serhii-korobchenko commited on
Commit
2e22f39
1 Parent(s): 1b84438

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -23
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ru-uk](https://huggingface.co/Helsinki-NLP/opus-mt-ru-uk) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0849
19
- - Validation Loss: 2.3247
20
  - Epoch: 19
21
 
22
  ## Model description
@@ -36,33 +36,33 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-06, 'decay_steps': 340, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 1e-06}
40
  - training_precision: mixed_float16
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 0.1952 | 2.2998 | 0 |
47
- | 0.1739 | 2.3022 | 1 |
48
- | 0.1706 | 2.3045 | 2 |
49
- | 0.1603 | 2.3055 | 3 |
50
- | 0.1395 | 2.3064 | 4 |
51
- | 0.1297 | 2.3077 | 5 |
52
- | 0.1273 | 2.3082 | 6 |
53
- | 0.1310 | 2.3089 | 7 |
54
- | 0.1171 | 2.3108 | 8 |
55
- | 0.1043 | 2.3141 | 9 |
56
- | 0.1011 | 2.3161 | 10 |
57
- | 0.1013 | 2.3183 | 11 |
58
- | 0.1042 | 2.3196 | 12 |
59
- | 0.0908 | 2.3210 | 13 |
60
- | 0.0902 | 2.3225 | 14 |
61
- | 0.0883 | 2.3232 | 15 |
62
- | 0.0909 | 2.3240 | 16 |
63
- | 0.0794 | 2.3244 | 17 |
64
- | 0.0842 | 2.3246 | 18 |
65
- | 0.0849 | 2.3247 | 19 |
66
 
67
 
68
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ru-uk](https://huggingface.co/Helsinki-NLP/opus-mt-ru-uk) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0194
19
+ - Validation Loss: 2.6788
20
  - Epoch: 19
21
 
22
  ## Model description
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-06, 'decay_steps': 2740, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 1e-06}
40
  - training_precision: mixed_float16
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 0.0892 | 2.5969 | 0 |
47
+ | 0.0658 | 2.6050 | 1 |
48
+ | 0.0609 | 2.6026 | 2 |
49
+ | 0.0519 | 2.6134 | 3 |
50
+ | 0.0411 | 2.6232 | 4 |
51
+ | 0.0392 | 2.6326 | 5 |
52
+ | 0.0333 | 2.6448 | 6 |
53
+ | 0.0311 | 2.6494 | 7 |
54
+ | 0.0277 | 2.6555 | 8 |
55
+ | 0.0245 | 2.6601 | 9 |
56
+ | 0.0249 | 2.6607 | 10 |
57
+ | 0.0234 | 2.6678 | 11 |
58
+ | 0.0213 | 2.6720 | 12 |
59
+ | 0.0210 | 2.6713 | 13 |
60
+ | 0.0192 | 2.6732 | 14 |
61
+ | 0.0203 | 2.6741 | 15 |
62
+ | 0.0173 | 2.6764 | 16 |
63
+ | 0.0170 | 2.6778 | 17 |
64
+ | 0.0170 | 2.6787 | 18 |
65
+ | 0.0194 | 2.6788 | 19 |
66
 
67
 
68
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a728a2b608d346a39bc312bfcbba17f5c6aedf368cec7e8cbce5f224e80d7d9d
3
  size 297496948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0d9eb6439b9ee34dffa4b204275dc8bbee8129fd88792143253ebb679c875f
3
  size 297496948