<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
ru_propaganda_opposition_and_neutral_class_model
This model is a fine-tuned version of DeepPavlov/bert-base-bg-cs-pl-ru-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0003
- Validation Loss: 0.2057
- Train Accuracy: 0.9641
- Epoch: 14
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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 20205, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.2750 | 0.1328 | 0.9508 | 0 |
| 0.0855 | 0.1143 | 0.9599 | 1 |
| 0.0384 | 0.1684 | 0.9574 | 2 |
| 0.0284 | 0.1341 | 0.9633 | 3 |
| 0.0182 | 0.1238 | 0.9641 | 4 |
| 0.0107 | 0.2324 | 0.9558 | 5 |
| 0.0098 | 0.2588 | 0.9416 | 6 |
| 0.0056 | 0.1881 | 0.9599 | 7 |
| 0.0098 | 0.1994 | 0.9566 | 8 |
| 0.0016 | 0.1788 | 0.9599 | 9 |
| 0.0021 | 0.1861 | 0.9633 | 10 |
| 0.0004 | 0.1889 | 0.9666 | 11 |
| 0.0004 | 0.1988 | 0.9674 | 12 |
| 0.0005 | 0.1852 | 0.9708 | 13 |
| 0.0003 | 0.2057 | 0.9641 | 14 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
