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-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2659
-- Accuracy: 0.9139
-- F1: 0.9146
+- Loss: 0.2384
+- Accuracy: 0.9067
+- F1: 0.9072
 
 ## Model description
 
@@ -45,21 +45,16 @@ 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: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.3249        | 0.2   | 500  | 0.3423          | 0.8562   | 0.8427 |
-| 0.286         | 0.4   | 1000 | 0.3201          | 0.8789   | 0.8861 |
-| 0.2842        | 0.6   | 1500 | 0.2544          | 0.9007   | 0.9009 |
-| 0.2594        | 0.81  | 2000 | 0.2487          | 0.9015   | 0.9036 |
-| 0.2184        | 1.01  | 2500 | 0.2627          | 0.9083   | 0.9081 |
-| 0.1807        | 1.21  | 3000 | 0.2750          | 0.9087   | 0.9070 |
-| 0.1628        | 1.41  | 3500 | 0.2839          | 0.9134   | 0.9130 |
-| 0.1811        | 1.61  | 4000 | 0.2909          | 0.9111   | 0.9094 |
-| 0.1802        | 1.81  | 4500 | 0.2708          | 0.9120   | 0.9133 |
+| 0.315         | 0.2   | 500  | 0.3246          | 0.8623   | 0.8525 |
+| 0.2853        | 0.4   | 1000 | 0.2960          | 0.8875   | 0.8912 |
+| 0.2658        | 0.6   | 1500 | 0.2958          | 0.8843   | 0.8767 |
+| 0.2488        | 0.81  | 2000 | 0.2495          | 0.9011   | 0.9046 |
 
 
 ### Framework versions