End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8678
-- Accuracy: 0.74
+- Loss: 0.9996
+- Accuracy: 0.7425
 
 ## Model description
 
@@ -43,17 +43,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 200  | 0.7607          | 0.66     |
-| No log        | 2.0   | 400  | 0.6765          | 0.735    |
-| 0.7461        | 3.0   | 600  | 0.7431          | 0.715    |
-| 0.7461        | 4.0   | 800  | 0.7622          | 0.7575   |
-| 0.3037        | 5.0   | 1000 | 0.8678          | 0.74     |
+| No log        | 1.0   | 200  | 0.8824          | 0.7      |
+| No log        | 2.0   | 400  | 0.9958          | 0.7475   |
+| 0.3019        | 3.0   | 600  | 0.9996          | 0.7425   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77770766faf9b0d402961e040317d2cd5aa036b929bac57fcd6b32a81caa984
+oid sha256:49f6c8cee736aae2772a3f019173a21cc5b76b649eeb8e27a95d255e78453304
 size 556802644