update model card README.md

README.md

@@ -1,4 +1,5 @@
 ---
+license: mit
 tags:
 - generated_from_trainer
 model-index:
@@ -11,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # QA_model
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [ukr-models/xlm-roberta-base-uk](https://huggingface.co/ukr-models/xlm-roberta-base-uk) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3301
+- Loss: 1.2469
 
 ## Model description
 
@@ -44,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1191        | 1.0   | 522  | 1.5923          |
-| 1.2952        | 2.0   | 1044 | 1.4592          |
-| 1.0273        | 3.0   | 1566 | 1.4694          |
+| 2.4142        | 1.0   | 617  | 1.4330          |
+| 1.3597        | 2.0   | 1234 | 1.2957          |
+| 1.0469        | 3.0   | 1851 | 1.3110          |
 
 
 ### Framework versions
 
 - Transformers 4.26.1
 - Pytorch 1.13.1+cu116
-- Datasets 2.10.0
+- Datasets 2.10.1
 - Tokenizers 0.13.2