GuysTrans
/

bart-base-re-attention-seq-512

Text2Text Generation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

GuysTrans commited on Nov 17, 2023

Commit

e774e74

•

1 Parent(s): 37da5d8

End of training

Files changed (2) hide show

README.md +7 -7
pytorch_model.bin +1 -1

README.md CHANGED Viewed

@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0170
-- Rouge1: 34.1887
-- Rouge2: 25.9559
-- Rougel: 32.5277
-- Rougelsum: 33.5841
-- Gen Len: 25.9109
 ## Model description
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 2.149         | 1.0   | 18247 | 1.0170          | 34.1887 | 25.9559 | 32.5277 | 33.5841   | 25.9109 |
 ### Framework versions

 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.0248
+- Rouge1: 33.2192
+- Rouge2: 24.9335
+- Rougel: 31.3845
+- Rougelsum: 32.5782
+- Gen Len: 25.9276
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.1741        | 1.0   | 18247 | 1.0248          | 33.2192 | 24.9335 | 31.3845 | 32.5782   | 25.9276 |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b87730d59f6f52476d167e76290688c1900604065e464e4ad4aaad90e43b3f1
 size 558018637

 version https://git-lfs.github.com/spec/v1
+oid sha256:7c294366c91ccdba7c605894aa5f7d6f795cd6164e385a8af5d8fe7feb42bf94
 size 558018637