Model save

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0755
-- Logloss: 1.0755
-- Accuracy: {'accuracy': 0.48}
+- Loss: 0.8782
+- Logloss: 0.8782
+- Accuracy: {'accuracy': 0.6225}
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy            |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------------------:|
-| No log        | 0.96  | 6    | 1.1961          | 1.1961  | {'accuracy': 0.415} |
-| 1.2502        | 1.92  | 12   | 1.0787          | 1.0787  | {'accuracy': 0.49}  |
-| 1.2502        | 2.88  | 18   | 1.0755          | 1.0755  | {'accuracy': 0.48}  |
+| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy             |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:--------------------:|
+| 1.2933        | 0.96  | 12   | 1.0099          | 1.0099  | {'accuracy': 0.5525} |
+| 0.9637        | 2.0   | 25   | 0.8718          | 0.8718  | {'accuracy': 0.6125} |
+| 0.9461        | 2.88  | 36   | 0.8782          | 0.8782  | {'accuracy': 0.6225} |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f50529eb6436618e4a8256af028d98133948887e071928593209319e9dcede
+oid sha256:2754a8794b28d4f477531124bf80b3acd335749104df0ab90e4530c0be87d992
 size 110352060