IntelDAOS20ALBERT_Unbalance
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1657
- Train Accuracy: 0.9610
- Validation Loss: 0.3170
- Validation Accuracy: 0.9099
- Epoch: 6
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': 'Adam', 'weight_decay': 0.001, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.1838 | 0.9610 | 0.3105 | 0.9099 | 0 |
| 0.1607 | 0.9610 | 0.3048 | 0.9099 | 1 |
| 0.2077 | 0.9450 | 0.3424 | 0.9099 | 2 |
| 0.1625 | 0.9580 | 0.3038 | 0.9099 | 3 |
| 0.1596 | 0.9610 | 0.3226 | 0.9099 | 4 |
| 0.1548 | 0.9610 | 0.3334 | 0.9099 | 5 |
| 0.1657 | 0.9610 | 0.3170 | 0.9099 | 6 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3