End of training

README.md

@@ -14,9 +14,9 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.8950
-- Validation Loss: 2.0686
-- Train Accuracy: 0.5385
+- Train Loss: 1.9094
+- Validation Loss: 2.0767
+- Train Accuracy: 0.4231
 - Epoch: 4
 
 ## Model description
@@ -43,11 +43,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.4425     | 2.3940          | 0.2308         | 0     |
-| 2.2887     | 2.3105          | 0.3846         | 1     |
-| 2.1358     | 2.2179          | 0.5            | 2     |
-| 1.9966     | 2.1405          | 0.4615         | 3     |
-| 1.8950     | 2.0686          | 0.5385         | 4     |
+| 2.4440     | 2.4069          | 0.1923         | 0     |
+| 2.3135     | 2.3220          | 0.2308         | 1     |
+| 2.1668     | 2.2474          | 0.3462         | 2     |
+| 2.0369     | 2.1577          | 0.3846         | 3     |
+| 1.9094     | 2.0767          | 0.4231         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d03306155b6a3dbd26e2e21174bd5b86e03c56836a918fb75326a63d2eb8c38
-size 343516856
+oid sha256:6b74309b31c3771da91d0efa109fe92cd16f07548e0baaca0348e8c31c6f8ede
+size 343500472