teacher_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: 0.3879
+- Loss: 0.3884
 
 ## Model description
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.8729        | 0.35  | 3000  | 0.5554          |
-| 0.5059        | 0.71  | 6000  | 0.4535          |
-| 0.4448        | 1.06  | 9000  | 0.4119          |
-| 0.4053        | 1.41  | 12000 | 0.4155          |
-| 0.3869        | 1.77  | 15000 | 0.3910          |
-| 0.3811        | 2.12  | 18000 | 0.3952          |
-| 0.3533        | 2.47  | 21000 | 0.3962          |
-| 0.349         | 2.83  | 24000 | 0.3879          |
+| 0.8696        | 0.35  | 3000  | 0.5508          |
+| 0.5071        | 0.71  | 6000  | 0.4578          |
+| 0.448         | 1.06  | 9000  | 0.4210          |
+| 0.4084        | 1.41  | 12000 | 0.4109          |
+| 0.3878        | 1.77  | 15000 | 0.3913          |
+| 0.3832        | 2.12  | 18000 | 0.3884          |
+| 0.3529        | 2.47  | 21000 | 0.3900          |
+| 0.3492        | 2.83  | 24000 | 0.3884          |
 
 
 ### Framework versions