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 [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1361
-- Logloss: 1.1361
-- Accuracy: {'accuracy': 0.52}
+- Loss: 0.9281
+- Logloss: 0.9281
+- Accuracy: {'accuracy': 0.635}
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy             |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:--------------------:|
-| 1.5112        | 0.96  | 12   | 1.3027          | 1.3027  | {'accuracy': 0.4525} |
-| 1.278         | 2.0   | 25   | 1.1611          | 1.1611  | {'accuracy': 0.51}   |
-| 1.18          | 2.88  | 36   | 1.1361          | 1.1361  | {'accuracy': 0.52}   |
+| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy            |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------------------:|
+| 1.1682        | 0.992 | 31   | 1.1087          | 1.1087  | {'accuracy': 0.521} |
+| 0.9964        | 1.984 | 62   | 0.9768          | 0.9768  | {'accuracy': 0.609} |
+| 0.9557        | 2.976 | 93   | 0.9281          | 0.9281  | {'accuracy': 0.635} |
 
 
 ### Framework versions