End of training

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-base-generator](https://huggingface.co/google/electra-base-generator) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.1073
+- Loss: 3.2155
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 10.3039       | 1.0   | 179  | 9.8668          |
-| 9.6565        | 2.0   | 358  | 9.2868          |
-| 9.2192        | 3.0   | 537  | 9.1073          |
+| 8.206         | 1.0   | 179  | 3.8146          |
+| 3.5779        | 2.0   | 358  | 3.2736          |
+| 3.3568        | 3.0   | 537  | 3.2155          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef08c7348bcf363e3da8ce2d4318dd835c2d69f726b759e65fb21cc31b09deca
+oid sha256:f5b95752488c7bb31c1e8fcf9082f82b4031329ce8951f7ae88c0ec26c1c5436
 size 105016