<!-- 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. -->
eliwill/stoic-generator-distil-gpt2
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.3439
- Validation Loss: 3.7738
- Epoch: 19
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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.2818 | 3.9629 | 0 |
| 4.0906 | 3.9052 | 1 |
| 3.9946 | 3.8684 | 2 |
| 3.9239 | 3.8412 | 3 |
| 3.8689 | 3.8316 | 4 |
| 3.8185 | 3.8156 | 5 |
| 3.7751 | 3.8032 | 6 |
| 3.7325 | 3.7950 | 7 |
| 3.6929 | 3.7901 | 8 |
| 3.6575 | 3.7770 | 9 |
| 3.6223 | 3.7658 | 10 |
| 3.5882 | 3.7745 | 11 |
| 3.5536 | 3.7642 | 12 |
| 3.5226 | 3.7645 | 13 |
| 3.4912 | 3.7616 | 14 |
| 3.4595 | 3.7598 | 15 |
| 3.4289 | 3.7604 | 16 |
| 3.3992 | 3.7555 | 17 |
| 3.3713 | 3.7646 | 18 |
| 3.3439 | 3.7738 | 19 |
Framework versions
- Transformers 4.22.1
- TensorFlow 2.8.2
- Datasets 2.5.1
- Tokenizers 0.12.1
