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: 1.0512
-- Validation Loss: 0.7301
-- Train Accuracy: 0.858
+- Train Loss: 1.0298
+- Validation Loss: 0.7463
+- Train Accuracy: 0.855
 - Epoch: 4
 
 ## Model description
@@ -43,11 +43,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.5456     | 1.8821          | 0.753          | 0     |
-| 1.7977     | 1.2879          | 0.829          | 1     |
-| 1.4118     | 0.9698          | 0.854          | 2     |
-| 1.1705     | 0.8239          | 0.846          | 3     |
-| 1.0512     | 0.7301          | 0.858          | 4     |
+| 2.5725     | 2.0070          | 0.654          | 0     |
+| 1.8037     | 1.3445          | 0.813          | 1     |
+| 1.4419     | 1.0304          | 0.829          | 2     |
+| 1.2025     | 0.8695          | 0.842          | 3     |
+| 1.0298     | 0.7463          | 0.855          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3988b8bfe1b0e7409f122bf47e91d2d6209acb7cd53ce77d4c29f8cda010cfb
-size 343525048
+oid sha256:547d38ed567e24c6a1fb451ff82ea95f6053d0d939e50e7408d54618661de10b
+size 343541432