update model card README.md

README.md

@@ -20,7 +20,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 0.335
+      value: 0.3278
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [panggi/t5-base-indonesian-summarization-cased](https://huggingface.co/panggi/t5-base-indonesian-summarization-cased) on the indosum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5550
-- Rouge1: 0.335
-- Rouge2: 0.2968
-- Rougel: 0.3301
-- Rougelsum: 0.3298
+- Loss: 0.5884
+- Rouge1: 0.3278
+- Rouge2: 0.2868
+- Rougel: 0.32
+- Rougelsum: 0.3198
 - Gen Len: 19.0
 
 ## Model description
@@ -60,18 +60,14 @@ 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: 5
-- mixed_precision_training: Native AMP
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.601         | 1.0   | 200  | 0.5132          | 0.3312 | 0.2926 | 0.3246 | 0.3246    | 19.0    |
-| 0.4765        | 2.0   | 400  | 0.5236          | 0.3301 | 0.2921 | 0.3247 | 0.3246    | 19.0    |
-| 0.3971        | 3.0   | 600  | 0.5281          | 0.3337 | 0.2958 | 0.3283 | 0.3281    | 19.0    |
-| 0.3419        | 4.0   | 800  | 0.5448          | 0.3335 | 0.2951 | 0.3281 | 0.3278    | 19.0    |
-| 0.3168        | 5.0   | 1000 | 0.5550          | 0.335  | 0.2968 | 0.3301 | 0.3298    | 19.0    |
+| 0.3815        | 1.0   | 4754 | 0.5584          | 0.3281 | 0.2866 | 0.3202 | 0.32      | 19.0    |
+| 0.3207        | 2.0   | 9508 | 0.5884          | 0.3278 | 0.2868 | 0.32   | 0.3198    | 19.0    |
 
 
 ### Framework versions