End of training

README.md

@@ -17,16 +17,16 @@ 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: 2.6613
-- Rouge1: 20.3928
-- Rouge2: 8.6637
-- Rougel: 16.2814
-- Rougelsum: 18.1751
-- Bleu-1: 0.0041
-- Bleu-2: 0.0024
-- Bleu-3: 0.0012
-- Bleu-4: 0.0007
-- Gen Len: 20.0
+- Loss: 2.3537
+- Rouge1: 19.7155
+- Rouge2: 9.8564
+- Rougel: 16.9911
+- Rougelsum: 18.5544
+- Bleu-1: 0.0038
+- Bleu-2: 0.002
+- Bleu-3: 0.0009
+- Bleu-4: 0.0004
+- Gen Len: 19.8869
 
 ## Model description
 
@@ -57,7 +57,7 @@ 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:------:|:------:|:------:|:------:|:-------:|
-| 2.9148        | 1.0   | 10886 | 2.6613          | 20.3928 | 8.6637 | 16.2814 | 18.1751   | 0.0041 | 0.0024 | 0.0012 | 0.0007 | 20.0    |
+| 2.5589        | 1.0   | 10886 | 2.3537          | 19.7155 | 9.8564 | 16.9911 | 18.5544   | 0.0038 | 0.002  | 0.0009 | 0.0004 | 19.8869 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de75e11a0b5055a4d4039cd42842c2254c4d7a68ebf0309ec7ad37ce58604752
+oid sha256:da04c40e8ceda717c74d1022c0a8da26940c7972959a36e6a23d3b6db6e138ea
 size 558018637