<!-- 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. -->
Andronius17/answer_text
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.9377
- Validation Loss: 3.9762
- Epoch: 32
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': 84, '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 | Epoch |
|---|---|---|
| 4.1663 | 3.9762 | 0 |
| 3.9427 | 3.9762 | 1 |
| 3.9499 | 3.9762 | 2 |
| 3.9448 | 3.9762 | 3 |
| 3.9429 | 3.9762 | 4 |
| 3.9460 | 3.9762 | 5 |
| 3.9372 | 3.9762 | 6 |
| 3.9375 | 3.9762 | 7 |
| 3.9359 | 3.9762 | 8 |
| 3.9398 | 3.9762 | 9 |
| 3.9488 | 3.9762 | 10 |
| 3.9429 | 3.9762 | 11 |
| 3.9482 | 3.9762 | 12 |
| 3.9383 | 3.9762 | 13 |
| 3.9415 | 3.9762 | 14 |
| 3.9377 | 3.9762 | 15 |
| 3.9440 | 3.9762 | 16 |
| 3.9415 | 3.9762 | 17 |
| 3.9374 | 3.9762 | 18 |
| 3.9327 | 3.9762 | 19 |
| 3.9477 | 3.9762 | 20 |
| 3.9424 | 3.9762 | 21 |
| 3.9375 | 3.9762 | 22 |
| 3.9419 | 3.9762 | 23 |
| 3.9459 | 3.9762 | 24 |
| 3.9463 | 3.9762 | 25 |
| 3.9410 | 3.9762 | 26 |
| 3.9414 | 3.9762 | 27 |
| 3.9458 | 3.9762 | 28 |
| 3.9479 | 3.9762 | 29 |
| 3.9370 | 3.9762 | 30 |
| 3.9465 | 3.9762 | 31 |
| 3.9377 | 3.9762 | 32 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
