<!-- 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. -->
MarcoLYH/distilbert-base-uncased-finetuned-v4
This model is a fine-tuned version of distilbert-base-uncased-distilled-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6362
- Train End Logits Accuracy: 0.8125
- Train Start Logits Accuracy: 0.8333
- Validation Loss: 0.5952
- Validation End Logits Accuracy: 0.9000
- Validation Start Logits Accuracy: 0.8000
- 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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 27, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 3, 'power': 1.0, '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 |
|---|---|---|---|---|---|---|
| 1.8589 | 0.4792 | 0.5625 | 1.3334 | 0.6500 | 0.7000 | 0 |
| 1.5485 | 0.5417 | 0.5625 | 0.9904 | 0.6500 | 0.8000 | 1 |
| 1.0423 | 0.7292 | 0.7292 | 0.8812 | 0.7000 | 0.8000 | 2 |
| 1.1265 | 0.7083 | 0.7917 | 0.7830 | 0.75 | 0.8000 | 3 |
| 0.8686 | 0.75 | 0.7292 | 0.7052 | 0.8000 | 0.8500 | 4 |
| 0.6936 | 0.8542 | 0.8333 | 0.6547 | 0.8000 | 0.8500 | 5 |
| 0.6408 | 0.875 | 0.8542 | 0.6239 | 0.9000 | 0.8000 | 6 |
| 0.7243 | 0.8333 | 0.7083 | 0.6059 | 0.9000 | 0.8000 | 7 |
| 0.6146 | 0.8333 | 0.8958 | 0.5976 | 0.9000 | 0.8000 | 8 |
| 0.6362 | 0.8125 | 0.8333 | 0.5952 | 0.9000 | 0.8000 | 9 |
Framework versions
- Transformers 4.30.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
