Hugging Face's logo

pijarcandra22
/
NMTIndoBaliBART

Text2Text Generation
Transformers
TensorFlow
bart
generated_from_keras_callback
Model card Files Community
pijarcandra22 commited on
Commit
49702c0
·
1 Parent(s): 854727d

Training in progress epoch 193

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 5.5361
19
- - Validation Loss: 5.5677
20
- - Epoch: 192
21
 
22
  ## Model description
23
 
@@ -236,6 +236,7 @@ The following hyperparameters were used during training:
236
  | 5.5369 | 5.5698 | 190 |
237
  | 5.5373 | 5.5665 | 191 |
238
  | 5.5361 | 5.5677 | 192 |
 
239
 
240
 
241
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 5.5355
19
+ - Validation Loss: 5.5775
20
+ - Epoch: 193
21
 
22
  ## Model description
23
 
 
236
  | 5.5369 | 5.5698 | 190 |
237
  | 5.5373 | 5.5665 | 191 |
238
  | 5.5361 | 5.5677 | 192 |
239
+ | 5.5355 | 5.5775 | 193 |
240
 
241
 
242
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b25b6cbe3fcf3243514bce57891ff5be7787718fa93c7d3ccf1a884b8b02712
3
  size 558172300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f02eb47c24ed1943a003194a6223f05ee1cd9bd9b34afee4462e1e4111d279
3
  size 558172300