<!-- 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. -->
amanneo/mail-generator-mini
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.4613
- Train Accuracy: 0.1611
- Validation Loss: 5.2617
- Validation Accuracy: 0.1386
- Epoch: 9
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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': -925, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 10.0053 | 0.1068 | 8.5247 | 0.1394 | 0 |
| 8.7772 | 0.1505 | 7.9685 | 0.1656 | 1 |
| 8.2057 | 0.1663 | 7.4436 | 0.1655 | 2 |
| 7.5786 | 0.1611 | 6.8572 | 0.1654 | 3 |
| 6.9698 | 0.1679 | 6.3646 | 0.1735 | 4 |
| 6.4911 | 0.1763 | 6.0124 | 0.1787 | 5 |
| 6.1632 | 0.1834 | 5.7751 | 0.1826 | 6 |
| 5.9057 | 0.1840 | 5.5786 | 0.1749 | 7 |
| 5.6874 | 0.1758 | 5.4023 | 0.1616 | 8 |
| 5.4613 | 0.1611 | 5.2617 | 0.1386 | 9 |
Framework versions
- Transformers 4.23.1
- TensorFlow 2.9.2
- Datasets 2.6.1
- Tokenizers 0.13.1
