<!-- 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. -->
badokorach/distilbert-base-cased-090823
This model is a fine-tuned version of EricPeter/distilbert-base-uncased-finetuned-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1635
- Validation Loss: 0.0
- 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1296, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 4, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.4650 | 0.0 | 0 |
| 0.3836 | 0.0 | 1 |
| 0.2715 | 0.0 | 2 |
| 0.2633 | 0.0 | 3 |
| 0.2229 | 0.0 | 4 |
| 0.2244 | 0.0 | 5 |
| 0.2053 | 0.0 | 6 |
| 0.2054 | 0.0 | 7 |
| 0.2014 | 0.0 | 8 |
| 0.1829 | 0.0 | 9 |
| 0.1838 | 0.0 | 10 |
| 0.1833 | 0.0 | 11 |
| 0.1755 | 0.0 | 12 |
| 0.1654 | 0.0 | 13 |
| 0.1706 | 0.0 | 14 |
| 0.1713 | 0.0 | 15 |
| 0.1733 | 0.0 | 16 |
| 0.1650 | 0.0 | 17 |
| 0.1668 | 0.0 | 18 |
| 0.1635 | 0.0 | 19 |
Framework versions
- Transformers 4.33.1
- TensorFlow 2.12.0
- Datasets 2.14.5
- Tokenizers 0.13.3
