Hugging Face's logo

eldor-97
/
MarianMix_en-10

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
eldor-97 commited on
Commit
9a49c64
·
1 Parent(s): 07c7256

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -16
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Helsinki-NLP/opus-tatoeba-en-ja](https://huggingface.co/Helsinki-NLP/opus-tatoeba-en-ja) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3230
20
- - Bleu: 15.0164
21
- - Gen Len: 53.3474
22
 
23
  ## Model description
24
 
@@ -49,19 +49,19 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
- | 2.396 | 0.45 | 500 | 2.5880 | 0.0846 | 98.5216 |
55
- | 1.4131 | 0.91 | 1000 | 2.1869 | 1.8498 | 77.0155 |
56
- | 1.1807 | 1.36 | 1500 | 1.8676 | 3.8379 | 59.0722 |
57
- | 1.0558 | 1.81 | 2000 | 1.6780 | 6.4673 | 53.6495 |
58
- | 0.9393 | 2.26 | 2500 | 1.5675 | 8.7123 | 51.3959 |
59
- | 0.8887 | 2.72 | 3000 | 1.4815 | 10.7083 | 52.4082 |
60
- | 0.8396 | 3.17 | 3500 | 1.4202 | 12.4178 | 51.5722 |
61
- | 0.7881 | 3.62 | 4000 | 1.3723 | 13.4971 | 53.2948 |
62
- | 0.7639 | 4.08 | 4500 | 1.3519 | 14.4199 | 53.4938 |
63
- | 0.7286 | 4.53 | 5000 | 1.3329 | 14.8435 | 53.2423 |
64
- | 0.7288 | 4.98 | 5500 | 1.3230 | 15.0164 | 53.3474 |
65
 
66
 
67
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [Helsinki-NLP/opus-tatoeba-en-ja](https://huggingface.co/Helsinki-NLP/opus-tatoeba-en-ja) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.0752
20
+ - Bleu: 14.601
21
+ - Gen Len: 45.8087
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:--------:|
54
+ | 2.1136 | 0.44 | 500 | 2.0044 | 0.2655 | 109.0201 |
55
+ | 1.1422 | 0.89 | 1000 | 1.7516 | 1.4123 | 71.0 |
56
+ | 0.9666 | 1.33 | 1500 | 1.5219 | 3.6611 | 64.6888 |
57
+ | 0.8725 | 1.78 | 2000 | 1.3606 | 4.6539 | 77.1641 |
58
+ | 0.7655 | 2.22 | 2500 | 1.2586 | 8.3456 | 60.3837 |
59
+ | 0.7149 | 2.67 | 3000 | 1.1953 | 11.2247 | 50.5921 |
60
+ | 0.6719 | 3.11 | 3500 | 1.1541 | 10.4303 | 54.3776 |
61
+ | 0.6265 | 3.56 | 4000 | 1.1186 | 13.3231 | 48.283 |
62
+ | 0.6157 | 4.0 | 4500 | 1.0929 | 13.8467 | 46.569 |
63
+ | 0.5736 | 4.44 | 5000 | 1.0848 | 14.2731 | 45.5035 |
64
+ | 0.5683 | 4.89 | 5500 | 1.0752 | 14.601 | 45.8087 |
65
 
66
 
67
  ### Framework versions