update model card README.md

README.md

@@ -5,7 +5,6 @@ metrics:
 - precision
 - recall
 - f1
-- accuracy
 model-index:
 - name: prot_bert_bfd
   results: []
@@ -18,11 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5239
-- Precision: 0.0334
-- Recall: 0.0425
-- F1: 0.0374
-- Accuracy: 0.7798
+- Loss: 0.4955
+- Precision: 0.7674
+- Recall: 0.7769
+- F1: 0.7666
 
 ## Model description
 
@@ -51,11 +49,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 61   | 0.5012          | 0.0392    | 0.0490 | 0.0435 | 0.7649   |
-| No log        | 2.0   | 122  | 0.4769          | 0.0265    | 0.0458 | 0.0336 | 0.7860   |
-| No log        | 3.0   | 183  | 0.5239          | 0.0334    | 0.0425 | 0.0374 | 0.7798   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 61   | 0.4786          | 0.7709    | 0.7746 | 0.7724 |
+| No log        | 2.0   | 122  | 0.4696          | 0.7810    | 0.7799 | 0.7804 |
+| No log        | 3.0   | 183  | 0.4955          | 0.7674    | 0.7769 | 0.7666 |
 
 
 ### Framework versions