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: 0.5030
-- Accuracy: 0.9086
-- F1: 0.9401
+- Loss: 0.6973
+- Accuracy: 0.9114
+- F1: 0.9427
 
 ## Model description
 
@@ -46,15 +46,18 @@ 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: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 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 |
+| 0.021         | 1.0   | 175  | 0.5527          | 0.8986   | 0.9354 |
+| 0.0123        | 2.0   | 350  | 0.5993          | 0.9029   | 0.9355 |
+| 0.0002        | 3.0   | 525  | 0.7007          | 0.9029   | 0.9382 |
+| 0.0313        | 4.0   | 700  | 0.6765          | 0.9086   | 0.9407 |
+| 0.023         | 5.0   | 875  | 0.6983          | 0.9086   | 0.9405 |
+| 0.0057        | 6.0   | 1050 | 0.6973          | 0.9114   | 0.9427 |
 
 
 ### Framework versions