Training in progress epoch 6

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: 0.5892
-- Train Accuracy: 0.8327
-- Validation Loss: 0.4402
-- Validation Accuracy: 0.8744
-- Epoch: 5
+- Train Loss: 0.4838
+- Train Accuracy: 0.8665
+- Validation Loss: 0.3478
+- Validation Accuracy: 0.9010
+- Epoch: 6
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 0.8911     | 0.7434         | 0.6902          | 0.7931              | 3     |
 | 0.7160     | 0.7937         | 0.5481          | 0.8486              | 4     |
 | 0.5892     | 0.8327         | 0.4402          | 0.8744              | 5     |
+| 0.4838     | 0.8665         | 0.3478          | 0.9010              | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd43094de273df22c025176512f6b2db27961dc7c4b1e13dfbc0d5473c15aad8
+oid sha256:faa0ea4032282f8d0352f53d2422f4b5d4e1ebb79b6cbc5ef0c401a8ecd6b6b9
 size 442938876