Model save

README.md

@@ -3,7 +3,6 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
-- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -17,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-oxford-iiit-pets
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the pcuenq/oxford-pets dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2277
-- Accuracy: 0.9323
+- Loss: 0.2073
+- Accuracy: 0.9296
 
 ## Model description
 
@@ -51,16 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3834        | 1.0   | 370  | 0.2994          | 0.9269   |
-| 0.207         | 2.0   | 740  | 0.2263          | 0.9364   |
-| 0.1794        | 3.0   | 1110 | 0.2058          | 0.9445   |
-| 0.143         | 4.0   | 1480 | 0.1970          | 0.9432   |
-| 0.1244        | 5.0   | 1850 | 0.1962          | 0.9445   |
+| 0.3825        | 1.0   | 370  | 0.2863          | 0.9269   |
+| 0.2196        | 2.0   | 740  | 0.2195          | 0.9310   |
+| 0.1563        | 3.0   | 1110 | 0.1977          | 0.9364   |
+| 0.1598        | 4.0   | 1480 | 0.1906          | 0.9364   |
+| 0.1444        | 5.0   | 1850 | 0.1876          | 0.9378   |
 
 
 ### Framework versions
 
 - Transformers 4.48.3
-- Pytorch 2.5.1+cu124
-- Datasets 3.3.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.0
 - Tokenizers 0.21.0

runs/Mar17_08-05-00_51f30ed1a00e/events.out.tfevents.1742199642.51f30ed1a00e.564.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89f8f8fc8818f6ebd5c093594d341884cf110e573941a772e3a88689895c234
+size 411