metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ru-uk
tags:
- generated_from_keras_callback
model-index:
- name: serhii-korobchenko/mt5-small_poetry_Helsinki-2024-02-23-17-44-34
results: []
serhii-korobchenko/mt5-small_poetry_Helsinki-2024-02-23-17-44-34
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ru-uk on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0849
- Validation Loss: 2.3247
- Epoch: 19
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- 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}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.1952 | 2.2998 | 0 |
| 0.1739 | 2.3022 | 1 |
| 0.1706 | 2.3045 | 2 |
| 0.1603 | 2.3055 | 3 |
| 0.1395 | 2.3064 | 4 |
| 0.1297 | 2.3077 | 5 |
| 0.1273 | 2.3082 | 6 |
| 0.1310 | 2.3089 | 7 |
| 0.1171 | 2.3108 | 8 |
| 0.1043 | 2.3141 | 9 |
| 0.1011 | 2.3161 | 10 |
| 0.1013 | 2.3183 | 11 |
| 0.1042 | 2.3196 | 12 |
| 0.0908 | 2.3210 | 13 |
| 0.0902 | 2.3225 | 14 |
| 0.0883 | 2.3232 | 15 |
| 0.0909 | 2.3240 | 16 |
| 0.0794 | 2.3244 | 17 |
| 0.0842 | 2.3246 | 18 |
| 0.0849 | 2.3247 | 19 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.1
- Tokenizers 0.15.2