update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5770
+- Loss: 0.7389
 
 ## Model description
 
@@ -42,16 +42,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6364        | 1.0   | 1267 | 0.5770          |
-| 0.457         | 2.0   | 2534 | 0.5003          |
-| 0.3175        | 3.0   | 3801 | 0.5770          |
+| 0.6584        | 1.0   | 1267 | 0.5709          |
+| 0.4877        | 2.0   | 2534 | 0.5579          |
+| 0.3675        | 3.0   | 3801 | 0.5669          |
+| 0.2323        | 4.0   | 5068 | 0.7389          |
 
 
 ### Framework versions