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 [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5393
+- Loss: 1.4859
 
 ## Model description
 
@@ -34,23 +34,33 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 7
+- eval_batch_size: 7
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8401        | 1.0   | 86   | 1.6843          |
-| 1.7607        | 2.0   | 172  | 1.6728          |
-| 1.7287        | 3.0   | 258  | 1.5888          |
-| 1.7125        | 4.0   | 344  | 1.5838          |
-| 1.6705        | 5.0   | 430  | 1.5415          |
+| 1.8338        | 1.0   | 98   | 1.6750          |
+| 1.7732        | 2.0   | 196  | 1.6229          |
+| 1.7208        | 3.0   | 294  | 1.6131          |
+| 1.6917        | 4.0   | 392  | 1.5936          |
+| 1.6579        | 5.0   | 490  | 1.6183          |
+| 1.6246        | 6.0   | 588  | 1.6015          |
+| 1.6215        | 7.0   | 686  | 1.5248          |
+| 1.5743        | 8.0   | 784  | 1.5454          |
+| 1.5621        | 9.0   | 882  | 1.5925          |
+| 1.5652        | 10.0  | 980  | 1.5213          |
+| 1.5615        | 11.0  | 1078 | 1.4845          |
+| 1.5349        | 12.0  | 1176 | 1.5443          |
+| 1.5165        | 13.0  | 1274 | 1.5304          |
+| 1.5164        | 14.0  | 1372 | 1.4773          |
+| 1.5293        | 15.0  | 1470 | 1.5537          |
 
 
 ### Framework versions