metadata
license: mit
base_model: microsoft/deberta-base
tags:
- generated_from_keras_callback
model-index:
- name: vladjr/deberta-teste
results: []
vladjr/deberta-teste
This model is a fine-tuned version of microsoft/deberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.4786
- Validation Loss: 0.1935
- Train Accuracy: 0.9387
- Epoch: 0
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': 2100, '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 |
|---|---|---|---|
| 1.4786 | 0.1935 | 0.9387 | 0 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1