Model save

README.md

@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0398
-- Rouge1: 35.4918
-- Rouge2: 17.885
-- Rougel: 29.6804
-- Rougelsum: 32.9507
-- Gen Len: 36.4740
+- Loss: 4.2050
+- Rouge1: 19.886
+- Rouge2: 6.0542
+- Rougel: 16.8703
+- Rougelsum: 18.2573
+- Gen Len: 30.875
 
 ## Model description
 
@@ -45,7 +45,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.001
 - train_batch_size: 16
-- eval_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 2.0683        | 1.0   | 12118 | 2.3723          | 33.423  | 16.5875 | 28.0723 | 31.0371   | 38.1132 |
-| 1.5342        | 2.0   | 24236 | 2.1400          | 34.4775 | 17.1757 | 28.8546 | 32.0264   | 36.7176 |
-| 1.241         | 3.0   | 36354 | 2.0398          | 35.4918 | 17.885  | 29.6804 | 32.9507   | 36.4740 |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 3.7824        | 1.0   | 63   | 3.8225          | 16.8681 | 5.1649 | 14.9393 | 15.6881   | 31.998  |
+| 2.0598        | 2.0   | 126  | 3.8557          | 18.6028 | 5.9301 | 15.9454 | 17.1143   | 38.822  |
+| 0.945         | 3.0   | 189  | 4.2050          | 19.886  | 6.0542 | 16.8703 | 18.2573   | 30.875  |
 
 
 ### Framework versions