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: 0.1032
-- Bleu Score: 24.5858
-- Gen Len: 18.81
+- Loss: 0.0872
+- Bleu Score: 25.2243
+- Gen Len: 18.8053
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 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   |
+| 0.2           | 1.0   | 838  | 0.1229          | 24.1188    | 18.8076 |
+| 0.1099        | 2.0   | 1676 | 0.0951          | 24.7563    | 18.8017 |
+| 0.0841        | 3.0   | 2514 | 0.0872          | 25.2243    | 18.8053 |
 
 
 ### Framework versions

logs/events.out.tfevents.1731555327.c4ea8cf1e012.8082.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad711e55d53bab43ce949e6c2b0ccc10def457e3fcb8e549fc73854a17fae561
-size 7459
+oid sha256:fbba8648602abb792506fef7c37c5868a27db529a22ad21fc47031d2fa1420da
+size 8189