smitmenon commited on
Commit
f677c1c
·
verified ·
1 Parent(s): d950443

Fine-tuned with 5000 samples mBART version mbart_v2

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. generation_config.json +1 -0
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  library_name: transformers
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # e2m_translation_project
14
 
15
- This model was trained from scratch on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.4409
18
 
19
  ## Model description
20
 
@@ -45,8 +46,8 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.5001 | 1.0 | 625 | 0.4536 |
49
- | 0.3662 | 2.0 | 1250 | 0.4409 |
50
 
51
 
52
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: facebook/mbart-large-50-one-to-many-mmt
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # e2m_translation_project
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: 0.3881
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.4269 | 1.0 | 625 | 0.3894 |
50
+ | 0.2929 | 2.0 | 1250 | 0.3881 |
51
 
52
 
53
  ### Framework versions
generation_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "decoder_start_token_id": 2,
5
  "early_stopping": true,
6
  "eos_token_id": 2,
 
7
  "max_length": 200,
8
  "num_beams": 5,
9
  "pad_token_id": 1,
 
4
  "decoder_start_token_id": 2,
5
  "early_stopping": true,
6
  "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
  "max_length": 200,
9
  "num_beams": 5,
10
  "pad_token_id": 1,