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: 0.1493
-- Precision: 0.4385
-- Recall: 0.5438
-- F1: 0.4855
-- Accuracy: 0.9567
+- Loss: 0.1455
+- Precision: 0.4444
+- Recall: 0.5388
+- F1: 0.4871
+- Accuracy: 0.9572
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 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   |
+| 0.3222        | 1.0   | 679  | 0.1763          | 0.3318    | 0.4574 | 0.3846 | 0.9472   |
+| 0.1664        | 2.0   | 1358 | 0.1612          | 0.3817    | 0.5044 | 0.4346 | 0.9522   |
+| 0.096         | 3.0   | 2037 | 0.1455          | 0.4444    | 0.5388 | 0.4871 | 0.9572   |
 
 
 ### Framework versions