update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.0035971223021582736
+      value: 0.09064748201438849
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Pokemons_Clasiffication2-Santiago-Garcia
 
-This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the pokemon-classification dataset.
+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 pokemon-classification dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.5905
-- Accuracy: 0.0036
+- Loss: 7.8691
+- Accuracy: 0.0906
 
 ## Model description
 
@@ -57,18 +57,16 @@ 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: 5
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.369         | 0.82  | 500  | 9.9652          | 0.0014   |
-| 3.524         | 1.64  | 1000 | 10.4226         | 0.0022   |
-| 3.1839        | 2.46  | 1500 | 10.6460         | 0.0022   |
-| 2.8221        | 3.28  | 2000 | 10.8534         | 0.0029   |
-| 2.5573        | 4.11  | 2500 | 10.9669         | 0.0050   |
-| 2.2332        | 4.93  | 3000 | 10.5905         | 0.0036   |
+| 2.8204        | 0.82  | 500  | 6.3147          | 0.0144   |
+| 0.3221        | 1.64  | 1000 | 7.2082          | 0.0770   |
+| 0.0757        | 2.46  | 1500 | 7.7975          | 0.0763   |
+| 0.0314        | 3.28  | 2000 | 7.8691          | 0.0906   |
 
 
 ### Framework versions