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 [ukr-models/xlm-roberta-base-uk](https://huggingface.co/ukr-models/xlm-roberta-base-uk) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4141
+- Loss: 1.6000
 
 ## Model description
 
@@ -34,8 +34,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 15
+- eval_batch_size: 15
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -45,9 +45,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.1571        | 1.0   | 549  | 1.5589          |
-| 1.0332        | 2.0   | 1098 | 1.3945          |
-| 0.8381        | 3.0   | 1647 | 1.4141          |
+| No log        | 1.0   | 268  | 1.8728          |
+| 2.5088        | 2.0   | 536  | 1.6342          |
+| 2.5088        | 3.0   | 804  | 1.6000          |
 
 
 ### Framework versions