<!-- 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. -->
soumya13/GPT2_CleanDesc_MAKE_v3.0
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0492
- Validation Loss: 0.5345
- Train Accuracy: 0.8462
- 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': 3040, '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 |
|---|---|---|---|
| 2.2952 | 2.0148 | 0.3846 | 0 |
| 1.6880 | 1.6117 | 0.4872 | 1 |
| 1.3471 | 1.4949 | 0.5385 | 2 |
| 1.1142 | 1.3389 | 0.6410 | 3 |
| 0.8515 | 1.1787 | 0.5897 | 4 |
| 0.6936 | 0.8458 | 0.7436 | 5 |
| 0.5641 | 0.7660 | 0.7436 | 6 |
| 0.4862 | 0.8724 | 0.6667 | 7 |
| 0.3327 | 0.7529 | 0.7692 | 8 |
| 0.2869 | 0.5615 | 0.8718 | 9 |
| 0.2437 | 0.5124 | 0.8462 | 10 |
| 0.1663 | 0.5285 | 0.8718 | 11 |
| 0.1589 | 0.6002 | 0.8718 | 12 |
| 0.1495 | 0.6048 | 0.8974 | 13 |
| 0.1131 | 0.5759 | 0.8462 | 14 |
| 0.1051 | 0.5339 | 0.8718 | 15 |
| 0.0582 | 0.5317 | 0.8974 | 16 |
| 0.0502 | 0.5349 | 0.8718 | 17 |
| 0.0492 | 0.5345 | 0.8462 | 18 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
