End of training

README.md

@@ -17,14 +17,14 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7560
-- Rouge1: 19.5866
-- Rouge2: 9.0841
-- Rougel: 15.7608
-- Rougelsum: 18.2904
-- Bleu-1: 0.0034
-- Bleu-2: 0.002
-- Bleu-3: 0.0009
+- Loss: 2.4519
+- Rouge1: 18.1817
+- Rouge2: 8.7791
+- Rougel: 15.2006
+- Rougelsum: 16.9658
+- Bleu-1: 0.0045
+- Bleu-2: 0.0027
+- Bleu-3: 0.0013
 - Bleu-4: 0.0005
 - Gen Len: 20.0
 
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Bleu-1 | Bleu-2 | Bleu-3 | Bleu-4 | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:------:|:------:|:------:|:------:|:-------:|
-| 3.013         | 1.0   | 10886 | 2.7560          | 19.5866 | 9.0841 | 15.7608 | 18.2904   | 0.0034 | 0.002  | 0.0009 | 0.0005 | 20.0    |
+| 2.6623        | 1.0   | 10886 | 2.4519          | 18.1817 | 8.7791 | 15.2006 | 16.9658   | 0.0045 | 0.0027 | 0.0013 | 0.0005 | 20.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145bca43319fee415dbc141354d6f71fd665e29e24c853aeceae4cbd2cd640fa
+oid sha256:ac2ce780e6413cfb3c416dac9f61d622c2895a9f3d9039fee7a5bcff702b55c2
 size 557939436

runs/Nov11_11-25-51_947bccbc6aa6/events.out.tfevents.1699713632.947bccbc6aa6.47.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b73d2f1837999304fe119e0a5cfdc06ea3ac036dfd61d9667b4289d614f3c4e
-size 8831
+oid sha256:f602ba953cdee906623ccafda027e1b317a03ffb92bb8b3cbb63ce2bbf67b139
+size 9910