metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: mmiteva/qa_model_upgraded
results: []
mmiteva/qa_model_upgraded
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: 0.3087
- Train End Logits Accuracy: 0.8935
- Train Start Logits Accuracy: 0.8884
- Validation Loss: 1.1857
- Validation End Logits Accuracy: 0.7448
- Validation Start Logits Accuracy: 0.7335
- Epoch: 4
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 68700, '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}
- 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 |
|---|---|---|---|---|---|---|
| 1.3498 | 0.6214 | 0.6049 | 1.0429 | 0.6891 | 0.6754 | 0 |
| 0.8373 | 0.7346 | 0.7236 | 0.9979 | 0.7117 | 0.6974 | 1 |
| 0.5988 | 0.8012 | 0.7931 | 0.9518 | 0.7267 | 0.7225 | 2 |
| 0.4309 | 0.8541 | 0.8465 | 1.0632 | 0.7417 | 0.7320 | 3 |
| 0.3087 | 0.8935 | 0.8884 | 1.1857 | 0.7448 | 0.7335 | 4 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.10.1
- Datasets 2.7.1
- Tokenizers 0.12.1