End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6359
-- Matthews Correlation: 0.5298
+- Loss: 0.8024
+- Matthews Correlation: 0.5553
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5237        | 1.0   | 535  | 0.4755          | 0.4358               |
-| 0.3503        | 2.0   | 1070 | 0.4684          | 0.4984               |
-| 0.2423        | 3.0   | 1605 | 0.6359          | 0.5298               |
-| 0.1824        | 4.0   | 2140 | 0.7712          | 0.5070               |
-| 0.1311        | 5.0   | 2675 | 0.8527          | 0.5265               |
+| 0.5215        | 1.0   | 535  | 0.4708          | 0.4553               |
+| 0.3521        | 2.0   | 1070 | 0.4657          | 0.5018               |
+| 0.2406        | 3.0   | 1605 | 0.6216          | 0.5156               |
+| 0.1828        | 4.0   | 2140 | 0.7251          | 0.5321               |
+| 0.1341        | 5.0   | 2675 | 0.8024          | 0.5553               |
 
 
 ### Framework versions

runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713886467.309eb7d6022b.9612.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592aedf77997ab4747fcd190228f44f7d7ebe55d27fef374abc2731e453a2de4
+size 423