briziel/distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.9786
- Train End Logits Accuracy: 0.7287
- Train Start Logits Accuracy: 0.6898
- Validation Loss: 1.1064
- Validation End Logits Accuracy: 0.6984
- Validation Start Logits Accuracy: 0.6615
- Epoch: 1
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', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 11064, '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}
- training_precision: float32
Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.5081 | 0.6050 | 0.5681 | 1.1607 | 0.6881 | 0.6499 | 0 |
| 0.9786 | 0.7287 | 0.6898 | 1.1064 | 0.6984 | 0.6615 | 1 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.13.0
- Datasets 2.13.1
- Tokenizers 0.13.3