Hugging Face's logo

KanWasTaken
/
EN-VI-Machine-Translation-RNN

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
Community
KanWasTaken commited on
Commit
7ca8495
·
verified ·
1 Parent(s): 225ccbf

KanWasTaken/EN-VI-Machine-Translation-RNN

Browse files
Files changed (3) hide show
  1. README.md +9 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.7149
18
 
19
  ## Model description
20
 
@@ -34,37 +34,22 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
- - train_batch_size: 1024
38
- - eval_batch_size: 1024
39
  - seed: 42
40
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
- - num_epochs: 20
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 7.829 | 1.0 | 131 | 5.6878 |
49
- | 4.0951 | 2.0 | 262 | 2.7482 |
50
- | 2.1201 | 3.0 | 393 | 1.5308 |
51
- | 1.3062 | 4.0 | 524 | 1.0420 |
52
- | 1.0218 | 5.0 | 655 | 0.8985 |
53
- | 0.927 | 6.0 | 786 | 0.8373 |
54
- | 0.8817 | 7.0 | 917 | 0.8036 |
55
- | 0.8538 | 8.0 | 1048 | 0.7808 |
56
- | 0.8348 | 9.0 | 1179 | 0.7639 |
57
- | 0.8204 | 10.0 | 1310 | 0.7518 |
58
- | 0.8099 | 11.0 | 1441 | 0.7427 |
59
- | 0.802 | 12.0 | 1572 | 0.7357 |
60
- | 0.7964 | 13.0 | 1703 | 0.7302 |
61
- | 0.7916 | 14.0 | 1834 | 0.7258 |
62
- | 0.7871 | 15.0 | 1965 | 0.7223 |
63
- | 0.7839 | 16.0 | 2096 | 0.7196 |
64
- | 0.7814 | 17.0 | 2227 | 0.7175 |
65
- | 0.7801 | 18.0 | 2358 | 0.7161 |
66
- | 0.7788 | 19.0 | 2489 | 0.7152 |
67
- | 0.7778 | 20.0 | 2620 | 0.7149 |
68
 
69
 
70
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.7180
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
+ - train_batch_size: 256
38
+ - eval_batch_size: 256
39
  - seed: 42
40
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 5
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 4.3656 | 1.0 | 521 | 1.1849 |
49
+ | 0.9343 | 2.0 | 1042 | 0.7810 |
50
+ | 0.8145 | 3.0 | 1563 | 0.7373 |
51
+ | 0.7882 | 4.0 | 2084 | 0.7221 |
52
+ | 0.7793 | 5.0 | 2605 | 0.7180 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fea7520dd444bfd19df0a9f12fb27fcc2196b3a1adf61406c110ba8e51c48a50
3
  size 23893728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207e2d19b486e542bbad23b7de68044bc99c39e0bfdceb56a14d1215fbda23d1
3
  size 23893728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f14e643cc297fdb3db7205c5a946d27a4acbaaf4306e2607a8e8d71d972e6c
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e087fb74a345090ebf9392a9de6e9411aebed501d9db7061affde8b69548d6
3
  size 5240