End of training

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2616
-- Accuracy: 0.9164
-- F1: 0.9164
+- Loss: 0.3104
+- Accuracy: 0.9212
+- F1: 0.9211
 
 ## Model description
 
@@ -46,14 +46,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 313  | 0.2698          | 0.9118   | 0.9117 |
-| 0.3126        | 2.0   | 626  | 0.2616          | 0.9164   | 0.9164 |
+| No log        | 1.0   | 313  | 0.2666          | 0.9118   | 0.9118 |
+| 0.2043        | 2.0   | 626  | 0.2748          | 0.9175   | 0.9175 |
+| 0.2043        | 3.0   | 939  | 0.3104          | 0.9212   | 0.9211 |
 
 
 ### Framework versions