update model card README.md

README.md

@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7113
-- Rouge1: 11.2822
-- Rouge2: 5.4812
-- Rougel: 9.2287
-- Rougelsum: 10.3078
+- Loss: 1.6608
+- Rouge1: 11.5777
+- Rouge2: 5.7493
+- Rougel: 9.5007
+- Rougelsum: 10.5779
 - Gen Len: 20.0
 
 ## Model description
@@ -41,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.7224        | 1.0   | 7506 | 1.7113          | 11.2822 | 5.4812 | 9.2287 | 10.3078   | 20.0    |
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
+| 1.7152        | 1.0   | 15011 | 1.6608          | 11.5777 | 5.7493 | 9.5007 | 10.5779   | 20.0    |
 
 
 ### Framework versions