smitmenon commited on
Commit
8679d3e
·
verified ·
1 Parent(s): bc0ddc8

Added Noise to english source, fine-tuned with denoising, version mbart_endenoised_v1

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/mbart-large-50-one-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3997
19
 
20
  ## Model description
21
 
@@ -46,8 +46,8 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 2.8775 | 1.0 | 125 | 0.4854 |
50
- | 0.4479 | 2.0 | 250 | 0.3997 |
51
 
52
 
53
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/mbart-large-50-one-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4057
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.9598 | 1.0 | 125 | 0.4112 |
50
+ | 0.4495 | 2.0 | 250 | 0.4057 |
51
 
52
 
53
  ### Framework versions