<!-- 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. -->
zakiasa/my_awesome_qa_model
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: 5.9713
- Train End Logits Accuracy: 0.0014
- Train Start Logits Accuracy: 0.0099
- Validation Loss: 5.9506
- Validation End Logits Accuracy: 0.0
- Validation Start Logits Accuracy: 0.0
- 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': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, '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 |
|---|---|---|---|---|---|---|
| 5.9405 | 0.0071 | 0.0 | 5.8036 | 0.0073 | 0.0109 | 0 |
| 5.9445 | 0.0028 | 0.0014 | 5.9506 | 0.0 | 0.0036 | 1 |
| 5.9622 | 0.0043 | 0.0 | 5.9506 | 0.0036 | 0.0036 | 2 |
| 5.9611 | 0.0 | 0.0014 | 5.9506 | 0.0073 | 0.0073 | 3 |
| 5.9612 | 0.0043 | 0.0043 | 5.9506 | 0.0 | 0.0 | 4 |
| 5.9621 | 0.0028 | 0.0057 | 5.9506 | 0.0 | 0.0 | 5 |
| 5.9579 | 0.0028 | 0.0 | 5.9506 | 0.0036 | 0.0 | 6 |
| 5.9666 | 0.0014 | 0.0028 | 5.9506 | 0.0036 | 0.0 | 7 |
| 5.9698 | 0.0071 | 0.0057 | 5.9506 | 0.0 | 0.0 | 8 |
| 5.9713 | 0.0014 | 0.0099 | 5.9506 | 0.0 | 0.0 | 9 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
