End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3245
-- Accuracy: 0.9029
-- F1: 0.9382
+- Loss: 0.5030
+- Accuracy: 0.9086
+- F1: 0.9401
 
 ## Model description
 
@@ -46,16 +46,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.5048        | 1.0   | 175  | 0.3577          | 0.8771   | 0.9225 |
-| 0.2879        | 2.0   | 350  | 0.2603          | 0.8986   | 0.9350 |
-| 0.2345        | 3.0   | 525  | 0.2564          | 0.91     | 0.9421 |
-| 0.1868        | 4.0   | 700  | 0.3245          | 0.9029   | 0.9382 |
+| 0.1075        | 1.0   | 175  | 0.3345          | 0.9129   | 0.9440 |
+| 0.1063        | 2.0   | 350  | 0.4080          | 0.9014   | 0.9359 |
+| 0.0262        | 3.0   | 525  | 0.5030          | 0.9086   | 0.9401 |
 
 
 ### Framework versions