End of training

README.md

@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VRLLab/TurkishBERTweet](https://huggingface.co/VRLLab/TurkishBERTweet) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1372
-- Precision: 0.8204
-- Recall: 0.5735
-- F1: 0.6751
+- Loss: 0.1383
+- Precision: 0.8301
+- Recall: 0.2220
+- F1: 0.3503
 - Accuracy: 0.9570
 
 ## Model description
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1746        | 1.0   | 298  | 0.1712          | 0.8174    | 0.5598 | 0.6645 | 0.9486   |
-| 0.1104        | 2.0   | 596  | 0.1771          | 0.8273    | 0.7134 | 0.7662 | 0.9581   |
-| 0.0684        | 3.0   | 894  | 0.2236          | 0.8564    | 0.6927 | 0.7659 | 0.9593   |
-| 0.0375        | 4.0   | 1192 | 0.2714          | 0.8429    | 0.7108 | 0.7712 | 0.9594   |
+| 0.1612        | 1.0   | 298  | 0.1726          | 0.8346    | 0.1606 | 0.2694 | 0.9495   |
+| 0.1151        | 2.0   | 596  | 0.1727          | 0.6627    | 0.4227 | 0.5162 | 0.9540   |
+| 0.0611        | 3.0   | 894  | 0.2019          | 0.6406    | 0.4591 | 0.5349 | 0.9537   |
+| 0.038         | 4.0   | 1192 | 0.2099          | 0.6010    | 0.5364 | 0.5669 | 0.9525   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460c87401b09ae789723713f0188ed6def463da35010ac4bb44a10e6dd1cf39c
+oid sha256:e603055b06c0a64751002ae17c0c3a42f537d03f1a08ca29c1edc8b8e83cc5c5
 size 649039236