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-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7604
-- Matthews Correlation: 0.6799
+- Loss: 0.5933
+- Matthews Correlation: 0.6947
 
 ## Model description
 
@@ -37,10 +37,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8.402773307129759e-06
-- train_batch_size: 4
+- learning_rate: 2.148295560459091e-05
+- train_batch_size: 16
 - eval_batch_size: 16
-- seed: 3
+- seed: 28
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.4745        | 1.0   | 2138 | 0.6074          | 0.6563               |
-| 0.3523        | 2.0   | 4276 | 0.7403          | 0.6752               |
-| 0.2013        | 3.0   | 6414 | 0.7604          | 0.6799               |
+| 0.3939        | 1.0   | 535  | 0.4206          | 0.6430               |
+| 0.2243        | 2.0   | 1070 | 0.4502          | 0.6676               |
+| 0.1443        | 3.0   | 1605 | 0.5933          | 0.6947               |
 
 
 ### Framework versions