harish3742/bert-base-cnn-ft-1

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0012
-- Rouge1: 0.0328
-- Rouge2: 0.0
-- Rougel: 0.0303
-- Rougelsum: 0.0303
+- Rouge1: 0.0309
+- Rouge2: 0.0002
+- Rougel: 0.0293
+- Rougelsum: 0.0294
 - Gen Len: 60.0
 
 ## 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 |
 |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.0383        | 0.0167 | 100  | 0.0019          | 0.0331 | 0.0    | 0.0306 | 0.0306    | 60.0    |
-| 0.0177        | 0.0334 | 200  | 0.0012          | 0.0328 | 0.0    | 0.0303 | 0.0303    | 60.0    |
+| 1.1563        | 0.0167 | 100  | 0.0032          | 0.0272 | 0.0001 | 0.0256 | 0.0256    | 60.0    |
+| 0.014         | 0.0334 | 200  | 0.0012          | 0.0309 | 0.0002 | 0.0293 | 0.0294    | 60.0    |
 
 
 ### Framework versions