metadata
tags:
- generated_from_keras_callback
model-index:
- name: badokorach/mobilebert-uncased-squad-v2
results: []
badokorach/mobilebert-uncased-squad-v2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1074
- 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': 1e-05, 'decay_steps': 2600, '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 |
|---|---|---|
| 0.3940 | 0.0 | 0 |
| 0.3436 | 0.0 | 1 |
| 0.3085 | 0.0 | 2 |
| 0.2538 | 0.0 | 3 |
| 0.2472 | 0.0 | 4 |
| 0.2225 | 0.0 | 5 |
| 0.2025 | 0.0 | 6 |
| 0.1712 | 0.0 | 7 |
| 0.1781 | 0.0 | 8 |
| 0.1583 | 0.0 | 9 |
| 0.1464 | 0.0 | 10 |
| 0.1299 | 0.0 | 11 |
| 0.1510 | 0.0 | 12 |
| 0.1181 | 0.0 | 13 |
| 0.1138 | 0.0 | 14 |
| 0.1144 | 0.0 | 15 |
| 0.1027 | 0.0 | 16 |
| 0.1074 | 0.0 | 17 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0