lemmein/kaggle_essay_fold_4

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8484
-- Qwk: 0.8102
+- Loss: 0.8502
+- Qwk: 0.8024
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Qwk    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.9013        | 1.0   | 1731 | 0.9318          | 0.7425 |
-| 0.783         | 2.0   | 3462 | 0.9151          | 0.7756 |
-| 0.7575        | 3.0   | 5193 | 0.8370          | 0.8000 |
-| 0.6995        | 4.0   | 6924 | 0.8484          | 0.8102 |
+| 0.8896        | 1.0   | 1731 | 0.8665          | 0.7900 |
+| 0.8217        | 2.0   | 3462 | 0.9017          | 0.7786 |
+| 0.7622        | 3.0   | 5193 | 0.8461          | 0.8013 |
+| 0.6973        | 4.0   | 6924 | 0.8502          | 0.8024 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f14c366b306b1691dfc8f57ed71dcdb7d76d3e5a93b960a9016c68ce7d07479
+oid sha256:6be616ab23839225772cf6af7f8cf5f3f837d269b21577db1af5379e2b10f2d7
 size 567312872