End of training

README.md

@@ -20,11 +20,11 @@ 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: nan
-- Precision: 0.3443
-- Recall: 0.6774
-- F1: 0.4565
-- Accuracy: 0.9913
+- Loss: 0.0388
+- Precision: 0.3571
+- Recall: 0.5769
+- F1: 0.4412
+- Accuracy: 0.9859
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.198         | 1.0   | 91   | nan             | 0.2059    | 0.4516 | 0.2828 | 0.9745   |
-| 0.2198        | 2.0   | 182  | nan             | 0.3279    | 0.6452 | 0.4348 | 0.9843   |
-| 0.0417        | 3.0   | 273  | nan             | 0.3167    | 0.6129 | 0.4176 | 0.9912   |
-| 0.015         | 4.0   | 364  | nan             | 0.3443    | 0.6774 | 0.4565 | 0.9913   |
+| 0.4874        | 1.0   | 32   | 0.0956          | 0.0339    | 0.0769 | 0.0471 | 0.9714   |
+| 0.1951        | 2.0   | 64   | 0.0448          | 0.2115    | 0.4231 | 0.2821 | 0.9829   |
+| 0.1086        | 3.0   | 96   | 0.0384          | 0.3556    | 0.6154 | 0.4507 | 0.9857   |
+| 0.0552        | 4.0   | 128  | 0.0388          | 0.3571    | 0.5769 | 0.4412 | 0.9859   |
 
 
 ### Framework versions