Training done for primera-pubmed-20k

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9668
+- Loss: 0.9693
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.0626        | 0.7477 | 500  | 0.9668          |
+| 1.0613        | 0.7477 | 500  | 0.9693          |
 
 
 ### Framework versions