Training complete

README.md

@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0925
-- Precision: 0.6771
+- Loss: 0.0909
+- Precision: 0.6831
 - Recall: 0.7942
-- F1: 0.7310
+- F1: 0.7344
 - Accuracy: 0.9787
 
 ## Model description
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1015        | 1.0   | 679  | 0.0678          | 0.6033    | 0.7827 | 0.6814 | 0.9765   |
-| 0.0476        | 2.0   | 1358 | 0.0707          | 0.6835    | 0.8094 | 0.7411 | 0.9791   |
-| 0.0136        | 3.0   | 2037 | 0.0925          | 0.6771    | 0.7942 | 0.7310 | 0.9787   |
+| 0.1074        | 1.0   | 679  | 0.0666          | 0.6112    | 0.7891 | 0.6889 | 0.9764   |
+| 0.0483        | 2.0   | 1358 | 0.0678          | 0.6894    | 0.8094 | 0.7446 | 0.9793   |
+| 0.0136        | 3.0   | 2037 | 0.0909          | 0.6831    | 0.7942 | 0.7344 | 0.9787   |
 
 
 ### Framework versions