Hugging Face's logo

Ragab167
/
output

Text2Text Generation
Transformers
Safetensors
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
Ragab167 commited on
Commit
47b0b80
•
1 Parent(s): 97da4e4

without_configration

Browse files
Files changed (3) hide show
  1. README.md +12 -28
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
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: 0.1802
19
 
20
  ## Model description
21
 
@@ -40,38 +40,22 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 3
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 3.7737 | 0.11 | 100 | 0.4133 |
50
- | 0.3772 | 0.23 | 200 | 0.2586 |
51
- | 0.2884 | 0.34 | 300 | 0.2401 |
52
- | 0.2732 | 0.46 | 400 | 0.2320 |
53
- | 0.285 | 0.57 | 500 | 0.2212 |
54
- | 0.2375 | 0.69 | 600 | 0.2143 |
55
- | 0.232 | 0.8 | 700 | 0.2113 |
56
- | 0.2468 | 0.91 | 800 | 0.2028 |
57
- | 0.2222 | 1.03 | 900 | 0.1996 |
58
- | 0.1715 | 1.14 | 1000 | 0.1971 |
59
- | 0.1442 | 1.26 | 1100 | 0.1949 |
60
- | 0.1726 | 1.37 | 1200 | 0.1936 |
61
- | 0.1359 | 1.49 | 1300 | 0.1932 |
62
- | 0.1613 | 1.6 | 1400 | 0.1912 |
63
- | 0.1599 | 1.71 | 1500 | 0.1886 |
64
- | 0.1431 | 1.83 | 1600 | 0.1856 |
65
- | 0.1607 | 1.94 | 1700 | 0.1829 |
66
- | 0.1269 | 2.06 | 1800 | 0.1867 |
67
- | 0.0838 | 2.17 | 1900 | 0.1837 |
68
- | 0.0982 | 2.29 | 2000 | 0.1850 |
69
- | 0.0936 | 2.4 | 2100 | 0.1831 |
70
- | 0.1009 | 2.51 | 2200 | 0.1832 |
71
- | 0.0889 | 2.63 | 2300 | 0.1824 |
72
- | 0.0956 | 2.74 | 2400 | 0.1813 |
73
- | 0.0967 | 2.86 | 2500 | 0.1807 |
74
- | 0.1075 | 2.97 | 2600 | 0.1802 |
75
 
76
 
77
  ### 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: 0.1841
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - training_steps: 1000
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.8401 | 0.11 | 100 | 0.4579 |
50
+ | 0.3757 | 0.23 | 200 | 0.2560 |
51
+ | 0.2783 | 0.34 | 300 | 0.2298 |
52
+ | 0.2618 | 0.46 | 400 | 0.2190 |
53
+ | 0.2733 | 0.57 | 500 | 0.2061 |
54
+ | 0.2236 | 0.69 | 600 | 0.2001 |
55
+ | 0.2183 | 0.8 | 700 | 0.1939 |
56
+ | 0.2315 | 0.91 | 800 | 0.1875 |
57
+ | 0.2058 | 1.03 | 900 | 0.1848 |
58
+ | 0.1705 | 1.14 | 1000 | 0.1841 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f72f4a9951a15e2cfad13f83988f5cfaad8532f7c5f810d06ddefa7760286fe
3
  size 1935681888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:314acd8c071d9509a125baffe9358b2cc400b84b8f0c9dc9ba2327d905d402c8
3
  size 1935681888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:774a400780f8f3a7cfc56b2b693e5c4207278d51d74db342f5df130e39be7596
3
- size 4008440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad81bce4b98a0b3ade66f43f51693ff5e8418b934f170d0117d93625b267206b
3
+ size 4008376