Training in progress epoch 10

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: 0.3485
-- Train Accuracy: 0.9174
-- Validation Loss: 0.2435
-- Validation Accuracy: 0.9444
-- Epoch: 8
+- Train Loss: 0.2601
+- Train Accuracy: 0.9492
+- Validation Loss: 0.1871
+- Validation Accuracy: 0.9544
+- Epoch: 10
 
 ## Model description
 
@@ -55,6 +55,8 @@ The following hyperparameters were used during training:
 | 0.5022     | 0.8635         | 0.3576          | 0.9127              | 6     |
 | 0.4176     | 0.8977         | 0.3104          | 0.9266              | 7     |
 | 0.3485     | 0.9174         | 0.2435          | 0.9444              | 8     |
+| 0.2946     | 0.9385         | 0.2144          | 0.9444              | 9     |
+| 0.2601     | 0.9492         | 0.1871          | 0.9544              | 10    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31a691f9f3e65f05c5c2d63588bb46bc9c1597ca31580c5e592bdc84889c853
+oid sha256:3ad5c02c942d0f662c1351d94eb990930d6ff42c50c835ad4c8eb45d94b7fe3a
 size 442938876