Middelz2/roberta-large-aphasia-narration-weightdecay0_eps_10
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.0094
- Validation Loss: 0.8917
- 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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.5337 | 1.3155 | 0 |
| 1.2936 | 1.1727 | 1 |
| 1.1965 | 1.1077 | 2 |
| 1.1361 | 1.0687 | 3 |
| 1.0949 | 1.0489 | 4 |
| 1.0621 | 0.9968 | 5 |
| 1.0537 | 0.9602 | 6 |
| 1.0273 | 0.9470 | 7 |
| 1.0333 | 0.9485 | 8 |
| 1.0094 | 0.8917 | 9 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.0
- Tokenizers 0.13.3