Model save

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mental/mental-roberta-base](https://huggingface.co/mental/mental-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4635
-- Accuracy: 0.7674
-- F1: 0.8684
-- Precision: 0.7674
-- Recall: 1.0
+- Loss: 0.3151
+- Accuracy: 0.8698
+- F1: 0.9191
+- Precision: 0.8785
+- Recall: 0.9636
 
 ## Model description
 
@@ -59,10 +59,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.7217        | 0.96  | 15   | 0.7036          | 0.3140   | 0.2680 | 0.7397    | 0.1636 |
-| 0.6899        | 1.98  | 31   | 0.6406          | 0.7744   | 0.8715 | 0.7741    | 0.9970 |
-| 0.5867        | 3.0   | 47   | 0.5256          | 0.7674   | 0.8684 | 0.7674    | 1.0    |
-| 0.5043        | 3.82  | 60   | 0.4635          | 0.7674   | 0.8684 | 0.7674    | 1.0    |
+| 0.4479        | 0.96  | 15   | 0.4467          | 0.7674   | 0.8684 | 0.7674    | 1.0    |
+| 0.4121        | 1.98  | 31   | 0.4025          | 0.7674   | 0.8684 | 0.7674    | 1.0    |
+| 0.3394        | 3.0   | 47   | 0.3229          | 0.7674   | 0.8684 | 0.7674    | 1.0    |
+| 0.2806        | 3.82  | 60   | 0.3151          | 0.8698   | 0.9191 | 0.8785    | 0.9636 |
 
 
 ### Framework versions