update model card README.md

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8904
+- Loss: 0.4267
 
 ## Model description
 
@@ -41,20 +41,28 @@ 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_steps: 400
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.9404        | 0.65  | 1000 | 2.6896          |
-| 2.0156        | 1.31  | 2000 | 1.6584          |
-| 1.2005        | 1.96  | 3000 | 1.2147          |
-| 0.8557        | 2.62  | 4000 | 1.0335          |
-| 0.6985        | 3.27  | 5000 | 0.9464          |
-| 0.6183        | 3.93  | 6000 | 0.9031          |
-| 0.5817        | 4.58  | 7000 | 0.8904          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5187        | 0.65  | 1000  | 0.6013          |
+| 0.4429        | 1.31  | 2000  | 0.5585          |
+| 0.3791        | 1.96  | 3000  | 0.5298          |
+| 0.3316        | 2.62  | 4000  | 0.5153          |
+| 0.2991        | 3.27  | 5000  | 0.5025          |
+| 0.3066        | 3.93  | 6000  | 0.4808          |
+| 0.2795        | 4.58  | 7000  | 0.4675          |
+| 0.2599        | 5.24  | 8000  | 0.4594          |
+| 0.2432        | 5.89  | 9000  | 0.4460          |
+| 0.2282        | 6.54  | 10000 | 0.4431          |
+| 0.2167        | 7.2   | 11000 | 0.4381          |
+| 0.2075        | 7.85  | 12000 | 0.4291          |
+| 0.2013        | 8.51  | 13000 | 0.4307          |
+| 0.1977        | 9.16  | 14000 | 0.4266          |
+| 0.1951        | 9.82  | 15000 | 0.4267          |
 
 
 ### Framework versions