End of training

README.md

@@ -19,12 +19,12 @@ 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: 0.1042
-- Bleu Score: 24.4829
-- Precision: 5.4958
-- Recall: 5.4958
-- Gen Len: 18.816
-- Err: 5.4958
+- Loss: 0.0872
+- Bleu Score: 25.2243
+- Precision: 6.2127
+- Recall: 6.2127
+- Gen Len: 18.8053
+- Err: 6.2127
 
 ## Model description
 
@@ -43,22 +43,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Precision | Recall | Gen Len | Err    |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:---------:|:------:|:-------:|:------:|
-| 0.2337        | 1.0   | 419  | 0.1422          | 23.4722    | 4.0621    | 4.0621 | 18.8088 | 4.0621 |
-| 0.1441        | 2.0   | 838  | 0.1186          | 24.2104    | 5.4958    | 5.4958 | 18.8041 | 5.4958 |
-| 0.1185        | 3.0   | 1257 | 0.1077          | 24.3846    | 5.3763    | 5.3763 | 18.8124 | 5.3763 |
-| 0.1069        | 4.0   | 1676 | 0.1042          | 24.4829    | 5.4958    | 5.4958 | 18.816  | 5.4958 |
+| 0.2           | 1.0   | 838  | 0.1229          | 24.1188    | 5.2569    | 5.2569 | 18.8076 | 5.2569 |
+| 0.1099        | 2.0   | 1676 | 0.0951          | 24.7563    | 5.8542    | 5.8542 | 18.8017 | 5.8542 |
+| 0.0841        | 3.0   | 2514 | 0.0872          | 25.2243    | 6.2127    | 6.2127 | 18.8053 | 6.2127 |
 
 
 ### Framework versions

logs/events.out.tfevents.1728128573.0c9c4cd5dd26.2535.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71bb8af367ca1c31187959c80b644fdf2ae700c7b1d9efbe5f48ec9989741cf
-size 7424
+oid sha256:0fb0e61b2b0a01574e07c71f015143098485199192cb4620b7362d48fc383068
+size 8515