Ragab167 commited on
Commit
67cd26c
1 Parent(s): f9bd7f0

Ragab167/m2m_translation_v2

Browse files
Files changed (3) hide show
  1. README.md +38 -18
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1872
19
 
20
  ## Model description
21
 
@@ -35,8 +35,8 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 4
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
@@ -46,21 +46,41 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 3.7586 | 0.25 | 100 | 0.4346 |
50
- | 0.3151 | 0.51 | 200 | 0.2401 |
51
- | 0.2789 | 0.76 | 300 | 0.2173 |
52
- | 0.2415 | 1.02 | 400 | 0.2048 |
53
- | 0.166 | 1.27 | 500 | 0.2021 |
54
- | 0.161 | 1.52 | 600 | 0.1979 |
55
- | 0.1653 | 1.78 | 700 | 0.1931 |
56
- | 0.1508 | 2.03 | 800 | 0.1921 |
57
- | 0.1107 | 2.28 | 900 | 0.1894 |
58
- | 0.0961 | 2.54 | 1000 | 0.1905 |
59
- | 0.1185 | 2.79 | 1100 | 0.1871 |
60
- | 0.1032 | 3.05 | 1200 | 0.1881 |
61
- | 0.0788 | 3.3 | 1300 | 0.1881 |
62
- | 0.0765 | 3.55 | 1400 | 0.1876 |
63
- | 0.0816 | 3.81 | 1500 | 0.1872 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1847
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.7809 | 0.11 | 100 | 0.3955 |
50
+ | 0.379 | 0.23 | 200 | 0.2623 |
51
+ | 0.2876 | 0.34 | 300 | 0.2431 |
52
+ | 0.2733 | 0.46 | 400 | 0.2327 |
53
+ | 0.2885 | 0.57 | 500 | 0.2230 |
54
+ | 0.2414 | 0.69 | 600 | 0.2162 |
55
+ | 0.2347 | 0.8 | 700 | 0.2119 |
56
+ | 0.2509 | 0.91 | 800 | 0.2056 |
57
+ | 0.2237 | 1.03 | 900 | 0.2042 |
58
+ | 0.1759 | 1.14 | 1000 | 0.2009 |
59
+ | 0.1471 | 1.26 | 1100 | 0.1984 |
60
+ | 0.1759 | 1.37 | 1200 | 0.1959 |
61
+ | 0.1396 | 1.49 | 1300 | 0.1960 |
62
+ | 0.1656 | 1.6 | 1400 | 0.1936 |
63
+ | 0.163 | 1.71 | 1500 | 0.1898 |
64
+ | 0.1463 | 1.83 | 1600 | 0.1879 |
65
+ | 0.1662 | 1.94 | 1700 | 0.1858 |
66
+ | 0.1297 | 2.06 | 1800 | 0.1889 |
67
+ | 0.0841 | 2.17 | 1900 | 0.1886 |
68
+ | 0.1 | 2.29 | 2000 | 0.1880 |
69
+ | 0.0937 | 2.4 | 2100 | 0.1873 |
70
+ | 0.1023 | 2.51 | 2200 | 0.1862 |
71
+ | 0.0918 | 2.63 | 2300 | 0.1864 |
72
+ | 0.0981 | 2.74 | 2400 | 0.1863 |
73
+ | 0.0993 | 2.86 | 2500 | 0.1841 |
74
+ | 0.1086 | 2.97 | 2600 | 0.1834 |
75
+ | 0.083 | 3.09 | 2700 | 0.1869 |
76
+ | 0.07 | 3.2 | 2800 | 0.1873 |
77
+ | 0.0609 | 3.31 | 2900 | 0.1865 |
78
+ | 0.0637 | 3.43 | 3000 | 0.1861 |
79
+ | 0.078 | 3.54 | 3100 | 0.1862 |
80
+ | 0.0605 | 3.66 | 3200 | 0.1844 |
81
+ | 0.0606 | 3.77 | 3300 | 0.1845 |
82
+ | 0.0579 | 3.89 | 3400 | 0.1849 |
83
+ | 0.0687 | 4.0 | 3500 | 0.1847 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcb7a604bbded2bbab46c1eabc882e52bec41b7e2682bdb8646d020de47b4f27
3
  size 1935681888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5b2552fd43bb3fc97bdeefba7badcd3fb7691723cbd17ecf9e287ad4c3b56d
3
  size 1935681888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673df13a22d1b7b8cd680550189c8efb8eeeb56a0bce87a3bcac55714d9e7cc0
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6207ef01ae82e58748893b35f70885aaff6eaf5ce4202eef20e57728b301f731
3
  size 5048