<!-- 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. -->
Nighthawks/bert-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: 0.7768
- Train End Logits Accuracy: 0.7784
- Train Start Logits Accuracy: 0.7395
- Validation Loss: 1.1178
- Validation End Logits Accuracy: 0.7121
- Validation Start Logits Accuracy: 0.6721
- Epoch: 2
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': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13278, '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}
- 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 |
---|---|---|---|---|---|---|
1.5823 | 0.5924 | 0.5516 | 1.1556 | 0.6903 | 0.6496 | 0 |
0.9907 | 0.7266 | 0.6861 | 1.0986 | 0.7079 | 0.6656 | 1 |
0.7768 | 0.7784 | 0.7395 | 1.1178 | 0.7121 | 0.6721 | 2 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3