update model card README.md

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3411
-- Accuracy: 0.865
-- F1: 0.9046
+- Loss: 0.2891
+- Accuracy: 0.8925
+- F1: 0.9228
 
 ## Model description
 
@@ -57,11 +57,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.4522        | 1.0   | 57   | 0.4265          | 0.8075   | 0.8666 |
-| 0.2951        | 2.0   | 114  | 0.3313          | 0.8625   | 0.9009 |
-| 0.3248        | 3.0   | 171  | 0.3604          | 0.855    | 0.9000 |
-| 0.1417        | 4.0   | 228  | 0.3411          | 0.865    | 0.9046 |
-| 0.1147        | 5.0   | 285  | 0.3359          | 0.865    | 0.9018 |
+| 0.5998        | 1.0   | 57   | 0.5425          | 0.74     | 0.8349 |
+| 0.5058        | 2.0   | 114  | 0.3020          | 0.875    | 0.9084 |
+| 0.3316        | 3.0   | 171  | 0.2891          | 0.8925   | 0.9228 |
+| 0.1617        | 4.0   | 228  | 0.2937          | 0.8825   | 0.9138 |
+| 0.3161        | 5.0   | 285  | 0.3193          | 0.8875   | 0.9171 |
 
 
 ### Framework versions