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 [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4030
-- Bleu Score: 45.1405
-- Gen Len: 16.8196
+- Loss: 0.3417
+- Bleu Score: 47.0526
+- Gen Len: 16.8315
 
 ## Model description
 
@@ -43,15 +43,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 2.8374        | 1.0   | 838  | 0.5595          | 41.3763    | 16.7802 |
-| 0.7564        | 2.0   | 1676 | 0.4503          | 44.4878    | 16.8124 |
-| 0.6103        | 3.0   | 2514 | 0.4030          | 45.1405    | 16.8196 |
+| 2.798         | 1.0   | 838  | 0.5495          | 41.8683    | 16.7766 |
+| 0.7216        | 2.0   | 1676 | 0.4311          | 44.9002    | 16.8148 |
+| 0.5551        | 3.0   | 2514 | 0.3565          | 46.5247    | 16.816  |
+| 0.4951        | 4.0   | 3352 | 0.3417          | 47.0526    | 16.8315 |
 
 
 ### Framework versions

logs/events.out.tfevents.1731690205.45659cea2274.248.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc44d63860e165525fc82c3272898c8f25ad36ede1026bd96cd5aac123a43fe3
-size 7073
+oid sha256:ab6c4386a3364b586bf133d0bdd1f3a535e6ff19764260121a98bcc970ba7828
+size 8014