Drigoro/my_awesome_model3
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5285
- Validation Loss: 1.5080
- Train Accuracy: 0.5554
- Epoch: 9
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1220, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 |
|---|---|---|---|
| 1.4494 | 1.3028 | 0.5110 | 0 |
| 1.2173 | 1.2547 | 0.5350 | 1 |
| 1.0579 | 1.2659 | 0.5595 | 2 |
| 0.9320 | 1.2806 | 0.5503 | 3 |
| 0.8199 | 1.3338 | 0.5375 | 4 |
| 0.7389 | 1.3642 | 0.5457 | 5 |
| 0.6608 | 1.4301 | 0.5477 | 6 |
| 0.6115 | 1.4599 | 0.5544 | 7 |
| 0.5594 | 1.4930 | 0.5503 | 8 |
| 0.5285 | 1.5080 | 0.5554 | 9 |
Framework versions
- Transformers 4.40.2
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4