Model save

README.md

@@ -17,8 +17,8 @@ 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: 0.2431
-- Accuracy: 0.9570
+- Loss: 0.2156
+- Accuracy: 0.9688
 
 ## Model description
 
@@ -51,14 +51,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 0.138         | 1.9531  | 500  | 0.3603          | 0.8975   |
-| 0.0517        | 3.9062  | 1000 | 0.2523          | 0.9473   |
-| 0.0184        | 5.8594  | 1500 | 0.4559          | 0.9043   |
-| 0.0097        | 7.8125  | 2000 | 0.2561          | 0.9492   |
-| 0.0035        | 9.7656  | 2500 | 0.2040          | 0.9629   |
-| 0.0025        | 11.7188 | 3000 | 0.2277          | 0.9609   |
-| 0.0021        | 13.6719 | 3500 | 0.2366          | 0.9600   |
-| 0.0016        | 15.625  | 4000 | 0.2431          | 0.9570   |
+| 0.4213        | 1.9531  | 500  | 0.3758          | 0.8955   |
+| 0.0224        | 3.9062  | 1000 | 0.2260          | 0.9502   |
+| 0.0012        | 5.8594  | 1500 | 0.2127          | 0.9570   |
+| 0.0007        | 7.8125  | 2000 | 0.2014          | 0.9678   |
+| 0.0005        | 9.7656  | 2500 | 0.2015          | 0.9697   |
+| 0.0004        | 11.7188 | 3000 | 0.2090          | 0.9688   |
+| 0.0004        | 13.6719 | 3500 | 0.2156          | 0.9688   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07789514ffe2a5e83047a3e0ff12007132d108e6215556d92b315635cfdfa666
+oid sha256:3bdc5b81d59487ed73c19e1bbf574427d4c24e23ccaaee049c5f77e2e5626a7e
 size 343230128