Ok!

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2005
-- Accuracy: 0.958
+- Loss: 0.2283
+- Accuracy: 0.9615
 
 ## Model description
 
@@ -38,23 +38,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 4
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.9984 | 312  | 0.1556          | 0.952    |
-| 0.1828        | 2.0    | 625  | 0.1576          | 0.957    |
-| 0.1828        | 2.9984 | 937  | 0.1968          | 0.957    |
-| 0.0635        | 3.9936 | 1248 | 0.2005          | 0.958    |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.195         | 1.0   | 625  | 0.1521          | 0.9565   |
+| 0.1095        | 2.0   | 1250 | 0.1770          | 0.9605   |
+| 0.0619        | 3.0   | 1875 | 0.2225          | 0.9595   |
+| 0.0188        | 4.0   | 2500 | 0.2283          | 0.9615   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826330f505d29fb3158f98f8f533c476879ba8d8eaa3b0bea1faecd2711fdd8f
+oid sha256:03a2977c0c076554ed08d03117324de3e1fba8e89fcf09a3d5d1cdba744cc635
 size 442502140