Correct Tokenization and Tagging

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [youscan/ukr-roberta-base](https://huggingface.co/youscan/ukr-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6314
-- Precision: 0.5111
-- Recall: 0.2640
-- F1: 0.3481
-- Accuracy: 0.9352
+- Loss: 0.5822
+- Precision: 0.5410
+- Recall: 0.3272
+- F1: 0.4078
+- Accuracy: 0.9386
 
 ## Model description
 
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.4284        | 1.0   | 3242 | 0.6027          | 0.4706    | 0.2603 | 0.3352 | 0.9329   |
-| 0.3635        | 2.0   | 6484 | 0.6314          | 0.5111    | 0.2640 | 0.3481 | 0.9352   |
+| 0.399         | 1.0   | 3242 | 0.5681          | 0.5227    | 0.3232 | 0.3994 | 0.9373   |
+| 0.3389        | 2.0   | 6484 | 0.5822          | 0.5410    | 0.3272 | 0.4078 | 0.9386   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c841a2ed843670428c9f3e64f2d89262d9e62855b4dccc3a8ee194d409e2e75
-size 517624608
+oid sha256:81186582533830594e81be22c9cdf78c3fbe11dc9fa4580b5c3afbd31e20d6c1
+size 517707660

runs/Dec09_18-18-57_1ba1901118ce/events.out.tfevents.1702145937.1ba1901118ce.716.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4c72f256b4e00e056d00613bc7a4d202bb1502c80560a6c5e6225499c2bb5d
+size 905457

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15baa84ec4d6a0cb255b018c4342ff6e8d2b66f8cb6ba7a897c06de156249870
+oid sha256:e469d75f1a48295c7d79f11c06dd75993e4267f89b14ebc2a22f4b54f94714aa
 size 4600