metadata
license: mit
base_model: csarron/mobilebert-uncased-squad-v2
tags:
- generated_from_keras_callback
model-index:
- name: badokorach/mobilebert-uncased-finetuned-agic-031223
results: []
badokorach/mobilebert-uncased-finetuned-agic-031223
This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.1210
- Validation Loss: 0.0
- Epoch: 14
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': 1380, '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 |
|---|---|---|
| 2.5468 | 0.0 | 0 |
| 2.1302 | 0.0 | 1 |
| 1.9414 | 0.0 | 2 |
| 1.8090 | 0.0 | 3 |
| 1.7032 | 0.0 | 4 |
| 1.5721 | 0.0 | 5 |
| 1.5043 | 0.0 | 6 |
| 1.4082 | 0.0 | 7 |
| 1.3307 | 0.0 | 8 |
| 1.2782 | 0.0 | 9 |
| 1.2426 | 0.0 | 10 |
| 1.2036 | 0.0 | 11 |
| 1.1784 | 0.0 | 12 |
| 1.1151 | 0.0 | 13 |
| 1.1210 | 0.0 | 14 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0