<!-- 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. -->
benjip/masked-lm-tpu
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 9.8771
- Train Accuracy: 0.0086
- Validation Loss: 9.7741
- Validation Accuracy: 0.0208
- Epoch: 9
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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 22325, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1175, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 10.3084 | 0.0000 | 10.3098 | 0.0000 | 0 |
| 10.2947 | 0.0 | 10.2947 | 0.0 | 1 |
| 10.2840 | 0.0000 | 10.2631 | 0.0 | 2 |
| 10.2555 | 0.0 | 10.2269 | 0.0 | 3 |
| 10.2161 | 0.0000 | 10.1759 | 0.0000 | 4 |
| 10.1694 | 0.0 | 10.1119 | 0.0 | 5 |
| 10.1126 | 0.0 | 10.0506 | 0.0000 | 6 |
| 10.0476 | 0.0001 | 9.9642 | 0.0013 | 7 |
| 9.9589 | 0.0015 | 9.8694 | 0.0116 | 8 |
| 9.8771 | 0.0086 | 9.7741 | 0.0208 | 9 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Tokenizers 0.13.3
