update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 0.1358
+      value: 0.1383
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,11 +31,11 @@ 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 the billsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6270
-- Rouge1: 0.1358
-- Rouge2: 0.0478
-- Rougel: 0.1138
-- Rougelsum: 0.1135
+- Loss: 2.5953
+- Rouge1: 0.1383
+- Rouge2: 0.0487
+- Rougel: 0.1135
+- Rougelsum: 0.1132
 - Gen Len: 19.0
 
 ## Model description
@@ -56,22 +56,20 @@ 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
-- num_epochs: 4
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 62   | 2.9180          | 0.1291 | 0.0391 | 0.1083 | 0.1082    | 19.0    |
-| No log        | 2.0   | 124  | 2.7081          | 0.1291 | 0.0426 | 0.1086 | 0.1085    | 19.0    |
-| No log        | 3.0   | 186  | 2.6432          | 0.1384 | 0.0486 | 0.1146 | 0.1146    | 19.0    |
-| No log        | 4.0   | 248  | 2.6270          | 0.1358 | 0.0478 | 0.1138 | 0.1135    | 19.0    |
+| No log        | 1.0   | 124  | 2.6810          | 0.1312 | 0.0415 | 0.1076 | 0.1077    | 19.0    |
+| No log        | 2.0   | 248  | 2.5953          | 0.1383 | 0.0487 | 0.1135 | 0.1132    | 19.0    |
 
 
 ### Framework versions