Model save

README.md

@@ -18,8 +18,8 @@ should 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:
-- Loss: 0.5102
-- Accuracy: 0.8590
+- Loss: 0.5310
+- Accuracy: 0.8593
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.8294        | 0.9981 | 133  | 0.6474          | 0.8250   |
-| 0.723         | 1.9962 | 266  | 0.5794          | 0.8411   |
-| 0.6554        | 2.9944 | 399  | 0.5468          | 0.8517   |
-| 0.5608        | 4.0    | 533  | 0.5229          | 0.8554   |
-| 0.539         | 4.9906 | 665  | 0.5102          | 0.8590   |
+| 0.8792        | 0.9981 | 133  | 0.6722          | 0.8189   |
+| 0.7263        | 1.9962 | 266  | 0.6078          | 0.8374   |
+| 0.6474        | 2.9944 | 399  | 0.5694          | 0.8495   |
+| 0.5784        | 4.0    | 533  | 0.5476          | 0.8564   |
+| 0.5341        | 4.9906 | 665  | 0.5310          | 0.8593   |
 
 
 ### Framework versions
@@ -65,4 +65,5 @@ The following hyperparameters were used during training:
 - PEFT 0.13.2
 - Transformers 4.46.3
 - Pytorch 2.5.1+cu121
+- Datasets 3.2.0
 - Tokenizers 0.20.3