update model card README.md

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the becasv3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0641
+- Loss: 3.1086
 
 ## Model description
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 8    | 5.0462          |
-| No log        | 2.0   | 16   | 4.3106          |
-| No log        | 3.0   | 24   | 3.8295          |
-| No log        | 4.0   | 32   | 3.5128          |
-| No log        | 5.0   | 40   | 3.2864          |
-| No log        | 6.0   | 48   | 3.1930          |
-| No log        | 7.0   | 56   | 3.1056          |
-| No log        | 8.0   | 64   | 3.0641          |
+| No log        | 1.0   | 8    | 5.1063          |
+| No log        | 2.0   | 16   | 4.4615          |
+| No log        | 3.0   | 24   | 3.9351          |
+| No log        | 4.0   | 32   | 3.5490          |
+| No log        | 5.0   | 40   | 3.3299          |
+| No log        | 6.0   | 48   | 3.2148          |
+| No log        | 7.0   | 56   | 3.1292          |
+| No log        | 8.0   | 64   | 3.1086          |
 
 
 ### Framework versions