Model save

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -17,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-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 beans 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5648
+- Loss: 0.2257
 - Accuracy: 0.9699
 
 ## Model description
@@ -45,15 +43,19 @@ The following hyperparameters were used during training:
 - seed: 1337
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 7.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9886        | 1.0   | 17   | 0.7761          | 0.9248   |
-| 0.7227        | 2.0   | 34   | 0.6195          | 0.9549   |
-| 0.6041        | 3.0   | 51   | 0.5648          | 0.9699   |
+| 0.9859        | 1.0   | 17   | 0.7496          | 0.9323   |
+| 0.6761        | 2.0   | 34   | 0.5277          | 0.9624   |
+| 0.4598        | 3.0   | 51   | 0.3717          | 0.9624   |
+| 0.4037        | 4.0   | 68   | 0.2968          | 0.9699   |
+| 0.3161        | 5.0   | 85   | 0.2529          | 0.9699   |
+| 0.2529        | 6.0   | 102  | 0.2268          | 0.9850   |
+| 0.2624        | 7.0   | 119  | 0.2257          | 0.9699   |
 
 
 ### Framework versions