End of training

README.md

@@ -15,8 +15,8 @@ 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: 2.3461
-- Validation Loss: 2.2604
+- Train Loss: 2.7907
+- Validation Loss: 2.5855
 - Train Accuracy: 1.0
 - Epoch: 4
 
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 3.6224     | 3.4151          | 1.0            | 0     |
-| 3.2387     | 3.0315          | 1.0            | 1     |
-| 2.8782     | 2.7287          | 1.0            | 2     |
-| 2.5780     | 2.4583          | 1.0            | 3     |
-| 2.3461     | 2.2604          | 1.0            | 4     |
+| 4.4326     | 4.2160          | 0.95           | 0     |
+| 4.0335     | 3.8139          | 1.0            | 1     |
+| 3.6154     | 3.3574          | 1.0            | 2     |
+| 3.1938     | 2.9409          | 1.0            | 3     |
+| 2.7907     | 2.5855          | 1.0            | 4     |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
 - TensorFlow 2.15.0
-- Datasets 2.16.1
+- Datasets 2.17.0
 - Tokenizers 0.15.1

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0a487d31230b22af451a31074012b680bb71bb579a31a636cf0ed1876279e1
+oid sha256:e9ece53562862d1f5e848e555f89f989d78d78d63f675885e54e8ee8dbe2442b
 size 343773880