Hugging Face's logo

kazandaev
/
opus-mt-ru-en-finetuned

Text2Text Generation
Transformers
PyTorch
TensorBoard
Rust
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kazandaev commited on
Commit
1e5af0b
•
1 Parent(s): 2053776

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -14
README.md CHANGED
@@ -13,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # opus-mt-ru-en-finetuned
15
 
16
- This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.2311
19
- - Bleu: 35.6405
20
- - Gen Len: 26.0366
21
 
22
  ## Model description
23
 
@@ -36,26 +36,33 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.0001
40
- - train_batch_size: 85
41
- - eval_batch_size: 42
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 3
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
51
- | 1.2 | 1.0 | 20262 | 1.3793 | 32.0937 | 26.0227 |
52
- | 1.1325 | 2.0 | 40524 | 1.2856 | 34.3345 | 26.1998 |
53
- | 1.0781 | 3.0 | 60786 | 1.2311 | 35.6405 | 26.0366 |
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
57
 
58
  - Transformers 4.16.2
59
- - Pytorch 1.10.2+cu113
60
  - Datasets 1.18.3
61
  - Tokenizers 0.11.0
 
13
 
14
  # opus-mt-ru-en-finetuned
15
 
16
+ This model is a fine-tuned version of [kazandaev/opus-mt-ru-en-finetuned](https://huggingface.co/kazandaev/opus-mt-ru-en-finetuned) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.1124
19
+ - Bleu: 39.6748
20
+ - Gen Len: 26.0628
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 49
41
+ - eval_batch_size: 24
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 10
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
+ |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|
51
+ | 1.172 | 1.0 | 35147 | 1.2856 | 34.1563 | 26.1419 |
52
+ | 1.1403 | 2.0 | 70294 | 1.2595 | 34.8515 | 26.198 |
53
+ | 1.0997 | 3.0 | 105441 | 1.2305 | 35.7998 | 26.115 |
54
+ | 1.0711 | 4.0 | 140588 | 1.2111 | 36.5266 | 26.17 |
55
+ | 1.0392 | 5.0 | 175735 | 1.1953 | 36.9092 | 26.0507 |
56
+ | 1.0109 | 6.0 | 210882 | 1.1662 | 37.7652 | 26.0546 |
57
+ | 0.9878 | 7.0 | 246029 | 1.1542 | 38.4936 | 25.9766 |
58
+ | 0.9573 | 8.0 | 281176 | 1.1298 | 39.06 | 26.1242 |
59
+ | 0.9263 | 9.0 | 316323 | 1.1214 | 39.5778 | 26.0582 |
60
+ | 0.9132 | 10.0 | 351470 | 1.1124 | 39.6748 | 26.0628 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - Transformers 4.16.2
66
+ - Pytorch 1.10.0+cu111
67
  - Datasets 1.18.3
68
  - Tokenizers 0.11.0