End of training

README.md

@@ -16,9 +16,9 @@ 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: 0.2302
-- Bleu Score: 73.8994
-- Gen Len: 13.2
+- Loss: 0.2349
+- Bleu Score: 79.2125
+- Gen Len: 12.7933
 
 ## Model description
 
@@ -43,13 +43,15 @@ 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: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 0.4035        | 1.0   | 1047 | 0.2302          | 73.8994    | 13.2    |
+| 0.4686        | 1.0   | 838  | 0.2500          | 77.4621    | 12.8244 |
+| 0.1722        | 2.0   | 1676 | 0.2120          | 78.5608    | 12.7933 |
+| 0.0703        | 3.0   | 2514 | 0.2349          | 79.2125    | 12.7933 |
 
 
 ### Framework versions

logs/events.out.tfevents.1727295204.c250080b61f6.4707.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb199d209230e91c834e9371cdfad8b9c9115d4e7d3f2aa7c5ae0db982de374
-size 6356
+oid sha256:45025fadda542b7cb2b274955b27fbade6a4bbf9aa0e9dd9e3434b022b29cf5d
+size 7297

model.safetensors

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