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: 1.5789
-- Logloss: 1.5789
-- Accuracy: {'accuracy': 0.275}
+- Loss: 1.3130
+- Logloss: 1.3130
+- Accuracy: {'accuracy': 0.43}
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy            |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------------------:|
-| No log        | 0.8   | 1    | 1.6327          | 1.6327  | {'accuracy': 0.225} |
-| No log        | 1.6   | 2    | 1.5966          | 1.5966  | {'accuracy': 0.275} |
-| No log        | 2.4   | 3    | 1.5789          | 1.5789  | {'accuracy': 0.275} |
+| No log        | 0.96  | 6    | 1.4663          | 1.4663  | {'accuracy': 0.42}  |
+| 1.4937        | 1.92  | 12   | 1.3507          | 1.3507  | {'accuracy': 0.445} |
+| 1.4937        | 2.88  | 18   | 1.3130          | 1.3130  | {'accuracy': 0.43}  |
 
 
 ### Framework versions