ 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: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6627        | 0.99  | 62   | 1.6351          | 0.889    |
-| 1.2914        | 2.0   | 125  | 1.2724          | 0.911    |
-| 1.143         | 2.98  | 186  | 1.1596          | 0.92     |
+| 0.8638        | 0.99  | 62   | 0.9578          | 0.913    |
+| 0.6163        | 2.0   | 125  | 0.7060          | 0.911    |
+| 0.5103        | 2.99  | 187  | 0.4994          | 0.936    |
+| 0.3659        | 4.0   | 250  | 0.4539          | 0.927    |
+| 0.3207        | 4.99  | 312  | 0.3999          | 0.933    |
+| 0.2523        | 6.0   | 375  | 0.3799          | 0.921    |
+| 0.2257        | 6.99  | 437  | 0.3703          | 0.922    |
+| 0.1937        | 8.0   | 500  | 0.3160          | 0.936    |
+| 0.1854        | 8.99  | 562  | 0.3229          | 0.93     |
+| 0.2048        | 9.92  | 620  | 0.3194          | 0.939    |
 
 
 ### Framework versions