End of training

README.md

@@ -25,13 +25,13 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9463049579045837
+      value: 0.9612769172648281
     - name: Recall
       type: recall
-      value: 0.9636121165936369
+      value: 0.9695180034292246
     - name: F1
       type: f1
-      value: 0.9548801208231075
+      value: 0.9653798729014512
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract) on the source_data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0082
-- Accuracy Score: 0.9978
-- Precision: 0.9463
-- Recall: 0.9636
-- F1: 0.9549
+- Loss: 0.0068
+- Accuracy Score: 0.9981
+- Precision: 0.9613
+- Recall: 0.9695
+- F1: 0.9654
 
 ## Model description
 
@@ -79,7 +79,7 @@ No additional optimizer arguments
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy Score | Precision | Recall | F1     |
 |:-------------:|:------:|:----:|:---------------:|:--------------:|:---------:|:------:|:------:|
-| 0.0047        | 0.9994 | 863  | 0.0082          | 0.9978         | 0.9463    | 0.9636 | 0.9549 |
+| 0.0046        | 0.9994 | 863  | 0.0068          | 0.9981         | 0.9613    | 0.9695 | 0.9654 |
 
 
 ### Framework versions