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 [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3425
-- Precision: 0.7075
-- Recall: 0.7106
-- F1: 0.7090
-- Accuracy: 0.9442
+- Loss: 0.3866
+- Precision: 0.6323
+- Recall: 0.6344
+- F1: 0.6333
+- Accuracy: 0.9484
 
 ## Model description
 
@@ -49,15 +49,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3743        | 1.0   | 2500 | 0.4070          | 0.6887    | 0.6918 | 0.6894 | 0.9183   |
-| 0.2331        | 2.0   | 5000 | 0.3845          | 0.6980    | 0.7000 | 0.6989 | 0.9308   |
-| 0.1176        | 3.0   | 7500 | 0.3425          | 0.7075    | 0.7106 | 0.7090 | 0.9442   |
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3835        | 1.0   | 2500  | 0.4185          | 0.6829    | 0.6859 | 0.6832 | 0.9097   |
+| 0.2718        | 2.0   | 5000  | 0.3822          | 0.7011    | 0.7016 | 0.7011 | 0.9329   |
+| 0.1602        | 3.0   | 7500  | 0.3330          | 0.6302    | 0.6321 | 0.6311 | 0.9451   |
+| 0.1018        | 4.0   | 10000 | 0.3639          | 0.6332    | 0.6351 | 0.6340 | 0.9496   |
+| 0.0508        | 5.0   | 12500 | 0.3866          | 0.6323    | 0.6344 | 0.6333 | 0.9484   |
 
 
 ### Framework versions