update model card README.md

README.md

@@ -16,7 +16,7 @@ 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2830
+- Loss: 0.2867
 
 ## Model description
 
@@ -41,24 +41,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3774        | 0.84  | 100  | 0.3771          |
-| 0.3135        | 1.68  | 200  | 0.3310          |
-| 0.2739        | 2.52  | 300  | 0.3116          |
-| 0.236         | 3.36  | 400  | 0.2887          |
-| 0.2108        | 4.2   | 500  | 0.2775          |
-| 0.2039        | 5.04  | 600  | 0.2745          |
-| 0.1783        | 5.88  | 700  | 0.2761          |
-| 0.1718        | 6.72  | 800  | 0.2787          |
-| 0.1601        | 7.56  | 900  | 0.2802          |
-| 0.1553        | 8.4   | 1000 | 0.2809          |
-| 0.1519        | 9.24  | 1100 | 0.2830          |
+| 0.3751        | 0.84  | 100  | 0.3845          |
+| 0.3237        | 1.68  | 200  | 0.3215          |
+| 0.2812        | 2.52  | 300  | 0.3092          |
+| 0.2441        | 3.36  | 400  | 0.2960          |
+| 0.2268        | 4.2   | 500  | 0.2884          |
+| 0.2236        | 5.04  | 600  | 0.2873          |
+| 0.2027        | 5.88  | 700  | 0.2859          |
+| 0.2024        | 6.72  | 800  | 0.2877          |
+| 0.1952        | 7.56  | 900  | 0.2867          |
 
 
 ### Framework versions