End of training

README.md

@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2401
-- Bleu Score: 78.0055
-- Precision: 51.2545
-- Recall: 51.2545
-- Gen Len: 12.7897
-- Err: 51.2545
+- Loss: 0.2349
+- Bleu Score: 79.18
+- Precision: 56.1529
+- Recall: 56.1529
+- Gen Len: 12.7933
+- Err: 56.1529
 
 ## Model description
 
@@ -44,18 +44,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
-- eval_batch_size: 4
+- 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: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Precision | Recall  | Gen Len | Err     |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:---------:|:-------:|:-------:|:-------:|
-| 0.4488        | 1.0   | 1675 | 0.2401          | 78.0055    | 51.2545   | 51.2545 | 12.7897 | 51.2545 |
+| 0.4686        | 1.0   | 838  | 0.2500          | 77.4389    | 50.1792   | 50.1792 | 12.8244 | 50.1792 |
+| 0.1722        | 2.0   | 1676 | 0.2120          | 78.5311    | 54.1219   | 54.1219 | 12.7933 | 54.1219 |
+| 0.0703        | 3.0   | 2514 | 0.2349          | 79.18      | 56.1529   | 56.1529 | 12.7933 | 56.1529 |
 
 
 ### Framework versions

logs/events.out.tfevents.1727521756.629f9c3a3a4c.2834.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a55bc887a71a1957efc74b1cdca646822c357266438f38f993e6d546339fcb
-size 6867
+oid sha256:ed172b8a4399e594a9d02c486adc3c981973cd4d2315c9f25778a95052b8aebb
+size 7747

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecfdc3c7fca7e6166726877e3910c67b7f44393b3d5a3e3d4fc755ec4c7918f1
+oid sha256:cebdc591a3e32a392cf8efd815278c785985d8e74ea693fae84b9937758cb2be
 size 903834408