Hugging Face's logo

KostiuchenkoArtem
/
bart_large_multi

Text2Text Generation
Transformers
TensorFlow
bart
generated_from_keras_callback
Inference Endpoints
Model card Files Community
KostiuchenkoArtem commited on
Commit
3500146
•
1 Parent(s): 24a85bf

Training in progress epoch 3

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 1.6451
18
- - Validation Loss: 2.1815
19
- - Epoch: 2
20
 
21
  ## Model description
22
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
45
  | 2.2305 | 2.1257 | 0 |
46
  | 1.9043 | 2.1163 | 1 |
47
  | 1.6451 | 2.1815 | 2 |
 
48
 
49
 
50
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.4183
18
+ - Validation Loss: 2.2949
19
+ - Epoch: 3
20
 
21
  ## Model description
22
 
 
45
  | 2.2305 | 2.1257 | 0 |
46
  | 1.9043 | 2.1163 | 1 |
47
  | 1.6451 | 2.1815 | 2 |
48
+ | 1.4183 | 2.2949 | 3 |
49
 
50
 
51
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9375ee9ae30b48f329f158dd8a386c2072099982758c1c8688b54dc2cd83f241
3
  size 1625921312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d066638971d04be792016407d7a26386a316c1093d2738e05eda649a85f1dc
3
  size 1625921312