End of training

README.md

@@ -5,6 +5,7 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
+- matthews_correlation
 model-index:
 - name: c4-binary-english-grammar-checker
   results: []
@@ -17,8 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7704
-- Accuracy: 0.8103
+- Loss: 0.3546
+- Accuracy: 0.8577
+- Matthews Correlation: 0.7192
 
 ## Model description
 
@@ -43,17 +45,14 @@ 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: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.4222        | 1.0   | 12500 | 0.4028          | 0.8196   |
-| 0.3544        | 2.0   | 25000 | 0.4459          | 0.8211   |
-| 0.2939        | 3.0   | 37500 | 0.5059          | 0.8174   |
-| 0.2327        | 4.0   | 50000 | 0.6280          | 0.8081   |
-| 0.1822        | 5.0   | 62500 | 0.7704          | 0.8103   |
+| Training Loss | Epoch | Step   | Validation Loss | Accuracy | Matthews Correlation |
+|:-------------:|:-----:|:------:|:---------------:|:--------:|:--------------------:|
+| 0.363         | 1.0   | 200000 | 0.3634          | 0.8487   | 0.7025               |
+| 0.3032        | 2.0   | 400000 | 0.3546          | 0.8577   | 0.7192               |
 
 
 ### Framework versions