<!-- 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. -->
lewtun/distilgpt2-finetuned-shakespeare-2
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.1788
- Validation Loss: 3.5061
- 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 |
|---|---|---|
| 4.2119 | 3.8250 | 0 |
| 3.8997 | 3.6971 | 1 |
| 3.7803 | 3.6246 | 2 |
| 3.7080 | 3.5948 | 3 |
| 3.6475 | 3.5694 | 4 |
| 3.6016 | 3.5486 | 5 |
| 3.5598 | 3.5395 | 6 |
| 3.5200 | 3.5272 | 7 |
| 3.4858 | 3.5161 | 8 |
| 3.4519 | 3.5131 | 9 |
| 3.4214 | 3.5058 | 10 |
| 3.3916 | 3.5044 | 11 |
| 3.3608 | 3.5085 | 12 |
| 3.3342 | 3.5016 | 13 |
| 3.3074 | 3.5018 | 14 |
| 3.2784 | 3.5015 | 15 |
| 3.2531 | 3.4982 | 16 |
| 3.2304 | 3.5036 | 17 |
| 3.1988 | 3.5071 | 18 |
| 3.1788 | 3.5061 | 19 |
Framework versions
- Transformers 4.22.2
- TensorFlow 2.8.2
- Datasets 2.5.2
- Tokenizers 0.12.1
