End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0885
-- Accuracy: 0.9708
+- Loss: 0.0785
+- Accuracy: 0.9725
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.3871        | 0.9867 | 37   | 0.2672          | 0.9071   |
-| 0.1877        | 2.0    | 75   | 0.1377          | 0.9552   |
-| 0.1302        | 2.9867 | 112  | 0.1129          | 0.9577   |
-| 0.1012        | 4.0    | 150  | 0.1165          | 0.9565   |
-| 0.0934        | 4.9333 | 185  | 0.0885          | 0.9708   |
+| 0.3738        | 0.9867 | 37   | 0.2391          | 0.9208   |
+| 0.1783        | 2.0    | 75   | 0.1439          | 0.95     |
+| 0.1213        | 2.9867 | 112  | 0.1164          | 0.9623   |
+| 0.0892        | 4.0    | 150  | 0.0962          | 0.9673   |
+| 0.0851        | 4.9333 | 185  | 0.0785          | 0.9725   |
 
 
 ### Framework versions