Trained 24 epoch (Double check overfiting)

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9966
-- Rouge1: 0.7313
-- Rouge2: 0.6085
-- Rougel: 0.7292
-- Rougelsum: 0.73
-- Gen Len: 6.9487
+- Loss: 0.9664
+- Rouge1: 0.7291
+- Rouge2: 0.6063
+- Rougel: 0.7259
+- Rougelsum: 0.7278
+- Gen Len: 6.9658
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.692         | 3.7879  | 500  | 1.0552          | 0.7273 | 0.6085 | 0.7224 | 0.7248    | 7.1709  |
-| 1.0841        | 7.5758  | 1000 | 1.0062          | 0.7346 | 0.6104 | 0.7318 | 0.7326    | 7.0342  |
-| 1.0105        | 11.3636 | 1500 | 0.9966          | 0.7313 | 0.6085 | 0.7292 | 0.73      | 6.9487  |
+| 0.9199        | 3.7879  | 500  | 0.9804          | 0.735  | 0.61   | 0.7309 | 0.7326    | 7.0299  |
+| 0.8632        | 7.5758  | 1000 | 0.9696          | 0.7269 | 0.6049 | 0.7237 | 0.7253    | 6.9786  |
+| 0.8398        | 11.3636 | 1500 | 0.9664          | 0.7291 | 0.6063 | 0.7259 | 0.7278    | 6.9658  |
 
 
 ### Framework versions

runs/Jul09_16-33-58_c5eadc05cc54/events.out.tfevents.1720542838.c5eadc05cc54.3138.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d18aee3e8b183b64f893d096b40929969bd4109f65064b92e521fef499394d
-size 8074
+oid sha256:a4850fe9742184746c7ce746f93b02c816d2e1caf5d4ae3ff98aa88ab4aa6b0a
+size 8428