End of training

README.md

@@ -25,13 +25,13 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8094689663785088
+      value: 0.8140302498537645
     - name: Recall
       type: recall
-      value: 0.8519438034874551
+      value: 0.8535940649005462
     - name: F1
       type: f1
-      value: 0.8301634398502927
+      value: 0.8333428384042887
 ---
 
 <!-- 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-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the source_data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1442
-- Accuracy Score: 0.9554
-- Precision: 0.8095
-- Recall: 0.8519
-- F1: 0.8302
+- Loss: 0.1432
+- Accuracy Score: 0.9557
+- Precision: 0.8140
+- Recall: 0.8536
+- F1: 0.8333
 
 ## Model description
 
@@ -77,8 +77,8 @@ No additional optimizer arguments
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Score | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:---------:|:------:|:------:|
-| 0.1078        | 1.0   | 864  | 0.1402          | 0.9529         | 0.8074    | 0.8323 | 0.8196 |
-| 0.0738        | 2.0   | 1728 | 0.1442          | 0.9554         | 0.8095    | 0.8519 | 0.8302 |
+| 0.1092        | 1.0   | 864  | 0.1403          | 0.9520         | 0.8061    | 0.8293 | 0.8175 |
+| 0.075         | 2.0   | 1728 | 0.1432          | 0.9557         | 0.8140    | 0.8536 | 0.8333 |
 
 
 ### Framework versions