Model save

README.md

@@ -17,7 +17,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7147
+- Loss: 0.7119
 - Rouge1: 0.677
 - Rouge2: 0.0
 - Rougel: 0.6766
@@ -43,7 +43,7 @@ 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 Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.2189        | 1.0   | 892  | 0.7782          | 0.6456 | 0.0    | 0.6409 | 0.6449    | 1.0     |
-| 0.6795        | 2.0   | 1784 | 0.6560          | 0.6574 | 0.0    | 0.6553 | 0.6569    | 1.0     |
-| 0.4861        | 3.0   | 2676 | 0.6245          | 0.6717 | 0.0    | 0.6667 | 0.6691    | 1.0     |
-| 0.3405        | 4.0   | 3568 | 0.6443          | 0.6974 | 0.0    | 0.6969 | 0.6948    | 1.0     |
-| 0.2041        | 5.0   | 4460 | 0.7147          | 0.677  | 0.0    | 0.6766 | 0.6756    | 1.0     |
+| 1.2189        | 1.0   | 892  | 0.7751          | 0.6416 | 0.0    | 0.6379 | 0.6405    | 1.0     |
+| 0.6795        | 2.0   | 1784 | 0.6535          | 0.6574 | 0.0    | 0.6553 | 0.6569    | 1.0     |
+| 0.4861        | 3.0   | 2676 | 0.6220          | 0.6717 | 0.0    | 0.6667 | 0.6691    | 1.0     |
+| 0.3405        | 4.0   | 3568 | 0.6415          | 0.6974 | 0.0    | 0.6969 | 0.6948    | 1.0     |
+| 0.2041        | 5.0   | 4460 | 0.7119          | 0.677  | 0.0    | 0.6766 | 0.6756    | 1.0     |
 
 
 ### Framework versions