mariav commited on
Commit
9e24061
1 Parent(s): 8f2902a

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +10 -21
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -5,14 +5,6 @@ tags:
5
  model-index:
6
  - name: mariav/helsinki-opus-de-en-fine-tuned-wmt16
7
  results: []
8
- datasets:
9
- - wmt16
10
- language:
11
- - de
12
- - en
13
- metrics:
14
- - bleu
15
- pipeline_tag: translation
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -22,43 +14,40 @@ probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-de-en](https://huggingface.co/Helsinki-NLP/opus-mt-de-en) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Train Loss: 1.1917
26
- - Validation Loss: 1.4099
27
- - Epoch: 2
28
 
29
  ## Model description
30
 
31
- This model is a fine-tuned version of the Helsinki-NLP/opus-mt-de-en with the dataset wmt16 with the pair of languages de-en.
32
 
33
  ## Intended uses & limitations
34
 
35
- Limitations: schoolar purposes.
36
 
37
  ## Training and evaluation data
38
 
39
- The training was done with tranformers keras with just a few epochs due to lack of more GPU.
40
- With more epochs the performance could be better.
41
 
42
  ## Training procedure
43
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 747, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
48
  - training_precision: mixed_float16
49
 
50
  ### Training results
51
 
52
  | Train Loss | Validation Loss | Epoch |
53
  |:----------:|:---------------:|:-----:|
54
- | 1.5114 | 1.4037 | 0 |
55
- | 1.2991 | 1.4064 | 1 |
56
- | 1.1917 | 1.4099 | 2 |
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.27.4
62
- - TensorFlow 2.11.0
63
  - Datasets 2.11.0
64
- - Tokenizers 0.13.2
 
5
  model-index:
6
  - name: mariav/helsinki-opus-de-en-fine-tuned-wmt16
7
  results: []
 
 
 
 
 
 
 
 
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information Keras had access to. You should
 
14
 
15
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-de-en](https://huggingface.co/Helsinki-NLP/opus-mt-de-en) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.5115
18
+ - Validation Loss: 1.4061
19
+ - Epoch: 0
20
 
21
  ## Model description
22
 
23
+ More information needed
24
 
25
  ## Intended uses & limitations
26
 
27
+ More information needed
28
 
29
  ## Training and evaluation data
30
 
31
+ More information needed
 
32
 
33
  ## Training procedure
34
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1245, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
  - training_precision: mixed_float16
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 1.5115 | 1.4061 | 0 |
 
 
46
 
47
 
48
  ### Framework versions
49
 
50
  - Transformers 4.27.4
51
+ - TensorFlow 2.12.0
52
  - Datasets 2.11.0
53
+ - Tokenizers 0.13.2
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d775affb6767d95893e961125bb5ed44410787beecf1e77185fb3465a5bba343
3
  size 298161796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef1bd87a7592624c8a6896dc31fa5b87ca0c506630d2e480b576d9c1370dcfa
3
  size 298161796