<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
nikoslefkos/rebert_trex_reformed
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2948
- Train Accuracy: 0.8854
- Validation Loss: 0.5403
- Validation Accuracy: 0.8205
- Epoch: 4
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': 0.01, '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': 1e-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 |
|---|---|---|---|---|
| 1.2096 | 0.7062 | 0.6814 | 0.7940 | 0 |
| 0.6040 | 0.8057 | 0.5633 | 0.8122 | 1 |
| 0.4794 | 0.8322 | 0.5344 | 0.8196 | 2 |
| 0.3969 | 0.8534 | 0.5437 | 0.8162 | 3 |
| 0.2948 | 0.8854 | 0.5403 | 0.8205 | 4 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
