student_electra_small

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6526
+- Loss: 0.6385
 
 ## Model description
 
@@ -47,15 +47,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.2909        | 0.4   | 1200  | 0.9714          |
-| 0.9297        | 0.81  | 2400  | 0.8711          |
-| 0.8196        | 1.21  | 3600  | 0.7628          |
-| 0.7322        | 1.62  | 4800  | 0.7175          |
-| 0.6985        | 2.02  | 6000  | 0.6786          |
-| 0.6502        | 2.43  | 7200  | 0.6681          |
-| 0.6277        | 2.83  | 8400  | 0.6602          |
-| 0.6068        | 3.24  | 9600  | 0.6606          |
-| 0.5994        | 3.64  | 10800 | 0.6526          |
+| 1.2869        | 0.4   | 1200  | 0.9636          |
+| 0.9176        | 0.81  | 2400  | 0.8391          |
+| 0.7991        | 1.21  | 3600  | 0.7501          |
+| 0.7191        | 1.62  | 4800  | 0.6928          |
+| 0.6846        | 2.02  | 6000  | 0.6669          |
+| 0.6356        | 2.43  | 7200  | 0.6525          |
+| 0.6087        | 2.83  | 8400  | 0.6383          |
+| 0.5962        | 3.24  | 9600  | 0.6397          |
+| 0.5749        | 3.64  | 10800 | 0.6385          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc59838d9170620720d2459e9a25c4a43722d2cc7d09d9f5bc52d1c41c1606c
+oid sha256:375f0deefcab3bbd16e43eac122933f58bbb97619b82080a0753608edecac60e
 size 54270390