Hugging Face's logo

NetherQuartz
/
tatoeba-vi-tok

Translation
Transformers
Safetensors
Vietnamese
Toki Pona
marian
text2text-generation
Generated from Trainer
Model card Files Community
NetherQuartz commited on
Commit
fa933b8
·
verified ·
1 Parent(s): 6457585

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -77
README.md CHANGED
@@ -1,77 +1,82 @@
1
- ---
2
- library_name: transformers
3
- license: apache-2.0
4
- base_model: Helsinki-NLP/opus-mt-vi-en
5
- tags:
6
- - translation
7
- - generated_from_trainer
8
- metrics:
9
- - bleu
10
- model-index:
11
- - name: tatoeba-vi-tok
12
- results: []
13
- ---
14
-
15
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
- should probably proofread and complete it, then remove this comment. -->
17
-
18
- # tatoeba-vi-tok
19
-
20
- This model is a fine-tuned version of [Helsinki-NLP/opus-mt-vi-en](https://huggingface.co/Helsinki-NLP/opus-mt-vi-en) on an unknown dataset.
21
- It achieves the following results on the evaluation set:
22
- - Loss: 0.6910
23
- - Bleu: 46.4356
24
-
25
- ## Model description
26
-
27
- More information needed
28
-
29
- ## Intended uses & limitations
30
-
31
- More information needed
32
-
33
- ## Training and evaluation data
34
-
35
- More information needed
36
-
37
- ## Training procedure
38
-
39
- ### Training hyperparameters
40
-
41
- The following hyperparameters were used during training:
42
- - learning_rate: 2e-05
43
- - train_batch_size: 64
44
- - eval_batch_size: 64
45
- - seed: 42
46
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
- - lr_scheduler_type: linear
48
- - num_epochs: 15
49
- - mixed_precision_training: Native AMP
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss | Bleu |
54
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|
55
- | 1.2609 | 1.0 | 1167 | 1.0286 | 33.8552 |
56
- | 0.98 | 2.0 | 2334 | 0.8700 | 39.5255 |
57
- | 0.8347 | 3.0 | 3501 | 0.8036 | 41.4872 |
58
- | 0.7753 | 4.0 | 4668 | 0.7661 | 43.3025 |
59
- | 0.7272 | 5.0 | 5835 | 0.7389 | 44.2770 |
60
- | 0.6876 | 6.0 | 7002 | 0.7254 | 45.1330 |
61
- | 0.659 | 7.0 | 8169 | 0.7153 | 45.4847 |
62
- | 0.6383 | 8.0 | 9336 | 0.7067 | 45.4353 |
63
- | 0.6122 | 9.0 | 10503 | 0.7015 | 45.7612 |
64
- | 0.5998 | 10.0 | 11670 | 0.6979 | 46.0799 |
65
- | 0.5836 | 11.0 | 12837 | 0.6960 | 46.1173 |
66
- | 0.5732 | 12.0 | 14004 | 0.6928 | 46.2538 |
67
- | 0.5607 | 13.0 | 15171 | 0.6919 | 46.3801 |
68
- | 0.553 | 14.0 | 16338 | 0.6911 | 46.3629 |
69
- | 0.5518 | 15.0 | 17505 | 0.6910 | 46.4356 |
70
-
71
-
72
- ### Framework versions
73
-
74
- - Transformers 4.52.4
75
- - Pytorch 2.7.1+cu128
76
- - Datasets 3.6.0
77
- - Tokenizers 0.21.1
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Helsinki-NLP/opus-mt-vi-en
5
+ tags:
6
+ - translation
7
+ - generated_from_trainer
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: tatoeba-vi-tok
12
+ results: []
13
+ language:
14
+ - vi
15
+ - tok
16
+ datasets:
17
+ - NetherQuartz/tatoeba-tokipona
18
+ ---
19
+
20
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
21
+ should probably proofread and complete it, then remove this comment. -->
22
+
23
+ # tatoeba-vi-tok
24
+
25
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-vi-en](https://huggingface.co/Helsinki-NLP/opus-mt-vi-en) on an unknown dataset.
26
+ It achieves the following results on the evaluation set:
27
+ - Loss: 0.6910
28
+ - Bleu: 46.4356
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 64
49
+ - eval_batch_size: 64
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 15
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
60
+ | 1.2609 | 1.0 | 1167 | 1.0286 | 33.8552 |
61
+ | 0.98 | 2.0 | 2334 | 0.8700 | 39.5255 |
62
+ | 0.8347 | 3.0 | 3501 | 0.8036 | 41.4872 |
63
+ | 0.7753 | 4.0 | 4668 | 0.7661 | 43.3025 |
64
+ | 0.7272 | 5.0 | 5835 | 0.7389 | 44.2770 |
65
+ | 0.6876 | 6.0 | 7002 | 0.7254 | 45.1330 |
66
+ | 0.659 | 7.0 | 8169 | 0.7153 | 45.4847 |
67
+ | 0.6383 | 8.0 | 9336 | 0.7067 | 45.4353 |
68
+ | 0.6122 | 9.0 | 10503 | 0.7015 | 45.7612 |
69
+ | 0.5998 | 10.0 | 11670 | 0.6979 | 46.0799 |
70
+ | 0.5836 | 11.0 | 12837 | 0.6960 | 46.1173 |
71
+ | 0.5732 | 12.0 | 14004 | 0.6928 | 46.2538 |
72
+ | 0.5607 | 13.0 | 15171 | 0.6919 | 46.3801 |
73
+ | 0.553 | 14.0 | 16338 | 0.6911 | 46.3629 |
74
+ | 0.5518 | 15.0 | 17505 | 0.6910 | 46.4356 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.52.4
80
+ - Pytorch 2.7.1+cu128
81
+ - Datasets 3.6.0
82
+ - Tokenizers 0.21.1