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: 0.0941
-- Bleu Score: 24.8094
-- Gen Len: 18.8172
+- Loss: 0.1150
+- Bleu Score: 24.3111
+- Gen Len: 18.8088
 
 ## Model description
 
@@ -38,21 +38,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 0.2195        | 1.0   | 838  | 0.1354          | 23.689     | 18.7945 |
-| 0.1289        | 2.0   | 1676 | 0.1085          | 24.4546    | 18.8053 |
-| 0.104         | 3.0   | 2514 | 0.0969          | 24.8285    | 18.8112 |
-| 0.0906        | 4.0   | 3352 | 0.0941          | 24.8094    | 18.8172 |
+| 0.2345        | 1.0   | 419  | 0.1435          | 23.4511    | 18.8112 |
+| 0.1464        | 2.0   | 838  | 0.1197          | 24.139     | 18.8053 |
+| 0.1238        | 3.0   | 1257 | 0.1150          | 24.3111    | 18.8088 |
 
 
 ### Framework versions

logs/events.out.tfevents.1731580553.2efa78e7df35.1476.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53bf12b10cd418edc02c6057b04e08a749ae0d4922d135e1945c513794adf73
-size 7250
+oid sha256:01b1bb8c9dc4c14e126235c61a40f12c95c4c9e77efef3c08be56b9cfc107e4d
+size 8191