metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_10
results: []
TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_10
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: 0.0067
- Validation Loss: 0.3379
- Train Accuracy: 0.9354
- 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12500, '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 | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.2338 | 0.1838 | 0.9304 | 0 |
| 0.1379 | 0.1821 | 0.931 | 1 |
| 0.0748 | 0.1896 | 0.9334 | 2 |
| 0.0427 | 0.2671 | 0.9318 | 3 |
| 0.0260 | 0.2814 | 0.933 | 4 |
| 0.0198 | 0.3015 | 0.9338 | 5 |
| 0.0134 | 0.3239 | 0.9342 | 6 |
| 0.0104 | 0.3797 | 0.9268 | 7 |
| 0.0088 | 0.3347 | 0.9338 | 8 |
| 0.0067 | 0.3379 | 0.9354 | 9 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.8.1
- Datasets 2.14.5
- Tokenizers 0.13.3