Training in progress epoch 4

README.md

@@ -16,11 +16,11 @@ 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:
-- Train Loss: 1.1069
-- Train Accuracy: 0.6872
-- Validation Loss: 0.8943
-- Validation Accuracy: 0.7295
-- Epoch: 2
+- Train Loss: 0.7160
+- Train Accuracy: 0.7937
+- Validation Loss: 0.5481
+- Validation Accuracy: 0.8486
+- Epoch: 4
 
 ## Model description
 
@@ -49,6 +49,8 @@ The following hyperparameters were used during training:
 | 3.0220     | 0.2760         | 1.7334          | 0.5717              | 0     |
 | 1.5144     | 0.5985         | 1.1455          | 0.6699              | 1     |
 | 1.1069     | 0.6872         | 0.8943          | 0.7295              | 2     |
+| 0.8911     | 0.7434         | 0.6902          | 0.7931              | 3     |
+| 0.7160     | 0.7937         | 0.5481          | 0.8486              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8a73ea3ec12202b0571608e7a49f8a882305e5575a5f5388b4f3fac1e62895
+oid sha256:3af4b2a924192e1367f9fc95a7229bd9e7049f76df7d9f6cdea9c0e11bb8acb0
 size 442938876