<!-- 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. -->
hoangtran0308/my_awesome_qa_model
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: 0.0727
- Validation Loss: 0.0552
- Epoch: 26
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': 1250, '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 | Epoch |
|---|---|---|
| 0.0707 | 0.0552 | 0 |
| 0.0714 | 0.0552 | 1 |
| 0.0717 | 0.0552 | 2 |
| 0.0705 | 0.0552 | 3 |
| 0.0697 | 0.0552 | 4 |
| 0.0725 | 0.0552 | 5 |
| 0.0728 | 0.0552 | 6 |
| 0.0713 | 0.0552 | 7 |
| 0.0725 | 0.0552 | 8 |
| 0.0705 | 0.0552 | 9 |
| 0.0724 | 0.0552 | 10 |
| 0.0701 | 0.0552 | 11 |
| 0.0710 | 0.0552 | 12 |
| 0.0714 | 0.0552 | 13 |
| 0.0730 | 0.0552 | 14 |
| 0.0710 | 0.0552 | 15 |
| 0.0710 | 0.0552 | 16 |
| 0.0728 | 0.0552 | 17 |
| 0.0693 | 0.0552 | 18 |
| 0.0730 | 0.0552 | 19 |
| 0.0730 | 0.0552 | 20 |
| 0.0729 | 0.0552 | 21 |
| 0.0726 | 0.0552 | 22 |
| 0.0713 | 0.0552 | 23 |
| 0.0722 | 0.0552 | 24 |
| 0.0722 | 0.0552 | 25 |
| 0.0727 | 0.0552 | 26 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
