update model card README.md

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2040
-- Rouge1: 41.009
-- Rouge2: 19.7854
-- Rougel: 35.9964
-- Rougelsum: 36.3683
+- Loss: 2.3633
+- Rouge1: 40.5438
+- Rouge2: 17.4543
+- Rougel: 35.3889
+- Rougelsum: 35.8547
 
 ## Model description
 
@@ -41,25 +41,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
-| 3.2258        | 1.0   | 45   | 2.5626          | 35.3318 | 14.4723 | 28.9743 | 29.7734   |
-| 2.6644        | 2.0   | 90   | 2.3661          | 37.9382 | 17.5774 | 33.0163 | 33.1361   |
-| 2.47          | 3.0   | 135  | 2.2789          | 38.6804 | 18.3594 | 33.702  | 34.0716   |
-| 2.3602        | 4.0   | 180  | 2.2382          | 40.5393 | 18.7869 | 35.2023 | 35.6811   |
-| 2.3251        | 5.0   | 225  | 2.2227          | 40.1596 | 18.9828 | 35.1999 | 35.5553   |
-| 2.2775        | 6.0   | 270  | 2.2114          | 40.8535 | 19.2204 | 35.8137 | 36.1612   |
-| 2.2247        | 7.0   | 315  | 2.2060          | 41.0105 | 19.7689 | 36.0327 | 36.3554   |
-| 2.2412        | 8.0   | 360  | 2.2040          | 41.009  | 19.7854 | 35.9964 | 36.3683   |
+| 3.2731        | 1.0   | 36   | 2.7149          | 31.9322 | 12.2221 | 27.5812 | 27.7701   |
+| 2.7097        | 2.0   | 72   | 2.4906          | 38.1302 | 15.5635 | 32.8281 | 33.1249   |
+| 2.5515        | 3.0   | 108  | 2.4084          | 40.3328 | 17.3795 | 34.7863 | 35.0262   |
+| 2.4601        | 4.0   | 144  | 2.3730          | 40.4377 | 17.2083 | 35.3265 | 35.7168   |
+| 2.377         | 5.0   | 180  | 2.3633          | 40.5438 | 17.4543 | 35.3889 | 35.8547   |
 
 
 ### Framework versions