<!-- 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. -->
HASAN55/ROBERTA_SQUAD_TST
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: 0.4088
- Train End Logits Accuracy: 0.8767
- Train Start Logits Accuracy: 0.8390
- Validation Loss: 0.9127
- Validation End Logits Accuracy: 0.7771
- Validation Start Logits Accuracy: 0.7501
- Epoch: 3
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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 24804, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.0168 | 0.7301 | 0.6920 | 0.8404 | 0.7696 | 0.7424 | 0 |
| 0.6780 | 0.8069 | 0.7677 | 0.8173 | 0.7698 | 0.7480 | 1 |
| 0.5150 | 0.8473 | 0.8093 | 0.8527 | 0.7764 | 0.7470 | 2 |
| 0.4088 | 0.8767 | 0.8390 | 0.9127 | 0.7771 | 0.7501 | 3 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
