training and evaluation complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1473
-- Precision: 0.8997
-- Recall: 0.9311
-- F1: 0.9151
-- Accuracy: 0.9721
+- Loss: 0.1280
+- Precision: 0.8723
+- Recall: 0.9143
+- F1: 0.8928
+- Accuracy: 0.9697
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 199  | 0.1382          | 0.8850    | 0.9270 | 0.9055 | 0.9701   |
-| No log        | 2.0   | 398  | 0.1359          | 0.9080    | 0.9250 | 0.9164 | 0.9706   |
-| 0.0325        | 3.0   | 597  | 0.1473          | 0.8997    | 0.9311 | 0.9151 | 0.9721   |
+| No log        | 1.0   | 199  | 0.1830          | 0.7612    | 0.8280 | 0.7932 | 0.9483   |
+| No log        | 2.0   | 398  | 0.1424          | 0.8580    | 0.9103 | 0.8834 | 0.9643   |
+| 0.2566        | 3.0   | 597  | 0.1280          | 0.8723    | 0.9143 | 0.8928 | 0.9697   |
 
 
 ### Framework versions