metadata
library_name: transformers
license: apache-2.0
base_model: bert-large-cased
tags:
- generated_from_keras_callback
model-index:
- name: vanhuyen/demo
results: []
vanhuyen/demo
This model is a fine-tuned version of bert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1698
- Train Accuracy: 0.9359
- Validation Loss: 0.0592
- Validation Accuracy: 0.9877
- Epoch: 7
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': 5e-06, 'decay_steps': 24350, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 1.1965 | 0.5073 | 0.6710 | 0.8000 | 0 |
| 0.7393 | 0.7065 | 0.2841 | 0.9377 | 1 |
| 0.4082 | 0.8426 | 0.1169 | 0.9762 | 2 |
| 0.2412 | 0.9114 | 0.0674 | 0.9877 | 3 |
| 0.1738 | 0.9385 | 0.0592 | 0.9877 | 4 |
| 0.1661 | 0.9405 | 0.0592 | 0.9877 | 5 |
| 0.1646 | 0.9395 | 0.0590 | 0.9877 | 6 |
| 0.1698 | 0.9359 | 0.0592 | 0.9877 | 7 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.17.0
- Datasets 3.0.2
- Tokenizers 0.19.1