badokorach/Albert-finetuned-210124
This model is a fine-tuned version of twmkn9/albert-base-v2-squad2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1484
- 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': 2e-05, 'decay_steps': 2265, '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': 0.002}
- training_precision: mixed_float16
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
2.5485 | 0.0 | 0 |
1.7396 | 0.0 | 1 |
1.2623 | 0.0 | 2 |
0.9069 | 0.0 | 3 |
0.6427 | 0.0 | 4 |
0.4773 | 0.0 | 5 |
0.3798 | 0.0 | 6 |
0.3165 | 0.0 | 7 |
0.2573 | 0.0 | 8 |
0.2261 | 0.0 | 9 |
0.2054 | 0.0 | 10 |
0.1899 | 0.0 | 11 |
0.1712 | 0.0 | 12 |
0.1603 | 0.0 | 13 |
0.1484 | 0.0 | 14 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 3