End of training

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.4044
-- Rouge1: 0.0757
-- Rouge2: 0.0166
-- Rougel: 0.0599
-- Rougelsum: 0.0599
+- Rouge1: 0.0761
+- Rouge2: 0.0165
+- Rougel: 0.0598
+- Rougelsum: 0.0597
 - Gen Len: 20.0
 
 ## Model description
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 1    | 2.6773          | 0.0728 | 0.0168 | 0.0601 | 0.0601    | 20.0    |
-| No log        | 2.0   | 2    | 2.5009          | 0.0728 | 0.0168 | 0.0601 | 0.0601    | 20.0    |
-| No log        | 3.0   | 3    | 2.4456          | 0.0728 | 0.0168 | 0.0601 | 0.0601    | 20.0    |
-| No log        | 4.0   | 4    | 2.4044          | 0.0757 | 0.0166 | 0.0599 | 0.0599    | 20.0    |
+| No log        | 1.0   | 1    | 2.6773          | 0.073  | 0.0165 | 0.06   | 0.0599    | 20.0    |
+| No log        | 2.0   | 2    | 2.5010          | 0.073  | 0.0165 | 0.06   | 0.0599    | 20.0    |
+| No log        | 3.0   | 3    | 2.4455          | 0.073  | 0.0165 | 0.06   | 0.0599    | 20.0    |
+| No log        | 4.0   | 4    | 2.4044          | 0.0761 | 0.0165 | 0.0598 | 0.0597    | 20.0    |
 
 
 ### Framework versions