Mariah64/distilbert-base-uncased-finetuned-squad-v2
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: 1.0669
- Train End Logits Accuracy: 0.7066
- Train Start Logits Accuracy: 0.6693
- Validation Loss: 1.1520
- Validation End Logits Accuracy: 0.6892
- Validation Start Logits Accuracy: 0.6556
- 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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5532, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, '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 |
|---|---|---|---|---|---|---|
| 1.6220 | 0.5853 | 0.5458 | 1.2017 | 0.6771 | 0.6414 | 0 |
| 1.0669 | 0.7066 | 0.6693 | 1.1520 | 0.6892 | 0.6556 | 1 |
Framework versions
- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2