Model save

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0412
-- Precision: 0.9367
-- Recall: 0.9359
-- F1: 0.9363
-- Accuracy: 0.9890
+- Loss: 0.0946
+- Precision: 0.9270
+- Recall: 0.9366
+- F1: 0.9318
+- Accuracy: 0.9788
 
 ## Model description
 
@@ -57,9 +57,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1821        | 1.0   | 164  | 0.0723          | 0.8931    | 0.9068 | 0.8999 | 0.9802   |
-| 0.0789        | 2.0   | 328  | 0.0403          | 0.9354    | 0.9402 | 0.9378 | 0.9897   |
-| 0.054         | 3.0   | 492  | 0.0412          | 0.9367    | 0.9359 | 0.9363 | 0.9890   |
+| 0.0932        | 1.0   | 250  | 0.1081          | 0.9037    | 0.9209 | 0.9122 | 0.9710   |
+| 0.0758        | 2.0   | 500  | 0.0907          | 0.9241    | 0.9371 | 0.9306 | 0.9777   |
+| 0.0348        | 3.0   | 750  | 0.0946          | 0.9270    | 0.9366 | 0.9318 | 0.9788   |
 
 
 ### Framework versions

logs/events.out.tfevents.1763833015.8b09dd3d6919.1459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b53ca685053f433297c6cba286de1146316135f68c3f65628a3f901fa3398c
+size 10598

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e82c8a60b0ffcc693e3958531f762d553c6cfac14e6d2308b507e9c8387c82c
+oid sha256:701e30bfc2b75f088e18575371630d758b13fe94e0a974ed85fa88e8d29441ab
 size 709090132