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: 0.1575
-- Precision: 0.4327
-- Recall: 0.5311
-- F1: 0.4769
-- Accuracy: 0.9551
+- Loss: 0.1507
+- Precision: 0.4388
+- Recall: 0.5464
+- F1: 0.4867
+- Accuracy: 0.9562
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2993        | 1.0   | 679  | 0.1742          | 0.3244    | 0.3990 | 0.3578 | 0.9458   |
-| 0.169         | 2.0   | 1358 | 0.1540          | 0.4128    | 0.5172 | 0.4591 | 0.9523   |
-| 0.0958        | 3.0   | 2037 | 0.1575          | 0.4327    | 0.5311 | 0.4769 | 0.9551   |
+| 0.2973        | 1.0   | 679  | 0.1688          | 0.3128    | 0.4447 | 0.3673 | 0.9464   |
+| 0.1679        | 2.0   | 1358 | 0.1500          | 0.4156    | 0.5070 | 0.4568 | 0.9555   |
+| 0.0985        | 3.0   | 2037 | 0.1507          | 0.4388    | 0.5464 | 0.4867 | 0.9562   |
 
 
 ### Framework versions