Training 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 [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1455
-- Precision: 0.4466
-- Recall: 0.5476
-- F1: 0.4920
-- Accuracy: 0.9579
+- Loss: 0.1493
+- Precision: 0.4385
+- Recall: 0.5438
+- F1: 0.4855
+- Accuracy: 0.9567
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3067        | 1.0   | 679  | 0.1668          | 0.3167    | 0.4358 | 0.3668 | 0.9470   |
-| 0.1696        | 2.0   | 1358 | 0.1520          | 0.4094    | 0.5108 | 0.4545 | 0.9532   |
-| 0.0952        | 3.0   | 2037 | 0.1455          | 0.4466    | 0.5476 | 0.4920 | 0.9579   |
+| 0.2947        | 1.0   | 679  | 0.1679          | 0.3119    | 0.4307 | 0.3618 | 0.9454   |
+| 0.1696        | 2.0   | 1358 | 0.1627          | 0.3868    | 0.5273 | 0.4462 | 0.9518   |
+| 0.0969        | 3.0   | 2037 | 0.1493          | 0.4385    | 0.5438 | 0.4855 | 0.9567   |
 
 
 ### Framework versions