<!-- 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. -->
arjunpatel/distilgpt2-finetuned-pokemon-moves
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.8709
- Validation Loss: 2.3512
- Epoch: 14
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 |
|---|---|---|
| 3.7146 | 3.2288 | 0 |
| 3.1159 | 2.8961 | 1 |
| 2.8592 | 2.7388 | 2 |
| 2.6684 | 2.6423 | 3 |
| 2.5358 | 2.5709 | 4 |
| 2.4330 | 2.5137 | 5 |
| 2.3308 | 2.4736 | 6 |
| 2.2499 | 2.4444 | 7 |
| 2.1843 | 2.4115 | 8 |
| 2.1322 | 2.3931 | 9 |
| 2.0683 | 2.3829 | 10 |
| 2.0122 | 2.3669 | 11 |
| 1.9676 | 2.3596 | 12 |
| 1.9087 | 2.3591 | 13 |
| 1.8709 | 2.3512 | 14 |
Framework versions
- Transformers 4.18.0
- TensorFlow 2.8.0
- Datasets 2.1.0
- Tokenizers 0.11.0
