bif02/pair_classifier

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6711
-- Accuracy: 0.9428
+- Loss: 1.0549
+- Accuracy: 0.5758
 
 ## Model description
 
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5939        | 1.0   | 756  | 0.7306          | 0.4960   |
-| 0.5951        | 2.0   | 1512 | 0.6877          | 0.9428   |
-| 0.696         | 3.0   | 2268 | 0.7393          | 0.0572   |
-| 0.6936        | 4.0   | 3024 | 0.7141          | 0.0572   |
-| 0.6949        | 5.0   | 3780 | 0.6734          | 0.9428   |
-| 0.6944        | 6.0   | 4536 | 0.6711          | 0.9428   |
+| 0.5863        | 1.0   | 694  | 0.8759          | 0.6      |
+| 0.5448        | 2.0   | 1388 | 0.7824          | 0.5742   |
+| 0.5244        | 3.0   | 2082 | 0.7285          | 0.6045   |
+| 0.4831        | 4.0   | 2776 | 0.8557          | 0.5955   |
+| 0.4684        | 5.0   | 3470 | 0.9415          | 0.5970   |
+| 0.3931        | 6.0   | 4164 | 1.0549          | 0.5758   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6590d764916eed1b81895ef995a7c86a653b28c1b1e1afd4241cdcbd2119f848
+oid sha256:0ffe9f8502589972cc1e94439cc8994a986c9fb1bb58b24d5c05581dd02e64c2
 size 1740304440

runs/Nov14_16-03-21_4031720785c0/events.out.tfevents.1731600206.4031720785c0.19272.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f77fd6ba4f9c4288731fffc7d6d235d9e41261347751ae031d063a6c6beee7b
-size 8871
+oid sha256:3d9289b7f089c88746be9c0cea5e31581aafa328e24fb5e51f6593bad790ac1a
+size 9225