End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [clicknext/phayathaibert](https://huggingface.co/clicknext/phayathaibert) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6888
+- Loss: 0.5959
 - Accuracy: 0.88
 
 ## Model description
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2516        | 1.0   | 21   | 1.2798          | 0.84     |
-| 0.9569        | 2.0   | 42   | 0.9437          | 0.8      |
-| 0.8593        | 3.0   | 63   | 0.7549          | 0.88     |
-| 0.5779        | 4.0   | 84   | 0.6888          | 0.88     |
+| 1.1054        | 1.0   | 21   | 1.2019          | 0.72     |
+| 0.8283        | 2.0   | 42   | 0.8349          | 0.88     |
+| 0.738         | 3.0   | 63   | 0.6560          | 0.88     |
+| 0.447         | 4.0   | 84   | 0.5959          | 0.88     |
 
 
 ### Framework versions

runs/Nov11_07-27-56_9001d05c08e5/events.out.tfevents.1731310088.9001d05c08e5.10775.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cda0ccf5f4ceb436fb54549d4daf39aa84c7069eaadbcc8d13f5a5ba24166fb
-size 23941
+oid sha256:8418cbc168ec907a48f5129cea920dea035204255779dcaf80b4fdaf868aed6e
+size 24289