metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_keras_callback
model-index:
- name: bert-large-model
results: []
bert-large-model
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5285
- Train Accuracy: 0.6667
- Validation Loss: 0.6526
- Validation Accuracy: 1.0
- Epoch: 2
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': False, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.6872 | 0.6667 | 0.5984 | 1.0 | 0 |
| 0.5637 | 0.6667 | 0.6125 | 1.0 | 1 |
| 0.5285 | 0.6667 | 0.6526 | 1.0 | 2 |
Framework versions
- Transformers 4.40.0
- TensorFlow 2.15.0
- Tokenizers 0.19.1