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: 0.4095
-- Validation Loss: 0.3716
-- Train Accuracy: 0.909
+- Train Loss: 0.3625
+- Validation Loss: 0.3347
+- Train Accuracy: 0.918
 - Epoch: 4
 
 ## Model description
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.8650     | 1.7381          | 0.789          | 0     |
-| 1.2807     | 0.8887          | 0.88           | 1     |
-| 0.7513     | 0.5793          | 0.898          | 2     |
-| 0.5116     | 0.4472          | 0.902          | 3     |
-| 0.4095     | 0.3716          | 0.909          | 4     |
+| 2.7562     | 1.5563          | 0.873          | 0     |
+| 1.1775     | 0.7872          | 0.892          | 1     |
+| 0.6780     | 0.4881          | 0.914          | 2     |
+| 0.4781     | 0.3626          | 0.925          | 3     |
+| 0.3625     | 0.3347          | 0.918          | 4     |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
+- Transformers 4.45.0.dev0
 - TensorFlow 2.17.0
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -224,5 +224,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.45.0.dev0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bcad8156e03d42663988958001989ba7e4cfa3009dbe3194964904c24df82b7
+oid sha256:f9865931a4d8575b69f9603d6b35e1b74a4ec2a7955be9e7079d2a8823c650bc
 size 343773880