Model save

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7903
+- Loss: 0.9781
 
 ## Model description
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 0.9375          |
-| No log        | 2.0   | 10   | 0.9331          |
-| No log        | 3.0   | 15   | 0.9256          |
-| No log        | 4.0   | 20   | 0.9151          |
-| No log        | 5.0   | 25   | 0.9015          |
-| No log        | 6.0   | 30   | 0.8850          |
-| No log        | 7.0   | 35   | 0.8656          |
-| No log        | 8.0   | 40   | 0.8433          |
-| No log        | 9.0   | 45   | 0.8182          |
-| No log        | 10.0  | 50   | 0.7903          |
+| No log        | 1.0   | 5    | 1.1439          |
+| No log        | 2.0   | 10   | 1.1388          |
+| No log        | 3.0   | 15   | 1.1303          |
+| No log        | 4.0   | 20   | 1.1182          |
+| No log        | 5.0   | 25   | 1.1027          |
+| No log        | 6.0   | 30   | 1.0839          |
+| No log        | 7.0   | 35   | 1.0618          |
+| No log        | 8.0   | 40   | 1.0368          |
+| No log        | 9.0   | 45   | 1.0089          |
+| No log        | 10.0  | 50   | 0.9781          |
 
 
 ### Framework versions