Hugging Face's logo

pijarcandra22
/
BartBali2Indo

Text2Text Generation
Transformers
TensorFlow
bart
generated_from_keras_callback
Inference Endpoints
Model card Files Community
pijarcandra22 commited on
Commit
f2683d6
•
1 Parent(s): 4ea2317

Training in progress epoch 56

Browse files
Files changed (2) hide show
  1. README.md +5 -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: 0.0021
19
- - Validation Loss: 2.8454
20
- - Epoch: 54
21
 
22
  ## Model description
23
 
@@ -98,6 +98,8 @@ The following hyperparameters were used during training:
98
  | 0.0019 | 2.8433 | 52 |
99
  | 0.0017 | 2.8747 | 53 |
100
  | 0.0021 | 2.8454 | 54 |
 
 
101
 
102
 
103
  ### 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: 0.0023
19
+ - Validation Loss: 2.8624
20
+ - Epoch: 56
21
 
22
  ## Model description
23
 
 
98
  | 0.0019 | 2.8433 | 52 |
99
  | 0.0017 | 2.8747 | 53 |
100
  | 0.0021 | 2.8454 | 54 |
101
+ | 0.0018 | 2.8685 | 55 |
102
+ | 0.0023 | 2.8624 | 56 |
103
 
104
 
105
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:711c34166c999601dd9a9d10ddc4b0668b2761ae78110f811bff1736ba4c0cd1
3
  size 558172300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736233e72d1bb12c8c3441408c4f9b9bba6dd580d9130095b6ad937d22b2393b
3
  size 558172300