Model save

README.md

@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [benjamin/roberta-large-wechsel-ukrainian](https://huggingface.co/benjamin/roberta-large-wechsel-ukrainian) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5681
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
+- Loss: 0.5271
+- Precision: 0.7143
+- Recall: 0.0004
+- F1: 0.0008
 - Accuracy: 0.7486
 
 ## Model description
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| 0.5796        | 1.0   | 483  | 0.5647          | 0.0       | 0.0    | 0.0 | 0.7486   |
-| 0.5651        | 2.0   | 966  | 0.5754          | 0.0       | 0.0    | 0.0 | 0.7486   |
-| 0.5493        | 3.0   | 1449 | 0.5681          | 0.0       | 0.0    | 0.0 | 0.7486   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.5773        | 1.0   | 483  | 0.5506          | 0.0       | 0.0    | 0.0    | 0.7486   |
+| 0.5529        | 2.0   | 966  | 0.5540          | 0.0       | 0.0    | 0.0    | 0.7486   |
+| 0.535         | 3.0   | 1449 | 0.5271          | 0.7143    | 0.0004 | 0.0008 | 0.7486   |
 
 
 ### Framework versions