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: 0.1182
-- Precision: 0.75
-- Recall: 0.6486
-- F1: 0.6957
-- Accuracy: 0.9772
+- Loss: 0.1519
+- Precision: 0.4616
+- Recall: 0.5578
+- F1: 0.5052
+- Accuracy: 0.9580
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2878        | 1.0   | 679  | 0.1882          | 0.5667    | 0.4595 | 0.5075 | 0.9642   |
-| 0.1976        | 2.0   | 1358 | 0.1157          | 0.7241    | 0.5676 | 0.6364 | 0.9740   |
-| 0.1096        | 3.0   | 2037 | 0.1182          | 0.75      | 0.6486 | 0.6957 | 0.9772   |
+| 0.3151        | 1.0   | 679  | 0.1658          | 0.3299    | 0.4066 | 0.3643 | 0.9487   |
+| 0.1695        | 2.0   | 1358 | 0.1571          | 0.4186    | 0.5095 | 0.4596 | 0.9542   |
+| 0.0994        | 3.0   | 2037 | 0.1519          | 0.4616    | 0.5578 | 0.5052 | 0.9580   |
 
 
 ### Framework versions