update model card README.md

README.md

@@ -14,9 +14,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3575
-- Exact match: 80.14
-- F2 Score: 82.99
+- Loss: 0.2601
 
 ## Model description
 
@@ -47,11 +45,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 16   | 2.1705          |
-| No log        | 2.0   | 32   | 0.6287          |
-| No log        | 3.0   | 48   | 0.4151          |
-| No log        | 4.0   | 64   | 0.3716          |
-| No log        | 5.0   | 80   | 0.3575          |
+| No log        | 1.0   | 24   | 0.8576          |
+| No log        | 2.0   | 48   | 0.3439          |
+| No log        | 3.0   | 72   | 0.2807          |
+| No log        | 4.0   | 96   | 0.2653          |
+| No log        | 5.0   | 120  | 0.2601          |
 
 
 ### Framework versions