bart_summarisation

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MeetK/bart_summarisation](https://huggingface.co/MeetK/bart_summarisation) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9859
-- Rouge1: 0.3097
-- Rouge2: 0.1098
-- Rougel: 0.2179
-- Rougelsum: 0.2179
-- Gen Len: 66.253
+- Loss: 1.8883
+- Rouge1: 0.3141
+- Rouge2: 0.1149
+- Rougel: 0.2245
+- Rougelsum: 0.2242
+- Gen Len: 65.948
 
 ## Model description
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 313  | 1.9651          | 0.3079 | 0.108  | 0.2162 | 0.2161    | 66.486  |
-| 1.5838        | 2.0   | 626  | 1.9859          | 0.3097 | 0.1098 | 0.2179 | 0.2179    | 66.253  |
+| No log        | 1.0   | 313  | 1.8695          | 0.3125 | 0.1133 | 0.2222 | 0.222     | 65.591  |
+| 2.1067        | 2.0   | 626  | 1.8883          | 0.3141 | 0.1149 | 0.2245 | 0.2242    | 65.948  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d64c5c0cdfa0fa50dfc8448efaa8e35b72b1db09d53fad8ad23481899cd05f3
+oid sha256:b50b8ef1f799b288adbc8697487c1fe49eaafe32c35c4bc6c283f829333ae0ff
 size 1625426996