metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: iftekher/web_classifier_model
results: []
iftekher/web_classifier_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1245
- Validation Loss: 0.1347
- Train Accuracy: 1.0
- Epoch: 19
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': 200, '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 | Train Accuracy | Epoch |
|---|---|---|---|
| 1.2434 | 1.0000 | 0.7222 | 0 |
| 0.8063 | 0.6510 | 0.7222 | 1 |
| 0.4802 | 0.4593 | 1.0 | 2 |
| 0.3227 | 0.3277 | 1.0 | 3 |
| 0.2251 | 0.2508 | 1.0 | 4 |
| 0.1981 | 0.1870 | 1.0 | 5 |
| 0.1617 | 0.1615 | 1.0 | 6 |
| 0.1418 | 0.1473 | 1.0 | 7 |
| 0.1320 | 0.1381 | 1.0 | 8 |
| 0.1261 | 0.1347 | 1.0 | 9 |
| 0.1250 | 0.1347 | 1.0 | 10 |
| 0.1208 | 0.1347 | 1.0 | 11 |
| 0.1285 | 0.1347 | 1.0 | 12 |
| 0.1273 | 0.1347 | 1.0 | 13 |
| 0.1280 | 0.1347 | 1.0 | 14 |
| 0.1237 | 0.1347 | 1.0 | 15 |
| 0.1186 | 0.1347 | 1.0 | 16 |
| 0.1266 | 0.1347 | 1.0 | 17 |
| 0.1323 | 0.1347 | 1.0 | 18 |
| 0.1245 | 0.1347 | 1.0 | 19 |
Framework versions
- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2