End of training

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/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7633
-- Rouge1: 7.5698
-- Rouge2: 7.2187
-- Rougel: 7.5696
-- Rougelsum: 7.5699
-- Gen Len: 0.0
+- Loss: 0.0076
+- Rouge1: 5.2564
+- Rouge2: 4.3885
+- Rougel: 4.8606
+- Rougelsum: 4.8628
+- Gen Len: 8.7847
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 48   | 7.0588          | 6.3855 | 5.6369 | 6.0034 | 6.001     | 4.2708  |
-| No log        | 2.0   | 96   | 4.2872          | 6.2467 | 5.4606 | 5.8714 | 5.8778    | 4.6979  |
-| No log        | 3.0   | 144  | 3.5187          | 6.3718 | 5.6928 | 6.0686 | 6.0805    | 4.0104  |
-| No log        | 4.0   | 192  | 2.9485          | 7.5698 | 7.2187 | 7.5696 | 7.5699    | 0.0     |
-| No log        | 5.0   | 240  | 2.7633          | 7.5698 | 7.2187 | 7.5696 | 7.5699    | 0.0     |
+| 0.0301        | 1.0   | 1500 | 0.0186          | 6.1606 | 5.3745 | 5.7762 | 5.7752    | 5.4517  |
+| 0.0169        | 2.0   | 3000 | 0.0115          | 5.5084 | 4.6793 | 5.1194 | 5.1214    | 7.6477  |
+| 0.0136        | 3.0   | 4500 | 0.0090          | 5.2597 | 4.4065 | 4.8716 | 4.8723    | 8.557   |
+| 0.0118        | 4.0   | 6000 | 0.0079          | 5.2273 | 4.3653 | 4.8349 | 4.8352    | 8.815   |
+| 0.0107        | 5.0   | 7500 | 0.0076          | 5.2564 | 4.3885 | 4.8606 | 4.8628    | 8.7847  |
 
 
 ### Framework versions