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: 3.9358
-- Rouge1: 30.5741
-- Rouge2: 11.5241
-- Rougel: 25.7323
-- Rougelsum: 26.7256
+- Loss: 2.3471
+- Rouge1: 41.0242
+- Rouge2: 19.337
+- Rougel: 36.0839
+- Rougelsum: 36.6467
 
 ## Model description
 
@@ -40,33 +40,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 20
-- eval_batch_size: 20
+- learning_rate: 5.6e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
-| 3.9531        | 1.0   | 18   | 4.0768          | 30.8668 | 12.0448 | 26.0748 | 27.0649   |
-| 3.8999        | 2.0   | 36   | 4.0458          | 30.9565 | 11.9145 | 26.1991 | 27.1728   |
-| 3.8301        | 3.0   | 54   | 4.0187          | 30.9917 | 11.8826 | 26.1494 | 27.1447   |
-| 3.8494        | 4.0   | 72   | 3.9960          | 30.6865 | 11.5462 | 25.9455 | 26.8867   |
-| 3.9007        | 5.0   | 90   | 3.9776          | 30.6963 | 11.549  | 25.9559 | 26.8594   |
-| 3.7678        | 6.0   | 108  | 3.9624          | 30.6872 | 11.599  | 25.9522 | 26.8569   |
-| 3.8246        | 7.0   | 126  | 3.9509          | 30.7149 | 11.6052 | 25.9879 | 26.861    |
-| 3.8238        | 8.0   | 144  | 3.9425          | 30.5069 | 11.3856 | 25.6649 | 26.6549   |
-| 3.7948        | 9.0   | 162  | 3.9374          | 30.5871 | 11.5312 | 25.743  | 26.6969   |
-| 3.807         | 10.0  | 180  | 3.9358          | 30.5741 | 11.5241 | 25.7323 | 26.7256   |
+| 3.1572        | 1.0   | 45   | 2.6835          | 33.9132 | 14.0293 | 29.7577 | 30.3774   |
+| 2.6239        | 2.0   | 90   | 2.4952          | 37.4638 | 16.3943 | 32.7409 | 32.9237   |
+| 2.3895        | 3.0   | 135  | 2.4129          | 38.4388 | 18.1436 | 34.3211 | 34.6526   |
+| 2.3312        | 4.0   | 180  | 2.3823          | 40.7946 | 19.4997 | 35.9918 | 36.3853   |
+| 2.279         | 5.0   | 225  | 2.3637          | 41.4433 | 20.0384 | 37.0637 | 37.4853   |
+| 2.2115        | 6.0   | 270  | 2.3553          | 41.215  | 19.6974 | 36.6077 | 37.1543   |
+| 2.1477        | 7.0   | 315  | 2.3493          | 41.0707 | 19.5007 | 36.2399 | 36.7966   |
+| 2.1176        | 8.0   | 360  | 2.3471          | 41.0242 | 19.337  | 36.0839 | 36.6467   |
 
 
 ### Framework versions
 
 - Transformers 4.18.0
-- Pytorch 1.10.0+cu111
+- Pytorch 1.11.0+cu113
 - Datasets 2.1.0
 - Tokenizers 0.12.1