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: 0.0300
-- Validation Loss: 0.2483
-- Train Accuracy: 0.937
+- Train Loss: 0.0074
+- Validation Loss: 0.2560
+- Train Accuracy: 0.945
 - Epoch: 4
 
 ## Model description
@@ -43,11 +43,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.0597     | 0.2589          | 0.939          | 0     |
-| 0.0388     | 0.2590          | 0.941          | 1     |
-| 0.0400     | 0.2966          | 0.925          | 2     |
-| 0.0437     | 0.2780          | 0.934          | 3     |
-| 0.0300     | 0.2483          | 0.937          | 4     |
+| 0.0180     | 0.2310          | 0.946          | 0     |
+| 0.0126     | 0.2385          | 0.946          | 1     |
+| 0.0104     | 0.2445          | 0.944          | 2     |
+| 0.0088     | 0.2505          | 0.944          | 3     |
+| 0.0074     | 0.2560          | 0.945          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4324d400121545ce3b662679a9bd93a60c3a39769f67e97561d9642f5a823d
+oid sha256:b4c78866c151a2d6957c216cf22175c08b0cb62fa33f46bc23812e6fafe2c06d
 size 343773984