metadata
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: distilbert-base-uncased
model-index:
- name: ratish/DBERT_CleanDesc_v2
results: []
ratish/DBERT_CleanDesc_v2
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0738
- Validation Loss: 0.6606
- Train Accuracy: 0.85
- Epoch: 18
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6180, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
|---|---|---|---|
| 2.2247 | 2.0414 | 0.375 | 0 |
| 1.6722 | 1.6034 | 0.575 | 1 |
| 1.2412 | 1.3270 | 0.6 | 2 |
| 0.9495 | 1.0999 | 0.6 | 3 |
| 0.7464 | 0.9892 | 0.65 | 4 |
| 0.6087 | 0.8445 | 0.75 | 5 |
| 0.4628 | 0.8918 | 0.7 | 6 |
| 0.3747 | 0.7971 | 0.775 | 7 |
| 0.3069 | 0.7776 | 0.75 | 8 |
| 0.2492 | 0.6877 | 0.825 | 9 |
| 0.2148 | 0.7085 | 0.8 | 10 |
| 0.1793 | 0.6896 | 0.85 | 11 |
| 0.1598 | 0.7230 | 0.85 | 12 |
| 0.1308 | 0.7365 | 0.85 | 13 |
| 0.1211 | 0.6985 | 0.85 | 14 |
| 0.1023 | 0.6592 | 0.85 | 15 |
| 0.0892 | 0.6621 | 0.85 | 16 |
| 0.0885 | 0.6387 | 0.85 | 17 |
| 0.0738 | 0.6606 | 0.85 | 18 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3