Model save

README.md

@@ -3,9 +3,6 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
-- image-classification
-- car
-- stanford-cars
 - generated_from_trainer
 metrics:
 - accuracy
@@ -19,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # car-classification
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the tanganke/stanford_cars dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7769
-- Accuracy: 0.7047
+- Loss: 0.8876
+- Accuracy: 0.6706
 
 ## Model description
 
@@ -53,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6202        | 1.0   | 97   | 1.1317          | 0.6198   |
-| 0.9989        | 2.0   | 194  | 0.9692          | 0.6875   |
-| 0.8444        | 3.0   | 291  | 0.8966          | 0.6927   |
-| 0.7864        | 4.0   | 388  | 0.8611          | 0.6927   |
-| 0.7452        | 5.0   | 485  | 0.8525          | 0.7031   |
+| 1.3683        | 1.0   | 128  | 1.1585          | 0.5529   |
+| 1.0935        | 2.0   | 256  | 0.9990          | 0.6627   |
+| 1.0052        | 3.0   | 384  | 0.9340          | 0.6667   |
+| 0.9467        | 4.0   | 512  | 0.9004          | 0.6549   |
+| 0.8865        | 5.0   | 640  | 0.8876          | 0.6706   |
 
 
 ### Framework versions