<!-- 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. -->
Flaubert_1619
This model is a fine-tuned version of flaubert/flaubert_base_cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2458
- Validation Loss: 0.5339
- Train Accuracy: 0.8170
- 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': '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': 1432, '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 |
|---|---|---|---|
| 1.0000 | 0.5841 | 0.7769 | 0 |
| 0.5526 | 0.5284 | 0.7845 | 1 |
| 0.3909 | 0.4806 | 0.8221 | 2 |
| 0.2798 | 0.5339 | 0.8170 | 3 |
| 0.2378 | 0.5339 | 0.8170 | 4 |
| 0.2514 | 0.5339 | 0.8170 | 5 |
| 0.2403 | 0.5339 | 0.8170 | 6 |
| 0.2373 | 0.5339 | 0.8170 | 7 |
| 0.2441 | 0.5339 | 0.8170 | 8 |
| 0.2529 | 0.5339 | 0.8170 | 9 |
| 0.2400 | 0.5339 | 0.8170 | 10 |
| 0.2337 | 0.5339 | 0.8170 | 11 |
| 0.2394 | 0.5339 | 0.8170 | 12 |
| 0.2383 | 0.5339 | 0.8170 | 13 |
| 0.2464 | 0.5339 | 0.8170 | 14 |
| 0.2464 | 0.5339 | 0.8170 | 15 |
| 0.2468 | 0.5339 | 0.8170 | 16 |
| 0.2427 | 0.5339 | 0.8170 | 17 |
| 0.2546 | 0.5339 | 0.8170 | 18 |
| 0.2458 | 0.5339 | 0.8170 | 19 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
