Model save

README.md

@@ -6,6 +6,9 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
+- precision
+- recall
+- f1
 model-index:
 - name: convnext-tiny-224-finetuned
   results: []
@@ -18,9 +21,11 @@ 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: 0.9429
-- Logloss: 0.9429
-- Accuracy: {'accuracy': 0.6371511068334937}
+- Loss: 0.9672
+- Accuracy: 0.6208
+- Precision: 0.5826
+- Recall: 0.6208
+- F1: 0.5945
 
 ## Model description
 
@@ -48,22 +53,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Logloss | Accuracy                         |
-|:-------------:|:------:|:----:|:---------------:|:-------:|:--------------------------------:|
-| 1.4538        | 0.9846 | 32   | 1.3816          | 1.3816  | {'accuracy': 0.4475457170356112} |
-| 1.2257        | 2.0    | 65   | 1.1411          | 1.1411  | {'accuracy': 0.5668912415784408} |
-| 1.0432        | 2.9846 | 97   | 1.0302          | 1.0302  | {'accuracy': 0.6034648700673725} |
-| 1.0002        | 4.0    | 130  | 0.9979          | 0.9979  | {'accuracy': 0.615014436958614}  |
-| 0.9492        | 4.9846 | 162  | 0.9781          | 0.9781  | {'accuracy': 0.631376323387873}  |
-| 0.9302        | 6.0    | 195  | 0.9664          | 0.9664  | {'accuracy': 0.629451395572666}  |
-| 0.8805        | 6.9846 | 227  | 0.9515          | 0.9515  | {'accuracy': 0.6371511068334937} |
-| 0.852         | 8.0    | 260  | 0.9504          | 0.9504  | {'accuracy': 0.6256015399422522} |
-| 0.8352        | 8.9846 | 292  | 0.9468          | 0.9468  | {'accuracy': 0.6371511068334937} |
-| 0.8245        | 9.8462 | 320  | 0.9429          | 0.9429  | {'accuracy': 0.6371511068334937} |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.0428        | 0.9846 | 32   | 1.0478          | 0.6015   | 0.5745    | 0.6015 | 0.5679 |
+| 0.9978        | 2.0    | 65   | 1.0032          | 0.6054   | 0.5653    | 0.6054 | 0.5762 |
+| 0.9449        | 2.9846 | 97   | 0.9914          | 0.6035   | 0.5685    | 0.6035 | 0.5763 |
+| 0.9432        | 4.0    | 130  | 0.9739          | 0.6141   | 0.5748    | 0.6141 | 0.5875 |
+| 0.9196        | 4.9231 | 160  | 0.9672          | 0.6208   | 0.5826    | 0.6208 | 0.5945 |
 
 
 ### Framework versions