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 [kravchenko/uk-mt5-small](https://huggingface.co/kravchenko/uk-mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.9233
+- Loss: 0.1393
 
 ## Model description
 
@@ -33,20 +33,23 @@ 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: 5
+- eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 36.3545       | 1.0   | 600  | 14.7369         |
-| 17.8623       | 2.0   | 1200 | 7.3282          |
-| 11.5209       | 3.0   | 1800 | 5.8238          |
+| 13.0967       | 1.0   | 1066 | 4.2630          |
+| 1.2776        | 2.0   | 2132 | 0.2823          |
+| 0.4383        | 3.0   | 3198 | 0.2164          |
+| 0.3195        | 4.0   | 4264 | 0.1831          |
+| 0.2614        | 5.0   | 5330 | 0.1596          |
+| 0.233         | 6.0   | 6396 | 0.1498          |
 
 
 ### Framework versions