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/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0809
-- Bleu Score: 25.4116
-- Gen Len: 18.8124
+- Loss: 0.1032
+- Bleu Score: 24.5858
+- Gen Len: 18.81
 
 ## Model description
 
@@ -37,22 +37,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - 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: 4
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 0.2003        | 1.0   | 838  | 0.1201          | 24.1793    | 18.8017 |
-| 0.11          | 2.0   | 1676 | 0.0926          | 24.8581    | 18.81   |
-| 0.0832        | 3.0   | 2514 | 0.0833          | 25.3868    | 18.8136 |
-| 0.0674        | 4.0   | 3352 | 0.0809          | 25.4116    | 18.8124 |
+| 0.2198        | 1.0   | 838  | 0.1347          | 23.608     | 18.7897 |
+| 0.1309        | 2.0   | 1676 | 0.1099          | 24.3086    | 18.8088 |
+| 0.1079        | 3.0   | 2514 | 0.1032          | 24.5858    | 18.81   |
 
 
 ### Framework versions

logs/events.out.tfevents.1731548527.feef9f44965a.800.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b00decd1122e272a72b73fa702eb7237e02cf94ee83b4ca9464c15a4bbe0320
-size 7459
+oid sha256:aea16b4662e6afa8d5883d88ecb82eeadaede33a7472ac461b5ae8267dae8e21
+size 8189