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 [t5-base](https://huggingface.co/t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8284
+- Loss: 0.8055
 
 ## Model description
 
@@ -41,16 +41,23 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2141        | 0.74  | 80   | 0.8865          |
-| 0.9324        | 1.48  | 160  | 0.8458          |
-| 0.8786        | 2.22  | 240  | 0.8299          |
-| 0.8284        | 2.95  | 320  | 0.8284          |
+| 1.2126        | 0.45  | 80   | 0.9040          |
+| 0.9754        | 0.89  | 160  | 0.8565          |
+| 0.8818        | 1.34  | 240  | 0.8393          |
+| 0.8645        | 1.78  | 320  | 0.8234          |
+| 0.8079        | 2.23  | 400  | 0.8177          |
+| 0.7862        | 2.67  | 480  | 0.8081          |
+| 0.7636        | 3.12  | 560  | 0.8101          |
+| 0.7377        | 3.56  | 640  | 0.8074          |
+| 0.7259        | 4.01  | 720  | 0.8052          |
+| 0.7014        | 4.45  | 800  | 0.8051          |
+| 0.7042        | 4.9   | 880  | 0.8055          |
 
 
 ### Framework versions