Model save

README.md

@@ -3,6 +3,11 @@ license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
+- recall
+- precision
 model-index:
 - name: vit-real-fake-classification-v3
   results: []
@@ -14,6 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 # vit-real-fake-classification-v3
 
 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: 0.0541
+- Accuracy: 0.9817
+- F1: 0.9834
+- Recall: 0.9834
+- Precision: 0.9834
 
 ## Model description
 
@@ -41,6 +52,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
+| 0.2481        | 1.0   | 233  | 0.0846          | 0.9667   | 0.9699 | 0.9737 | 0.9662    |
+| 0.1881        | 2.0   | 466  | 0.0773          | 0.9726   | 0.9756 | 0.9912 | 0.9604    |
+| 0.1036        | 3.0   | 699  | 0.0691          | 0.9774   | 0.9796 | 0.9815 | 0.9777    |
+| 0.0007        | 4.0   | 932  | 0.0698          | 0.9817   | 0.9835 | 0.9854 | 0.9816    |
+| 0.0029        | 5.0   | 1165 | 0.0541          | 0.9817   | 0.9834 | 0.9834 | 0.9834    |
+
+
 ### Framework versions
 
 - Transformers 4.41.1