update model card README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: pegasus-xsum_summarization
   results: []
@@ -13,7 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9498
+- Loss: 1.7876
+- Rouge1: 25.7148
+- Rouge2: 10.9685
+- Rougel: 21.6394
+- Rougelsum: 22.3122
 
 ## Model description
 
@@ -42,16 +48,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.4508        | 1.0   | 50   | 2.5701          |
-| 2.655         | 2.0   | 100  | 2.2977          |
-| 2.3635        | 3.0   | 150  | 2.1554          |
-| 2.0941        | 4.0   | 200  | 2.0545          |
-| 2.0085        | 5.0   | 250  | 2.0147          |
-| 1.8447        | 6.0   | 300  | 1.9754          |
-| 1.7749        | 7.0   | 350  | 1.9592          |
-| 1.7061        | 8.0   | 400  | 1.9498          |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 1.633         | 1.0   | 50   | 1.8839          | 24.9703 | 9.6517  | 19.9759 | 21.088    |
+| 1.3917        | 2.0   | 100  | 1.8565          | 24.4395 | 9.1755  | 19.5702 | 20.5489   |
+| 1.2576        | 3.0   | 150  | 1.8361          | 24.8266 | 10.2009 | 20.074  | 21.382    |
+| 1.1191        | 4.0   | 200  | 1.8226          | 25.9635 | 11.7704 | 21.7787 | 22.365    |
+| 1.1138        | 5.0   | 250  | 1.8239          | 26.7874 | 12.2832 | 22.7792 | 23.4501   |
+| 1.0338        | 6.0   | 300  | 1.8094          | 26.3543 | 12.0501 | 22.3172 | 23.1194   |
+| 1.0084        | 7.0   | 350  | 1.7923          | 25.5686 | 11.0213 | 21.5288 | 21.8892   |
+| 1.0098        | 8.0   | 400  | 1.7876          | 25.7148 | 10.9685 | 21.6394 | 22.3122   |
 
 
 ### Framework versions