update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 9.5595
+      value: 9.944
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,12 +31,12 @@ 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 the eli5 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7516
-- Rouge1: 9.5595
-- Rouge2: 1.7879
-- Rougel: 7.7084
-- Rougelsum: 8.8886
-- Gen Len: 18.9998
+- Loss: 3.7275
+- Rouge1: 9.944
+- Rouge2: 1.908
+- Rougel: 8.0145
+- Rougelsum: 9.2275
+- Gen Len: 18.9988
 
 ## Model description
 
@@ -61,19 +61,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.9648        | 1.0   | 17040 | 3.7545          | 9.6972 | 1.8303 | 7.8132 | 8.9964    | 18.9982 |
+| 3.9806        | 1.0   | 17040 | 3.7726          | 9.8475 | 1.872  | 7.9462 | 9.1258    | 18.9972 |
+| 3.9458        | 2.0   | 34080 | 3.7369          | 9.9232 | 1.8981 | 7.9922 | 9.2061    | 18.9988 |
+| 3.9355        | 3.0   | 51120 | 3.7275          | 9.944  | 1.908  | 8.0145 | 9.2275    | 18.9988 |
 
 
 ### Framework versions
 
-- Transformers 4.22.1
+- Transformers 4.22.2
 - Pytorch 1.12.1+cu113
 - Datasets 2.5.1
 - Tokenizers 0.12.1