Model save

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1609
-- Precision: 0.9074
-- Recall: 0.9232
-- F1: 0.9152
-- Accuracy: 0.9618
+- Loss: 0.1591
+- Precision: 0.9068
+- Recall: 0.9245
+- F1: 0.9156
+- Accuracy: 0.9622
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2227        | 1.0   | 1250 | 0.1614          | 0.8848    | 0.9046 | 0.8946 | 0.9537   |
-| 0.1229        | 2.0   | 2500 | 0.1599          | 0.9020    | 0.9191 | 0.9105 | 0.9594   |
-| 0.0778        | 3.0   | 3750 | 0.1609          | 0.9074    | 0.9232 | 0.9152 | 0.9618   |
+| 0.2222        | 1.0   | 1250 | 0.1655          | 0.8835    | 0.9037 | 0.8935 | 0.9533   |
+| 0.1227        | 2.0   | 2500 | 0.1618          | 0.8954    | 0.9199 | 0.9075 | 0.9590   |
+| 0.0783        | 3.0   | 3750 | 0.1591          | 0.9068    | 0.9245 | 0.9156 | 0.9622   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77cc980684a847dc856bfeb1b353f9d2692b02bed8d80dcc17a7ee8abed7258
+oid sha256:eb22fcfe2bc86cc7664af8e1cf77f3ed25e3d0b3bd35a8bdb028dc186f4c3bb4
 size 440194956