Hugging Face's logo

rbcurzon
/
opus-ph-ph

Transformers
Safetensors
marian
text2text-generation
Generated from Trainer
Model card Files
xet
Community
rbcurzon commited on
Commit
f7ffa90
·
verified ·
1 Parent(s): 2f7cc5f

End of training

Browse files
Files changed (4) hide show
  1. README.md +17 -22
  2. model.safetensors +1 -1
  3. special_tokens_map.json +10 -22
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,7 @@
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
@@ -12,11 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # opus-ph-ph
14
 
15
- This model was trained from scratch on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.9171
18
- - Bleu Global: 28.0878
19
- - Gen Len: 7.4973
20
 
21
  ## Model description
22
 
@@ -35,31 +36,25 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-06
39
- - train_batch_size: 64
40
- - eval_batch_size: 64
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 15
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Bleu Global | Gen Len | Validation Loss |
50
- |:-------------:|:-----:|:----:|:-----------:|:-------:|:---------------:|
51
- | 0.1176 | 1.0 | 634 | 27.2355 | 7.6117 | 2.3737 |
52
- | 0.1024 | 2.0 | 1268 | 28.4868 | 7.5173 | 2.4315 |
53
- | 0.0788 | 3.0 | 1902 | 28.2414 | 7.5385 | 2.5622 |
54
- | 0.0438 | 4.0 | 2536 | 27.6541 | 7.4658 | 2.6708 |
55
- | 0.0344 | 5.0 | 3170 | 28.4412 | 7.5115 | 2.6867 |
56
- | 0.0294 | 6.0 | 3804 | 28.9421 | 7.5008 | 2.7144 |
57
- | 0.0253 | 7.0 | 4438 | 28.5901 | 7.5542 | 2.8013 |
58
- | 0.0176 | 8.0 | 5072 | 28.4891 | 7.5348 | 2.8497 |
59
- | 0.0155 | 9.0 | 5706 | 28.5233 | 7.5419 | 2.8761 |
60
- | 0.014 | 10.0 | 6340 | 28.3278 | 7.5328 | 2.8908 |
61
- | 0.0167 | 11.0 | 6974 | 2.8892 | 28.2921 | 7.502 |
62
- | 0.0161 | 12.0 | 7608 | 2.9171 | 28.0878 | 7.4973 |
63
 
64
 
65
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Helsinki-NLP/opus-mt-tc-bible-big-mul-mul
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # opus-ph-ph
16
 
17
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-bible-big-mul-mul](https://huggingface.co/Helsinki-NLP/opus-mt-tc-bible-big-mul-mul) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.7528
20
+ - Bleu Global: 28.4879
 
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 10
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Bleu Global |
51
+ |:-------------:|:-----:|:----:|:---------------:|:-----------:|
52
+ | 0.6364 | 1.0 | 1268 | 1.9412 | 25.9524 |
53
+ | 0.1826 | 2.0 | 2536 | 2.2076 | 25.5630 |
54
+ | 0.1035 | 3.0 | 3804 | 2.3956 | 28.8255 |
55
+ | 0.06 | 4.0 | 5072 | 2.5487 | 28.1852 |
56
+ | 0.0436 | 5.0 | 6340 | 2.6189 | 28.7365 |
57
+ | 0.0298 | 6.0 | 7608 | 2.7528 | 28.4879 |
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c668294176d0e54c71a9fed52fb651c63de9cb1fd76e09905257f23666927fb
3
  size 991093820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780483067b493ccfafec5ad0af65ad1b85e705df692d9d28dc3002eb18984e00
3
  size 991093820
special_tokens_map.json CHANGED
@@ -1,26 +1,14 @@
1
  {
2
  "additional_special_tokens": [
3
- ">>mdh<<"
 
 
 
 
 
 
4
  ],
5
- "eos_token": {
6
- "content": "</s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "unk_token": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- }
26
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": ">>mdh<<",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
  ],
11
+ "eos_token": "</s>",
12
+ "pad_token": "<pad>",
13
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73eda5ee9cf32ff01a29e8c1552a48af8854603707302725e40ddbf82d6070d5
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a4da7d1f7805ac730e39a13e1e0ee863442f98930e123242538858ecf99ebf
3
  size 5905