Hugging Face's logo

dapooni
/
sorsolingo-mt-en-bsl-test

Translation
Transformers
TensorBoard
Safetensors
marian
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dapooni commited on
Commit
395f40f
•
1 Parent(s): fa190d1

Training complete

Browse files
Files changed (2) hide show
  1. README.md +56 -4
  2. runs/Apr29_15-57-31_6c5600b9a3c8/events.out.tfevents.1714409062.6c5600b9a3c8.168.3 +3 -0
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-bcl](https://huggingface.co/Helsinki-NLP/opus-mt-en-bcl) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 5.9633
22
- - Bleu: 16.7926
23
 
24
  ## Model description
25
 
@@ -38,17 +38,69 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.001
42
  - train_batch_size: 32
43
  - eval_batch_size: 64
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 25
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-bcl](https://huggingface.co/Helsinki-NLP/opus-mt-en-bcl) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 4.2588
22
+ - Bleu: 23.7702
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
  - train_batch_size: 32
43
  - eval_batch_size: 64
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 50
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
53
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
+ | No log | 1.0 | 103 | 4.0970 | 5.8754 |
55
+ | No log | 2.0 | 206 | 4.0029 | 6.2348 |
56
+ | No log | 3.0 | 309 | 3.9156 | 7.5329 |
57
+ | No log | 4.0 | 412 | 3.8566 | 8.0661 |
58
+ | 2.681 | 5.0 | 515 | 3.8107 | 8.7715 |
59
+ | 2.681 | 6.0 | 618 | 3.7977 | 9.8792 |
60
+ | 2.681 | 7.0 | 721 | 3.7714 | 10.9895 |
61
+ | 2.681 | 8.0 | 824 | 3.7653 | 12.6583 |
62
+ | 2.681 | 9.0 | 927 | 3.7693 | 13.1814 |
63
+ | 1.4678 | 10.0 | 1030 | 3.7831 | 14.5860 |
64
+ | 1.4678 | 11.0 | 1133 | 3.8004 | 15.2984 |
65
+ | 1.4678 | 12.0 | 1236 | 3.8128 | 16.7877 |
66
+ | 1.4678 | 13.0 | 1339 | 3.8292 | 16.9259 |
67
+ | 1.4678 | 14.0 | 1442 | 3.8403 | 17.8362 |
68
+ | 0.7873 | 15.0 | 1545 | 3.8601 | 18.7291 |
69
+ | 0.7873 | 16.0 | 1648 | 3.8750 | 18.6286 |
70
+ | 0.7873 | 17.0 | 1751 | 3.9023 | 19.6639 |
71
+ | 0.7873 | 18.0 | 1854 | 3.9345 | 20.4112 |
72
+ | 0.7873 | 19.0 | 1957 | 3.9422 | 20.1680 |
73
+ | 0.435 | 20.0 | 2060 | 3.9760 | 20.5031 |
74
+ | 0.435 | 21.0 | 2163 | 3.9929 | 21.2985 |
75
+ | 0.435 | 22.0 | 2266 | 3.9957 | 21.4619 |
76
+ | 0.435 | 23.0 | 2369 | 4.0200 | 21.9504 |
77
+ | 0.435 | 24.0 | 2472 | 4.0418 | 22.0801 |
78
+ | 0.2564 | 25.0 | 2575 | 4.0617 | 22.2107 |
79
+ | 0.2564 | 26.0 | 2678 | 4.0865 | 22.7690 |
80
+ | 0.2564 | 27.0 | 2781 | 4.1003 | 22.1801 |
81
+ | 0.2564 | 28.0 | 2884 | 4.1085 | 23.1518 |
82
+ | 0.2564 | 29.0 | 2987 | 4.1167 | 23.0701 |
83
+ | 0.1634 | 30.0 | 3090 | 4.1261 | 22.8401 |
84
+ | 0.1634 | 31.0 | 3193 | 4.1484 | 23.3273 |
85
+ | 0.1634 | 32.0 | 3296 | 4.1544 | 23.0479 |
86
+ | 0.1634 | 33.0 | 3399 | 4.1702 | 23.1654 |
87
+ | 0.1135 | 34.0 | 3502 | 4.1863 | 23.5357 |
88
+ | 0.1135 | 35.0 | 3605 | 4.1936 | 23.2926 |
89
+ | 0.1135 | 36.0 | 3708 | 4.2078 | 23.9066 |
90
+ | 0.1135 | 37.0 | 3811 | 4.2071 | 23.1740 |
91
+ | 0.1135 | 38.0 | 3914 | 4.2060 | 23.6421 |
92
+ | 0.0867 | 39.0 | 4017 | 4.2129 | 23.2291 |
93
+ | 0.0867 | 40.0 | 4120 | 4.2213 | 23.5411 |
94
+ | 0.0867 | 41.0 | 4223 | 4.2345 | 23.2913 |
95
+ | 0.0867 | 42.0 | 4326 | 4.2367 | 23.8147 |
96
+ | 0.0867 | 43.0 | 4429 | 4.2445 | 23.5416 |
97
+ | 0.07 | 44.0 | 4532 | 4.2456 | 23.6258 |
98
+ | 0.07 | 45.0 | 4635 | 4.2573 | 23.4067 |
99
+ | 0.07 | 46.0 | 4738 | 4.2551 | 23.0979 |
100
+ | 0.07 | 47.0 | 4841 | 4.2541 | 23.3768 |
101
+ | 0.07 | 48.0 | 4944 | 4.2596 | 23.5246 |
102
+ | 0.0606 | 49.0 | 5047 | 4.2596 | 23.5083 |
103
+ | 0.0606 | 50.0 | 5150 | 4.2588 | 23.7702 |
104
 
105
 
106
  ### Framework versions
runs/Apr29_15-57-31_6c5600b9a3c8/events.out.tfevents.1714409062.6c5600b9a3c8.168.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa8330273e83acc4d4f393b8f30c11b60ebc46c553dfd3cbc334ee340b8b37f
3
+ size 407