metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: yusyel/bert_faq
results: []
yusyel/bert_faq
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: 0.7985
- Validation Loss: 0.8954
- Epoch: 13
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': 896, '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 | Validation Loss | Epoch |
|---|---|---|
| 1.7394 | 1.4158 | 0 |
| 1.3291 | 1.2100 | 1 |
| 1.1664 | 1.1007 | 2 |
| 1.0144 | 1.0112 | 3 |
| 0.9238 | 0.9387 | 4 |
| 0.8509 | 0.9155 | 5 |
| 0.8117 | 0.8954 | 6 |
| 0.7988 | 0.8954 | 7 |
| 0.7966 | 0.8954 | 8 |
| 0.7857 | 0.8954 | 9 |
| 0.8042 | 0.8954 | 10 |
| 0.7911 | 0.8954 | 11 |
| 0.7971 | 0.8954 | 12 |
| 0.7985 | 0.8954 | 13 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.1