badokorach/distilbert-base-uncased-distilled-squad-17
This model is a fine-tuned version of distilbert-base-uncased-distilled-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.4761
- Validation Loss: 0.0
- Epoch: 17
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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.7877 | 0.0 | 0 |
| 3.5579 | 0.0 | 1 |
| 3.4117 | 0.0 | 2 |
| 3.2112 | 0.0 | 3 |
| 2.9211 | 0.0 | 4 |
| 2.5860 | 0.0 | 5 |
| 2.2459 | 0.0 | 6 |
| 1.9209 | 0.0 | 7 |
| 1.6627 | 0.0 | 8 |
| 1.3934 | 0.0 | 9 |
| 1.2150 | 0.0 | 10 |
| 1.0406 | 0.0 | 11 |
| 0.8977 | 0.0 | 12 |
| 0.7730 | 0.0 | 13 |
| 0.6944 | 0.0 | 14 |
| 0.6361 | 0.0 | 15 |
| 0.5495 | 0.0 | 16 |
| 0.4761 | 0.0 | 17 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3