Update README.md

README.md

@@ -19,7 +19,7 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0568
+- Loss: 0.7968
 - Accuracy: 0.8598
 - F1 Macro: 0.6798
 - F1 Weighted: 0.7825
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
-| 2.5353        | 1.0   | 69   | 2.2417          | 0.4041   | 0.3083   | 0.4288      |
-| 2.2018        | 2.0   | 138  | 1.8271          | 0.5619   | 0.5319   | 0.5691      |
-| 1.3566        | 3.0   | 207  | 1.5606          | 0.7808   | 0.6107   | 0.6679       |
-| 1.0568        | 4.0   | 276  | 1.068          | 0.8598   | 0.6798   | 0.7825      |
+| 2.0353        | 1.0   | 69   | 2.2417          | 0.4041   | 0.3083   | 0.4288      |
+| 1.1018        | 2.0   | 138  | 1.8271          | 0.5619   | 0.5319   | 0.5691      |
+| 1.0166        | 3.0   | 207  | 1.0606          | 0.7808   | 0.6107   | 0.6679       |
+| 0.7968        | 4.0   | 276  | 0.9268          | 0.8598   | 0.6798   | 0.7825      |
 
 
 ### Framework versions