End of training

README.md

@@ -15,9 +15,9 @@ 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: 0.4913
-- Validation Loss: 0.6695
-- Train Accuracy: 0.7364
+- Train Loss: 0.5468
+- Validation Loss: 0.6111
+- Train Accuracy: 0.7674
 - Epoch: 4
 
 ## Model description
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.0611     | 1.0265          | 0.5969         | 0     |
-| 0.9429     | 0.9217          | 0.7364         | 1     |
-| 0.7961     | 0.7753          | 0.7674         | 2     |
-| 0.6281     | 0.6510          | 0.7984         | 3     |
-| 0.4913     | 0.6695          | 0.7364         | 4     |
+| 1.0659     | 1.0044          | 0.6279         | 0     |
+| 0.9502     | 0.9168          | 0.7442         | 1     |
+| 0.8135     | 0.7778          | 0.7287         | 2     |
+| 0.6570     | 0.6767          | 0.7442         | 3     |
+| 0.5468     | 0.6111          | 0.7674         | 4     |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.38.1
 - TensorFlow 2.15.0
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -28,5 +28,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.38.1"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f741eb83491e2f400c0cf0891f92b4fb707f8db4136a2958c65d38f2fec78d4e
+oid sha256:4cba052e7b0645a65e276e60a9d107d0ed651eb1ba6a98b8b1777e6b3746c020
 size 343472824