Hugging Face's logo

VaniLara
/
esp-to-lsm-model

Text2Text Generation
Transformers
TensorBoard
Safetensors
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
VaniLara commited on
Commit
03bc8b5
·
verified ·
1 Parent(s): 3c702d6

Model save

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3973
21
- - Bleu: 81.4153
22
 
23
  ## Model description
24
 
@@ -50,26 +50,26 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
- | 0.1786 | 1.0 | 75 | 0.4405 | 77.3385 |
54
- | 0.2491 | 2.0 | 150 | 0.4423 | 76.4996 |
55
- | 0.1663 | 3.0 | 225 | 0.4190 | 77.6994 |
56
- | 0.1269 | 4.0 | 300 | 0.4220 | 79.6564 |
57
- | 0.1402 | 5.0 | 375 | 0.4102 | 79.7149 |
58
- | 0.11 | 6.0 | 450 | 0.4060 | 81.3666 |
59
- | 0.0931 | 7.0 | 525 | 0.4095 | 80.3040 |
60
- | 0.1084 | 8.0 | 600 | 0.4052 | 79.8359 |
61
- | 0.0929 | 9.0 | 675 | 0.4037 | 81.0943 |
62
- | 0.0782 | 10.0 | 750 | 0.4045 | 80.5705 |
63
- | 0.0572 | 11.0 | 825 | 0.4074 | 80.6900 |
64
- | 0.0472 | 12.0 | 900 | 0.4053 | 80.8490 |
65
- | 0.0589 | 13.0 | 975 | 0.4016 | 81.2969 |
66
- | 0.0664 | 14.0 | 1050 | 0.4027 | 80.6536 |
67
- | 0.0534 | 15.0 | 1125 | 0.3967 | 81.1367 |
68
- | 0.0689 | 16.0 | 1200 | 0.3966 | 81.2154 |
69
- | 0.0607 | 17.0 | 1275 | 0.3989 | 80.5909 |
70
- | 0.0577 | 18.0 | 1350 | 0.3982 | 81.3339 |
71
- | 0.0462 | 19.0 | 1425 | 0.3975 | 81.1189 |
72
- | 0.048 | 20.0 | 1500 | 0.3973 | 81.4153 |
73
 
74
 
75
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4524
21
+ - Bleu: 68.8807
22
 
23
  ## Model description
24
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 3.7222 | 1.0 | 75 | 2.6073 | 14.3097 |
54
+ | 1.9035 | 2.0 | 150 | 1.5408 | 44.9883 |
55
+ | 1.2424 | 3.0 | 225 | 1.1446 | 60.7215 |
56
+ | 0.9993 | 4.0 | 300 | 0.9445 | 49.9656 |
57
+ | 0.8131 | 5.0 | 375 | 0.8136 | 51.1677 |
58
+ | 0.68 | 6.0 | 450 | 0.7128 | 38.5475 |
59
+ | 0.63 | 7.0 | 525 | 0.6493 | 49.2921 |
60
+ | 0.4891 | 8.0 | 600 | 0.5980 | 67.6139 |
61
+ | 0.434 | 9.0 | 675 | 0.5642 | 74.1258 |
62
+ | 0.3897 | 10.0 | 750 | 0.5409 | 73.4943 |
63
+ | 0.3651 | 11.0 | 825 | 0.5166 | 56.0140 |
64
+ | 0.3205 | 12.0 | 900 | 0.4993 | 75.9506 |
65
+ | 0.3043 | 13.0 | 975 | 0.4861 | 76.3040 |
66
+ | 0.2814 | 14.0 | 1050 | 0.4757 | 52.8020 |
67
+ | 0.2571 | 15.0 | 1125 | 0.4648 | 67.2947 |
68
+ | 0.2743 | 16.0 | 1200 | 0.4632 | 52.5347 |
69
+ | 0.2327 | 17.0 | 1275 | 0.4568 | 69.9258 |
70
+ | 0.227 | 18.0 | 1350 | 0.4550 | 69.4897 |
71
+ | 0.2317 | 19.0 | 1425 | 0.4535 | 67.6997 |
72
+ | 0.2236 | 20.0 | 1500 | 0.4524 | 68.8807 |
73
 
74
 
75
  ### Framework versions